github ubuntu doesnt support testing python2 anymore

add ubuntu 22 support

test python 2 in ubuntu 20

.github/FUNDING.yml

@@ -0,0 +1,5 @@
+# These are supported funding model platforms
+
+github: psy0rz
+ko_fi: psy0rz
+custom: https://paypal.me/psy0rz

.github/ISSUE_TEMPLATE/issue.md

@@ -0,0 +1,11 @@
+---
+name: Issue
+about: 'Use this if you have issues or feature requests'
+
+title: ''
+labels: ''
+assignees: ''
+
+---
+
+(Please add the commandline that you use to the issue. Also at least add the output of --verbose. Sometimes it helps if you add the output of --debug-output instead, but its huge, so use an attachment for that.)

.github/dependabot.yml

@@ -0,0 +1,11 @@
+# To get started with Dependabot version updates, you'll need to specify which
+# package ecosystems to update and where the package manifests are located.
+# Please see the documentation for all configuration options:
+# https://docs.github.com/github/administering-a-repository/configuration-options-for-dependency-updates
+
+version: 2
+updates:
+  - package-ecosystem: "python" # See documentation for possible values
+    directory: "/" # Location of package manifests
+    schedule:
+      interval: "weekly"

.github/workflows/codeql-analysis.yml

@@ -0,0 +1,71 @@
+# For most projects, this workflow file will not need changing; you simply need
+# to commit it to your repository.
+#
+# You may wish to alter this file to override the set of languages analyzed,
+# or to provide custom queries or build logic.
+#
+# ******** NOTE ********
+# We have attempted to detect the languages in your repository. Please check
+# the `language` matrix defined below to confirm you have the correct set of
+# supported CodeQL languages.
+#
+name: "CodeQL"
+
+on:
+  push:
+    branches: [ master ]
+  pull_request:
+    # The branches below must be a subset of the branches above
+    branches: [ master ]
+#  schedule:
+#    - cron: '26 23 * * 3'
+
+jobs:
+  analyze:
+    name: Analyze
+    runs-on: ubuntu-latest
+    permissions:
+      actions: read
+      contents: read
+      security-events: write
+
+    strategy:
+      fail-fast: false
+      matrix:
+        language: [ 'python' ]
+        # CodeQL supports [ 'cpp', 'csharp', 'go', 'java', 'javascript', 'python', 'ruby' ]
+        # Learn more about CodeQL language support at https://git.io/codeql-language-support
+
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v2
+
+
+    # Initializes the CodeQL tools for scanning.
+    - name: Initialize CodeQL
+      uses: github/codeql-action/init@v2
+      with:
+        languages: ${{ matrix.language }}
+        # If you wish to specify custom queries, you can do so here or in a config file.
+        # By default, queries listed here will override any specified in a config file.
+        # Prefix the list here with "+" to use these queries and those in the config file.
+        # queries: ./path/to/local/query, your-org/your-repo/queries@main
+
+    # Autobuild attempts to build any compiled languages  (C/C++, C#, or Java).
+    # If this step fails, then you should remove it and run the build manually (see below)
+    - name: Autobuild
+      uses: github/codeql-action/autobuild@v2
+
+    # ℹ️ Command-line programs to run using the OS shell.
+    # 📚 https://git.io/JvXDl
+
+    # ✏️ If the Autobuild fails above, remove it and uncomment the following three lines
+    #    and modify them (or add more) to build your code if your project
+    #    uses a compiled language
+
+    #- run: |
+    #   make bootstrap
+    #   make release
+
+    - name: Perform CodeQL Analysis
+      uses: github/codeql-action/analyze@v2

.github/workflows/python-publish.yml

@@ -0,0 +1,46 @@
+# This workflow will upload a Python Package using Twine when a release is created
+# For more information see: https://help.github.com/en/actions/language-and-framework-guides/using-python-with-github-actions#publishing-to-package-registries
+
+name: Upload Python Package
+
+on:
+  release:
+    types: [created]
+
+jobs:
+  deploy:
+
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v2
+
+    - name: Set up Python 3.x
+      uses: actions/setup-python@v2
+      with:
+        python-version: '3.x'
+
+    - name: Set up Python 2.x
+      uses: actions/setup-python@v2
+      with:
+        python-version: '2.x'
+
+    - name: Install dependencies 3.x
+      run: |
+        python -m pip install --upgrade pip
+        pip3 install setuptools wheel twine
+
+    - name: Install dependencies 2.x
+      run: |
+        python2 -m pip install --upgrade pip
+        pip2 install setuptools wheel twine
+
+    - name: Build and publish
+      env:
+        TWINE_USERNAME: ${{ secrets.TWINE_USERNAME }}
+        TWINE_PASSWORD: ${{ secrets.TWINE_PASSWORD }}
+      run: |
+        python3 setup.py sdist bdist_wheel
+        python2 setup.py sdist bdist_wheel
+        twine check dist/*
+        twine upload dist/*

.github/workflows/regression.yml

@@ -0,0 +1,48 @@
+name: Regression tests
+
+
+on: ["push", "pull_request"]
+
+
+
+jobs:
+  ubuntu22:
+    runs-on: ubuntu-22.04
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3.5.0
+
+      - name: Prepare
+        run: sudo apt update && sudo apt install zfsutils-linux lzop pigz zstd gzip xz-utils lz4 mbuffer && sudo -H pip3 install coverage unittest2 mock==3.0.5 coveralls
+
+
+      - name: Regression test
+        run: sudo -E ./tests/run_tests
+
+
+      - name: Coveralls
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: coveralls --service=github || true
+
+  ubuntu20:
+    runs-on: ubuntu-20.04
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3.5.0
+
+      - name: Prepare
+        run: sudo apt update && sudo apt install zfsutils-linux lzop pigz zstd gzip xz-utils lz4 mbuffer && sudo -H pip3 install coverage unittest2 mock==3.0.5 coveralls
+
+
+      - name: Regression test
+        run: sudo -E ./tests/run_tests
+
+
+      - name: Coveralls
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: coveralls --service=github || true
+

.gitignore

@@ -6,3 +6,9 @@ build/
 zfs_autobackup.egg-info
 .eggs/
 __pycache__
+.coverage
+*.pyc
+python2.env
+venv
+.idea
+password.sh

README.md

@@ -1,406 +1,65 @@
+
 # ZFS autobackup
 
-## New in v3
-
-* Complete rewrite, cleaner object oriented code.
-* Python 3 and 2 support.
-* Installable via pip.
-* Backwards compatible with your current backups and parameters.
-* Progressive thinning (via a destroy schedule. default schedule should be fine for most people)
-* Cleaner output, with optional color support (pip install colorama).
-* Clear distinction between local and remote output.
-* Summary at the beginning, displaying what will happen and the current thinning-schedule.
-* More effient destroying/skipping snaphots on the fly. (no more space issues if your backup is way behind)
-* Progress indicator (--progress)
-* Better property management (--set-properties and --filter-properties)
-* Better resume handling, automaticly abort invalid resumes.
-* More robust error handling.
-* Prepared for future enhanchements.
-* Supports raw backups for encryption.
+[![Tests](https://github.com/psy0rz/zfs_autobackup/workflows/Regression%20tests/badge.svg)](https://github.com/psy0rz/zfs_autobackup/actions?query=workflow%3A%22Regression+tests%22) [![Coverage Status](https://coveralls.io/repos/github/psy0rz/zfs_autobackup/badge.svg)](https://coveralls.io/github/psy0rz/zfs_autobackup)  [![Python Package](https://github.com/psy0rz/zfs_autobackup/workflows/Upload%20Python%20Package/badge.svg)](https://pypi.org/project/zfs-autobackup/)
+[![CodeQL](https://github.com/psy0rz/zfs_autobackup/actions/workflows/codeql-analysis.yml/badge.svg)](https://github.com/psy0rz/zfs_autobackup/actions/workflows/codeql-analysis.yml)
 
 ## Introduction
 
-ZFS autobackup is used to periodicly backup ZFS filesystems to other locations. This is done using the very effcient zfs send and receive commands.
+ZFS-autobackup tries to be the most reliable and easiest to use tool, while having all the features.
 
-It has the following features:
+You can either use it as a **backup** tool, **replication** tool or **snapshot** tool.
 
-* Works across operating systems: Tested with Linux, FreeBSD/FreeNAS and SmartOS.
-* Works in combination with existing replication systems. (Like Proxmox HA)
-* Automatically selects filesystems to backup by looking at a simple ZFS property. (recursive)
-* Creates consistent snapshots. (takes all snapshots at once, atomic.)
+You can select what to backup by setting a custom `ZFS property`. This makes it easy to add/remove specific datasets, or just backup your whole pool.
+
+Other settings are just specified on the commandline: Simply setup and test your zfs-autobackup command and  fix all the issues you might encounter. When you're done you can just copy/paste your command to a cron or script.
+
+Since it's using ZFS commands, you can see what it's actually doing by specifying `--debug`. This also helps a lot if you run into some strange problem or errors. You can just copy-paste the command that fails and play around with it on the commandline. (something I missed in other tools)
+
+An important feature that's missing from other tools is a reliable `--test` option: This allows you to see what zfs-autobackup will do and tune your parameters. It will do everything, except make changes to your system.
+
+## Features
+
+* Works across operating systems: Tested with **Linux**, **FreeBSD/FreeNAS** and **SmartOS**.
+* Low learning curve: no complex daemons or services, no additional software or networking needed. 
+* Plays nicely with existing replication systems. (Like Proxmox HA)
+* Automatically selects filesystems to backup by looking at a simple ZFS property. 
+* Creates consistent snapshots. (takes all snapshots at once, atomicly.)
 * Multiple backups modes:
   * Backup local data on the same server.
   * "push" local data to a backup-server via SSH.
   * "pull" remote data from a server via SSH and backup it locally.
-  * Or even pull data from a server while pushing the backup to another server.
-* Can be scheduled via a simple cronjob or run directly from commandline.
-* Supports resuming of interrupted transfers. (via the zfs extensible_dataset feature)
-* Backups and snapshots can be named to prevent conflicts. (multiple backups from and to the same filesystems are no problem)
-* Always creates a new snapshot before starting.
-* Checks everything but tries continue on non-fatal errors when possible. (Reports error-count when done)
-* Ability to 'finish' aborted backups to see what goes wrong.
+  * "pull+push": Zero trust between source and target.
+* Can be scheduled via simple cronjob or run directly from commandline.
+* Also supports complex backup geometries.
+* ZFS encryption support: Can decrypt / encrypt or even re-encrypt datasets during transfer.
+* Supports sending with compression. (Using pigz, zstd etc)
+* IO buffering to speed up transfer.
+* Bandwidth rate limiting.
+* Multiple backups from and to the same datasets are no problem.
+* Resillient to errors.
+* Ability to manually 'finish' failed backups to see whats going on.
 * Easy to debug and has a test-mode. Actual unix commands are printed.
-* Keeps latest X snapshots remote and locally. (default 30, configurable)
-* Uses zfs-holds on important snapshots so they cant be accidentally destroyed.
+* Uses progressive thinning for older snapshots.
+* Uses zfs-holds on important snapshots to prevent accidental deletion.
+* Automatic resuming of failed transfers.
+* Easy migration from other zfs backup systems to zfs-autobackup.
+* Gracefully handles datasets that no longer exist on source.
+* Complete and clean logging.
+* All code is regression tested against actual ZFS environments.
 * Easy installation:
-  * Just install zfs-autobackup via pip, or download it manually.
-  * Written in python and uses zfs-commands, no 3rd party dependency's or libraries.
-  * No separate config files or properties. Just one zfs-autobackup command you can copy/paste in your backup script.
+  * Just install zfs-autobackup via pip.
+  * Only needs to be installed on one side.
+  * Written in python and uses zfs-commands, no special 3rd party dependency's or compiled libraries needed.
+  * No annoying config files or properties. 
 
-## Installation
+## Getting started
 
-Use pip to install:
+Please look at our wiki to [Get started](https://github.com/psy0rz/zfs_autobackup/wiki).
 
-```console
-[root@server ~]# pip install zfs-autobackup
-```
+# Sponsor list
 
-On older servers you might have to use easy_install
+This project was sponsorred by:
 
-```console
-[root@server ~]# easy_install zfs-autobackup
-```
-
-Its also possible to just download <https://raw.githubusercontent.com/psy0rz/zfs_autobackup/v3/bin/zfs_autobackup> and run it directly.
-
-## Usage
-
-```console
-[root@server ~]# zfs-autobackup --help
-usage: zfs-autobackup [-h] [--ssh-source SSH_SOURCE] [--ssh-target SSH_TARGET]
-                      [--keep-source KEEP_SOURCE] [--keep-target KEEP_TARGET]
-                      [--no-snapshot] [--allow-empty] [--ignore-replicated]
-                      [--no-holds] [--resume] [--strip-path STRIP_PATH]
-                      [--buffer BUFFER] [--clear-refreservation]
-                      [--clear-mountpoint]
-                      [--filter-properties FILTER_PROPERTIES]
-                      [--set-properties SET_PROPERTIES] [--rollback]
-                      [--ignore-transfer-errors] [--raw] [--test] [--verbose]
-                      [--debug] [--debug-output] [--progress]
-                      backup_name target_path
-
-ZFS autobackup 3.0-beta6
-
-positional arguments:
-  backup_name           Name of the backup (you should set the zfs property
-                        "autobackup:backup-name" to true on filesystems you
-                        want to backup
-  target_path           Target ZFS filesystem
-
-optional arguments:
-  -h, --help            show this help message and exit
-  --ssh-source SSH_SOURCE
-                        Source host to get backup from. (user@hostname)
-                        Default None.
-  --ssh-target SSH_TARGET
-                        Target host to push backup to. (user@hostname) Default
-                        None.
-  --keep-source KEEP_SOURCE
-                        Thinning schedule for old source snapshots. Default:
-                        10,1d1w,1w1m,1m1y
-  --keep-target KEEP_TARGET
-                        Thinning schedule for old target snapshots. Default:
-                        10,1d1w,1w1m,1m1y
-  --no-snapshot         dont create new snapshot (usefull for finishing
-                        uncompleted backups, or cleanups)
-  --allow-empty         if nothing has changed, still create empty snapshots.
-  --ignore-replicated   Ignore datasets that seem to be replicated some other
-                        way. (No changes since lastest snapshot. Usefull for
-                        proxmox HA replication)
-  --no-holds            Dont lock snapshots on the source. (Usefull to allow
-                        proxmox HA replication to switches nodes)
-  --resume              support resuming of interrupted transfers by using the
-                        zfs extensible_dataset feature (both zpools should
-                        have it enabled) Disadvantage is that you need to use
-                        zfs recv -A if another snapshot is created on the
-                        target during a receive. Otherwise it will keep
-                        failing.
-  --strip-path STRIP_PATH
-                        number of directory to strip from path (use 1 when
-                        cloning zones between 2 SmartOS machines)
-  --buffer BUFFER       Use mbuffer with specified size to speedup zfs
-                        transfer. (e.g. --buffer 1G) Will also show nice
-                        progress output.
-  --clear-refreservation
-                        Filter "refreservation" property. (recommended, safes
-                        space. same as --filter-properties refreservation)
-  --clear-mountpoint    Filter "canmount" property. You still have to set
-                        canmount=noauto on the backup server. (recommended,
-                        prevents mount conflicts. same as --filter-properties
-                        canmount)
-  --filter-properties FILTER_PROPERTIES
-                        List of propererties to "filter" when receiving
-                        filesystems. (you can still restore them with zfs
-                        inherit -S)
-  --set-properties SET_PROPERTIES
-                        List of propererties to override when receiving
-                        filesystems. (you can still restore them with zfs
-                        inherit -S)
-  --rollback            Rollback changes on the target before starting a
-                        backup. (normally you can prevent changes by setting
-                        the readonly property on the target_path to on)
-  --ignore-transfer-errors
-                        Ignore transfer errors (still checks if received
-                        filesystem exists. usefull for acltype errors)
-  --raw                 For encrypted datasets, send data exactly as it exists
-                        on disk.
-  --test                dont change anything, just show what would be done
-                        (still does all read-only operations)
-  --verbose             verbose output
-  --debug               Show zfs commands that are executed, stops after an
-                        exception.
-  --debug-output        Show zfs commands and their output/exit codes. (noisy)
-  --progress            show zfs progress output (to stderr)
-
-When a filesystem fails, zfs_backup will continue and report the number of
-failures at that end. Also the exit code will indicate the number of failures.
-
-```
-
-## Backup example
-
-In this example we're going to backup a machine called `pve` to our backupserver.
-
-Its important to choose a unique and consistent backup name. In this case we name our backup: `offsite1`.
-
-### Select filesystems to backup
-
-On the source zfs system set the ```autobackup:offsite``` zfs property to true:
-
-```console
-[root@pve ~]# zfs set autobackup:offsite1=true rpool
-[root@pve ~]# zfs get -t filesystem,volume autobackup:offsite1
-NAME                                    PROPERTY             VALUE                SOURCE
-rpool                                   autobackup:offsite1  true                 local
-rpool/ROOT                              autobackup:offsite1  true                 inherited from rpool
-rpool/ROOT/pve-1                        autobackup:offsite1  true                 inherited from rpool
-rpool/data                              autobackup:offsite1  true                 inherited from rpool
-rpool/data/vm-100-disk-0                autobackup:offsite1  true                 inherited from rpool
-rpool/swap                              autobackup:offsite1  true                 inherited from rpool
-...
-```
-
-Because we dont want to backup everything, we can exclude certain filesystem by setting the property to false:
-
-```console
-[root@pve ~]# zfs set autobackup:offsite1=false rpool/swap
-[root@pve ~]# zfs get -t filesystem,volume autobackup:offsite1
-NAME                                    PROPERTY             VALUE                SOURCE
-rpool                                   autobackup:offsite1  true                 local
-rpool/ROOT                              autobackup:offsite1  true                 inherited from rpool
-rpool/ROOT/pve-1                        autobackup:offsite1  true                 inherited from rpool
-rpool/data                              autobackup:offsite1  true                 inherited from rpool
-rpool/data/vm-100-disk-0                autobackup:offsite1  true                 inherited from rpool
-rpool/swap                              autobackup:offsite1  false                local
-...
-```
-
-### Running zfs-autobackup
-
-There are 2 ways to run the backup, but the endresult is always the same. Its just a matter of security (trust relations between the servers) and preference.
-
-First install the ssh-key on the server that you specify with --ssh-source or --ssh-target.
-
-#### Method 1: Run the script on the backup server and pull the data from the server specfied by --ssh-source. This is usually the preferred way and prevents a hacked server from accesing the backup-data
-
-```console
-[root@backup ~]# zfs-autobackup --ssh-source pve.server.com offsite1 backup/pve --progress --verbose --resume
-
-  #### Settings summary
-  [Source] Datasets on: pve.server.com
-  [Source] Keep the last 10 snapshots.
-  [Source] Keep oldest of 1 day, delete after 1 week.
-  [Source] Keep oldest of 1 week, delete after 1 month.
-  [Source] Keep oldest of 1 month, delete after 1 year.
-  [Source] Send all datasets that have 'autobackup:offsite1=true' or 'autobackup:offsite1=child'
-  
-  [Target] Datasets are local
-  [Target] Keep the last 10 snapshots.
-  [Target] Keep oldest of 1 day, delete after 1 week.
-  [Target] Keep oldest of 1 week, delete after 1 month.
-  [Target] Keep oldest of 1 month, delete after 1 year.
-  [Target] Receive datasets under: backup/pve
-  
-  #### Selecting
-  [Source] rpool: Selected (direct selection)
-  [Source] rpool/ROOT: Selected (inherited selection)
-  [Source] rpool/ROOT/pve-1: Selected (inherited selection)
-  [Source] rpool/data: Selected (inherited selection)
-  [Source] rpool/data/vm-100-disk-0: Selected (inherited selection)
-  [Source] rpool/swap: Ignored (disabled)
-  
-  #### Snapshotting
-  [Source] rpool: No changes since offsite1-20200218175435
-  [Source] rpool/ROOT: No changes since offsite1-20200218175435
-  [Source] rpool/data: No changes since offsite1-20200218175435
-  [Source] Creating snapshot offsite1-20200218180123
-  
-  #### Transferring
-  [Target] backup/pve/rpool/ROOT/pve-1@offsite1-20200218175435: resuming
-  [Target] backup/pve/rpool/ROOT/pve-1@offsite1-20200218175435: receiving full
-  [Target] backup/pve/rpool/ROOT/pve-1@offsite1-20200218175547: receiving incremental
-  [Target] backup/pve/rpool/ROOT/pve-1@offsite1-20200218175706: receiving incremental
-  [Target] backup/pve/rpool/ROOT/pve-1@offsite1-20200218180049: receiving incremental
-  [Target] backup/pve/rpool/ROOT/pve-1@offsite1-20200218180123: receiving incremental
-  [Target] backup/pve/rpool/data@offsite1-20200218175435: receiving full
-  [Target] backup/pve/rpool/data/vm-100-disk-0@offsite1-20200218175435: receiving full
-  ...
-```
-
-#### Method 2: Run the script on the server and push the data to the backup server specified by --ssh-target
-
-```console
-[root@pve ~]# zfs-autobackup --ssh-target backup.server.com offsite1 backup/pve --progress --verbose --resume
-
-  #### Settings summary
-  [Source] Datasets are local
-  [Source] Keep the last 10 snapshots.
-  [Source] Keep oldest of 1 day, delete after 1 week.
-  [Source] Keep oldest of 1 week, delete after 1 month.
-  [Source] Keep oldest of 1 month, delete after 1 year.
-  [Source] Send all datasets that have 'autobackup:offsite1=true' or 'autobackup:offsite1=child'
-  
-  [Target] Datasets on: backup.server.com
-  [Target] Keep the last 10 snapshots.
-  [Target] Keep oldest of 1 day, delete after 1 week.
-  [Target] Keep oldest of 1 week, delete after 1 month.
-  [Target] Keep oldest of 1 month, delete after 1 year.
-  [Target] Receive datasets under: backup/pve
-  ...
-
-```
-
-
-### Automatic backups
-
-Now everytime you run the command, zfs-autobackup will create a new snapshot and replicate your data. 
-
-Older snapshots will evertually be deleted, depending on the --keep-source and --keep-target settings. (The defaults are shown above under the 'Settings summary')
-
-Once you've got the correct settings for your situation, you can just store the command in a cronjob. Or just create a script and run it manually when you need it.
-
-## Tips
-
-* Use ```--verbose``` to see details, otherwise zfs-autobackup will be quiet and only show errors, like a nice unix command.
-* Use ```--debug``` if something goes wrong and you want to see the commands that are executed. This will also stop at the first error.
-* Use ```--resume``` to be able to resume aborted backups. (not all zfs versions support this)
-* Set the ```readonly``` property of the target filesystem to ```on```. This prevents changes on the target side. If there are changes the next backup will fail and will require a zfs rollback. (by using the --rollback option for example)
-* Use ```--clear-refreservation``` to save space on your backup server.
-* Use ```--clear-mountpoint``` to prevent the target server from mounting the backupped filesystem in the wrong place during a reboot.
-
-### Speeding up SSH and prevent connection flooding
-
-Add this to your ~/.ssh/config:
-
-```console
-Host *
-    ControlPath ~/.ssh/control-master-%r@%h:%p
-    ControlMaster auto
-    ControlPersist 3600
-```
-
-This will make all your ssh connections persistent and greatly speed up zfs-autobackup for jobs with short intervals.
-
-Thanks @mariusvw :)
-
-### Specifying ssh port or options
-
-The correct way to do this is by creating ~/.ssh/config:
-
-```console
-Host smartos04
-    Hostname 1.2.3.4
-    Port 1234
-    user root
-    Compression yes
-```
-
-This way you can just specify "smartos04" as host.
-
-Also uses compression on slow links.
-
-Look in man ssh_config for many more options.
-
-## Troubleshooting
-
-> ###  cannot receive incremental stream: invalid backup stream
-
-This usually means you've created a new snapshot on the target side during a backup:
-
-* Solution 1: Restart zfs-autobackup and make sure you dont use --resume. If you did use --resume, be sure to "abort" the recveive on the target side with zfs recv -A.
-* Solution 2: Destroy the newly created snapshot and restart zfs-autobackup.
-
-> ### internal error: Invalid argument
-
-In some cases (Linux -> FreeBSD) this means certain properties are not fully supported on the target system.
-
-Try using something like: --filter-properties xattr
-
-## Restore example
-
-Restoring can be done with simple zfs commands. For example, use this to restore a specific SmartOS disk image to a temporary restore location:
-
-```console
-root@fs1:/home/psy#  zfs send fs1/zones/backup/zfsbackups/smartos01.server.com/zones/a3abd6c8-24c6-4125-9e35-192e2eca5908-disk0@smartos01_fs1-20160110000003 | ssh root@2.2.2.2 "zfs recv zones/restore"
-```
-
-After that you can rename the disk image from the temporary location to the location of a new SmartOS machine you've created.
-
-## Monitoring with Zabbix-jobs
-
-You can monitor backups by using my zabbix-jobs script. (<https://github.com/psy0rz/stuff/tree/master/zabbix-jobs>)
-
-Put this command directly after the zfs_backup command in your cronjob:
-
-```console
-zabbix-job-status backup_smartos01_fs1 daily $?
-```
-
-This will update the zabbix server with the exitcode and will also alert you if the job didnt run for more than 2 days.
-
-## Backuping up a proxmox cluster with HA replication
-
-Due to the nature of proxmox we had to make a few enhancements to zfs-autobackup. This will probably also benefit other systems that use their own replication in combination with zfs-autobackup.
-
-All data under rpool/data can be on multiple nodes of the cluster. The naming of those filesystem is unique over the whole cluster. Because of this we should backup rpool/data of all nodes to the same destination. This way we wont have duplicate backups of the filesystems that are replicated. Because of various options, you can even migrate hosts and zfs-autobackup will be fine. (and it will get the next backup from the new node automaticly)
-
-In the example below we have 3 nodes, named h4, h5 and h6.
-
-The backup will go to a machine named smartos03.
-
-### Preparing the proxmox nodes
-
-On each node select the filesystems as following:
-
-```console
-root@h4:~# zfs set autobackup:h4_smartos03=true rpool
-root@h4:~# zfs set autobackup:h4_smartos03=false rpool/data
-root@h4:~# zfs set autobackup:data_smartos03=child rpool/data
-```
-
-* rpool will be backuped the usual way, and is named h4_smartos03. (each node will have a unique name)
-* rpool/data will be excluded from the usual backup
-* The CHILDREN of rpool/data be selected for a cluster wide backup named data_smartos03. (each node uses the same backup name)
-
-### Preparing the backup server
-
-Extra options needed for proxmox with HA:
-
-* --no-holds: To allow proxmox to destroy our snapshots if a VM migrates to another node.
-* --ignore-replicated: To ignore the replicated filesystems of proxmox on the receiving proxmox nodes. (e.g: only backup from the node where the VM is active)
-
-I use the following backup script on the backup server:
-
-```shell
-for H in h4 h5 h6; do
-  echo "################################### DATA $H"
-  #backup data filesystems to a common place
-  ./zfs-autobackup --ssh-source root@$H data_smartos03 zones/backup/zfsbackups/pxe1_data --clear-refreservation --clear-mountpoint  --ignore-transfer-errors --strip-path 2 --verbose --resume --ignore-replicated --no-holds $@
-  zabbix-job-status backup_$H""_data_smartos03 daily $? >/dev/null 2>/dev/null
-
-  echo "################################### RPOOL $H"
-  #backup rpool to own place
-  ./zfs-autobackup --ssh-source root@$H $H""_smartos03 zones/backup/zfsbackups/$H --verbose --clear-refreservation --clear-mountpoint  --resume --ignore-transfer-errors $@
-  zabbix-job-status backup_$H""_smartos03 daily $? >/dev/null 2>/dev/null
-done
-```
+* JetBrains (Provided me with a license for their whole professional product line, https://www.jetbrains.com/pycharm/ )
+* [DatuX](https://www.datux.nl) 

bin/zfs-autobackup

@@ -1 +0,0 @@
-zfs_autobackup

bin/zfs_autobackup.py

@@ -1 +0,0 @@
-zfs_autobackup

requirements.txt

@@ -0,0 +1,6 @@
+colorama
+argparse
+coverage
+python-coveralls
+unittest2
+mock

scripts/enctest

@@ -0,0 +1,33 @@
+#!/bin/bash
+
+#NOTE: usually the speed is the same, but the cpu usage is much higher for ccm
+
+set -e
+
+D=/enctest123
+DS=rpool$D
+
+echo sdflsakjfklsjfsda > key.txt
+
+dd if=/dev/urandom of=dump.bin bs=1M count=10000
+
+#readcache
+cat dump.bin > /dev/null
+
+zfs destroy $DS || true
+
+zfs create $DS
+
+echo Unencrypted:
+sync
+time ( cp dump.bin $D/dump.bin;  sync )
+
+
+for E in aes-128-ccm aes-192-ccm aes-256-ccm aes-128-gcm aes-192-gcm aes-256-gcm; do
+ zfs destroy $DS
+ zfs create -o encryption=$E -o keylocation=file://`pwd`/key.txt -o keyformat=passphrase $DS
+ echo $E
+ sync
+ time ( cp dump.bin $D/dump.bin;  sync )
+done
+

scripts/release

@@ -1,6 +1,6 @@
 #!/bin/bash
 
-set -e 
+set -e
 
 
 rm -rf dist
@@ -15,3 +15,4 @@ source token
 python3 -m twine check dist/*
 python3 -m twine upload dist/*
 
+git push --tags

scripts/releasetest

@@ -1,6 +1,6 @@
 #!/bin/bash
 
-set -e 
+set -e
 
 
 rm -rf dist
@@ -14,4 +14,3 @@ source tokentest
 
 python3 -m twine check dist/*
 python3 -m twine upload --repository-url https://test.pypi.org/legacy/ dist/* --verbose
-

setup.py

@@ -1,24 +1,30 @@
 import setuptools
-import bin.zfs_autobackup
+from zfs_autobackup.ZfsAutobackup import ZfsAutobackup
 import os
 
-os.system("git tag -m'' -a v{}".format(bin.zfs_autobackup.VERSION))
-
 with open("README.md", "r") as fh:
     long_description = fh.read()
 
 setuptools.setup(
-    name="zfs_autobackup", 
-    version=bin.zfs_autobackup.VERSION,
+    name="zfs_autobackup",
+    version=ZfsAutobackup.VERSION,
     author="Edwin Eefting",
     author_email="edwin@datux.nl",
     description="ZFS autobackup is used to periodicly backup ZFS filesystems to other locations. It tries to be the most friendly to use and easy to debug ZFS backup tool.",
     long_description=long_description,
     long_description_content_type="text/markdown",
-    
+
     url="https://github.com/psy0rz/zfs_autobackup",
-    scripts=["bin/zfs_autobackup", "bin/zfs-autobackup"],
+    entry_points={
+        'console_scripts':
+            [
+                'zfs-autobackup = zfs_autobackup.ZfsAutobackup:cli',
+                'zfs-autoverify = zfs_autobackup.ZfsAutoverify:cli',
+                'zfs-check = zfs_autobackup.ZfsCheck:cli',
+            ]
+    },
     packages=setuptools.find_packages(),
+
     classifiers=[
         "Programming Language :: Python :: 2",
         "Programming Language :: Python :: 3",

tests/autoruntests

@@ -0,0 +1,6 @@
+#!/bin/bash
+
+#NOTE: run from top directory
+
+find tests/*.py zfs_autobackup/*.py| entr -r ./tests/run_tests $@
+

tests/basetest.py

@@ -0,0 +1,107 @@
+
+# To run tests as non-root, use this hack:
+# chmod 4755 /usr/sbin/zpool /usr/sbin/zfs
+
+import sys
+
+#dirty hack for this error:
+#AttributeError: module 'collections' has no attribute 'MutableMapping'
+
+if sys.version_info.major == 3 and sys.version_info.minor >= 10:
+    import collections
+    setattr(collections, "MutableMapping", collections.abc.MutableMapping)
+
+import subprocess
+import random
+
+#default test stuff
+import unittest2
+import subprocess
+import time
+from pprint import *
+from zfs_autobackup.ZfsAutobackup import *
+from zfs_autobackup.ZfsAutoverify import *
+from zfs_autobackup.ZfsCheck import *
+from zfs_autobackup.util import *
+from mock import *
+import contextlib
+import sys
+import io
+
+TEST_POOLS="test_source1 test_source2 test_target1"
+ZFS_USERSPACE=  subprocess.check_output("dpkg-query -W zfsutils-linux |cut -f2", shell=True).decode('utf-8').rstrip()
+ZFS_KERNEL=     subprocess.check_output("modinfo zfs|grep ^version |sed 's/.* //'", shell=True).decode('utf-8').rstrip()
+
+print("###########################################")
+print("#### Unit testing against:")
+print("#### Python                :"+sys.version.replace("\n", " "))
+print("#### ZFS userspace         :"+ZFS_USERSPACE)
+print("#### ZFS kernel            :"+ZFS_KERNEL)
+print("#############################################")
+
+
+
+# for python2 compatibility
+if sys.version_info.major==2:
+    OutputIO=io.BytesIO
+else:
+    OutputIO=io.StringIO
+
+
+# for python2 compatibility (python 3 has this already)
+@contextlib.contextmanager
+def redirect_stdout(target):
+    original = sys.stdout
+    try:
+        sys.stdout = target
+        yield
+    finally:
+        sys.stdout = original
+
+# for python2 compatibility (python 3 has this already)
+@contextlib.contextmanager
+def redirect_stderr(target):
+    original = sys.stderr
+    try:
+        sys.stderr = target
+        yield
+    finally:
+        sys.stderr = original
+
+
+
+def shelltest(cmd):
+    """execute and print result as nice copypastable string for unit tests (adds extra newlines on top/bottom)"""
+
+    ret=(subprocess.check_output("SUDO_ASKPASS=./password.sh sudo -A "+cmd , shell=True).decode('utf-8'))
+
+    print("######### result of: {}".format(cmd))
+    print(ret)
+    print("#########")
+    ret='\n'+ret
+    return(ret)
+
+def prepare_zpools():
+    print("Preparing zfs filesystems...")
+
+    #need ram blockdevice
+    subprocess.check_call("modprobe brd rd_size=512000", shell=True)
+
+    #remove old stuff
+    subprocess.call("zpool destroy test_source1 2>/dev/null", shell=True)
+    subprocess.call("zpool destroy test_source2 2>/dev/null", shell=True)
+    subprocess.call("zpool destroy test_target1 2>/dev/null", shell=True)
+
+    #create pools
+    subprocess.check_call("zpool create test_source1 /dev/ram0", shell=True)
+    subprocess.check_call("zpool create test_source2 /dev/ram1", shell=True)
+    subprocess.check_call("zpool create test_target1 /dev/ram2", shell=True)
+
+    #create test structure
+    subprocess.check_call("zfs create -p test_source1/fs1/sub", shell=True)
+    subprocess.check_call("zfs create -p test_source2/fs2/sub", shell=True)
+    subprocess.check_call("zfs create -p test_source2/fs3/sub", shell=True)
+    subprocess.check_call("zfs set autobackup:test=true test_source1/fs1", shell=True)
+    subprocess.check_call("zfs set autobackup:test=child test_source2/fs2", shell=True)
+
+    print("Prepare done")

tests/data/partial

@@ -0,0 +1 @@
+xC<78><43>ʟ<EFBFBD>ZG<5A><47>М<EFBFBD><D09C><EFBFBD>?<3F><><1D>ZG<>#<0F><>,<>ƻ<>Q=<3D>><3E>ك1<D983>NU<4E><15>u<>{Zj;<3B>`<60><19><19><>Dv<44><76>Q<EFBFBD>j<EFBFBD>voQFN<46><4E><EFBFBD><EFBFBD><EFBFBD>;3Sa<53>R<EFBFBD>^2Z<32><5A>

tests/run_test

@@ -0,0 +1,5 @@
+#!/bin/bash
+
+#run one test. start from main directory
+
+python -m unittest discover tests $@ -vvvf

tests/run_tests

@@ -0,0 +1,29 @@
+#!/bin/bash 
+
+SCRIPTDIR=`dirname $0`
+
+#cd $SCRIPTDIR || exit 1
+
+
+if [ "$USER" != "root" ]; then
+    echo "Need root to do proper zfs testing"
+    exit 1
+fi
+
+
+# test needs ssh access to localhost for testing
+if ! [ -e /root/.ssh/id_rsa ]; then
+    ssh-keygen -t rsa -f /root/.ssh/id_rsa -P '' || exit 1
+    cat /root/.ssh/id_rsa.pub  >> /root/.ssh/authorized_keys || exit 1
+    ssh -oStrictHostKeyChecking=no localhost true || exit 1
+fi
+
+umount /tmp/ZfsCheck*
+
+coverage run --branch --source zfs_autobackup -m unittest discover -vvvvf $SCRIPTDIR $@ 2>&1
+EXIT=$?
+
+echo
+coverage report
+
+exit $EXIT

tests/test_blockhasher.py

@@ -0,0 +1,157 @@
+from basetest import *
+from zfs_autobackup.BlockHasher import BlockHasher
+
+
+# make VERY sure this works correctly under all circumstances.
+
+# sha1 sums of files, (bs=4096)
+# da39a3ee5e6b4b0d3255bfef95601890afd80709  empty
+# 642027d63bb0afd7e0ba197f2c66ad03e3d70de1  partial
+# 3c0bf91170d873b8e327d3bafb6bc074580d11b7  whole
+# 2e863f1fcccd6642e4e28453eba10d2d3f74d798  whole2
+# 959e6b58078f0cfd2fb3d37e978fda51820473ff  whole_whole2
+# 309ffffba2e1977d12f3b7469971f30d28b94bd8  whole_whole2_partial
+
+class TestBlockHasher(unittest2.TestCase):
+
+    def setUp(self):
+        pass
+
+    def test_empty(self):
+        block_hasher = BlockHasher(count=1)
+        self.assertEqual(
+            list(block_hasher.generate("tests/data/empty")),
+            []
+        )
+
+    def test_partial(self):
+        block_hasher = BlockHasher(count=1)
+        self.assertEqual(
+            list(block_hasher.generate("tests/data/partial")),
+            [(0, "642027d63bb0afd7e0ba197f2c66ad03e3d70de1")]
+        )
+
+    def test_whole(self):
+        block_hasher = BlockHasher(count=1)
+        self.assertEqual(
+            list(block_hasher.generate("tests/data/whole")),
+            [(0, "3c0bf91170d873b8e327d3bafb6bc074580d11b7")]
+        )
+
+    def test_whole2(self):
+        block_hasher = BlockHasher(count=1)
+        self.assertEqual(
+            list(block_hasher.generate("tests/data/whole_whole2")),
+            [
+                (0, "3c0bf91170d873b8e327d3bafb6bc074580d11b7"),
+                (1, "2e863f1fcccd6642e4e28453eba10d2d3f74d798")
+            ]
+        )
+
+    def test_wwp(self):
+        block_hasher = BlockHasher(count=1)
+        self.assertEqual(
+            list(block_hasher.generate("tests/data/whole_whole2_partial")),
+            [
+                (0, "3c0bf91170d873b8e327d3bafb6bc074580d11b7"),  # whole
+                (1, "2e863f1fcccd6642e4e28453eba10d2d3f74d798"),  # whole2
+                (2, "642027d63bb0afd7e0ba197f2c66ad03e3d70de1")  # partial
+            ]
+        )
+
+    def test_wwp_count2(self):
+        block_hasher = BlockHasher(count=2)
+        self.assertEqual(
+            list(block_hasher.generate("tests/data/whole_whole2_partial")),
+            [
+                (0, "959e6b58078f0cfd2fb3d37e978fda51820473ff"),  # whole_whole2
+                (1, "642027d63bb0afd7e0ba197f2c66ad03e3d70de1")  # partial
+            ]
+        )
+
+    def test_big(self):
+        block_hasher = BlockHasher(count=10)
+        self.assertEqual(
+            list(block_hasher.generate("tests/data/whole_whole2_partial")),
+            [
+                (0, "309ffffba2e1977d12f3b7469971f30d28b94bd8"),  # whole_whole2_partial
+            ])
+
+    def test_blockhash_compare(self):
+        #no errors
+        block_hasher = BlockHasher(count=1)
+        generator = block_hasher.generate("tests/data/whole_whole2_partial")
+        self.assertEqual([], list(block_hasher.compare("tests/data/whole_whole2_partial", generator)))
+
+        #compare file is smaller (EOF errors)
+        block_hasher = BlockHasher(count=1)
+        generator = block_hasher.generate("tests/data/whole_whole2_partial")
+        self.assertEqual(
+            [(1, '2e863f1fcccd6642e4e28453eba10d2d3f74d798', 'EOF'),
+             (2, '642027d63bb0afd7e0ba197f2c66ad03e3d70de1', 'EOF')],
+            list(block_hasher.compare("tests/data/whole", generator)))
+
+        #no errors, huge chunks
+        block_hasher = BlockHasher(count=10)
+        generator = block_hasher.generate("tests/data/whole_whole2_partial")
+        self.assertEqual([], list(block_hasher.compare("tests/data/whole_whole2_partial", generator)))
+
+        # different order to make sure seek functions are ok
+        block_hasher = BlockHasher(count=1)
+        checksums = list(block_hasher.generate("tests/data/whole_whole2_partial"))
+        checksums.reverse()
+        self.assertEqual([], list(block_hasher.compare("tests/data/whole_whole2_partial", checksums)))
+
+    def test_skip1(self):
+        block_hasher = BlockHasher(count=1, skip=1)
+        self.assertEqual(
+            list(block_hasher.generate("tests/data/whole_whole2_partial")),
+            [
+                (0, "3c0bf91170d873b8e327d3bafb6bc074580d11b7"),  # whole
+                # (1, "2e863f1fcccd6642e4e28453eba10d2d3f74d798"),  # whole2
+                (2, "642027d63bb0afd7e0ba197f2c66ad03e3d70de1")  # partial
+            ]
+        )
+
+        #should continue the pattern on the next file:
+        self.assertEqual(
+            list(block_hasher.generate("tests/data/whole_whole2_partial")),
+            [
+                # (0, "3c0bf91170d873b8e327d3bafb6bc074580d11b7"),  # whole
+                (1, "2e863f1fcccd6642e4e28453eba10d2d3f74d798"),  # whole2
+                # (2, "642027d63bb0afd7e0ba197f2c66ad03e3d70de1")  # partial
+            ]
+        )
+
+    def test_skip6(self):
+        block_hasher = BlockHasher(count=1, skip=6)
+        self.assertEqual(
+            list(block_hasher.generate("tests/data/whole_whole2_partial")),
+            [
+                (0, "3c0bf91170d873b8e327d3bafb6bc074580d11b7"),  # whole
+                # (1, "2e863f1fcccd6642e4e28453eba10d2d3f74d798"),  # whole2
+                # (2, "642027d63bb0afd7e0ba197f2c66ad03e3d70de1")  # partial
+            ]
+        )
+
+        #all blocks of next file are skipped
+        self.assertEqual(
+            list(block_hasher.generate("tests/data/whole_whole2_partial")),
+            [
+                # (0, "3c0bf91170d873b8e327d3bafb6bc074580d11b7"),  # whole
+                # (1, "2e863f1fcccd6642e4e28453eba10d2d3f74d798"),  # whole2
+                # (2, "642027d63bb0afd7e0ba197f2c66ad03e3d70de1")  # partial
+            ]
+        )
+
+        #first block of this one is the 6th to be skipped:
+        self.assertEqual(
+            list(block_hasher.generate("tests/data/whole_whole2_partial")),
+            [
+                # (0, "3c0bf91170d873b8e327d3bafb6bc074580d11b7"),  # whole
+                (1, "2e863f1fcccd6642e4e28453eba10d2d3f74d798"),  # whole2
+                # (2, "642027d63bb0afd7e0ba197f2c66ad03e3d70de1")  # partial
+            ]
+        )
+
+    #NOTE: compare doesnt use skip. thats the job of its input generator

tests/test_cmdpipe.py

@@ -0,0 +1,175 @@
+from basetest import *
+from zfs_autobackup.CmdPipe import CmdPipe,CmdItem
+
+
+class TestCmdPipe(unittest2.TestCase):
+
+    def test_single(self):
+        """single process stdout and stderr"""
+        p=CmdPipe(readonly=False, inp=None)
+        err=[]
+        out=[]
+        p.add(CmdItem(["ls", "-d", "/", "/", "/nonexistent"], stderr_handler=lambda line: err.append(line), exit_handler=lambda exit_code: self.assertEqual(exit_code,2), stdout_handler=lambda line: out.append(line)))
+        executed=p.execute()
+
+        self.assertEqual(err, ["ls: cannot access '/nonexistent': No such file or directory"])
+        self.assertEqual(out, ["/","/"])
+        self.assertIsNone(executed)
+
+    def test_input(self):
+        """test stdinput"""
+        p=CmdPipe(readonly=False, inp="test")
+        err=[]
+        out=[]
+        p.add(CmdItem(["cat"], stderr_handler=lambda line: err.append(line), exit_handler=lambda exit_code: self.assertEqual(exit_code,0), stdout_handler=lambda line: out.append(line) ))
+        executed=p.execute()
+
+        self.assertEqual(err, [])
+        self.assertEqual(out, ["test"])
+        self.assertIsNone(executed)
+
+    def test_pipe(self):
+        """test piped"""
+        p=CmdPipe(readonly=False)
+        err1=[]
+        err2=[]
+        err3=[]
+        out=[]
+        p.add(CmdItem(["echo", "test"], stderr_handler=lambda line: err1.append(line), exit_handler=lambda exit_code: self.assertEqual(exit_code,0)))
+        p.add(CmdItem(["tr", "e", "E"], stderr_handler=lambda line: err2.append(line), exit_handler=lambda exit_code: self.assertEqual(exit_code,0)))
+        p.add(CmdItem(["tr", "t", "T"], stderr_handler=lambda line: err3.append(line), exit_handler=lambda exit_code: self.assertEqual(exit_code,0), stdout_handler=lambda line: out.append(line)))
+        executed=p.execute()
+
+        self.assertEqual(err1, [])
+        self.assertEqual(err2, [])
+        self.assertEqual(err3, [])
+        self.assertEqual(out, ["TEsT"])
+        self.assertIsNone(executed)
+
+        #test str representation as well
+        self.assertEqual(str(p), "(echo test) | (tr e E) | (tr t T)")
+
+    def test_pipeerrors(self):
+        """test piped stderrs """
+        p=CmdPipe(readonly=False)
+        err1=[]
+        err2=[]
+        err3=[]
+        out=[]
+        p.add(CmdItem(["ls", "/nonexistent1"], stderr_handler=lambda line: err1.append(line), exit_handler=lambda exit_code: self.assertEqual(exit_code,2)))
+        p.add(CmdItem(["ls", "/nonexistent2"], stderr_handler=lambda line: err2.append(line), exit_handler=lambda exit_code: self.assertEqual(exit_code,2)))
+        p.add(CmdItem(["ls", "/nonexistent3"], stderr_handler=lambda line: err3.append(line), exit_handler=lambda exit_code: self.assertEqual(exit_code,2), stdout_handler=lambda line: out.append(line)))
+        executed=p.execute()
+
+        self.assertEqual(err1, ["ls: cannot access '/nonexistent1': No such file or directory"])
+        self.assertEqual(err2, ["ls: cannot access '/nonexistent2': No such file or directory"])
+        self.assertEqual(err3, ["ls: cannot access '/nonexistent3': No such file or directory"])
+        self.assertEqual(out, [])
+        self.assertIsNone(executed)
+
+    def test_exitcode(self):
+        """test piped exitcodes """
+        p=CmdPipe(readonly=False)
+        err1=[]
+        err2=[]
+        err3=[]
+        out=[]
+        p.add(CmdItem(["bash", "-c", "exit 1"], stderr_handler=lambda line: err1.append(line), exit_handler=lambda exit_code: self.assertEqual(exit_code,1)))
+        p.add(CmdItem(["bash", "-c", "exit 2"], stderr_handler=lambda line: err2.append(line), exit_handler=lambda exit_code: self.assertEqual(exit_code,2)))
+        p.add(CmdItem(["bash", "-c", "exit 3"], stderr_handler=lambda line: err3.append(line), exit_handler=lambda exit_code: self.assertEqual(exit_code,3), stdout_handler=lambda line: out.append(line)))
+        executed=p.execute()
+
+        self.assertEqual(err1, [])
+        self.assertEqual(err2, [])
+        self.assertEqual(err3, [])
+        self.assertEqual(out, [])
+        self.assertIsNone(executed)
+
+    def test_readonly_execute(self):
+        """everything readonly, just should execute"""
+
+        p=CmdPipe(readonly=True)
+        err1=[]
+        err2=[]
+        out=[]
+
+        def true_exit(exit_code):
+            return True
+
+        p.add(CmdItem(["echo", "test1"], stderr_handler=lambda line: err1.append(line), exit_handler=true_exit, readonly=True))
+        p.add(CmdItem(["echo", "test2"], stderr_handler=lambda line: err2.append(line), exit_handler=true_exit, readonly=True, stdout_handler=lambda line: out.append(line)))
+        executed=p.execute()
+
+        self.assertEqual(err1, [])
+        self.assertEqual(err2, [])
+        self.assertEqual(out, ["test2"])
+        self.assertTrue(executed)
+
+    def test_readonly_skip(self):
+        """one command not readonly, skip"""
+
+        p=CmdPipe(readonly=True)
+        err1=[]
+        err2=[]
+        out=[]
+        p.add(CmdItem(["echo", "test1"], stderr_handler=lambda line: err1.append(line), readonly=False))
+        p.add(CmdItem(["echo", "test2"], stderr_handler=lambda line: err2.append(line), readonly=True, stdout_handler=lambda line: out.append(line)))
+        executed=p.execute()
+
+        self.assertEqual(err1, [])
+        self.assertEqual(err2, [])
+        self.assertEqual(out, [])
+        self.assertTrue(executed)
+
+    def test_no_handlers(self):
+        with self.assertRaises(Exception):
+            p=CmdPipe()
+            p.add(CmdItem([ "echo" ]))
+            p.execute()
+
+        #NOTE: this will give some resource warnings
+
+    def test_manual_pipes(self):
+
+        # manual piping means: a command in the pipe has a stdout_handler, which is responsible for sending the data into the next item of the pipe.
+
+        result=[]
+
+
+        def stdout_handler(line):
+            item2.process.stdin.write(line.encode('utf8'))
+
+            # item2.process.stdin.close()
+
+        item1=CmdItem(["echo", "test"], stdout_handler=stdout_handler)
+        item2=CmdItem(["tr", "e", "E"], stdout_handler=lambda line: result.append(line))
+
+        p=CmdPipe()
+        p.add(item1)
+        p.add(item2)
+        p.execute()
+
+        self.assertEqual(result, ["tEst"])
+
+    def test_multiprocess(self):
+
+        #dont do any piping at all, just run multiple processes and handle outputs
+
+        result1=[]
+        result2=[]
+        result3=[]
+
+        item1=CmdItem(["echo", "test1"], stdout_handler=lambda line: result1.append(line))
+        item2=CmdItem(["echo", "test2"], stdout_handler=lambda line: result2.append(line))
+        item3=CmdItem(["echo", "test3"], stdout_handler=lambda line: result3.append(line))
+
+        p=CmdPipe()
+        p.add(item1)
+        p.add(item2)
+        p.add(item3)
+        p.execute()
+
+        self.assertEqual(result1, ["test1"])
+        self.assertEqual(result2, ["test2"])
+        self.assertEqual(result3, ["test3"])
+

tests/test_destroymissing.py

@@ -0,0 +1,135 @@
+
+from basetest import *
+
+
+class TestZfsNode(unittest2.TestCase):
+
+    def setUp(self):
+        prepare_zpools()
+        self.longMessage=True
+
+
+
+    def  test_destroymissing(self):
+
+        #initial backup
+        with patch('time.strftime', return_value="test-19101111000000"): #1000 years in past
+            self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose --no-holds".split(" ")).run())
+
+        with patch('time.strftime', return_value="test-20101111000000"): #far in past
+            self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose --no-holds --allow-empty".split(" ")).run())
+
+
+        with self.subTest("Should do nothing yet"):
+            with OutputIO() as buf:
+                with redirect_stdout(buf):
+                    self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose --no-snapshot --destroy-missing 0s".split(" ")).run())
+
+                print(buf.getvalue())
+                self.assertNotIn(": Destroy missing", buf.getvalue())
+
+
+        with self.subTest("missing dataset of us that still has children"):
+
+            #just deselect it so it counts as 'missing'
+            shelltest("zfs set autobackup:test=child test_source1/fs1")
+
+            with OutputIO() as buf:
+                with redirect_stdout(buf), redirect_stderr(buf):
+                        self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose --no-snapshot --destroy-missing 0s".split(" ")).run())
+
+                print(buf.getvalue())
+                #should have done the snapshot cleanup for destoy missing:
+                self.assertIn("fs1@test-19101111000000: Destroying", buf.getvalue())
+
+                self.assertIn("fs1: Destroy missing: Still has children here.", buf.getvalue())
+
+            shelltest("zfs inherit autobackup:test test_source1/fs1")
+
+
+        with self.subTest("Normal destroyed leaf"):
+            shelltest("zfs destroy -r test_source1/fs1/sub")
+
+            #wait for deadline of last snapshot
+            with OutputIO() as buf:
+                with redirect_stdout(buf):
+                    #100y: lastest should not be old enough, while second to latest snapshot IS old enough:
+                    self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose --no-snapshot --destroy-missing 100y".split(" ")).run())
+
+                print(buf.getvalue())
+                self.assertIn(": Waiting for deadline", buf.getvalue())
+
+            #past deadline, destroy
+            with OutputIO() as buf:
+                with redirect_stdout(buf):
+                    self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose --no-snapshot --destroy-missing 1y".split(" ")).run())
+
+                print(buf.getvalue())
+                self.assertIn("sub: Destroying", buf.getvalue())
+
+
+        with self.subTest("Leaf with other snapshot still using it"):
+            shelltest("zfs destroy -r test_source1/fs1")
+            shelltest("zfs snapshot -r test_target1/test_source1/fs1@other1")
+
+
+            with OutputIO() as buf:
+                with redirect_stdout(buf):
+                    self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose --no-snapshot --destroy-missing 0s".split(" ")).run())
+
+                print(buf.getvalue())
+
+                #cant finish because still in use:
+                self.assertIn("fs1: Destroy missing: Still in use", buf.getvalue())
+
+            shelltest("zfs destroy test_target1/test_source1/fs1@other1")
+
+
+        with self.subTest("In use by clone"):
+            shelltest("zfs clone test_target1/test_source1/fs1@test-20101111000000 test_target1/clone1")
+
+            with OutputIO() as buf:
+                with redirect_stdout(buf), redirect_stderr(buf):
+                        self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose --no-snapshot --destroy-missing 0s".split(" ")).run())
+
+                print(buf.getvalue())
+                #now tries to destroy our own last snapshot (before the final destroy of the dataset)
+                self.assertIn("fs1@test-20101111000000: Destroying", buf.getvalue())
+                #but cant finish because still in use:
+                self.assertIn("fs1: Error during --destroy-missing", buf.getvalue())
+
+            shelltest("zfs destroy test_target1/clone1")
+
+
+        with self.subTest("Should leave test_source1 parent"):
+
+            with OutputIO() as buf:
+                with redirect_stdout(buf), redirect_stderr(buf):
+                        self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose --no-snapshot --destroy-missing 0s".split(" ")).run())
+
+                print(buf.getvalue())
+                #should have done the snapshot cleanup for destoy missing:
+                self.assertIn("fs1: Destroying", buf.getvalue())
+
+            with OutputIO() as buf:
+                with redirect_stdout(buf), redirect_stderr(buf):
+                        self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose --no-snapshot --destroy-missing 0s".split(" ")).run())
+
+                print(buf.getvalue())
+                #on second run it sees the dangling ex-parent but doesnt know what to do with it (since it has no own snapshot)
+                self.assertIn("test_source1: Destroy missing: has no snapshots made by us", buf.getvalue())
+
+
+
+
+        #end result
+        r=shelltest("zfs list -H -o name -r -t all test_target1")
+        self.assertMultiLineEqual(r,"""
+test_target1
+test_target1/test_source1
+test_target1/test_source2
+test_target1/test_source2/fs2
+test_target1/test_source2/fs2/sub
+test_target1/test_source2/fs2/sub@test-19101111000000
+test_target1/test_source2/fs2/sub@test-20101111000000
+""")

tests/test_encryption.py

@@ -0,0 +1,193 @@
+from zfs_autobackup.CmdPipe import CmdPipe
+from basetest import *
+import time
+
+# We have to do a LOT to properly test encryption/decryption/raw transfers
+#
+# For every scenario we need at least:
+# - plain source dataset
+# - encrypted source dataset
+# - plain target path
+# - encrypted target path
+# - do a full transfer
+# - do a incremental transfer
+
+# Scenarios:
+# - Raw transfer
+# - Decryption transfer (--decrypt)
+# - Encryption transfer (--encrypt)
+# - Re-encryption transfer (--decrypt --encrypt)
+
+class TestZfsEncryption(unittest2.TestCase):
+
+
+    def setUp(self):
+        prepare_zpools()
+
+        try:
+            shelltest("zfs get encryption test_source1")
+        except:
+            self.skipTest("Encryption not supported on this ZFS version.")
+
+    def prepare_encrypted_dataset(self, key, path, unload_key=False):
+
+        # create encrypted source dataset
+        shelltest("rm /tmp/zfstest.key 2>/dev/null;true")
+        shelltest("echo {} > /tmp/zfstest.key".format(key))
+        shelltest("zfs create -o keylocation=file:///tmp/zfstest.key -o keyformat=passphrase -o encryption=on {}".format(path))
+
+        if unload_key:
+            shelltest("zfs unmount {}".format(path))
+            shelltest("zfs unload-key {}".format(path))
+
+        # r=shelltest("dd if=/dev/zero of=/test_source1/fs1/enc1/data.txt bs=200000 count=1")
+
+    def  test_raw(self):
+        """send encrypted data unaltered (standard operation)"""
+
+        self.prepare_encrypted_dataset("11111111", "test_source1/fs1/encryptedsource")
+        self.prepare_encrypted_dataset("11111111", "test_source1/fs1/encryptedsourcekeyless", unload_key=True) # raw mode shouldn't need a key
+        self.prepare_encrypted_dataset("22222222", "test_target1/encryptedtarget")
+
+        with patch('time.strftime', return_value="test-20101111000000"):
+            self.assertFalse(ZfsAutobackup("test test_target1 --verbose --no-progress --allow-empty --exclude-received".split(" ")).run())
+            self.assertFalse(ZfsAutobackup("test test_target1/encryptedtarget --verbose --no-progress --no-snapshot --exclude-received".split(" ")).run())
+
+        with patch('time.strftime', return_value="test-20101111000001"):
+            self.assertFalse(ZfsAutobackup("test test_target1 --verbose --no-progress --allow-empty --exclude-received".split(" ")).run())
+            self.assertFalse(ZfsAutobackup("test test_target1/encryptedtarget --verbose --no-progress --no-snapshot --exclude-received".split(" ")).run())
+
+        r = shelltest("zfs get -r -t filesystem encryptionroot test_target1")
+        self.assertMultiLineEqual(r,"""
+NAME                                                                  PROPERTY        VALUE                                                                 SOURCE
+test_target1                                                          encryptionroot  -                                                                     -
+test_target1/encryptedtarget                                          encryptionroot  test_target1/encryptedtarget                                          -
+test_target1/encryptedtarget/test_source1                             encryptionroot  test_target1/encryptedtarget                                          -
+test_target1/encryptedtarget/test_source1/fs1                         encryptionroot  -                                                                     -
+test_target1/encryptedtarget/test_source1/fs1/encryptedsource         encryptionroot  test_target1/encryptedtarget/test_source1/fs1/encryptedsource         -
+test_target1/encryptedtarget/test_source1/fs1/encryptedsourcekeyless  encryptionroot  test_target1/encryptedtarget/test_source1/fs1/encryptedsourcekeyless  -
+test_target1/encryptedtarget/test_source1/fs1/sub                     encryptionroot  -                                                                     -
+test_target1/encryptedtarget/test_source2                             encryptionroot  test_target1/encryptedtarget                                          -
+test_target1/encryptedtarget/test_source2/fs2                         encryptionroot  test_target1/encryptedtarget                                          -
+test_target1/encryptedtarget/test_source2/fs2/sub                     encryptionroot  -                                                                     -
+test_target1/test_source1                                             encryptionroot  -                                                                     -
+test_target1/test_source1/fs1                                         encryptionroot  -                                                                     -
+test_target1/test_source1/fs1/encryptedsource                         encryptionroot  test_target1/test_source1/fs1/encryptedsource                         -
+test_target1/test_source1/fs1/encryptedsourcekeyless                  encryptionroot  test_target1/test_source1/fs1/encryptedsourcekeyless                  -
+test_target1/test_source1/fs1/sub                                     encryptionroot  -                                                                     -
+test_target1/test_source2                                             encryptionroot  -                                                                     -
+test_target1/test_source2/fs2                                         encryptionroot  -                                                                     -
+test_target1/test_source2/fs2/sub                                     encryptionroot  -                                                                     -
+""")
+
+    def  test_decrypt(self):
+        """decrypt data and store unencrypted (--decrypt)"""
+
+        self.prepare_encrypted_dataset("11111111", "test_source1/fs1/encryptedsource")
+        self.prepare_encrypted_dataset("22222222", "test_target1/encryptedtarget")
+
+        with patch('time.strftime', return_value="test-20101111000000"):
+            self.assertFalse(ZfsAutobackup("test test_target1 --verbose --no-progress --decrypt --allow-empty --exclude-received".split(" ")).run())
+            self.assertFalse(ZfsAutobackup("test test_target1/encryptedtarget --verbose --no-progress --decrypt --no-snapshot --exclude-received".split(" ")).run())
+
+        with patch('time.strftime', return_value="test-20101111000001"):
+            self.assertFalse(ZfsAutobackup("test test_target1 --verbose --no-progress --decrypt --allow-empty --exclude-received".split(" ")).run())
+            self.assertFalse(ZfsAutobackup("test test_target1/encryptedtarget --verbose --no-progress --decrypt --no-snapshot --exclude-received".split(" ")).run())
+
+        r = shelltest("zfs get -r -t filesystem encryptionroot test_target1")
+        self.assertEqual(r, """
+NAME                                                           PROPERTY        VALUE                         SOURCE
+test_target1                                                   encryptionroot  -                             -
+test_target1/encryptedtarget                                   encryptionroot  test_target1/encryptedtarget  -
+test_target1/encryptedtarget/test_source1                      encryptionroot  test_target1/encryptedtarget  -
+test_target1/encryptedtarget/test_source1/fs1                  encryptionroot  -                             -
+test_target1/encryptedtarget/test_source1/fs1/encryptedsource  encryptionroot  -                             -
+test_target1/encryptedtarget/test_source1/fs1/sub              encryptionroot  -                             -
+test_target1/encryptedtarget/test_source2                      encryptionroot  test_target1/encryptedtarget  -
+test_target1/encryptedtarget/test_source2/fs2                  encryptionroot  test_target1/encryptedtarget  -
+test_target1/encryptedtarget/test_source2/fs2/sub              encryptionroot  -                             -
+test_target1/test_source1                                      encryptionroot  -                             -
+test_target1/test_source1/fs1                                  encryptionroot  -                             -
+test_target1/test_source1/fs1/encryptedsource                  encryptionroot  -                             -
+test_target1/test_source1/fs1/sub                              encryptionroot  -                             -
+test_target1/test_source2                                      encryptionroot  -                             -
+test_target1/test_source2/fs2                                  encryptionroot  -                             -
+test_target1/test_source2/fs2/sub                              encryptionroot  -                             -
+""")
+
+    def  test_encrypt(self):
+        """send normal data set and store encrypted on the other side (--encrypt) issue #60 """
+
+        self.prepare_encrypted_dataset("11111111", "test_source1/fs1/encryptedsource")
+        self.prepare_encrypted_dataset("22222222", "test_target1/encryptedtarget")
+
+        with patch('time.strftime', return_value="test-20101111000000"):
+            self.assertFalse(ZfsAutobackup("test test_target1 --verbose --no-progress --encrypt --debug --allow-empty --exclude-received".split(" ")).run())
+            self.assertFalse(ZfsAutobackup("test test_target1/encryptedtarget --verbose --no-progress --encrypt --debug --no-snapshot --exclude-received".split(" ")).run())
+
+        with patch('time.strftime', return_value="test-20101111000001"):
+            self.assertFalse(ZfsAutobackup("test test_target1 --verbose --no-progress --encrypt --debug --allow-empty --exclude-received".split(" ")).run())
+            self.assertFalse(ZfsAutobackup("test test_target1/encryptedtarget --verbose --no-progress --encrypt --debug --no-snapshot --exclude-received".split(" ")).run())
+
+        r = shelltest("zfs get -r -t filesystem encryptionroot test_target1")
+        self.assertEqual(r, """
+NAME                                                           PROPERTY        VALUE                                                          SOURCE
+test_target1                                                   encryptionroot  -                                                              -
+test_target1/encryptedtarget                                   encryptionroot  test_target1/encryptedtarget                                   -
+test_target1/encryptedtarget/test_source1                      encryptionroot  test_target1/encryptedtarget                                   -
+test_target1/encryptedtarget/test_source1/fs1                  encryptionroot  test_target1/encryptedtarget                                   -
+test_target1/encryptedtarget/test_source1/fs1/encryptedsource  encryptionroot  test_target1/encryptedtarget/test_source1/fs1/encryptedsource  -
+test_target1/encryptedtarget/test_source1/fs1/sub              encryptionroot  test_target1/encryptedtarget                                   -
+test_target1/encryptedtarget/test_source2                      encryptionroot  test_target1/encryptedtarget                                   -
+test_target1/encryptedtarget/test_source2/fs2                  encryptionroot  test_target1/encryptedtarget                                   -
+test_target1/encryptedtarget/test_source2/fs2/sub              encryptionroot  test_target1/encryptedtarget                                   -
+test_target1/test_source1                                      encryptionroot  -                                                              -
+test_target1/test_source1/fs1                                  encryptionroot  -                                                              -
+test_target1/test_source1/fs1/encryptedsource                  encryptionroot  test_target1/test_source1/fs1/encryptedsource                  -
+test_target1/test_source1/fs1/sub                              encryptionroot  -                                                              -
+test_target1/test_source2                                      encryptionroot  -                                                              -
+test_target1/test_source2/fs2                                  encryptionroot  -                                                              -
+test_target1/test_source2/fs2/sub                              encryptionroot  -                                                              -
+""")
+
+    def test_reencrypt(self):
+        """reencrypt data (--decrypt --encrypt) """
+
+        self.prepare_encrypted_dataset("11111111", "test_source1/fs1/encryptedsource")
+        self.prepare_encrypted_dataset("22222222", "test_target1/encryptedtarget")
+
+        with patch('time.strftime', return_value="test-20101111000000"):
+            self.assertFalse(ZfsAutobackup(
+                "test test_target1 --verbose --no-progress --decrypt --encrypt --debug --allow-empty --exclude-received".split(" ")).run())
+            self.assertFalse(ZfsAutobackup(
+                "test test_target1/encryptedtarget --verbose --no-progress --decrypt --encrypt --debug --no-snapshot --exclude-received".split(
+                    " ")).run())
+
+        with patch('time.strftime', return_value="test-20101111000001"):
+            self.assertFalse(ZfsAutobackup(
+                "test test_target1 --verbose --no-progress --decrypt --encrypt --debug --allow-empty --exclude-received".split(" ")).run())
+            self.assertFalse(ZfsAutobackup(
+                "test test_target1/encryptedtarget --verbose --no-progress --decrypt --encrypt --debug --no-snapshot --exclude-received".split(
+                    " ")).run())
+
+        r = shelltest("zfs get -r -t filesystem encryptionroot test_target1")
+        self.assertEqual(r, """
+NAME                                                           PROPERTY        VALUE                         SOURCE
+test_target1                                                   encryptionroot  -                             -
+test_target1/encryptedtarget                                   encryptionroot  test_target1/encryptedtarget  -
+test_target1/encryptedtarget/test_source1                      encryptionroot  test_target1/encryptedtarget  -
+test_target1/encryptedtarget/test_source1/fs1                  encryptionroot  test_target1/encryptedtarget  -
+test_target1/encryptedtarget/test_source1/fs1/encryptedsource  encryptionroot  test_target1/encryptedtarget  -
+test_target1/encryptedtarget/test_source1/fs1/sub              encryptionroot  test_target1/encryptedtarget  -
+test_target1/encryptedtarget/test_source2                      encryptionroot  test_target1/encryptedtarget  -
+test_target1/encryptedtarget/test_source2/fs2                  encryptionroot  test_target1/encryptedtarget  -
+test_target1/encryptedtarget/test_source2/fs2/sub              encryptionroot  test_target1/encryptedtarget  -
+test_target1/test_source1                                      encryptionroot  -                             -
+test_target1/test_source1/fs1                                  encryptionroot  -                             -
+test_target1/test_source1/fs1/encryptedsource                  encryptionroot  -                             -
+test_target1/test_source1/fs1/sub                              encryptionroot  -                             -
+test_target1/test_source2                                      encryptionroot  -                             -
+test_target1/test_source2/fs2                                  encryptionroot  -                             -
+test_target1/test_source2/fs2/sub                              encryptionroot  -                             -
+""")
+

tests/test_executenode.py

@@ -0,0 +1,213 @@
+from basetest import *
+from zfs_autobackup.ExecuteNode import *
+
+print("THIS TEST REQUIRES SSH TO LOCALHOST")
+
+class TestExecuteNode(unittest2.TestCase):
+
+    # def setUp(self):
+
+    #     return super().setUp()
+
+    def basics(self, node ):
+
+        with self.subTest("simple echo"):
+            self.assertEqual(node.run(["echo","test"]), ["test"])
+
+        with self.subTest("error exit code"):
+            with self.assertRaises(ExecuteError):
+                node.run(["false"])
+
+        #
+        with self.subTest("multiline without tabsplit"):
+            self.assertEqual(node.run(["echo","l1c1\tl1c2\nl2c1\tl2c2"], tab_split=False), ["l1c1\tl1c2", "l2c1\tl2c2"])
+
+        #multiline tabsplit
+        with self.subTest("multiline tabsplit"):
+            self.assertEqual(node.run(["echo","l1c1\tl1c2\nl2c1\tl2c2"], tab_split=True), [['l1c1', 'l1c2'], ['l2c1', 'l2c2']])
+
+        #escaping test
+        with self.subTest("escape test"):
+            s="><`'\"@&$()$bla\\/.* !#test _+-={}[]|${bla} $bla"
+            self.assertEqual(node.run(["echo",s]), [s])
+
+        #return std err as well, trigger stderr by listing something non existing
+        with self.subTest("stderr return"):
+            (stdout, stderr)=node.run(["ls", "nonexistingfile"], return_stderr=True, valid_exitcodes=[2])
+            self.assertEqual(stdout,[])
+            self.assertRegex(stderr[0],"nonexistingfile")
+
+        #slow command, make sure things dont exit too early
+        with self.subTest("early exit test"):
+            start_time=time.time()
+            self.assertEqual(node.run(["sleep","1"]), [])
+            self.assertGreaterEqual(time.time()-start_time,1)
+
+        #input a string and check it via cat
+        with self.subTest("stdin input string"):
+            self.assertEqual(node.run(["cat"], inp="test"), ["test"])
+
+        #command that wants input, while we dont have input, shouldnt hang forever.
+        with self.subTest("stdin process with inp=None (shouldn't hang)"):
+            self.assertEqual(node.run(["cat"]), [])
+
+        # let the system do the piping with an unescaped |:
+        with self.subTest("system piping test"):
+
+            #first make sure the actual | character is still properly escaped:
+            self.assertEqual(node.run(["echo","|"]), ["|"])
+
+            #now pipe
+            self.assertEqual(node.run(["echo", "abc", node.PIPE, "tr", "a", "A" ]), ["Abc"])
+
+    def test_basics_local(self):
+        node=ExecuteNode(debug_output=True)
+        self.basics(node)
+
+    def test_basics_remote(self):
+        node=ExecuteNode(ssh_to="localhost", debug_output=True)
+        self.basics(node)
+
+    ################
+
+    def test_readonly(self):
+        node=ExecuteNode(debug_output=True, readonly=True)
+
+        self.assertEqual(node.run(["echo","test"], readonly=False), [])
+        self.assertEqual(node.run(["echo","test"], readonly=True), ["test"])
+
+
+    ################
+
+    def pipe(self, nodea, nodeb):
+
+        with self.subTest("pipe data"):
+            output=nodea.run(["dd", "if=/dev/zero", "count=1000"],pipe=True)
+            self.assertEqual(nodeb.run(["md5sum"], inp=output), ["816df6f64deba63b029ca19d880ee10a  -"])
+
+        with self.subTest("exit code both ends of pipe ok"):
+            output=nodea.run(["true"], pipe=True)
+            nodeb.run(["true"], inp=output)
+
+        with self.subTest("error on pipe input side"):
+            with self.assertRaises(ExecuteError):
+                output=nodea.run(["false"], pipe=True)
+                nodeb.run(["true"], inp=output)
+
+        with self.subTest("error on both sides, ignore exit codes"):
+            output=nodea.run(["false"], pipe=True, valid_exitcodes=[])
+            nodeb.run(["false"], inp=output, valid_exitcodes=[])
+
+        with self.subTest("error on pipe output side "):
+            with self.assertRaises(ExecuteError):
+                output=nodea.run(["true"], pipe=True)
+                nodeb.run(["false"], inp=output)
+
+        with self.subTest("error on both sides of pipe"):
+            with self.assertRaises(ExecuteError):
+                output=nodea.run(["false"], pipe=True)
+                nodeb.run(["false"], inp=output)
+
+        with self.subTest("check stderr on pipe output side"):
+            output=nodea.run(["true"], pipe=True, valid_exitcodes=[0])
+            (stdout, stderr)=nodeb.run(["ls", "nonexistingfile"], inp=output, return_stderr=True, valid_exitcodes=[2])
+            self.assertEqual(stdout,[])
+            self.assertRegex(stderr[0], "nonexistingfile" )
+
+        with self.subTest("check stderr on pipe input side (should be only printed)"):
+            output=nodea.run(["ls", "nonexistingfile"], pipe=True, valid_exitcodes=[2])
+            (stdout, stderr)=nodeb.run(["true"], inp=output, return_stderr=True, valid_exitcodes=[0])
+            self.assertEqual(stdout,[])
+            self.assertEqual(stderr,[])
+
+
+
+
+    def test_pipe_local_local(self):
+        nodea=ExecuteNode(debug_output=True)
+        nodeb=ExecuteNode(debug_output=True)
+        self.pipe(nodea, nodeb)
+
+    def test_pipe_remote_remote(self):
+        nodea=ExecuteNode(ssh_to="localhost", debug_output=True)
+        nodeb=ExecuteNode(ssh_to="localhost", debug_output=True)
+        self.pipe(nodea, nodeb)
+
+    def test_pipe_local_remote(self):
+        nodea=ExecuteNode(debug_output=True)
+        nodeb=ExecuteNode(ssh_to="localhost", debug_output=True)
+        self.pipe(nodea, nodeb)
+
+    def test_pipe_remote_local(self):
+        nodea=ExecuteNode(ssh_to="localhost", debug_output=True)
+        nodeb=ExecuteNode(debug_output=True)
+        self.pipe(nodea, nodeb)
+
+
+    def test_cwd(self):
+
+        nodea=ExecuteNode(ssh_to="localhost", debug_output=True)
+        nodeb=ExecuteNode(debug_output=True)
+
+        #change to a directory with a space and execute a system pipe, check if all piped commands are executed in correct directory.
+        shelltest("mkdir '/tmp/space test' 2>/dev/null; true")
+        self.assertEqual(nodea.run(cmd=["pwd", ExecuteNode.PIPE, "cat"], cwd="/tmp/space test"), ["/tmp/space test"])
+        self.assertEqual(nodea.run(cmd=["cat", ExecuteNode.PIPE, "pwd"], cwd="/tmp/space test"), ["/tmp/space test"])
+        self.assertEqual(nodeb.run(cmd=["pwd", ExecuteNode.PIPE, "cat"], cwd="/tmp/space test"), ["/tmp/space test"])
+        self.assertEqual(nodeb.run(cmd=["cat", ExecuteNode.PIPE, "pwd"], cwd="/tmp/space test"), ["/tmp/space test"])
+
+    def test_script_handlers(self):
+
+        def test(node):
+            results = []
+            node.script(lines=["echo line1", "echo line2 1>&2", "exit 123"],
+                                  stdout_handler=lambda line: results.append(line),
+                                  stderr_handler=lambda line: results.append(line),
+                                  exit_handler=lambda exit_code: results.append(exit_code),
+                                  valid_exitcodes=[123]
+                                  )
+
+            self.assertEqual(results, ["line1", "line2", 123 ])
+
+        with self.subTest("remote"):
+            test(ExecuteNode(ssh_to="localhost", debug_output=True))
+        #
+        with self.subTest("local"):
+            test(ExecuteNode(debug_output=True))
+
+    def test_script_defaults(self):
+
+        result=[]
+        nodea=ExecuteNode(debug_output=True)
+        nodea.script(lines=["echo test"], stdout_handler=lambda line: result.append(line))
+
+        self.assertEqual(result, ["test"])
+
+    def test_script_pipe(self):
+
+        result=[]
+        nodea=ExecuteNode()
+        cmd_pipe=nodea.script(lines=["echo test"], pipe=True)
+        nodea.script(lines=["tr e E"], inp=cmd_pipe,stdout_handler=lambda line: result.append(line))
+
+        self.assertEqual(result, ["tEst"])
+
+
+    def test_mixed(self):
+
+        #should be able to mix run() and script()
+        node=ExecuteNode()
+
+        result=[]
+        pipe=node.run(["echo", "test"], pipe=True)
+        node.script(["tr e E"], inp=pipe, stdout_handler=lambda line: result.append(line))
+
+        self.assertEqual(result, ["tEst"])
+
+
+
+
+
+
+if __name__ == '__main__':
+    unittest.main()

tests/test_externalfailures.py

@@ -0,0 +1,314 @@
+from basetest import *
+
+
+class TestExternalFailures(unittest2.TestCase):
+
+    def setUp(self):
+        prepare_zpools()
+        self.longMessage = True
+
+    # generate a resumable state
+    # NOTE: this generates two resumable test_target1/test_source1/fs1 and test_target1/test_source1/fs1/sub
+    def generate_resume(self):
+
+        r = shelltest("zfs set compress=off test_source1 test_target1")
+
+        # big change on source
+        r = shelltest("dd if=/dev/zero of=/test_source1/fs1/data bs=250M count=1")
+
+        # waste space on target
+        r = shelltest("dd if=/dev/zero of=/test_target1/waste bs=250M count=1")
+
+        # should fail and leave resume token (if supported)
+        self.assertTrue(ZfsAutobackup("test test_target1 --no-progress --verbose".split(" ")).run())
+
+        # free up space
+        r = shelltest("rm /test_target1/waste")
+        # sync
+        r = shelltest("zfs umount test_target1")
+        r = shelltest("zfs mount test_target1")
+
+    # resume initial backup
+    def test_initial_resume(self):
+
+        # inital backup, leaves resume token
+        with patch('time.strftime', return_value="test-20101111000000"):
+            self.generate_resume()
+
+        # --test should resume and succeed
+        with OutputIO() as buf:
+            with redirect_stdout(buf):
+                self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose --test".split(" ")).run())
+
+            print(buf.getvalue())
+
+            # did we really resume?
+            if "0.6.5" in ZFS_USERSPACE:
+                # abort this late, for beter coverage
+                self.skipTest("Resume not supported in this ZFS userspace version")
+            else:
+                self.assertIn(": resuming", buf.getvalue())
+
+        # should resume and succeed
+        with OutputIO() as buf:
+            with redirect_stdout(buf):
+                self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose".split(" ")).run())
+
+            print(buf.getvalue())
+
+            # did we really resume?
+            if "0.6.5" in ZFS_USERSPACE:
+                # abort this late, for beter coverage
+                self.skipTest("Resume not supported in this ZFS userspace version")
+            else:
+                self.assertIn(": resuming", buf.getvalue())
+
+        r = shelltest("zfs list -H -o name -r -t all test_target1")
+        self.assertMultiLineEqual(r, """
+test_target1
+test_target1/test_source1
+test_target1/test_source1/fs1
+test_target1/test_source1/fs1@test-20101111000000
+test_target1/test_source1/fs1/sub
+test_target1/test_source1/fs1/sub@test-20101111000000
+test_target1/test_source2
+test_target1/test_source2/fs2
+test_target1/test_source2/fs2/sub
+test_target1/test_source2/fs2/sub@test-20101111000000
+""")
+
+    # resume incremental backup
+    def test_incremental_resume(self):
+
+        # initial backup
+        with patch('time.strftime', return_value="test-20101111000000"):
+            self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose --allow-empty".split(" ")).run())
+
+        # incremental backup leaves resume token
+        with patch('time.strftime', return_value="test-20101111000001"):
+            self.generate_resume()
+
+        # --test should resume and succeed
+        with OutputIO() as buf:
+            with redirect_stdout(buf):
+                self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose --test".split(" ")).run())
+
+            print(buf.getvalue())
+
+            # did we really resume?
+            if "0.6.5" in ZFS_USERSPACE:
+                # abort this late, for beter coverage
+                self.skipTest("Resume not supported in this ZFS userspace version")
+            else:
+                self.assertIn(": resuming", buf.getvalue())
+
+        # should resume and succeed
+        with OutputIO() as buf:
+            with redirect_stdout(buf):
+                self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose".split(" ")).run())
+
+            print(buf.getvalue())
+
+            # did we really resume?
+            if "0.6.5" in ZFS_USERSPACE:
+                # abort this late, for beter coverage
+                self.skipTest("Resume not supported in this ZFS userspace version")
+            else:
+                self.assertIn(": resuming", buf.getvalue())
+
+        r = shelltest("zfs list -H -o name -r -t all test_target1")
+        self.assertMultiLineEqual(r, """
+test_target1
+test_target1/test_source1
+test_target1/test_source1/fs1
+test_target1/test_source1/fs1@test-20101111000000
+test_target1/test_source1/fs1@test-20101111000001
+test_target1/test_source1/fs1/sub
+test_target1/test_source1/fs1/sub@test-20101111000000
+test_target1/test_source2
+test_target1/test_source2/fs2
+test_target1/test_source2/fs2/sub
+test_target1/test_source2/fs2/sub@test-20101111000000
+""")
+
+    # generate an invalid resume token, and verify if its aborted automaticly
+    def test_initial_resumeabort(self):
+
+        if "0.6.5" in ZFS_USERSPACE:
+            self.skipTest("Resume not supported in this ZFS userspace version")
+
+        # inital backup, leaves resume token
+        with patch('time.strftime', return_value="test-20101111000000"):
+            self.generate_resume()
+
+        # remove corresponding source snapshot, so it becomes invalid
+        shelltest("zfs destroy test_source1/fs1@test-20101111000000")
+
+        # NOTE: it can only abort the initial dataset if it has no subs
+        shelltest("zfs destroy test_target1/test_source1/fs1/sub; true")
+
+        # --test try again, should abort old resume
+        with patch('time.strftime', return_value="test-20101111000001"):
+            self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose --test".split(" ")).run())
+
+        # try again, should abort old resume
+        with patch('time.strftime', return_value="test-20101111000001"):
+            self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose".split(" ")).run())
+
+        r = shelltest("zfs list -H -o name -r -t all test_target1")
+        self.assertMultiLineEqual(r, """
+test_target1
+test_target1/test_source1
+test_target1/test_source1/fs1
+test_target1/test_source1/fs1@test-20101111000001
+test_target1/test_source1/fs1/sub
+test_target1/test_source1/fs1/sub@test-20101111000000
+test_target1/test_source2
+test_target1/test_source2/fs2
+test_target1/test_source2/fs2/sub
+test_target1/test_source2/fs2/sub@test-20101111000000
+""")
+
+    # generate an invalid resume token, and verify if its aborted automaticly
+    def test_incremental_resumeabort(self):
+
+        if "0.6.5" in ZFS_USERSPACE:
+            self.skipTest("Resume not supported in this ZFS userspace version")
+
+        # initial backup
+        with patch('time.strftime', return_value="test-20101111000000"):
+            self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose --allow-empty".split(" ")).run())
+
+        # icremental backup, leaves resume token
+        with patch('time.strftime', return_value="test-20101111000001"):
+            self.generate_resume()
+
+        # remove corresponding source snapshot, so it becomes invalid
+        shelltest("zfs destroy test_source1/fs1@test-20101111000001")
+
+        # --test try again, should abort old resume
+        with patch('time.strftime', return_value="test-20101111000002"):
+            self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose --test".split(" ")).run())
+
+        # try again, should abort old resume
+        with patch('time.strftime', return_value="test-20101111000002"):
+            self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose".split(" ")).run())
+
+        r = shelltest("zfs list -H -o name -r -t all test_target1")
+        self.assertMultiLineEqual(r, """
+test_target1
+test_target1/test_source1
+test_target1/test_source1/fs1
+test_target1/test_source1/fs1@test-20101111000000
+test_target1/test_source1/fs1@test-20101111000002
+test_target1/test_source1/fs1/sub
+test_target1/test_source1/fs1/sub@test-20101111000000
+test_target1/test_source2
+test_target1/test_source2/fs2
+test_target1/test_source2/fs2/sub
+test_target1/test_source2/fs2/sub@test-20101111000000
+""")
+
+    # create a resume situation, where the other side doesnt want the snapshot anymore ( should abort resume )
+    def test_abort_unwanted_resume(self):
+
+        if "0.6.5" in ZFS_USERSPACE:
+            self.skipTest("Resume not supported in this ZFS userspace version")
+
+        with patch('time.strftime', return_value="test-20101111000000"):
+            self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose".split(" ")).run())
+
+        # generate resume
+        with patch('time.strftime', return_value="test-20101111000001"):
+            self.generate_resume()
+
+        with OutputIO() as buf:
+            with redirect_stdout(buf):
+                # incremental, doesnt want previous anymore
+                with patch('time.strftime', return_value="test-20101111000002"):
+                    self.assertFalse(ZfsAutobackup(
+                        "test test_target1 --no-progress --verbose --keep-target=0 --allow-empty".split(" ")).run())
+
+            print(buf.getvalue())
+
+            self.assertIn("Aborting resume, we dont want that snapshot anymore.", buf.getvalue())
+
+        r = shelltest("zfs list -H -o name -r -t all test_target1")
+        self.assertMultiLineEqual(r, """
+test_target1
+test_target1/test_source1
+test_target1/test_source1/fs1
+test_target1/test_source1/fs1@test-20101111000002
+test_target1/test_source1/fs1/sub
+test_target1/test_source1/fs1/sub@test-20101111000002
+test_target1/test_source2
+test_target1/test_source2/fs2
+test_target1/test_source2/fs2/sub
+test_target1/test_source2/fs2/sub@test-20101111000002
+""")
+
+    # test with empty snapshot list (this was a bug)
+    def test_abort_resume_emptysnapshotlist(self):
+
+        if "0.6.5" in ZFS_USERSPACE:
+            self.skipTest("Resume not supported in this ZFS userspace version")
+
+        with patch('time.strftime', return_value="test-20101111000000"):
+            self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose".split(" ")).run())
+
+        # generate resume
+        with patch('time.strftime', return_value="test-20101111000001"):
+            self.generate_resume()
+
+        shelltest("zfs destroy test_source1/fs1@test-20101111000001")
+
+        with OutputIO() as buf:
+            with redirect_stdout(buf):
+                # incremental, doesnt want previous anymore
+                with patch('time.strftime', return_value="test-20101111000002"):
+                    self.assertFalse(ZfsAutobackup(
+                        "test test_target1 --no-progress --verbose --no-snapshot".split(
+                            " ")).run())
+
+            print(buf.getvalue())
+
+            self.assertIn("Aborting resume, its obsolete", buf.getvalue())
+
+
+    def test_missing_common(self):
+
+        with patch('time.strftime', return_value="test-20101111000000"):
+            self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose --allow-empty".split(" ")).run())
+
+        # remove common snapshot and leave nothing
+        shelltest("zfs release zfs_autobackup:test test_source1/fs1@test-20101111000000")
+        shelltest("zfs destroy test_source1/fs1@test-20101111000000")
+
+        with patch('time.strftime', return_value="test-20101111000001"):
+            self.assertTrue(ZfsAutobackup("test test_target1 --no-progress --verbose --allow-empty".split(" ")).run())
+
+    #UPDATE: offcourse the one thing that wasn't tested had a bug :(  (in ExecuteNode.run()).
+    def test_ignoretransfererrors(self):
+
+            self.skipTest("Not sure how to implement a test for this without some serious hacking and patching.")
+
+#         #recreate target pool without any features
+#         # shelltest("zfs set compress=on test_source1; zpool destroy test_target1; zpool create test_target1 -o feature@project_quota=disabled /dev/ram2")
+#
+#         with patch('time.strftime', return_value="test-20101111000000"):
+#             self.assertFalse(ZfsAutobackup("test test_target1 --verbose --allow-empty --no-progress".split(" ")).run())
+#
+#         r = shelltest("zfs list -H -o name -r -t all test_target1")
+#
+#         self.assertMultiLineEqual(r, """
+# test_target1
+# test_target1/test_source1
+# test_target1/test_source1/fs1
+# test_target1/test_source1/fs1@test-20101111000002
+# test_target1/test_source1/fs1/sub
+# test_target1/test_source1/fs1/sub@test-20101111000002
+# test_target1/test_source2
+# test_target1/test_source2/fs2
+# test_target1/test_source2/fs2/sub
+# test_target1/test_source2/fs2/sub@test-20101111000002
+#         """)

tests/test_log.py

@@ -0,0 +1,52 @@
+from zfs_autobackup.LogConsole import LogConsole
+from basetest import *
+
+
+class TestLog(unittest2.TestCase):
+
+    def test_colored(self):
+        """test with color output"""
+        with OutputIO() as buf:
+            with redirect_stdout(buf):
+                l= LogConsole(show_verbose=False, show_debug=False, color=True)
+                l.verbose("verbose")
+                l.debug("debug")
+
+            with redirect_stdout(buf):
+                l=LogConsole(show_verbose=True, show_debug=True, color=True)
+                l.verbose("verbose")
+                l.debug("debug")
+
+            with redirect_stderr(buf):
+                l=LogConsole(show_verbose=False, show_debug=False, color=True)
+                l.error("error")
+
+            print(list(buf.getvalue()))
+            self.assertEqual(list(buf.getvalue()), ['\x1b', '[', '2', '2', 'm', ' ', ' ', 'v', 'e', 'r', 'b', 'o', 's', 'e', '\x1b', '[', '0', 'm', '\n', '\x1b', '[', '3', '2', 'm', '#', ' ', 'd', 'e', 'b', 'u', 'g', '\x1b', '[', '0', 'm', '\n', '\x1b', '[', '3', '1', 'm', '\x1b', '[', '1', 'm', '!', ' ', 'e', 'r', 'r', 'o', 'r', '\x1b', '[', '0', 'm', '\n'])
+
+    def test_nocolor(self):
+        """test without color output"""
+
+        with OutputIO() as buf:
+            with redirect_stdout(buf):
+                l=LogConsole(show_verbose=False, show_debug=False, color=False)
+                l.verbose("verbose")
+                l.debug("debug")
+
+            with redirect_stdout(buf):
+                l=LogConsole(show_verbose=True, show_debug=True, color=False)
+                l.verbose("verbose")
+                l.debug("debug")
+
+            with redirect_stderr(buf):
+                l=LogConsole(show_verbose=False, show_debug=False, color=False)
+                l.error("error")
+
+            print(list(buf.getvalue()))
+            self.assertEqual(list(buf.getvalue()), [' ', ' ', 'v', 'e', 'r', 'b', 'o', 's', 'e', '\n', '#', ' ', 'd', 'e', 'b', 'u', 'g', '\n', '!', ' ', 'e', 'r', 'r', 'o', 'r', '\n'])
+
+
+        # zfs_autobackup.LogConsole.colorama=False
+
+
+

tests/test_regressions.py

@@ -0,0 +1,105 @@
+
+from basetest import *
+
+
+class TestZfsNode(unittest2.TestCase):
+
+    def setUp(self):
+        prepare_zpools()
+        self.longMessage=True
+
+    def test_keepsource0target10queuedsend(self):
+        """Test if thinner doesnt destroy too much early on if there are no common snapshots YET. Issue #84"""
+
+        with patch('time.strftime', return_value="test-20101111000000"):
+            self.assertFalse(ZfsAutobackup(
+                "test test_target1 --no-progress --verbose --keep-source=0 --keep-target=10 --allow-empty --no-send".split(
+                    " ")).run())
+
+        with patch('time.strftime', return_value="test-20101111000001"):
+            self.assertFalse(ZfsAutobackup(
+                "test test_target1 --no-progress --verbose --keep-source=0 --keep-target=10 --allow-empty --no-send".split(
+                    " ")).run())
+
+        with patch('time.strftime', return_value="test-20101111000002"):
+            self.assertFalse(ZfsAutobackup(
+                "test test_target1 --no-progress --verbose --keep-source=0 --keep-target=10 --allow-empty".split(
+                    " ")).run())
+
+        r = shelltest("zfs list -H -o name -r -t all " + TEST_POOLS)
+        self.assertMultiLineEqual(r, """
+test_source1
+test_source1/fs1
+test_source1/fs1@test-20101111000002
+test_source1/fs1/sub
+test_source1/fs1/sub@test-20101111000002
+test_source2
+test_source2/fs2
+test_source2/fs2/sub
+test_source2/fs2/sub@test-20101111000002
+test_source2/fs3
+test_source2/fs3/sub
+test_target1
+test_target1/test_source1
+test_target1/test_source1/fs1
+test_target1/test_source1/fs1@test-20101111000000
+test_target1/test_source1/fs1@test-20101111000001
+test_target1/test_source1/fs1@test-20101111000002
+test_target1/test_source1/fs1/sub
+test_target1/test_source1/fs1/sub@test-20101111000000
+test_target1/test_source1/fs1/sub@test-20101111000001
+test_target1/test_source1/fs1/sub@test-20101111000002
+test_target1/test_source2
+test_target1/test_source2/fs2
+test_target1/test_source2/fs2/sub
+test_target1/test_source2/fs2/sub@test-20101111000000
+test_target1/test_source2/fs2/sub@test-20101111000001
+test_target1/test_source2/fs2/sub@test-20101111000002
+""")
+
+
+    def test_excludepaths(self):
+        """Test issue #103"""
+
+        shelltest("zfs create test_target1/target_shouldnotbeexcluded")
+        shelltest("zfs set autobackup:test=true test_target1/target_shouldnotbeexcluded")
+        shelltest("zfs create test_target1/target")
+
+        with patch('time.strftime', return_value="test-20101111000000"):
+            self.assertFalse(ZfsAutobackup(
+                "test test_target1/target --no-progress --verbose --allow-empty".split(
+                    " ")).run())
+
+
+        r = shelltest("zfs list -H -o name -r -t all " + TEST_POOLS)
+        self.assertMultiLineEqual(r, """
+test_source1
+test_source1/fs1
+test_source1/fs1@test-20101111000000
+test_source1/fs1/sub
+test_source1/fs1/sub@test-20101111000000
+test_source2
+test_source2/fs2
+test_source2/fs2/sub
+test_source2/fs2/sub@test-20101111000000
+test_source2/fs3
+test_source2/fs3/sub
+test_target1
+test_target1/target
+test_target1/target/test_source1
+test_target1/target/test_source1/fs1
+test_target1/target/test_source1/fs1@test-20101111000000
+test_target1/target/test_source1/fs1/sub
+test_target1/target/test_source1/fs1/sub@test-20101111000000
+test_target1/target/test_source2
+test_target1/target/test_source2/fs2
+test_target1/target/test_source2/fs2/sub
+test_target1/target/test_source2/fs2/sub@test-20101111000000
+test_target1/target/test_target1
+test_target1/target/test_target1/target_shouldnotbeexcluded
+test_target1/target/test_target1/target_shouldnotbeexcluded@test-20101111000000
+test_target1/target_shouldnotbeexcluded
+test_target1/target_shouldnotbeexcluded@test-20101111000000
+""")
+
+

tests/test_scaling.py

@@ -0,0 +1,99 @@
+from basetest import *
+
+from zfs_autobackup.ExecuteNode import ExecuteNode
+
+run_orig=ExecuteNode.run
+run_counter=0
+
+def run_count(*args, **kwargs):
+    global run_counter
+    run_counter=run_counter+1
+    return (run_orig(*args, **kwargs))
+
+class TestZfsScaling(unittest2.TestCase):
+
+    def setUp(self):
+        prepare_zpools()
+        self.longMessage = True
+
+    def test_manysnapshots(self):
+        """count the number of commands when there are many snapshots."""
+
+        snapshot_count=100
+
+        print("Creating many snapshots...")
+        s=""
+        for i in range(1970,1970+snapshot_count):
+            s=s+"zfs snapshot test_source1/fs1@test-{:04}1111000000;".format(i)
+
+        shelltest(s)
+
+        global run_counter
+
+        run_counter=0
+        with patch.object(ExecuteNode,'run', run_count) as p:
+
+            with patch('time.strftime', return_value="test-20101112000000"):
+                self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose --keep-source=10000 --keep-target=10000 --no-holds --allow-empty".split(" ")).run())
+
+
+            #this triggers if you make a change with an impact of more than O(snapshot_count/2)
+            expected_runs=343
+            print("ACTUAL RUNS: {}".format(run_counter))
+            self.assertLess(abs(run_counter-expected_runs), snapshot_count/2)
+
+
+        run_counter=0
+        with patch.object(ExecuteNode,'run', run_count) as p:
+
+            with patch('time.strftime', return_value="test-20101112000001"):
+                self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose --keep-source=10000 --keep-target=10000 --no-holds --allow-empty".split(" ")).run())
+
+
+            #this triggers if you make a change with a performance impact of more than O(snapshot_count/2)
+            expected_runs=47
+            print("ACTUAL RUNS: {}".format(run_counter))
+            self.assertLess(abs(run_counter-expected_runs), snapshot_count/2)
+
+    def test_manydatasets(self):
+        """count the number of commands when when there are many datasets"""
+
+        dataset_count=100
+
+        print("Creating many datasets...")
+        s=""
+        for i in range(0,dataset_count):
+            s=s+"zfs create test_source1/fs1/{};".format(i)
+
+        shelltest(s)
+
+        global run_counter
+
+        #first run
+        run_counter=0
+        with patch.object(ExecuteNode,'run', run_count) as p:
+
+            with patch('time.strftime', return_value="test-20101112000000"):
+                self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose --no-holds --allow-empty".split(" ")).run())
+
+
+            #this triggers if you make a change with an impact of more than O(snapshot_count/2)
+            expected_runs=636
+            print("EXPECTED RUNS: {}".format(expected_runs))
+            print("ACTUAL RUNS: {}".format(run_counter))
+            self.assertLess(abs(run_counter-expected_runs), dataset_count/2)
+
+
+        #second run, should have higher number of expected_runs
+        run_counter=0
+        with patch.object(ExecuteNode,'run', run_count) as p:
+
+            with patch('time.strftime', return_value="test-20101112000001"):
+                self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose --no-holds --allow-empty".split(" ")).run())
+
+
+            #this triggers if you make a change with a performance impact of more than O(snapshot_count/2)
+            expected_runs=842
+            print("EXPECTED RUNS: {}".format(expected_runs))
+            print("ACTUAL RUNS: {}".format(run_counter))
+            self.assertLess(abs(run_counter-expected_runs), dataset_count/2)

tests/test_sendrecvpipes.py

@@ -0,0 +1,147 @@
+import zfs_autobackup.compressors
+from basetest import *
+import time
+
+
+class TestSendRecvPipes(unittest2.TestCase):
+    """test input/output pipes for zfs send and recv"""
+
+    def setUp(self):
+        prepare_zpools()
+        self.longMessage = True
+
+    def test_send_basics(self):
+        """send basics (remote/local send pipe)"""
+
+        with self.subTest("local local pipe"):
+            with patch('time.strftime', return_value="test-20101111000000"):
+                self.assertFalse(ZfsAutobackup(
+                    ["test", "test_target1", "--allow-empty", "--exclude-received", "--no-holds", "--no-progress",
+                     "--send-pipe=dd bs=1M", "--recv-pipe=dd bs=2M"]).run())
+
+            shelltest("zfs destroy -r test_target1/test_source1/fs1/sub")
+
+        with self.subTest("remote local pipe"):
+            with patch('time.strftime', return_value="test-20101111000001"):
+                self.assertFalse(ZfsAutobackup(
+                    ["test", "test_target1", "--allow-empty", "--exclude-received", "--no-holds", "--no-progress",
+                     "--ssh-source=localhost", "--send-pipe=dd bs=1M", "--recv-pipe=dd bs=2M"]).run())
+
+            shelltest("zfs destroy -r test_target1/test_source1/fs1/sub")
+
+        with self.subTest("local remote pipe"):
+            with patch('time.strftime', return_value="test-20101111000002"):
+                self.assertFalse(ZfsAutobackup(
+                    ["test", "test_target1", "--allow-empty", "--exclude-received", "--no-holds", "--no-progress",
+                     "--ssh-target=localhost", "--send-pipe=dd bs=1M", "--recv-pipe=dd bs=2M"]).run())
+
+            shelltest("zfs destroy -r test_target1/test_source1/fs1/sub")
+
+        with self.subTest("remote remote pipe"):
+            with patch('time.strftime', return_value="test-20101111000003"):
+                self.assertFalse(ZfsAutobackup(
+                    ["test", "test_target1", "--allow-empty", "--exclude-received", "--no-holds", "--no-progress",
+                     "--ssh-source=localhost", "--ssh-target=localhost", "--send-pipe=dd bs=1M",
+                     "--recv-pipe=dd bs=2M"]).run())
+
+        r = shelltest("zfs list -H -o name -r -t all test_target1")
+        self.assertMultiLineEqual(r, """
+test_target1
+test_target1/test_source1
+test_target1/test_source1/fs1
+test_target1/test_source1/fs1@test-20101111000000
+test_target1/test_source1/fs1@test-20101111000001
+test_target1/test_source1/fs1@test-20101111000002
+test_target1/test_source1/fs1@test-20101111000003
+test_target1/test_source1/fs1/sub
+test_target1/test_source1/fs1/sub@test-20101111000000
+test_target1/test_source1/fs1/sub@test-20101111000001
+test_target1/test_source1/fs1/sub@test-20101111000002
+test_target1/test_source1/fs1/sub@test-20101111000003
+test_target1/test_source2
+test_target1/test_source2/fs2
+test_target1/test_source2/fs2/sub
+test_target1/test_source2/fs2/sub@test-20101111000000
+test_target1/test_source2/fs2/sub@test-20101111000001
+test_target1/test_source2/fs2/sub@test-20101111000002
+test_target1/test_source2/fs2/sub@test-20101111000003
+""")
+
+    def test_compress(self):
+        """send basics (remote/local send pipe)"""
+
+        for compress in zfs_autobackup.compressors.COMPRESS_CMDS.keys():
+            with self.subTest("compress " + compress):
+                with patch('time.strftime', return_value="test-20101111000000"):
+                    self.assertFalse(ZfsAutobackup(
+                        ["test", "test_target1", "--exclude-received", "--no-holds", "--no-progress", "--verbose",
+                         "--compress=" + compress]).run())
+
+                shelltest("zfs destroy -r test_target1/test_source1/fs1/sub")
+
+    def test_buffer(self):
+        """test different buffer configurations"""
+
+        with self.subTest("local local pipe"):
+            with patch('time.strftime', return_value="test-20101111000000"):
+                self.assertFalse(ZfsAutobackup(
+                    ["test", "test_target1", "--allow-empty", "--exclude-received", "--no-holds", "--no-progress",
+                     "--buffer=1M"]).run())
+
+            shelltest("zfs destroy -r test_target1/test_source1/fs1/sub")
+
+        with self.subTest("remote local pipe"):
+            with patch('time.strftime', return_value="test-20101111000001"):
+                self.assertFalse(ZfsAutobackup(
+                    ["test", "test_target1", "--allow-empty", "--verbose", "--exclude-received", "--no-holds",
+                     "--no-progress", "--ssh-source=localhost", "--buffer=1M"]).run())
+
+            shelltest("zfs destroy -r test_target1/test_source1/fs1/sub")
+
+        with self.subTest("local remote pipe"):
+            with patch('time.strftime', return_value="test-20101111000002"):
+                self.assertFalse(ZfsAutobackup(
+                    ["test", "test_target1", "--allow-empty", "--exclude-received", "--no-holds", "--no-progress",
+                     "--ssh-target=localhost", "--buffer=1M"]).run())
+
+            shelltest("zfs destroy -r test_target1/test_source1/fs1/sub")
+
+        with self.subTest("remote remote pipe"):
+            with patch('time.strftime', return_value="test-20101111000003"):
+                self.assertFalse(ZfsAutobackup(
+                    ["test", "test_target1", "--allow-empty", "--exclude-received", "--no-holds", "--no-progress",
+                     "--ssh-source=localhost", "--ssh-target=localhost", "--buffer=1M"]).run())
+
+        r = shelltest("zfs list -H -o name -r -t all test_target1")
+        self.assertMultiLineEqual(r, """
+test_target1
+test_target1/test_source1
+test_target1/test_source1/fs1
+test_target1/test_source1/fs1@test-20101111000000
+test_target1/test_source1/fs1@test-20101111000001
+test_target1/test_source1/fs1@test-20101111000002
+test_target1/test_source1/fs1@test-20101111000003
+test_target1/test_source1/fs1/sub
+test_target1/test_source1/fs1/sub@test-20101111000000
+test_target1/test_source1/fs1/sub@test-20101111000001
+test_target1/test_source1/fs1/sub@test-20101111000002
+test_target1/test_source1/fs1/sub@test-20101111000003
+test_target1/test_source2
+test_target1/test_source2/fs2
+test_target1/test_source2/fs2/sub
+test_target1/test_source2/fs2/sub@test-20101111000000
+test_target1/test_source2/fs2/sub@test-20101111000001
+test_target1/test_source2/fs2/sub@test-20101111000002
+test_target1/test_source2/fs2/sub@test-20101111000003
+""")
+
+    def test_rate(self):
+        """test rate limit"""
+
+        start = time.time()
+        with patch('time.strftime', return_value="test-20101111000000"):
+            self.assertFalse(ZfsAutobackup(
+                ["test", "test_target1", "--exclude-received", "--no-holds", "--no-progress", "--rate=50k"]).run())
+
+        # not a great way of verifying but it works.
+        self.assertGreater(time.time() - start, 5)

tests/test_thinner.py

@@ -0,0 +1,159 @@
+from basetest import *
+import pprint
+
+from zfs_autobackup.Thinner import Thinner
+
+# randint is different in python 2 vs 3
+randint_compat = lambda lo, hi: lo + int(random.random() * (hi + 1 - lo))
+
+
+class Thing:
+    def __init__(self, timestamp):
+        self.timestamp=timestamp
+
+    def __str__(self):
+        # age=now-self.timestamp
+        struct=time.gmtime(self.timestamp)
+        return("{}".format(time.strftime("%Y-%m-%d %H:%M:%S",struct)))
+
+
+class TestThinner(unittest2.TestCase):
+
+    # def setUp(self):
+
+        # return super().setUp()
+
+    def test_exceptions(self):
+        with self.assertRaisesRegexp(Exception, "^Invalid period"):
+            ThinnerRule("12X12m")
+
+        with self.assertRaisesRegexp(Exception, "^Invalid ttl"):
+            ThinnerRule("12d12X")
+
+        with self.assertRaisesRegexp(Exception, "^Period cant be"):
+            ThinnerRule("12d1d")
+
+        with self.assertRaisesRegexp(Exception, "^Invalid schedule"):
+            ThinnerRule("XXX")
+
+        with self.assertRaisesRegexp(Exception, "^Number of"):
+            Thinner("-1")
+
+
+    def test_incremental(self):
+        ok=['2023-01-03 10:53:16',
+            '2024-01-02 15:43:29',
+            '2025-01-01 06:15:32',
+            '2026-01-01 02:48:23',
+            '2026-04-07 20:07:36',
+            '2026-05-07 02:30:29',
+            '2026-06-06 01:19:46',
+            '2026-07-06 06:38:09',
+            '2026-08-05 05:08:53',
+            '2026-09-04 03:33:04',
+            '2026-10-04 05:27:09',
+            '2026-11-04 04:01:17',
+            '2026-12-03 13:49:56',
+            '2027-01-01 17:02:00',
+            '2027-01-03 04:26:42',
+            '2027-02-01 14:16:02',
+            '2027-02-12 03:31:02',
+            '2027-02-18 00:33:10',
+            '2027-02-26 21:09:54',
+            '2027-03-02 08:05:18',
+            '2027-03-03 16:46:09',
+            '2027-03-04 06:39:14',
+            '2027-03-06 03:35:41',
+            '2027-03-08 12:24:42',
+            '2027-03-08 20:34:57']
+
+
+
+
+        #some arbitrary date
+        now=1589229252
+        #we want deterministic results
+        random.seed(1337)
+        thinner=Thinner("5,10s1min,1d1w,1w1m,1m12m,1y5y")
+        things=[]
+
+        #thin incrementally while adding
+        for i in range(0,5000):
+
+            #increase random amount of time and maybe add a thing
+            now=now+randint_compat(0,3600*24)
+            if random.random()>=0.5:
+                things.append(Thing(now))
+
+            (keeps, removes)=thinner.thin(things, now=now)
+            things=keeps
+
+
+        result=[]
+        for thing in things:
+            result.append(str(thing))
+
+        print("Thinner result incremental:")
+        pprint.pprint(result)
+
+        self.assertEqual(result, ok)
+
+
+    def test_full(self):
+        ok=['2022-03-09 01:56:23',
+            '2023-01-03 10:53:16',
+            '2024-01-02 15:43:29',
+            '2025-01-01 06:15:32',
+            '2026-01-01 02:48:23',
+            '2026-03-14 09:08:04',
+            '2026-04-07 20:07:36',
+            '2026-05-07 02:30:29',
+            '2026-06-06 01:19:46',
+            '2026-07-06 06:38:09',
+            '2026-08-05 05:08:53',
+            '2026-09-04 03:33:04',
+            '2026-10-04 05:27:09',
+            '2026-11-04 04:01:17',
+            '2026-12-03 13:49:56',
+            '2027-01-01 17:02:00',
+            '2027-01-03 04:26:42',
+            '2027-02-01 14:16:02',
+            '2027-02-08 02:41:14',
+            '2027-02-12 03:31:02',
+            '2027-02-18 00:33:10',
+            '2027-02-26 21:09:54',
+            '2027-03-02 08:05:18',
+            '2027-03-03 16:46:09',
+            '2027-03-04 06:39:14',
+            '2027-03-06 03:35:41',
+            '2027-03-08 12:24:42',
+            '2027-03-08 20:34:57']
+
+        #some arbitrary date
+        now=1589229252
+        #we want deterministic results
+        random.seed(1337)
+        thinner=Thinner("5,10s1min,1d1w,1w1m,1m12m,1y5y")
+        things=[]
+
+        for i in range(0,5000):
+
+            #increase random amount of time and maybe add a thing
+            now=now+randint_compat(0,3600*24)
+            if random.random()>=0.5:
+                things.append(Thing(now))
+
+        (things, removes)=thinner.thin(things, now=now)
+
+        result=[]
+        for thing in things:
+            result.append(str(thing))
+
+        print("Thinner result full:")
+        pprint.pprint(result)
+
+        self.assertEqual(result, ok)
+
+
+# if __name__ == '__main__':
+#     unittest.main()

tests/test_treehasher.py

@@ -0,0 +1,84 @@
+from basetest import *
+from zfs_autobackup.BlockHasher import BlockHasher
+
+
+# sha1 sums of files, (bs=4096)
+# da39a3ee5e6b4b0d3255bfef95601890afd80709  empty
+# 642027d63bb0afd7e0ba197f2c66ad03e3d70de1  partial
+# 3c0bf91170d873b8e327d3bafb6bc074580d11b7  whole
+# 2e863f1fcccd6642e4e28453eba10d2d3f74d798  whole2
+# 959e6b58078f0cfd2fb3d37e978fda51820473ff  whole_whole2
+# 309ffffba2e1977d12f3b7469971f30d28b94bd8  whole_whole2_partial
+
+
+class TestTreeHasher(unittest2.TestCase):
+
+    def test_treehasher(self):
+        shelltest("rm -rf /tmp/treehashertest; mkdir /tmp/treehashertest")
+        shelltest("cp tests/data/whole /tmp/treehashertest")
+        shelltest("mkdir /tmp/treehashertest/emptydir")
+        shelltest("mkdir /tmp/treehashertest/dir")
+        shelltest("cp tests/data/whole_whole2_partial /tmp/treehashertest/dir")
+
+        # it should ignore these:
+        shelltest("ln -s / /tmp/treehashertest/symlink")
+        shelltest("mknod /tmp/treehashertest/c c 1 1")
+        shelltest("mknod /tmp/treehashertest/b b 1 1")
+        shelltest("mkfifo /tmp/treehashertest/f")
+
+
+        block_hasher = BlockHasher(count=1, skip=0)
+        tree_hasher = TreeHasher(block_hasher)
+        with self.subTest("Test output, count 1, skip 0"):
+            self.assertEqual(list(tree_hasher.generate("/tmp/treehashertest")), [
+                ('whole', 0, '3c0bf91170d873b8e327d3bafb6bc074580d11b7'),
+                ('dir/whole_whole2_partial', 0, '3c0bf91170d873b8e327d3bafb6bc074580d11b7'),
+                ('dir/whole_whole2_partial', 1, '2e863f1fcccd6642e4e28453eba10d2d3f74d798'),
+                ('dir/whole_whole2_partial', 2, '642027d63bb0afd7e0ba197f2c66ad03e3d70de1')
+            ])
+
+        block_hasher = BlockHasher(count=1, skip=1)
+        tree_hasher = TreeHasher(block_hasher)
+        with self.subTest("Test output, count 1, skip 1"):
+            self.assertEqual(list(tree_hasher.generate("/tmp/treehashertest")), [
+                ('whole', 0, '3c0bf91170d873b8e327d3bafb6bc074580d11b7'),
+                # ('dir/whole_whole2_partial', 0, '3c0bf91170d873b8e327d3bafb6bc074580d11b7'),
+                ('dir/whole_whole2_partial', 1, '2e863f1fcccd6642e4e28453eba10d2d3f74d798'),
+                # ('dir/whole_whole2_partial', 2, '642027d63bb0afd7e0ba197f2c66ad03e3d70de1')
+            ])
+
+
+
+        block_hasher = BlockHasher(count=2)
+        tree_hasher = TreeHasher(block_hasher)
+
+        with self.subTest("Test output, count 2, skip 0"):
+            self.assertEqual(list(tree_hasher.generate("/tmp/treehashertest")), [
+                ('whole', 0, '3c0bf91170d873b8e327d3bafb6bc074580d11b7'),
+                ('dir/whole_whole2_partial', 0, '959e6b58078f0cfd2fb3d37e978fda51820473ff'),
+                ('dir/whole_whole2_partial', 1, '642027d63bb0afd7e0ba197f2c66ad03e3d70de1')
+            ])
+
+        with self.subTest("Test compare"):
+            generator = tree_hasher.generate("/tmp/treehashertest")
+            errors = list(tree_hasher.compare("/tmp/treehashertest", generator))
+            self.assertEqual(errors, [])
+
+        with self.subTest("Test mismatch"):
+            generator = list(tree_hasher.generate("/tmp/treehashertest"))
+            shelltest("cp tests/data/whole2 /tmp/treehashertest/whole")
+
+            self.assertEqual(list(tree_hasher.compare("/tmp/treehashertest", generator)),
+                             [('whole',
+                               0,
+                               '3c0bf91170d873b8e327d3bafb6bc074580d11b7',
+                               '2e863f1fcccd6642e4e28453eba10d2d3f74d798')])
+
+        with self.subTest("Test missing file compare"):
+            generator = list(tree_hasher.generate("/tmp/treehashertest"))
+            shelltest("rm /tmp/treehashertest/whole")
+
+            self.assertEqual(list(tree_hasher.compare("/tmp/treehashertest", generator)),
+                             [('whole', '-', '-', "ERROR: [Errno 2] No such file or directory: '/tmp/treehashertest/whole'")])
+
+

tests/test_verify.py

@@ -0,0 +1,102 @@
+
+from basetest import *
+
+
+# test zfs-verify:
+# - when there is no common snapshot at all
+# - when encryption key not loaded
+# - --test mode
+# - --fs-compare methods
+# - on snapshots of datasets:
+#   - that are correct
+#   - that are different
+# - on snapshots of zvols
+#  - that are correct
+#  - that are different
+# - test all directions (local, remote/local, local/remote, remote/remote)
+#
+
+class TestZfsVerify(unittest2.TestCase):
+
+
+    def setUp(self):
+        self.skipTest("WIP")
+
+        prepare_zpools()
+
+        #create actual test files and data
+        shelltest("zfs create test_source1/fs1/ok_filesystem")
+        shelltest("cp tests/*.py /test_source1/fs1/ok_filesystem")
+
+        shelltest("zfs create test_source1/fs1/bad_filesystem")
+        shelltest("cp tests/*.py /test_source1/fs1/bad_filesystem")
+
+        shelltest("zfs create -V 1M test_source1/fs1/ok_zvol")
+        shelltest("dd if=/dev/urandom of=/dev/zvol/test_source1/fs1/ok_zvol count=1 bs=512k")
+
+        shelltest("zfs create -V 1M test_source1/fs1/bad_zvol")
+        shelltest("dd if=/dev/urandom of=/dev/zvol/test_source1/fs1/bad_zvol count=1 bs=512k")
+
+        #create backup
+        with patch('time.strftime', return_value="test-20101111000000"):
+            self.assertFalse(ZfsAutobackup("test test_target1 --verbose --no-progress --no-holds".split(" ")).run())
+
+        #Do an ugly hack to create a fault in the bad filesystem
+        #In zfs-autoverify it doenst matter that the snapshot isnt actually the same snapshot, so this hack works
+        shelltest("zfs destroy test_target1/test_source1/fs1/bad_filesystem@test-20101111000000")
+        shelltest("zfs mount test_target1/test_source1/fs1/bad_filesystem")
+        shelltest("echo >> /test_target1/test_source1/fs1/bad_filesystem/test_verify.py")
+        shelltest("zfs snapshot test_target1/test_source1/fs1/bad_filesystem@test-20101111000000")
+
+        #do the same hack for the bad zvol
+        shelltest("zfs destroy test_target1/test_source1/fs1/bad_zvol@test-20101111000000")
+        shelltest("dd if=/dev/urandom of=/dev/zvol/test_target1/test_source1/fs1/bad_zvol count=1 bs=1")
+        shelltest("zfs snapshot test_target1/test_source1/fs1/bad_zvol@test-20101111000000")
+
+
+        # make sure we cant accidently compare current data
+        shelltest("zfs mount test_target1/test_source1/fs1/ok_filesystem")
+        shelltest("rm /test_source1/fs1/ok_filesystem/*")
+        shelltest("rm /test_source1/fs1/bad_filesystem/*")
+        shelltest("dd if=/dev/zero of=/dev/zvol/test_source1/fs1/ok_zvol count=1 bs=512k")
+
+
+
+    def test_verify(self):
+
+
+        with self.subTest("default --test"):
+            self.assertFalse(ZfsAutoverify("test test_target1 --verbose --test".split(" ")).run())
+
+        with self.subTest("rsync, remote source and target. (not supported, all 6 fail)"):
+            self.assertEqual(6, ZfsAutoverify("test test_target1 --ssh-source=localhost --ssh-target=localhost --verbose --exclude-received --fs-compare=rsync".split(" ")).run())
+
+        def runchecked(testname, command):
+            with self.subTest(testname):
+                with OutputIO() as buf:
+                    result=None
+                    with redirect_stderr(buf):
+                        result=ZfsAutoverify(command.split(" ")).run()
+
+                    print(buf.getvalue())
+                    self.assertEqual(2,result)
+                    self.assertRegex(buf.getvalue(), "bad_filesystem: FAILED:")
+                    self.assertRegex(buf.getvalue(), "bad_zvol: FAILED:")
+
+        runchecked("rsync, remote source", "test test_target1 --ssh-source=localhost --verbose --exclude-received --fs-compare=rsync")
+        runchecked("rsync, remote target", "test test_target1 --ssh-target=localhost --verbose --exclude-received --fs-compare=rsync")
+        runchecked("rsync, local", "test test_target1 --verbose --exclude-received --fs-compare=rsync")
+
+        runchecked("tar, remote source and remote target",
+                   "test test_target1 --ssh-source=localhost --ssh-target=localhost --verbose --exclude-received --fs-compare=find")
+        runchecked("tar, remote source",
+                   "test test_target1 --ssh-source=localhost --verbose --exclude-received --fs-compare=find")
+        runchecked("tar, remote target",
+                   "test test_target1 --ssh-target=localhost --verbose --exclude-received --fs-compare=find")
+        runchecked("tar, local", "test test_target1 --verbose --exclude-received --fs-compare=find")
+
+        with self.subTest("no common snapshot"):
+            #destroy common snapshot, now 3 should fail
+            shelltest("zfs destroy test_source1/fs1/ok_zvol@test-20101111000000")
+            self.assertEqual(3, ZfsAutoverify("test test_target1 --verbose --exclude-received".split(" ")).run())
+

tests/test_zfsautobackup.py

@@ -0,0 +1,910 @@
+from zfs_autobackup.CmdPipe import CmdPipe
+
+from basetest import *
+import time
+
+from zfs_autobackup.LogConsole import  LogConsole
+
+
+class TestZfsAutobackup(unittest2.TestCase):
+
+    def setUp(self):
+        prepare_zpools()
+        self.longMessage=True
+
+    def test_invalidpars(self):
+
+        self.assertEqual(ZfsAutobackup("test test_target1 --no-progress --keep-source -1".split(" ")).run(), 255)
+
+        with OutputIO() as buf:
+            with redirect_stdout(buf):
+                self.assertEqual(ZfsAutobackup("test test_target1 --no-progress --resume --verbose --no-snapshot".split(" ")).run(), 0)
+
+            print(buf.getvalue())
+            self.assertIn("The --resume", buf.getvalue())
+
+        with OutputIO() as buf:
+            with redirect_stderr(buf):
+                self.assertEqual(ZfsAutobackup("test test_target_nonexisting --no-progress".split(" ")).run(), 255)
+
+            print(buf.getvalue())
+            # correct message?
+            self.assertIn("Please create this dataset", buf.getvalue())
+
+
+    def  test_snapshotmode(self):
+        """test snapshot tool mode"""
+
+        with patch('time.strftime', return_value="test-20101111000000"):
+            self.assertFalse(ZfsAutobackup("test --no-progress --verbose".split(" ")).run())
+
+        r=shelltest("zfs list -H -o name -r -t all "+TEST_POOLS)
+        self.assertMultiLineEqual(r,"""
+test_source1
+test_source1/fs1
+test_source1/fs1@test-20101111000000
+test_source1/fs1/sub
+test_source1/fs1/sub@test-20101111000000
+test_source2
+test_source2/fs2
+test_source2/fs2/sub
+test_source2/fs2/sub@test-20101111000000
+test_source2/fs3
+test_source2/fs3/sub
+test_target1
+""")
+
+    def  test_defaults(self):
+
+        with self.subTest("no datasets selected"):
+            with OutputIO() as buf:
+                with redirect_stderr(buf):
+                    with patch('time.strftime', return_value="test-20101111000000"):
+                        self.assertTrue(ZfsAutobackup("nonexisting test_target1 --verbose --debug --no-progress".split(" ")).run())
+
+                print(buf.getvalue())
+                #correct message?
+                self.assertIn("No source filesystems selected", buf.getvalue())
+
+
+        with self.subTest("defaults with full verbose and debug"):
+
+            with patch('time.strftime', return_value="test-20101111000000"):
+                self.assertFalse(ZfsAutobackup("test test_target1 --verbose --debug --no-progress".split(" ")).run())
+
+            r=shelltest("zfs list -H -o name -r -t all "+TEST_POOLS)
+            self.assertMultiLineEqual(r,"""
+test_source1
+test_source1/fs1
+test_source1/fs1@test-20101111000000
+test_source1/fs1/sub
+test_source1/fs1/sub@test-20101111000000
+test_source2
+test_source2/fs2
+test_source2/fs2/sub
+test_source2/fs2/sub@test-20101111000000
+test_source2/fs3
+test_source2/fs3/sub
+test_target1
+test_target1/test_source1
+test_target1/test_source1/fs1
+test_target1/test_source1/fs1@test-20101111000000
+test_target1/test_source1/fs1/sub
+test_target1/test_source1/fs1/sub@test-20101111000000
+test_target1/test_source2
+test_target1/test_source2/fs2
+test_target1/test_source2/fs2/sub
+test_target1/test_source2/fs2/sub@test-20101111000000
+""")
+
+        with self.subTest("bare defaults, allow empty"):
+            with patch('time.strftime', return_value="test-20101111000001"):
+                self.assertFalse(ZfsAutobackup("test test_target1 --allow-empty --no-progress".split(" ")).run())
+
+
+            r=shelltest("zfs list -H -o name -r -t all "+TEST_POOLS)
+            self.assertMultiLineEqual(r,"""
+test_source1
+test_source1/fs1
+test_source1/fs1@test-20101111000000
+test_source1/fs1@test-20101111000001
+test_source1/fs1/sub
+test_source1/fs1/sub@test-20101111000000
+test_source1/fs1/sub@test-20101111000001
+test_source2
+test_source2/fs2
+test_source2/fs2/sub
+test_source2/fs2/sub@test-20101111000000
+test_source2/fs2/sub@test-20101111000001
+test_source2/fs3
+test_source2/fs3/sub
+test_target1
+test_target1/test_source1
+test_target1/test_source1/fs1
+test_target1/test_source1/fs1@test-20101111000000
+test_target1/test_source1/fs1@test-20101111000001
+test_target1/test_source1/fs1/sub
+test_target1/test_source1/fs1/sub@test-20101111000000
+test_target1/test_source1/fs1/sub@test-20101111000001
+test_target1/test_source2
+test_target1/test_source2/fs2
+test_target1/test_source2/fs2/sub
+test_target1/test_source2/fs2/sub@test-20101111000000
+test_target1/test_source2/fs2/sub@test-20101111000001
+""")
+
+        with self.subTest("verify holds"):
+
+            r=shelltest("zfs get -r userrefs test_source1 test_source2 test_target1")
+            self.assertMultiLineEqual(r,"""
+NAME                                                   PROPERTY  VALUE     SOURCE
+test_source1                                           userrefs  -         -
+test_source1/fs1                                       userrefs  -         -
+test_source1/fs1@test-20101111000000                   userrefs  0         -
+test_source1/fs1@test-20101111000001                   userrefs  1         -
+test_source1/fs1/sub                                   userrefs  -         -
+test_source1/fs1/sub@test-20101111000000               userrefs  0         -
+test_source1/fs1/sub@test-20101111000001               userrefs  1         -
+test_source2                                           userrefs  -         -
+test_source2/fs2                                       userrefs  -         -
+test_source2/fs2/sub                                   userrefs  -         -
+test_source2/fs2/sub@test-20101111000000               userrefs  0         -
+test_source2/fs2/sub@test-20101111000001               userrefs  1         -
+test_source2/fs3                                       userrefs  -         -
+test_source2/fs3/sub                                   userrefs  -         -
+test_target1                                           userrefs  -         -
+test_target1/test_source1                              userrefs  -         -
+test_target1/test_source1/fs1                          userrefs  -         -
+test_target1/test_source1/fs1@test-20101111000000      userrefs  0         -
+test_target1/test_source1/fs1@test-20101111000001      userrefs  1         -
+test_target1/test_source1/fs1/sub                      userrefs  -         -
+test_target1/test_source1/fs1/sub@test-20101111000000  userrefs  0         -
+test_target1/test_source1/fs1/sub@test-20101111000001  userrefs  1         -
+test_target1/test_source2                              userrefs  -         -
+test_target1/test_source2/fs2                          userrefs  -         -
+test_target1/test_source2/fs2/sub                      userrefs  -         -
+test_target1/test_source2/fs2/sub@test-20101111000000  userrefs  0         -
+test_target1/test_source2/fs2/sub@test-20101111000001  userrefs  1         -
+""")
+
+        #make sure time handling is correctly. try to make snapshots a year appart and verify that only snapshots mostly 1y old are kept
+        with self.subTest("test time checking"):
+            with patch('time.strftime', return_value="test-20111111000000"):
+                self.assertFalse(ZfsAutobackup("test test_target1 --allow-empty --verbose --no-progress".split(" ")).run())
+
+
+            time_str="20111112000000" #month in the "future"
+            future_timestamp=time_secs=time.mktime(time.strptime(time_str,"%Y%m%d%H%M%S"))
+            with patch('time.time', return_value=future_timestamp):
+                with patch('time.strftime', return_value="test-20111111000001"):
+                    self.assertFalse(ZfsAutobackup("test test_target1 --allow-empty --verbose --keep-source 1y1y --keep-target 1d1y --no-progress".split(" ")).run())
+
+
+            r=shelltest("zfs list -H -o name -r -t all "+TEST_POOLS)
+            self.assertMultiLineEqual(r,"""
+test_source1
+test_source1/fs1
+test_source1/fs1@test-20111111000000
+test_source1/fs1@test-20111111000001
+test_source1/fs1/sub
+test_source1/fs1/sub@test-20111111000000
+test_source1/fs1/sub@test-20111111000001
+test_source2
+test_source2/fs2
+test_source2/fs2/sub
+test_source2/fs2/sub@test-20111111000000
+test_source2/fs2/sub@test-20111111000001
+test_source2/fs3
+test_source2/fs3/sub
+test_target1
+test_target1/test_source1
+test_target1/test_source1/fs1
+test_target1/test_source1/fs1@test-20111111000000
+test_target1/test_source1/fs1@test-20111111000001
+test_target1/test_source1/fs1/sub
+test_target1/test_source1/fs1/sub@test-20111111000000
+test_target1/test_source1/fs1/sub@test-20111111000001
+test_target1/test_source2
+test_target1/test_source2/fs2
+test_target1/test_source2/fs2/sub
+test_target1/test_source2/fs2/sub@test-20111111000000
+test_target1/test_source2/fs2/sub@test-20111111000001
+""")
+
+    def  test_ignore_othersnaphots(self):
+
+        r=shelltest("zfs snapshot test_source1/fs1@othersimple")
+        r=shelltest("zfs snapshot test_source1/fs1@otherdate-20001111000000")
+
+        with patch('time.strftime', return_value="test-20101111000000"):
+            self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose".split(" ")).run())
+
+            r=shelltest("zfs list -H -o name -r -t all "+TEST_POOLS)
+            self.assertMultiLineEqual(r,"""
+test_source1
+test_source1/fs1
+test_source1/fs1@othersimple
+test_source1/fs1@otherdate-20001111000000
+test_source1/fs1@test-20101111000000
+test_source1/fs1/sub
+test_source1/fs1/sub@test-20101111000000
+test_source2
+test_source2/fs2
+test_source2/fs2/sub
+test_source2/fs2/sub@test-20101111000000
+test_source2/fs3
+test_source2/fs3/sub
+test_target1
+test_target1/test_source1
+test_target1/test_source1/fs1
+test_target1/test_source1/fs1@test-20101111000000
+test_target1/test_source1/fs1/sub
+test_target1/test_source1/fs1/sub@test-20101111000000
+test_target1/test_source2
+test_target1/test_source2/fs2
+test_target1/test_source2/fs2/sub
+test_target1/test_source2/fs2/sub@test-20101111000000
+""")
+
+    def  test_othersnaphots(self):
+
+        r=shelltest("zfs snapshot test_source1/fs1@othersimple")
+        r=shelltest("zfs snapshot test_source1/fs1@otherdate-20001111000000")
+
+        with patch('time.strftime', return_value="test-20101111000000"):
+            self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose --other-snapshots".split(" ")).run())
+
+            r=shelltest("zfs list -H -o name -r -t all "+TEST_POOLS)
+            self.assertMultiLineEqual(r,"""
+test_source1
+test_source1/fs1
+test_source1/fs1@othersimple
+test_source1/fs1@otherdate-20001111000000
+test_source1/fs1@test-20101111000000
+test_source1/fs1/sub
+test_source1/fs1/sub@test-20101111000000
+test_source2
+test_source2/fs2
+test_source2/fs2/sub
+test_source2/fs2/sub@test-20101111000000
+test_source2/fs3
+test_source2/fs3/sub
+test_target1
+test_target1/test_source1
+test_target1/test_source1/fs1
+test_target1/test_source1/fs1@othersimple
+test_target1/test_source1/fs1@otherdate-20001111000000
+test_target1/test_source1/fs1@test-20101111000000
+test_target1/test_source1/fs1/sub
+test_target1/test_source1/fs1/sub@test-20101111000000
+test_target1/test_source2
+test_target1/test_source2/fs2
+test_target1/test_source2/fs2/sub
+test_target1/test_source2/fs2/sub@test-20101111000000
+""")
+
+
+    def  test_nosnapshot(self):
+
+        with patch('time.strftime', return_value="test-20101111000000"):
+            self.assertFalse(ZfsAutobackup("test test_target1 --verbose --no-snapshot --no-progress".split(" ")).run())
+
+            r=shelltest("zfs list -H -o name -r -t all "+TEST_POOLS)
+            #(only parents are created )
+            #TODO: it probably shouldn't create these
+            self.assertMultiLineEqual(r,"""
+test_source1
+test_source1/fs1
+test_source1/fs1/sub
+test_source2
+test_source2/fs2
+test_source2/fs2/sub
+test_source2/fs3
+test_source2/fs3/sub
+test_target1
+test_target1/test_source1
+test_target1/test_source2
+test_target1/test_source2/fs2
+""")
+
+
+    def  test_nosend(self):
+
+        with patch('time.strftime', return_value="test-20101111000000"):
+            self.assertFalse(ZfsAutobackup("test test_target1 --verbose --no-send --no-progress".split(" ")).run())
+
+            r=shelltest("zfs list -H -o name -r -t all "+TEST_POOLS)
+            self.assertMultiLineEqual(r,"""
+test_source1
+test_source1/fs1
+test_source1/fs1@test-20101111000000
+test_source1/fs1/sub
+test_source1/fs1/sub@test-20101111000000
+test_source2
+test_source2/fs2
+test_source2/fs2/sub
+test_source2/fs2/sub@test-20101111000000
+test_source2/fs3
+test_source2/fs3/sub
+test_target1
+""")
+
+
+    def  test_ignorereplicated(self):
+        r=shelltest("zfs snapshot test_source1/fs1@otherreplication")
+
+        with patch('time.strftime', return_value="test-20101111000000"):
+            self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose --ignore-replicated".split(" ")).run())
+
+            r=shelltest("zfs list -H -o name -r -t all "+TEST_POOLS)
+            self.assertMultiLineEqual(r,"""
+test_source1
+test_source1/fs1
+test_source1/fs1@otherreplication
+test_source1/fs1/sub
+test_source1/fs1/sub@test-20101111000000
+test_source2
+test_source2/fs2
+test_source2/fs2/sub
+test_source2/fs2/sub@test-20101111000000
+test_source2/fs3
+test_source2/fs3/sub
+test_target1
+test_target1/test_source1
+test_target1/test_source1/fs1
+test_target1/test_source1/fs1/sub
+test_target1/test_source1/fs1/sub@test-20101111000000
+test_target1/test_source2
+test_target1/test_source2/fs2
+test_target1/test_source2/fs2/sub
+test_target1/test_source2/fs2/sub@test-20101111000000
+""")
+
+    def  test_noholds(self):
+
+        with patch('time.strftime', return_value="test-20101111000000"):
+            self.assertFalse(ZfsAutobackup("test test_target1 --verbose --no-holds --no-progress".split(" ")).run())
+
+            r=shelltest("zfs get -r userrefs test_source1 test_source2 test_target1")
+            self.assertMultiLineEqual(r,"""
+NAME                                                   PROPERTY  VALUE     SOURCE
+test_source1                                           userrefs  -         -
+test_source1/fs1                                       userrefs  -         -
+test_source1/fs1@test-20101111000000                   userrefs  0         -
+test_source1/fs1/sub                                   userrefs  -         -
+test_source1/fs1/sub@test-20101111000000               userrefs  0         -
+test_source2                                           userrefs  -         -
+test_source2/fs2                                       userrefs  -         -
+test_source2/fs2/sub                                   userrefs  -         -
+test_source2/fs2/sub@test-20101111000000               userrefs  0         -
+test_source2/fs3                                       userrefs  -         -
+test_source2/fs3/sub                                   userrefs  -         -
+test_target1                                           userrefs  -         -
+test_target1/test_source1                              userrefs  -         -
+test_target1/test_source1/fs1                          userrefs  -         -
+test_target1/test_source1/fs1@test-20101111000000      userrefs  0         -
+test_target1/test_source1/fs1/sub                      userrefs  -         -
+test_target1/test_source1/fs1/sub@test-20101111000000  userrefs  0         -
+test_target1/test_source2                              userrefs  -         -
+test_target1/test_source2/fs2                          userrefs  -         -
+test_target1/test_source2/fs2/sub                      userrefs  -         -
+test_target1/test_source2/fs2/sub@test-20101111000000  userrefs  0         -
+""")
+
+
+    def  test_strippath(self):
+
+        with patch('time.strftime', return_value="test-20101111000000"):
+            self.assertFalse(ZfsAutobackup("test test_target1 --verbose --strip-path=1 --no-progress".split(" ")).run())
+
+            r=shelltest("zfs list -H -o name -r -t all "+TEST_POOLS)
+            self.assertMultiLineEqual(r,"""
+test_source1
+test_source1/fs1
+test_source1/fs1@test-20101111000000
+test_source1/fs1/sub
+test_source1/fs1/sub@test-20101111000000
+test_source2
+test_source2/fs2
+test_source2/fs2/sub
+test_source2/fs2/sub@test-20101111000000
+test_source2/fs3
+test_source2/fs3/sub
+test_target1
+test_target1/fs1
+test_target1/fs1@test-20101111000000
+test_target1/fs1/sub
+test_target1/fs1/sub@test-20101111000000
+test_target1/fs2
+test_target1/fs2/sub
+test_target1/fs2/sub@test-20101111000000
+""")
+
+    def test_strippath_collision(self):
+        with self.assertRaisesRegexp(Exception,"collision"):
+            ZfsAutobackup("test test_target1 --verbose --strip-path=2 --no-progress --debug".split(" ")).run()
+
+    def test_strippath_toomuch(self):
+        with self.assertRaisesRegexp(Exception,"too much"):
+            ZfsAutobackup("test test_target1 --verbose --strip-path=3 --no-progress --debug".split(" ")).run()
+
+    def  test_clearrefres(self):
+
+        #on zfs utils 0.6.x -x isnt supported
+        r=shelltest("zfs recv -x bla test >/dev/null </dev/zero; echo $?")
+        if r=="\n2\n":
+            self.skipTest("This zfs-userspace version doesnt support -x")
+
+        r=shelltest("zfs set refreservation=1M test_source1/fs1")
+
+        with patch('time.strftime', return_value="test-20101111000000"):
+            self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose --clear-refreservation".split(" ")).run())
+
+            r=shelltest("zfs get refreservation -r test_source1 test_source2 test_target1")
+            self.assertMultiLineEqual(r,"""
+NAME                                                   PROPERTY        VALUE      SOURCE
+test_source1                                           refreservation  none       default
+test_source1/fs1                                       refreservation  1M         local
+test_source1/fs1@test-20101111000000                   refreservation  -          -
+test_source1/fs1/sub                                   refreservation  none       default
+test_source1/fs1/sub@test-20101111000000               refreservation  -          -
+test_source2                                           refreservation  none       default
+test_source2/fs2                                       refreservation  none       default
+test_source2/fs2/sub                                   refreservation  none       default
+test_source2/fs2/sub@test-20101111000000               refreservation  -          -
+test_source2/fs3                                       refreservation  none       default
+test_source2/fs3/sub                                   refreservation  none       default
+test_target1                                           refreservation  none       default
+test_target1/test_source1                              refreservation  none       default
+test_target1/test_source1/fs1                          refreservation  none       default
+test_target1/test_source1/fs1@test-20101111000000      refreservation  -          -
+test_target1/test_source1/fs1/sub                      refreservation  none       default
+test_target1/test_source1/fs1/sub@test-20101111000000  refreservation  -          -
+test_target1/test_source2                              refreservation  none       default
+test_target1/test_source2/fs2                          refreservation  none       default
+test_target1/test_source2/fs2/sub                      refreservation  none       default
+test_target1/test_source2/fs2/sub@test-20101111000000  refreservation  -          -
+""")
+
+
+    def  test_clearmount(self):
+
+        #on zfs utils 0.6.x -o isnt supported
+        r=shelltest("zfs recv -o bla=1 test >/dev/null </dev/zero; echo $?")
+        if r=="\n2\n":
+            self.skipTest("This zfs-userspace version doesnt support -o")
+
+
+        with patch('time.strftime', return_value="test-20101111000000"):
+            self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose --clear-mountpoint --debug".split(" ")).run())
+
+            r=shelltest("zfs get canmount -r test_source1 test_source2 test_target1")
+            self.assertMultiLineEqual(r,"""
+NAME                                                   PROPERTY  VALUE     SOURCE
+test_source1                                           canmount  on        default
+test_source1/fs1                                       canmount  on        default
+test_source1/fs1@test-20101111000000                   canmount  -         -
+test_source1/fs1/sub                                   canmount  on        default
+test_source1/fs1/sub@test-20101111000000               canmount  -         -
+test_source2                                           canmount  on        default
+test_source2/fs2                                       canmount  on        default
+test_source2/fs2/sub                                   canmount  on        default
+test_source2/fs2/sub@test-20101111000000               canmount  -         -
+test_source2/fs3                                       canmount  on        default
+test_source2/fs3/sub                                   canmount  on        default
+test_target1                                           canmount  on        default
+test_target1/test_source1                              canmount  on        default
+test_target1/test_source1/fs1                          canmount  noauto    local
+test_target1/test_source1/fs1@test-20101111000000      canmount  -         -
+test_target1/test_source1/fs1/sub                      canmount  noauto    local
+test_target1/test_source1/fs1/sub@test-20101111000000  canmount  -         -
+test_target1/test_source2                              canmount  on        default
+test_target1/test_source2/fs2                          canmount  on        default
+test_target1/test_source2/fs2/sub                      canmount  noauto    local
+test_target1/test_source2/fs2/sub@test-20101111000000  canmount  -         -
+""")
+
+
+    def  test_rollback(self):
+
+        #initial backup
+        with patch('time.strftime', return_value="test-20101111000000"):
+            self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose".split(" ")).run())
+
+        #make change
+        r=shelltest("zfs mount test_target1/test_source1/fs1")
+        r=shelltest("touch /test_target1/test_source1/fs1/change.txt")
+
+        with patch('time.strftime', return_value="test-20101111000001"):
+            #should fail (busy)
+            self.assertTrue(ZfsAutobackup("test test_target1 --no-progress --verbose --allow-empty".split(" ")).run())
+
+        with patch('time.strftime', return_value="test-20101111000002"):
+            #rollback, should succeed
+            self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose --allow-empty --rollback".split(" ")).run())
+
+
+    def  test_destroyincompat(self):
+
+        #initial backup
+        with patch('time.strftime', return_value="test-20101111000000"):
+            self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose".split(" ")).run())
+
+        #add multiple compatible snapshot (written is still 0)
+        r=shelltest("zfs snapshot test_target1/test_source1/fs1@compatible1")
+        r=shelltest("zfs snapshot test_target1/test_source1/fs1@compatible2")
+
+        with patch('time.strftime', return_value="test-20101111000001"):
+            #should be ok, is compatible
+            self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose --allow-empty".split(" ")).run())
+
+        #add incompatible snapshot by changing and snapshotting
+        r=shelltest("zfs mount test_target1/test_source1/fs1")
+        r=shelltest("touch /test_target1/test_source1/fs1/change.txt")
+        r=shelltest("zfs snapshot test_target1/test_source1/fs1@incompatible1")
+
+
+        with patch('time.strftime', return_value="test-20101111000002"):
+            #--test should fail, now incompatible
+            self.assertTrue(ZfsAutobackup("test test_target1 --no-progress --verbose --allow-empty --test".split(" ")).run())
+
+        with patch('time.strftime', return_value="test-20101111000002"):
+            #should fail, now incompatible
+            self.assertTrue(ZfsAutobackup("test test_target1 --no-progress --verbose --allow-empty".split(" ")).run())
+
+        with patch('time.strftime', return_value="test-20101111000003"):
+            #--test should succeed by destroying incompatibles
+            self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose --allow-empty --destroy-incompatible --test".split(" ")).run())
+
+        with patch('time.strftime', return_value="test-20101111000003"):
+            #should succeed by destroying incompatibles
+            self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose --allow-empty --destroy-incompatible".split(" ")).run())
+
+        r = shelltest("zfs list -H -o name -r -t all test_target1")
+        self.assertMultiLineEqual(r, """
+test_target1
+test_target1/test_source1
+test_target1/test_source1/fs1
+test_target1/test_source1/fs1@test-20101111000000
+test_target1/test_source1/fs1@compatible1
+test_target1/test_source1/fs1@compatible2
+test_target1/test_source1/fs1@test-20101111000001
+test_target1/test_source1/fs1@test-20101111000002
+test_target1/test_source1/fs1@test-20101111000003
+test_target1/test_source1/fs1/sub
+test_target1/test_source1/fs1/sub@test-20101111000000
+test_target1/test_source1/fs1/sub@test-20101111000001
+test_target1/test_source1/fs1/sub@test-20101111000002
+test_target1/test_source1/fs1/sub@test-20101111000003
+test_target1/test_source2
+test_target1/test_source2/fs2
+test_target1/test_source2/fs2/sub
+test_target1/test_source2/fs2/sub@test-20101111000000
+test_target1/test_source2/fs2/sub@test-20101111000001
+test_target1/test_source2/fs2/sub@test-20101111000002
+test_target1/test_source2/fs2/sub@test-20101111000003
+""")
+
+
+
+
+
+
+    def test_ssh(self):
+
+        #test all ssh directions
+
+        with patch('time.strftime', return_value="test-20101111000000"):
+            self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose --allow-empty --ssh-source localhost --exclude-received".split(" ")).run())
+
+        with patch('time.strftime', return_value="test-20101111000001"):
+            self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose --allow-empty --ssh-target localhost --exclude-received".split(" ")).run())
+
+        with patch('time.strftime', return_value="test-20101111000002"):
+            self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose --allow-empty --ssh-source localhost --ssh-target localhost".split(" ")).run())
+
+
+        r=shelltest("zfs list -H -o name -r -t all "+TEST_POOLS)
+        self.assertMultiLineEqual(r,"""
+test_source1
+test_source1/fs1
+test_source1/fs1@test-20101111000000
+test_source1/fs1@test-20101111000001
+test_source1/fs1@test-20101111000002
+test_source1/fs1/sub
+test_source1/fs1/sub@test-20101111000000
+test_source1/fs1/sub@test-20101111000001
+test_source1/fs1/sub@test-20101111000002
+test_source2
+test_source2/fs2
+test_source2/fs2/sub
+test_source2/fs2/sub@test-20101111000000
+test_source2/fs2/sub@test-20101111000001
+test_source2/fs2/sub@test-20101111000002
+test_source2/fs3
+test_source2/fs3/sub
+test_target1
+test_target1/test_source1
+test_target1/test_source1/fs1
+test_target1/test_source1/fs1@test-20101111000000
+test_target1/test_source1/fs1@test-20101111000001
+test_target1/test_source1/fs1@test-20101111000002
+test_target1/test_source1/fs1/sub
+test_target1/test_source1/fs1/sub@test-20101111000000
+test_target1/test_source1/fs1/sub@test-20101111000001
+test_target1/test_source1/fs1/sub@test-20101111000002
+test_target1/test_source2
+test_target1/test_source2/fs2
+test_target1/test_source2/fs2/sub
+test_target1/test_source2/fs2/sub@test-20101111000000
+test_target1/test_source2/fs2/sub@test-20101111000001
+test_target1/test_source2/fs2/sub@test-20101111000002
+""")
+
+
+    def  test_minchange(self):
+
+        #initial
+        with patch('time.strftime', return_value="test-20101111000000"):
+            self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose --min-change 100000".split(" ")).run())
+
+        #make small change, use umount to reflect the changes immediately
+        r=shelltest("zfs set compress=off test_source1")
+        r=shelltest("touch /test_source1/fs1/change.txt")
+        r=shelltest("zfs umount test_source1/fs1; zfs mount test_source1/fs1")
+
+
+        #too small change, takes no snapshots
+        with patch('time.strftime', return_value="test-20101111000001"):
+            self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose --min-change 100000".split(" ")).run())
+
+        #make big change
+        r=shelltest("dd if=/dev/zero of=/test_source1/fs1/change.txt bs=200000 count=1")
+        r=shelltest("zfs umount test_source1/fs1; zfs mount test_source1/fs1")
+
+        #bigger change, should take snapshot
+        with patch('time.strftime', return_value="test-20101111000002"):
+            self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose --min-change 100000".split(" ")).run())
+
+        r=shelltest("zfs list -H -o name -r -t all "+TEST_POOLS)
+        self.assertMultiLineEqual(r,"""
+test_source1
+test_source1/fs1
+test_source1/fs1@test-20101111000000
+test_source1/fs1@test-20101111000002
+test_source1/fs1/sub
+test_source1/fs1/sub@test-20101111000000
+test_source2
+test_source2/fs2
+test_source2/fs2/sub
+test_source2/fs2/sub@test-20101111000000
+test_source2/fs3
+test_source2/fs3/sub
+test_target1
+test_target1/test_source1
+test_target1/test_source1/fs1
+test_target1/test_source1/fs1@test-20101111000000
+test_target1/test_source1/fs1@test-20101111000002
+test_target1/test_source1/fs1/sub
+test_target1/test_source1/fs1/sub@test-20101111000000
+test_target1/test_source2
+test_target1/test_source2/fs2
+test_target1/test_source2/fs2/sub
+test_target1/test_source2/fs2/sub@test-20101111000000
+""")
+
+    def  test_test(self):
+
+        #initial
+        with patch('time.strftime', return_value="test-20101111000000"):
+            self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose --test".split(" ")).run())
+
+        r=shelltest("zfs list -H -o name -r -t all "+TEST_POOLS)
+        self.assertMultiLineEqual(r,"""
+test_source1
+test_source1/fs1
+test_source1/fs1/sub
+test_source2
+test_source2/fs2
+test_source2/fs2/sub
+test_source2/fs3
+test_source2/fs3/sub
+test_target1
+""")
+
+        #actual make initial backup
+        with patch('time.strftime', return_value="test-20101111000001"):
+            self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose".split(" ")).run())
+
+
+        #test incremental
+        with patch('time.strftime', return_value="test-20101111000002"):
+            self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --allow-empty --verbose --test".split(" ")).run())
+
+        r=shelltest("zfs list -H -o name -r -t all "+TEST_POOLS)
+        self.assertMultiLineEqual(r,"""
+test_source1
+test_source1/fs1
+test_source1/fs1@test-20101111000001
+test_source1/fs1/sub
+test_source1/fs1/sub@test-20101111000001
+test_source2
+test_source2/fs2
+test_source2/fs2/sub
+test_source2/fs2/sub@test-20101111000001
+test_source2/fs3
+test_source2/fs3/sub
+test_target1
+test_target1/test_source1
+test_target1/test_source1/fs1
+test_target1/test_source1/fs1@test-20101111000001
+test_target1/test_source1/fs1/sub
+test_target1/test_source1/fs1/sub@test-20101111000001
+test_target1/test_source2
+test_target1/test_source2/fs2
+test_target1/test_source2/fs2/sub
+test_target1/test_source2/fs2/sub@test-20101111000001
+""")
+
+
+    def test_migrate(self):
+        """test migration from other snapshotting systems. zfs-autobackup should be able to continue from any common snapshot, not just its own."""
+
+        shelltest("zfs snapshot test_source1/fs1@migrate1")
+        shelltest("zfs create test_target1/test_source1")
+        shelltest("zfs send  test_source1/fs1@migrate1| zfs recv test_target1/test_source1/fs1")
+
+        with patch('time.strftime', return_value="test-20101111000000"):
+            self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose".split(" ")).run())
+
+        r=shelltest("zfs list -H -o name -r -t all "+TEST_POOLS)
+        self.assertMultiLineEqual(r,"""
+test_source1
+test_source1/fs1
+test_source1/fs1@migrate1
+test_source1/fs1@test-20101111000000
+test_source1/fs1/sub
+test_source1/fs1/sub@test-20101111000000
+test_source2
+test_source2/fs2
+test_source2/fs2/sub
+test_source2/fs2/sub@test-20101111000000
+test_source2/fs3
+test_source2/fs3/sub
+test_target1
+test_target1/test_source1
+test_target1/test_source1/fs1
+test_target1/test_source1/fs1@migrate1
+test_target1/test_source1/fs1@test-20101111000000
+test_target1/test_source1/fs1/sub
+test_target1/test_source1/fs1/sub@test-20101111000000
+test_target1/test_source2
+test_target1/test_source2/fs2
+test_target1/test_source2/fs2/sub
+test_target1/test_source2/fs2/sub@test-20101111000000
+""")
+
+    def test_keep0(self):
+        """test if keep-source=0 and keep-target=0 dont delete common snapshot and break backup"""
+
+        with patch('time.strftime', return_value="test-20101111000000"):
+            self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose --keep-source=0 --keep-target=0".split(" ")).run())
+
+        #make snapshot, shouldnt delete 0
+        with patch('time.strftime', return_value="test-20101111000001"):
+            self.assertFalse(ZfsAutobackup("test --no-progress --verbose --keep-source=0 --keep-target=0 --allow-empty".split(" ")).run())
+
+        #make snapshot 2, shouldnt delete 0 since it has holds, but will delete 1 since it has no holds
+        with patch('time.strftime', return_value="test-20101111000002"):
+            self.assertFalse(ZfsAutobackup("test --no-progress --verbose --keep-source=0 --keep-target=0 --allow-empty".split(" ")).run())
+
+        r = shelltest("zfs list -H -o name -r -t all " + TEST_POOLS)
+        self.assertMultiLineEqual(r, """
+test_source1
+test_source1/fs1
+test_source1/fs1@test-20101111000000
+test_source1/fs1@test-20101111000002
+test_source1/fs1/sub
+test_source1/fs1/sub@test-20101111000000
+test_source1/fs1/sub@test-20101111000002
+test_source2
+test_source2/fs2
+test_source2/fs2/sub
+test_source2/fs2/sub@test-20101111000000
+test_source2/fs2/sub@test-20101111000002
+test_source2/fs3
+test_source2/fs3/sub
+test_target1
+test_target1/test_source1
+test_target1/test_source1/fs1
+test_target1/test_source1/fs1@test-20101111000000
+test_target1/test_source1/fs1/sub
+test_target1/test_source1/fs1/sub@test-20101111000000
+test_target1/test_source2
+test_target1/test_source2/fs2
+test_target1/test_source2/fs2/sub
+test_target1/test_source2/fs2/sub@test-20101111000000
+""")
+
+        #make another backup but with no-holds. we should naturally endup with only number 3
+        with patch('time.strftime', return_value="test-20101111000003"):
+            self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose --keep-source=0 --keep-target=0 --no-holds --allow-empty".split(" ")).run())
+
+        r = shelltest("zfs list -H -o name -r -t all " + TEST_POOLS)
+        self.assertMultiLineEqual(r, """
+test_source1
+test_source1/fs1
+test_source1/fs1@test-20101111000003
+test_source1/fs1/sub
+test_source1/fs1/sub@test-20101111000003
+test_source2
+test_source2/fs2
+test_source2/fs2/sub
+test_source2/fs2/sub@test-20101111000003
+test_source2/fs3
+test_source2/fs3/sub
+test_target1
+test_target1/test_source1
+test_target1/test_source1/fs1
+test_target1/test_source1/fs1@test-20101111000003
+test_target1/test_source1/fs1/sub
+test_target1/test_source1/fs1/sub@test-20101111000003
+test_target1/test_source2
+test_target1/test_source2/fs2
+test_target1/test_source2/fs2/sub
+test_target1/test_source2/fs2/sub@test-20101111000003
+""")
+
+
+        # run with snapshot-only for 4, since we used no-holds, it will delete 3 on the source, breaking the backup
+        with patch('time.strftime', return_value="test-20101111000004"):
+            self.assertFalse(ZfsAutobackup("test --no-progress --verbose --keep-source=0 --keep-target=0 --allow-empty".split(" ")).run())
+
+        r = shelltest("zfs list -H -o name -r -t all " + TEST_POOLS)
+        self.assertMultiLineEqual(r, """
+test_source1
+test_source1/fs1
+test_source1/fs1@test-20101111000004
+test_source1/fs1/sub
+test_source1/fs1/sub@test-20101111000004
+test_source2
+test_source2/fs2
+test_source2/fs2/sub
+test_source2/fs2/sub@test-20101111000004
+test_source2/fs3
+test_source2/fs3/sub
+test_target1
+test_target1/test_source1
+test_target1/test_source1/fs1
+test_target1/test_source1/fs1@test-20101111000003
+test_target1/test_source1/fs1/sub
+test_target1/test_source1/fs1/sub@test-20101111000003
+test_target1/test_source2
+test_target1/test_source2/fs2
+test_target1/test_source2/fs2/sub
+test_target1/test_source2/fs2/sub@test-20101111000003
+""")
+
+
+    def test_progress(self):
+
+        r=shelltest("dd if=/dev/zero of=/test_source1/data.txt bs=200000 count=1")
+        r = shelltest("zfs snapshot test_source1@test")
+
+        l=LogConsole(show_verbose=True, show_debug=False, color=False)
+        n=ZfsNode(utc=False, snapshot_time_format="bla", hold_name="bla", logger=l)
+        d=ZfsDataset(n,"test_source1@test")
+
+        sp=d.send_pipe([], prev_snapshot=None, resume_token=None, show_progress=True, raw=False, send_pipes=[], send_properties=True, write_embedded=True, zfs_compressed=True)
+
+
+        with OutputIO() as buf:
+            with redirect_stderr(buf):
+                try:
+                    n.run(["sleep", "2"], inp=sp)
+                except:
+                    pass
+
+            print(buf.getvalue())
+            # correct message?
+            self.assertRegex(buf.getvalue(),".*>>> .*minutes left.*")

tests/test_zfsautobackup31.py

@@ -0,0 +1,119 @@
+from basetest import *
+import time
+
+class TestZfsAutobackup31(unittest2.TestCase):
+    """various new 3.1 features"""
+
+    def setUp(self):
+        prepare_zpools()
+        self.longMessage=True
+
+    def test_no_thinning(self):
+
+        with patch('time.strftime', return_value="test-20101111000000"):
+            self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose --allow-empty".split(" ")).run())
+
+        with patch('time.strftime', return_value="test-20101111000001"):
+            self.assertFalse(ZfsAutobackup("test test_target1 --no-progress --verbose --allow-empty --keep-target=0 --keep-source=0 --no-thinning".split(" ")).run())
+
+            r=shelltest("zfs list -H -o name -r -t all "+TEST_POOLS)
+            self.assertMultiLineEqual(r,"""
+test_source1
+test_source1/fs1
+test_source1/fs1@test-20101111000000
+test_source1/fs1@test-20101111000001
+test_source1/fs1/sub
+test_source1/fs1/sub@test-20101111000000
+test_source1/fs1/sub@test-20101111000001
+test_source2
+test_source2/fs2
+test_source2/fs2/sub
+test_source2/fs2/sub@test-20101111000000
+test_source2/fs2/sub@test-20101111000001
+test_source2/fs3
+test_source2/fs3/sub
+test_target1
+test_target1/test_source1
+test_target1/test_source1/fs1
+test_target1/test_source1/fs1@test-20101111000000
+test_target1/test_source1/fs1@test-20101111000001
+test_target1/test_source1/fs1/sub
+test_target1/test_source1/fs1/sub@test-20101111000000
+test_target1/test_source1/fs1/sub@test-20101111000001
+test_target1/test_source2
+test_target1/test_source2/fs2
+test_target1/test_source2/fs2/sub
+test_target1/test_source2/fs2/sub@test-20101111000000
+test_target1/test_source2/fs2/sub@test-20101111000001
+""")
+
+
+    def test_re_replication(self):
+        """test re-replication of something thats already a backup (new in v3.1-beta5)"""
+
+        shelltest("zfs create test_target1/a")
+        shelltest("zfs create test_target1/b")
+
+        with patch('time.strftime', return_value="test-20101111000000"):
+            self.assertFalse(ZfsAutobackup("test test_target1/a --no-progress --verbose --debug".split(" ")).run())
+
+        with patch('time.strftime', return_value="test-20101111000001"):
+            self.assertFalse(ZfsAutobackup("test test_target1/b --no-progress --verbose".split(" ")).run())
+
+            r=shelltest("zfs list -H -o name -r -t snapshot test_target1")
+            #NOTE: it wont backup test_target1/a/test_source2/fs2/sub to test_target1/b since it doesnt have the zfs_autobackup property anymore.
+            self.assertMultiLineEqual(r,"""
+test_target1/a/test_source1/fs1@test-20101111000000
+test_target1/a/test_source1/fs1/sub@test-20101111000000
+test_target1/a/test_source2/fs2/sub@test-20101111000000
+test_target1/b/test_source1/fs1@test-20101111000000
+test_target1/b/test_source1/fs1/sub@test-20101111000000
+test_target1/b/test_source2/fs2/sub@test-20101111000000
+test_target1/b/test_target1/a/test_source1/fs1@test-20101111000000
+test_target1/b/test_target1/a/test_source1/fs1/sub@test-20101111000000
+""")
+
+    def test_zfs_compressed(self):
+
+        with patch('time.strftime', return_value="test-20101111000000"):
+            self.assertFalse(
+                ZfsAutobackup("test test_target1 --no-progress --verbose --debug --zfs-compressed".split(" ")).run())
+
+    def test_force(self):
+        """test 1:1 replication"""
+
+        shelltest("zfs set autobackup:test=true test_source1")
+
+        with patch('time.strftime', return_value="test-20101111000000"):
+            self.assertFalse(
+                ZfsAutobackup("test test_target1 --no-progress --verbose --debug --force --strip-path=1".split(" ")).run())
+
+            r=shelltest("zfs list -H -o name -r -t snapshot test_target1")
+            self.assertMultiLineEqual(r,"""
+test_target1@test-20101111000000
+test_target1/fs1@test-20101111000000
+test_target1/fs1/sub@test-20101111000000
+test_target1/fs2/sub@test-20101111000000
+""")
+
+
+    def test_exclude_unchanged(self):
+
+        shelltest("zfs snapshot -r test_source1@somesnapshot")
+
+        with patch('time.strftime', return_value="test-20101111000000"):
+            self.assertFalse(
+                ZfsAutobackup(
+                    "test test_target1 --verbose --allow-empty --exclude-unchanged=1".split(" ")).run())
+
+        #everything should be excluded, but should not return an error (see #190)
+        with patch('time.strftime', return_value="test-20101111000001"):
+            self.assertFalse(
+                ZfsAutobackup(
+                    "test test_target1 --verbose --allow-empty --exclude-unchanged=1".split(" ")).run())
+
+        r = shelltest("zfs list -H -o name -r -t snapshot test_target1")
+        self.assertMultiLineEqual(r, """
+test_target1/test_source2/fs2/sub@test-20101111000000
+""")
+

tests/test_zfscheck.py

@@ -0,0 +1,216 @@
+from basetest import *
+from zfs_autobackup.BlockHasher import BlockHasher
+
+
+class TestZfsCheck(unittest2.TestCase):
+
+    def setUp(self):
+        pass
+
+
+    def test_volume(self):
+        prepare_zpools()
+
+        shelltest("zfs create -V200M test_source1/vol")
+        shelltest("zfs snapshot test_source1/vol@test")
+
+        with self.subTest("Generate"):
+            with OutputIO() as buf:
+                with redirect_stdout(buf):
+                    self.assertFalse(ZfsCheck("test_source1/vol@test".split(" "),print_arguments=False).run())
+
+                print(buf.getvalue())
+                self.assertEqual("""0	2c2ceccb5ec5574f791d45b63c940cff20550f9a
+1	2c2ceccb5ec5574f791d45b63c940cff20550f9a
+""", buf.getvalue())
+
+                #store on disk for next step, add one error.
+                with open("/tmp/testhashes", "w") as fh:
+                    fh.write(buf.getvalue()+"1\t2c2ceccb5ec5574f791d45b63c940cff20550f9X")
+
+        with self.subTest("Compare"):
+            with OutputIO() as buf:
+                with redirect_stdout(buf):
+                    self.assertEqual(1, ZfsCheck("test_source1/vol@test --check=/tmp/testhashes".split(" "),print_arguments=False).run())
+                print(buf.getvalue())
+                self.assertEqual("Chunk 1 failed: 2c2ceccb5ec5574f791d45b63c940cff20550f9X 2c2ceccb5ec5574f791d45b63c940cff20550f9a\n", buf.getvalue())
+
+    def test_filesystem(self):
+        prepare_zpools()
+
+        shelltest("cp tests/data/whole /test_source1/testfile")
+        shelltest("mkdir /test_source1/emptydir")
+        shelltest("mkdir /test_source1/dir")
+        shelltest("cp tests/data/whole2 /test_source1/dir/testfile")
+
+        #it should ignore these:
+        shelltest("ln -s / /test_source1/symlink")
+        shelltest("mknod /test_source1/c c 1 1")
+        shelltest("mknod /test_source1/b b 1 1")
+        shelltest("mkfifo /test_source1/f")
+
+        shelltest("zfs snapshot test_source1@test")
+
+        with self.subTest("Generate"):
+            with OutputIO() as buf:
+                with redirect_stdout(buf):
+                    self.assertFalse(ZfsCheck("test_source1@test".split(" "), print_arguments=False).run())
+
+                print(buf.getvalue())
+                self.assertEqual("""testfile	0	3c0bf91170d873b8e327d3bafb6bc074580d11b7
+dir/testfile	0	2e863f1fcccd6642e4e28453eba10d2d3f74d798
+""", buf.getvalue())
+
+                #store on disk for next step, add error
+                with open("/tmp/testhashes", "w") as fh:
+                    fh.write(buf.getvalue()+"dir/testfile	0	2e863f1fcccd6642e4e28453eba10d2d3f74d79X")
+
+        with self.subTest("Compare"):
+            with OutputIO() as buf:
+                with redirect_stdout(buf):
+                    self.assertEqual(1, ZfsCheck("test_source1@test --check=/tmp/testhashes".split(" "),print_arguments=False).run())
+
+                print(buf.getvalue())
+                self.assertEqual("dir/testfile: Chunk 0 failed: 2e863f1fcccd6642e4e28453eba10d2d3f74d79X 2e863f1fcccd6642e4e28453eba10d2d3f74d798\n", buf.getvalue())
+
+    def test_file(self):
+
+        with self.subTest("Generate"):
+            with OutputIO() as buf:
+                with redirect_stdout(buf):
+                    self.assertFalse(ZfsCheck("tests/data/whole".split(" "), print_arguments=False).run())
+
+                print(buf.getvalue())
+                self.assertEqual("""0	3c0bf91170d873b8e327d3bafb6bc074580d11b7
+""", buf.getvalue())
+
+                # store on disk for next step, add error
+                with open("/tmp/testhashes", "w") as fh:
+                    fh.write(buf.getvalue()+"0	3c0bf91170d873b8e327d3bafb6bc074580d11bX")
+
+        with self.subTest("Compare"):
+            with OutputIO() as buf:
+                with redirect_stdout(buf):
+                    self.assertEqual(1,ZfsCheck("tests/data/whole --check=/tmp/testhashes".split(" "), print_arguments=False).run())
+                print(buf.getvalue())
+                self.assertEqual("Chunk 0 failed: 3c0bf91170d873b8e327d3bafb6bc074580d11bX 3c0bf91170d873b8e327d3bafb6bc074580d11b7\n", buf.getvalue())
+
+    def test_tree(self):
+        shelltest("rm -rf /tmp/testtree; mkdir /tmp/testtree")
+        shelltest("cp tests/data/whole /tmp/testtree")
+        shelltest("cp tests/data/whole_whole2 /tmp/testtree")
+        shelltest("cp tests/data/whole2 /tmp/testtree")
+        shelltest("cp tests/data/partial /tmp/testtree")
+        shelltest("cp tests/data/whole_whole2_partial /tmp/testtree")
+
+        ####################################
+        with self.subTest("Generate, skip 1"):
+            with OutputIO() as buf:
+                with redirect_stdout(buf):
+                    self.assertFalse(ZfsCheck("/tmp/testtree --skip=1".split(" "), print_arguments=False).run())
+
+                #since order varies, just check count (there is one empty line for some reason, only when testing like this)
+                print(buf.getvalue().split("\n"))
+                self.assertEqual(len(buf.getvalue().split("\n")),4)
+
+        ######################################
+        with self.subTest("Compare, all incorrect, skip 1"):
+
+            # store on disk for next step, add error
+            with open("/tmp/testhashes", "w") as fh:
+                fh.write("""
+partial	0	642027d63bb0afd7e0ba197f2c66ad03e3d70deX
+whole	0	3c0bf91170d873b8e327d3bafb6bc074580d11bX
+whole2	0	2e863f1fcccd6642e4e28453eba10d2d3f74d79X
+whole_whole2	0	959e6b58078f0cfd2fb3d37e978fda51820473fX
+whole_whole2_partial	0	309ffffba2e1977d12f3b7469971f30d28b94bdX
+""")
+
+            with OutputIO() as buf:
+                with redirect_stdout(buf):
+                    self.assertEqual(ZfsCheck("/tmp/testtree --check=/tmp/testhashes --skip=1".split(" "), print_arguments=False).run(), 3)
+
+                print(buf.getvalue())
+                self.assertMultiLineEqual("""partial: Chunk 0 failed: 642027d63bb0afd7e0ba197f2c66ad03e3d70deX 642027d63bb0afd7e0ba197f2c66ad03e3d70de1
+whole2: Chunk 0 failed: 2e863f1fcccd6642e4e28453eba10d2d3f74d79X 2e863f1fcccd6642e4e28453eba10d2d3f74d798
+whole_whole2_partial: Chunk 0 failed: 309ffffba2e1977d12f3b7469971f30d28b94bdX 309ffffba2e1977d12f3b7469971f30d28b94bd8
+""",buf.getvalue())
+
+        ####################################
+        with self.subTest("Generate"):
+            with OutputIO() as buf:
+                with redirect_stdout(buf):
+                    self.assertFalse(ZfsCheck("/tmp/testtree".split(" "), print_arguments=False).run())
+
+                #file order on disk can vary, so sort it..
+                sorted=buf.getvalue().split("\n")
+                sorted.sort()
+                sorted="\n".join(sorted)+"\n"
+
+                print(sorted)
+                self.assertEqual("""
+partial	0	642027d63bb0afd7e0ba197f2c66ad03e3d70de1
+whole	0	3c0bf91170d873b8e327d3bafb6bc074580d11b7
+whole2	0	2e863f1fcccd6642e4e28453eba10d2d3f74d798
+whole_whole2	0	959e6b58078f0cfd2fb3d37e978fda51820473ff
+whole_whole2_partial	0	309ffffba2e1977d12f3b7469971f30d28b94bd8
+""", sorted)
+
+                # store on disk for next step, add error
+                with open("/tmp/testhashes", "w") as fh:
+                    fh.write(buf.getvalue() + "whole_whole2_partial	0	309ffffba2e1977d12f3b7469971f30d28b94bdX")
+
+        ####################################
+        with self.subTest("Compare"):
+            with OutputIO() as buf:
+                with redirect_stdout(buf):
+                    self.assertEqual(1, ZfsCheck("/tmp/testtree --check=/tmp/testhashes".split(" "),
+                                                 print_arguments=False).run())
+                print(buf.getvalue())
+                self.assertEqual(
+                    "whole_whole2_partial: Chunk 0 failed: 309ffffba2e1977d12f3b7469971f30d28b94bdX 309ffffba2e1977d12f3b7469971f30d28b94bd8\n",
+                    buf.getvalue())
+
+    def test_brokenpipe_cleanup_filesystem(self):
+        """test if stuff is cleaned up correctly, in debugging mode , when a pipe breaks. """
+
+        prepare_zpools()
+        shelltest("cp tests/data/whole /test_source1/testfile")
+        shelltest("zfs snapshot test_source1@test")
+
+        #breaks pipe when grep exists:
+        #important to use --debug, since that generates extra output which would be problematic if we didnt do correct SIGPIPE handling
+        shelltest("python -m zfs_autobackup.ZfsCheck test_source1@test --debug | grep -m1 'Hashing tree'")
+        # time.sleep(5)
+
+        #should NOT be mounted anymore if cleanup went ok:
+        self.assertNotRegex(shelltest("mount"), "test_source1@test")
+
+    def test_brokenpipe_cleanup_volume(self):
+
+        prepare_zpools()
+        shelltest("zfs create -V200M test_source1/vol")
+        shelltest("zfs snapshot test_source1/vol@test")
+
+        #breaks pipe when grep exists:
+        #important to use --debug, since that generates extra output which would be problematic if we didnt do correct SIGPIPE handling
+        shelltest("python -m zfs_autobackup.ZfsCheck test_source1/vol@test --debug | grep -m1 'Hashing file'")
+        # time.sleep(1)
+
+        r = shelltest("zfs list -H -o name -r -t all " + TEST_POOLS)
+        self.assertMultiLineEqual("""
+test_source1
+test_source1/fs1
+test_source1/fs1/sub
+test_source1/vol
+test_source1/vol@test
+test_source2
+test_source2/fs2
+test_source2/fs2/sub
+test_source2/fs3
+test_source2/fs3/sub
+test_target1
+""",r )
+
+
+

tests/test_zfsnode.py

@@ -0,0 +1,207 @@
+from basetest import *
+from zfs_autobackup.LogStub import LogStub
+from zfs_autobackup.ExecuteNode import ExecuteError
+
+
+class TestZfsNode(unittest2.TestCase):
+
+    def setUp(self):
+        prepare_zpools()
+        # return super().setUp()
+
+    def test_consistent_snapshot(self):
+        logger = LogStub()
+        description = "[Source]"
+        node = ZfsNode(utc=False, snapshot_time_format="test-%Y%m%d%H%M%S", hold_name="zfs_autobackup:test", logger=logger, description=description)
+
+        with self.subTest("first snapshot"):
+            (selected_datasets, excluded_datasets)=node.selected_datasets(property_name="autobackup:test", exclude_paths=[], exclude_received=False,
+                                   exclude_unchanged=0)
+            node.consistent_snapshot(selected_datasets, "test-20101111000001", 100000)
+            r = shelltest("zfs list -H -o name -r -t all " + TEST_POOLS)
+            self.assertEqual(r, """
+test_source1
+test_source1/fs1
+test_source1/fs1@test-20101111000001
+test_source1/fs1/sub
+test_source1/fs1/sub@test-20101111000001
+test_source2
+test_source2/fs2
+test_source2/fs2/sub
+test_source2/fs2/sub@test-20101111000001
+test_source2/fs3
+test_source2/fs3/sub
+test_target1
+""")
+
+        with self.subTest("second snapshot, no changes, no snapshot"):
+            (selected_datasets, excluded_datasets)=node.selected_datasets(property_name="autobackup:test", exclude_paths=[], exclude_received=False,
+                                   exclude_unchanged=0)
+            node.consistent_snapshot(selected_datasets, "test-20101111000002", 1)
+            r = shelltest("zfs list -H -o name -r -t all " + TEST_POOLS)
+            self.assertEqual(r, """
+test_source1
+test_source1/fs1
+test_source1/fs1@test-20101111000001
+test_source1/fs1/sub
+test_source1/fs1/sub@test-20101111000001
+test_source2
+test_source2/fs2
+test_source2/fs2/sub
+test_source2/fs2/sub@test-20101111000001
+test_source2/fs3
+test_source2/fs3/sub
+test_target1
+""")
+
+        with self.subTest("second snapshot, no changes, empty snapshot"):
+            (selected_datasets, excluded_datasets) =node.selected_datasets(property_name="autobackup:test", exclude_paths=[], exclude_received=False, exclude_unchanged=0)
+            node.consistent_snapshot(selected_datasets, "test-20101111000002", 0)
+            r = shelltest("zfs list -H -o name -r -t all " + TEST_POOLS)
+            self.assertEqual(r, """
+test_source1
+test_source1/fs1
+test_source1/fs1@test-20101111000001
+test_source1/fs1@test-20101111000002
+test_source1/fs1/sub
+test_source1/fs1/sub@test-20101111000001
+test_source1/fs1/sub@test-20101111000002
+test_source2
+test_source2/fs2
+test_source2/fs2/sub
+test_source2/fs2/sub@test-20101111000001
+test_source2/fs2/sub@test-20101111000002
+test_source2/fs3
+test_source2/fs3/sub
+test_target1
+""")
+
+    def test_consistent_snapshot_prepostcmds(self):
+        logger = LogStub()
+        description = "[Source]"
+        node = ZfsNode(utc=False, snapshot_time_format="test", hold_name="test", logger=logger, description=description, debug_output=True)
+
+        with self.subTest("Test if all cmds are executed correctly (no failures)"):
+            with OutputIO() as buf:
+                with redirect_stdout(buf):
+                    (selected_datasets, excluded_datasets) =node.selected_datasets(property_name="autobackup:test", exclude_paths=[], exclude_received=False, exclude_unchanged=0)
+                    node.consistent_snapshot(selected_datasets, "test-1",
+                                             0,
+                                             pre_snapshot_cmds=["echo pre1", "echo pre2"],
+                                             post_snapshot_cmds=["echo post1 >&2", "echo post2 >&2"]
+                                             )
+
+                self.assertIn("STDOUT > pre1", buf.getvalue())
+                self.assertIn("STDOUT > pre2", buf.getvalue())
+                self.assertIn("STDOUT > post1", buf.getvalue())
+                self.assertIn("STDOUT > post2", buf.getvalue())
+
+
+        with self.subTest("Failure in the middle, only pre1 and both post1 and post2 should be executed, no snapshot should be attempted"):
+            with OutputIO() as buf:
+                with redirect_stdout(buf):
+                    with self.assertRaises(ExecuteError):
+                        (selected_datasets, excluded_datasets) =node.selected_datasets(property_name="autobackup:test", exclude_paths=[], exclude_received=False, exclude_unchanged=0)
+                        node.consistent_snapshot(selected_datasets, "test-1",
+                                                 0,
+                                                 pre_snapshot_cmds=["echo pre1", "false", "echo pre2"],
+                                                 post_snapshot_cmds=["echo post1", "false", "echo post2"]
+                                                 )
+
+                print(buf.getvalue())
+                self.assertIn("STDOUT > pre1", buf.getvalue())
+                self.assertNotIn("STDOUT > pre2", buf.getvalue())
+                self.assertIn("STDOUT > post1", buf.getvalue())
+                self.assertIn("STDOUT > post2", buf.getvalue())
+
+        with self.subTest("Snapshot fails"):
+            with OutputIO() as buf:
+                with redirect_stdout(buf):
+                    with self.assertRaises(ExecuteError):
+                        #same snapshot name as before so it fails
+                        (selected_datasets, excluded_datasets) =node.selected_datasets(property_name="autobackup:test", exclude_paths=[], exclude_received=False, exclude_unchanged=0)
+                        node.consistent_snapshot(selected_datasets, "test-1",
+                                                 0,
+                                                 pre_snapshot_cmds=["echo pre1", "echo pre2"],
+                                                 post_snapshot_cmds=["echo post1", "echo post2"]
+                                                 )
+
+                print(buf.getvalue())
+                self.assertIn("STDOUT > pre1", buf.getvalue())
+                self.assertIn("STDOUT > pre2", buf.getvalue())
+                self.assertIn("STDOUT > post1", buf.getvalue())
+                self.assertIn("STDOUT > post2", buf.getvalue())
+
+    def test_timestamps(self):
+        # Assert that timestamps keep relative order both for utc and for localtime
+        logger = LogStub()
+        description = "[Source]"
+        node_local = ZfsNode(utc=False, snapshot_time_format="test-%Y%m%d%H%M%S", hold_name="zfs_autobackup:test", logger=logger, description=description)
+        node_utc = ZfsNode(utc=True, snapshot_time_format="test-%Y%m%d%H%M%S", hold_name="zfs_autobackup:test", logger=logger, description=description)
+
+        for node in [node_local, node_utc]:
+            with self.subTest("timestamp ordering " + ("utc" if node == node_utc else "localtime")):
+                dataset_a = ZfsDataset(node,"test_source1@test-20101111000001")
+                dataset_b = ZfsDataset(node,"test_source1@test-20101111000002")
+                dataset_c = ZfsDataset(node,"test_source1@test-20240101020202")
+                self.assertGreater(dataset_b.timestamp, dataset_a.timestamp)
+                self.assertGreater(dataset_c.timestamp, dataset_b.timestamp)
+
+
+    def test_getselected(self):
+
+        # should be excluded by property
+        shelltest("zfs create test_source1/fs1/subexcluded")
+        shelltest("zfs set autobackup:test=false test_source1/fs1/subexcluded")
+
+        # only select parent
+        shelltest("zfs create test_source1/fs1/onlyparent")
+        shelltest("zfs create test_source1/fs1/onlyparent/child")
+        shelltest("zfs set autobackup:test=parent test_source1/fs1/onlyparent")
+
+        # should be excluded by being unchanged
+        shelltest("zfs create test_source1/fs1/unchanged")
+        shelltest("zfs snapshot test_source1/fs1/unchanged@somesnapshot")
+
+        logger = LogStub()
+        description = "[Source]"
+        node = ZfsNode(utc=False, snapshot_time_format="test-%Y%m%d%H%M%S", hold_name="zfs_autobackup:test", logger=logger, description=description)
+        (selected_datasets, excluded_datasets)=node.selected_datasets(property_name="autobackup:test", exclude_paths=[], exclude_received=False,
+                               exclude_unchanged=1)
+        s = pformat(selected_datasets)
+        print(s)
+
+        # basics
+        self.assertEqual(s, """[(local): test_source1/fs1,
+ (local): test_source1/fs1/onlyparent,
+ (local): test_source1/fs1/sub,
+ (local): test_source2/fs2/sub]""")
+
+
+    def test_validcommand(self):
+        logger = LogStub()
+        description = "[Source]"
+        node = ZfsNode(utc=False, snapshot_time_format="test-%Y%m%d%H%M%S", hold_name="zfs_autobackup:test", logger=logger, description=description)
+
+        with self.subTest("test invalid option"):
+            self.assertFalse(node.valid_command(["zfs", "send", "--invalid-option", "nonexisting"]))
+        with self.subTest("test valid option"):
+            self.assertTrue(node.valid_command(["zfs", "send", "-v", "nonexisting"]))
+
+    def test_supportedsendoptions(self):
+        logger = LogStub()
+        description = "[Source]"
+        node = ZfsNode(utc=False, snapshot_time_format="test-%Y%m%d%H%M%S", hold_name="zfs_autobackup:test", logger=logger, description=description)
+        # -D propably always supported
+        self.assertGreater(len(node.supported_send_options), 0)
+
+    def test_supportedrecvoptions(self):
+        logger = LogStub()
+        description = "[Source]"
+        # NOTE: this could hang via ssh if we dont close filehandles properly. (which was a previous bug)
+        node = ZfsNode(utc=False, snapshot_time_format="test-%Y%m%d%H%M%S", hold_name="zfs_autobackup:test", logger=logger, description=description, ssh_to='localhost')
+        self.assertIsInstance(node.supported_recv_options, list)
+
+
+if __name__ == '__main__':
+    unittest.main()

zfs_autobackup/BlockHasher.py

@@ -0,0 +1,127 @@
+import hashlib
+import os
+
+
+class BlockHasher():
+    """This class was created to checksum huge files and blockdevices (TB's)
+    Instead of one sha1sum of the whole file, it generates sha1susms of chunks of the file.
+
+    The chunksize is count*bs (bs is the read blocksize from disk)
+
+    Its also possible to only read a certain percentage of blocks to just check a sample.
+
+    Input and output generators are in the format ( chunk_nr, hexdigest )
+
+    NOTE: skipping is only used on the generator side. The compare side just compares what it gets from the input generator.
+
+    """
+
+    def __init__(self, count=10000, bs=4096, hash_class=hashlib.sha1, skip=0):
+        self.count = count
+        self.bs = bs
+        self.chunk_size=bs*count
+        self.hash_class = hash_class
+
+        # self.coverage=coverage
+        self.skip=skip
+        self._skip_count=0
+
+        self.stats_total_bytes=0
+
+
+    def _seek_next_chunk(self, fh, fsize):
+        """seek fh to next chunk and update skip counter.
+        returns chunk_nr
+        return false it should skip the rest of the file
+
+
+        """
+
+        #ignore rempty files
+        if fsize==0:
+            return False
+
+        # need to skip chunks?
+        if self._skip_count > 0:
+            chunks_left = ((fsize - fh.tell()) // self.chunk_size) + 1
+            # not enough chunks left in this file?
+            if self._skip_count >= chunks_left:
+                # skip rest of this file
+                self._skip_count = self._skip_count - chunks_left
+                return False
+            else:
+                # seek to next chunk, reset skip count
+                fh.seek(self.chunk_size * self._skip_count, os.SEEK_CUR)
+                self._skip_count = self.skip
+                return  fh.tell()//self.chunk_size
+        else:
+            # should read this chunk, reset skip count
+            self._skip_count = self.skip
+            return fh.tell() // self.chunk_size
+
+    def generate(self, fname):
+        """Generates checksums
+
+        yields(chunk_nr, hexdigest)
+
+        yields nothing for empty files.
+        """
+
+
+        with open(fname, "rb") as fh:
+
+            fh.seek(0, os.SEEK_END)
+            fsize=fh.tell()
+            fh.seek(0)
+
+            while fh.tell()<fsize:
+                chunk_nr=self._seek_next_chunk(fh, fsize)
+                if chunk_nr is False:
+                    return
+
+                #read chunk
+                hash = self.hash_class()
+                block_nr = 0
+                while block_nr != self.count:
+                    block=fh.read(self.bs)
+                    if block==b"":
+                        break
+                    hash.update(block)
+                    block_nr = block_nr + 1
+
+                yield (chunk_nr, hash.hexdigest())
+
+    def compare(self, fname, generator):
+        """reads from generator and compares blocks
+        Yields mismatches in the form: ( chunk_nr, hexdigest, actual_hexdigest)
+        Yields errors in the form: ( chunk_nr, hexdigest, "message" )
+
+        """
+
+        try:
+            checked = 0
+            with open(fname, "rb") as f:
+                for (chunk_nr, hexdigest) in generator:
+                    try:
+
+                        checked = checked + 1
+                        hash = self.hash_class()
+                        f.seek(int(chunk_nr) * self.bs * self.count)
+                        block_nr = 0
+                        for block in iter(lambda: f.read(self.bs), b""):
+                            hash.update(block)
+                            block_nr = block_nr + 1
+                            if block_nr == self.count:
+                                break
+
+                        if block_nr == 0:
+                            yield (chunk_nr, hexdigest, 'EOF')
+
+                        elif (hash.hexdigest() != hexdigest):
+                            yield (chunk_nr, hexdigest, hash.hexdigest())
+
+                    except Exception as e:
+                        yield ( chunk_nr , hexdigest, 'ERROR: '+str(e))
+
+        except Exception as e:
+            yield ( '-', '-', 'ERROR: '+ str(e))

zfs_autobackup/CachedProperty.py

@@ -0,0 +1,39 @@
+# NOTE: this should inherit from (object) to function correctly with python 2.7
+class CachedProperty(object):
+    """ A property that is only computed once per instance and
+    then stores the result in _cached_properties of the object.
+
+        Source: https://github.com/bottlepy/bottle/commit/fa7733e075da0d790d809aa3d2f53071897e6f76
+        """
+
+    def __init__(self, func):
+        self.__doc__ = getattr(func, '__doc__')
+        self.func = func
+
+    def __get__(self, obj, cls):
+        if obj is None:
+            return self
+
+        propname = self.func.__name__
+
+        if not hasattr(obj, '_cached_properties'):
+            obj._cached_properties = {}
+
+        if propname not in obj._cached_properties:
+            obj._cached_properties[propname] = self.func(obj)
+            # value = obj.__dict__[propname] = self.func(obj)
+
+        return obj._cached_properties[propname]
+
+    @staticmethod
+    def clear(obj):
+        """clears cache of obj"""
+        if hasattr(obj, '_cached_properties'):
+            obj._cached_properties = {}
+
+    @staticmethod
+    def is_cached(obj, propname):
+        if hasattr(obj, '_cached_properties') and propname in obj._cached_properties:
+            return True
+        else:
+            return False

zfs_autobackup/CliBase.py

@@ -0,0 +1,111 @@
+import argparse
+import os.path
+import sys
+
+from .LogConsole import LogConsole
+
+
+class CliBase(object):
+    """Base class for all cli programs
+    Overridden in subclasses that add stuff for the specific programs."""
+
+    # also used by setup.py
+    VERSION = "3.2"
+    HEADER = "{} v{} - (c)2022 E.H.Eefting (edwin@datux.nl)".format(os.path.basename(sys.argv[0]), VERSION)
+
+    def __init__(self, argv, print_arguments=True):
+
+        self.parser=self.get_parser()
+        self.args = self.parse_args(argv)
+
+        # helps with investigating failed regression tests:
+        if print_arguments:
+            print("ARGUMENTS: " + " ".join(argv))
+
+    def parse_args(self, argv):
+        """parses the arguments and does additional checks, might print warnings or notes
+        Overridden in subclasses with extra checks.
+        """
+
+        args = self.parser.parse_args(argv)
+
+        if args.help:
+            self.parser.print_help()
+            sys.exit(255)
+
+        if args.version:
+            print(self.HEADER)
+            sys.exit(255)
+
+        # auto enable progress?
+        if sys.stderr.isatty() and not args.no_progress:
+            args.progress = True
+
+        if args.debug_output:
+            args.debug = True
+
+        if args.test:
+            args.verbose = True
+
+        if args.debug:
+            args.verbose = True
+
+        self.log = LogConsole(show_debug=args.debug, show_verbose=args.verbose, color=sys.stdout.isatty())
+
+        self.verbose(self.HEADER)
+        self.verbose("")
+
+        return args
+
+    def get_parser(self):
+        """build up the argument parser
+        Overridden in subclasses that add extra arguments
+        """
+
+        parser = argparse.ArgumentParser(description=self.HEADER, add_help=False,
+                                         epilog='Full manual at: https://github.com/psy0rz/zfs_autobackup')
+
+        # Basic options
+        group=parser.add_argument_group("Common options")
+        group.add_argument('--help', '-h', action='store_true', help='show help')
+        group.add_argument('--test', '--dry-run', '-n', action='store_true',
+                            help='Dry run, dont change anything, just show what would be done (still does all read-only '
+                                 'operations)')
+        group.add_argument('--verbose', '-v', action='store_true', help='verbose output')
+        group.add_argument('--debug', '-d', action='store_true',
+                            help='Show zfs commands that are executed, stops after an exception.')
+        group.add_argument('--debug-output', action='store_true',
+                            help='Show zfs commands and their output/exit codes. (noisy)')
+        group.add_argument('--progress', action='store_true',
+                            help='show zfs progress output. Enabled automaticly on ttys. (use --no-progress to disable)')
+        group.add_argument('--no-progress', action='store_true',
+                            help=argparse.SUPPRESS)  # needed to workaround a zfs recv -v bug
+        group.add_argument('--utc', action='store_true',
+                            help='Use UTC instead of local time when dealing with timestamps for both formatting and parsing. To snapshot in an ISO 8601 compliant time format you may for example specify --snapshot-format "{}-%%Y-%%m-%%dT%%H:%%M:%%SZ". Changing this parameter after-the-fact (existing snapshots) will cause their timestamps to be interpreted as a different time than before.')
+        group.add_argument('--version', action='store_true',
+                            help='Show version.')
+
+
+        return parser
+
+    def verbose(self, txt):
+        self.log.verbose(txt)
+
+    def warning(self, txt):
+        self.log.warning(txt)
+
+    def error(self, txt):
+        self.log.error(txt)
+
+    def debug(self, txt):
+        self.log.debug(txt)
+
+    def progress(self, txt):
+        self.log.progress(txt)
+
+    def clear_progress(self):
+        self.log.clear_progress()
+
+    def set_title(self, title):
+        self.log.verbose("")
+        self.log.verbose("#### " + title)

zfs_autobackup/CmdPipe.py

@@ -0,0 +1,214 @@
+# This is the low level process executing stuff.
+# It makes piping and parallel process handling more easy.
+
+# You can specify a handler for each line of stderr output for each item in the pipe.
+# Every item also has its own exitcode handler.
+
+# Normally you add a stdout_handler to the last item in the pipe.
+# However: You can also add stdout_handler to other items in a pipe. This will turn that item in to a manual pipe: your
+# handler is responsible for sending data into the next item of the pipe. (avaiable in item.next)
+
+# You can also use manual pipe mode to just execute multiple command in parallel and handle their output parallel,
+# without doing any actual pipe stuff. (because you dont HAVE to send data into the next item.)
+
+
+import subprocess
+import os
+import select
+
+try:
+    from shlex import quote as cmd_quote
+except ImportError:
+    from pipes import quote as cmd_quote
+
+
+class CmdItem:
+    """one command item, to be added to a CmdPipe"""
+
+    def __init__(self, cmd, readonly=False, stderr_handler=None, exit_handler=None, stdout_handler=None, shell=False):
+        """create item. caller has to make sure cmd is properly escaped when using shell.
+
+        If stdout_handler is None, it will connect the stdout to the stdin of the next item in the pipe, like
+        and actual system pipe. (no python overhead)
+
+        :type cmd: list of str
+        """
+
+        self.cmd = cmd
+        self.readonly = readonly
+        self.stderr_handler = stderr_handler
+        self.stdout_handler = stdout_handler
+        self.exit_handler = exit_handler
+        self.shell = shell
+        self.process = None
+        self.next = None #next item in pipe, set by CmdPipe
+
+    def __str__(self):
+        """return copy-pastable version of command."""
+        if self.shell:
+            # its already copy pastable for a shell:
+            return " ".join(self.cmd)
+        else:
+            # make it copy-pastable, will make a mess of quotes sometimes, but is correct
+            return " ".join(map(cmd_quote, self.cmd))
+
+    def create(self, stdin):
+        """actually create the subprocess (called by CmdPipe)"""
+
+        # make sure the command gets all the data in utf8 format:
+        # (this is necessary if LC_ALL=en_US.utf8 is not set in the environment)
+        encoded_cmd = []
+        for arg in self.cmd:
+            encoded_cmd.append(arg.encode('utf-8'))
+
+        self.process = subprocess.Popen(encoded_cmd, env=os.environ, stdout=subprocess.PIPE, stdin=stdin,
+                                        stderr=subprocess.PIPE, shell=self.shell)
+
+
+class CmdPipe:
+    """a pipe of one or more commands. also takes care of utf-8 encoding/decoding and line based parsing"""
+
+    def __init__(self, readonly=False, inp=None):
+        """
+        :param inp: input string for stdin
+        :param readonly: Only execute if entire pipe consist of readonly commands
+        """
+        # list of commands + error handlers to execute
+        self.items = []
+
+        self.inp = inp
+        self.readonly = readonly
+        self._should_execute = True
+
+    def add(self, cmd_item):
+        """adds a CmdItem to pipe.
+        :type cmd_item: CmdItem
+        """
+
+        self.items.append(cmd_item)
+
+        if not cmd_item.readonly and self.readonly:
+            self._should_execute = False
+
+    def __str__(self):
+        """transform whole pipe into oneliner for debugging and testing. this should generate a copy-pastable string for in a console """
+
+        ret = ""
+        for item in self.items:
+            if ret:
+                ret = ret + " | "
+            ret = ret + "({})".format(item)  # this will do proper escaping to make it copypastable
+
+        return ret
+
+    def should_execute(self):
+        return self._should_execute
+
+    def execute(self):
+        """run the pipe. returns True all exit handlers returned true. (otherwise it will be False/None depending on exit handlers returncode) """
+
+        if not self._should_execute:
+            return True
+
+        selectors = self.__create()
+
+        if not selectors:
+            raise (Exception("Cant use cmdpipe without any output handlers."))
+
+        self.__process_outputs(selectors)
+
+        # close filehandles
+        for item in self.items:
+            item.process.stderr.close()
+            item.process.stdout.close()
+
+        # call exit handlers
+        success = True
+        for item in self.items:
+            if item.exit_handler is not None:
+                success=item.exit_handler(item.process.returncode) and success
+
+        return success
+
+    def __process_outputs(self, selectors):
+        """watch all output selectors and call handlers"""
+
+        while True:
+            # wait for output on one of the stderrs or last_stdout
+            (read_ready, write_ready, ex_ready) = select.select(selectors, [], [])
+
+            eof_count = 0
+            done_count = 0
+
+            # read line and call appropriate handlers
+
+            for item in self.items:
+                if item.process.stdout in read_ready:
+                    line = item.process.stdout.readline().decode('utf-8').rstrip()
+                    if line != "":
+                        item.stdout_handler(line)
+                    else:
+                        eof_count = eof_count + 1
+                        if item.next:
+                            item.next.process.stdin.close()
+
+                if item.process.stderr in read_ready:
+                    line = item.process.stderr.readline().decode('utf-8').rstrip()
+                    if line != "":
+                        item.stderr_handler(line)
+                    else:
+                        eof_count = eof_count + 1
+
+
+                if item.process.poll() is not None:
+                    done_count = done_count + 1
+
+            # all filehandles are eof and all processes are done (poll() is not None)
+            if eof_count == len(selectors) and done_count == len(self.items):
+                break
+
+
+
+    def __create(self):
+        """create actual processes, do piping and return selectors."""
+
+        selectors = []
+        next_stdin = subprocess.PIPE  # means we write input via python instead of an actual system pipe
+        first = True
+        prev_item = None
+
+        for item in self.items:
+
+            # creates the actual subprocess via subprocess.popen
+            item.create(next_stdin)
+
+            # we piped previous process? dont forget to close its stdout
+            if next_stdin != subprocess.PIPE:
+                next_stdin.close()
+
+            if item.stderr_handler:
+                selectors.append(item.process.stderr)
+
+            # we're the first process in the pipe
+            if first:
+                if self.inp is not None:
+                    # write the input we have
+                    item.process.stdin.write(self.inp.encode('utf-8'))
+                item.process.stdin.close()
+                first = False
+
+            # manual stdout handling or pipe it to the next process?
+            if item.stdout_handler is None:
+                # no manual stdout handling, pipe it to the next process via sytem pipe
+                next_stdin = item.process.stdout
+            else:
+                # manual stdout handling via python
+                selectors.append(item.process.stdout)
+                # next process will get input from python:
+                next_stdin = subprocess.PIPE
+
+            if prev_item is not None:
+                prev_item.next = item
+
+            prev_item = item
+        return selectors

zfs_autobackup/ExecuteNode.py

@@ -0,0 +1,271 @@
+import os
+import select
+import subprocess
+from .CmdPipe import CmdPipe, CmdItem
+from .LogStub import LogStub
+
+try:
+    from shlex import quote as cmd_quote
+except ImportError:
+    from pipes import quote as cmd_quote
+
+
+class ExecuteError(Exception):
+    pass
+
+
+class ExecuteNode(LogStub):
+    """an endpoint to execute local or remote commands via ssh"""
+
+    PIPE=1
+
+    def __init__(self, ssh_config=None, ssh_to=None, readonly=False, debug_output=False):
+        """ssh_config: custom ssh config
+           ssh_to: server you want to ssh to. none means local
+           readonly: only execute commands that don't make any changes (useful for testing-runs)
+           debug_output: show output and exit codes of commands in debugging output.
+        """
+
+        self.ssh_config = ssh_config
+        self.ssh_to = ssh_to
+        self.readonly = readonly
+        self.debug_output = debug_output
+
+    def __repr__(self):
+        if self.ssh_to is None:
+            return "(local)"
+        else:
+            return self.ssh_to
+
+    def _parse_stdout(self, line):
+        """parse stdout. can be overridden in subclass"""
+        if self.debug_output:
+            self.debug("STDOUT > " + line.rstrip())
+
+    def _parse_stderr(self, line, hide_errors):
+        """parse stderr. can be overridden in subclass"""
+        if hide_errors:
+            self.debug("STDERR > " + line.rstrip())
+        else:
+            self.error("STDERR > " + line.rstrip())
+
+    def _quote(self, cmd):
+        """return quoted version of command. if it has value PIPE it will add an actual | """
+        if cmd==self.PIPE:
+            return('|')
+        else:
+            return cmd_quote(cmd)
+
+    def _shell_cmd(self, cmd, cwd):
+        """prefix specified ssh shell to command and escape shell characters"""
+
+        ret=[]
+
+        #add remote shell
+        if not self.is_local():
+            #note: dont escape this part (executed directly without shell)
+            ret=["ssh"]
+
+            if self.ssh_config is not None:
+                ret.extend(["-F", self.ssh_config])
+
+            ret.append(self.ssh_to)
+
+        #note: DO escape from here, executed in either local or remote shell.
+
+        shell_str=""
+
+        #add cwd change?
+        if cwd is not None:
+            shell_str=shell_str + "cd " + self._quote(cwd) + "; "
+
+        shell_str=shell_str + " ".join(map(self._quote, cmd))
+
+        ret.append(shell_str)
+
+        return ret
+
+    def is_local(self):
+        return self.ssh_to is None
+
+    def run(self, cmd, inp=None, tab_split=False, valid_exitcodes=None, readonly=False, hide_errors=False,
+            return_stderr=False, pipe=False, return_all=False, cwd=None):
+        """run a command on the node , checks output and parses/handle output and returns it
+
+        Takes care of proper quoting/escaping/ssh and logging of stdout/err/exit codes.
+
+        Either uses a local shell (sh -c) or remote shell (ssh) to execute the command.
+        Therefore the command can have stuff like actual pipes in it, if you dont want to use pipe=True to pipe stuff.
+
+        :param cmd: the actual command, should be a list, where the first item is the command
+                    and the rest are parameters. use ExecuteNode.PIPE to add an unescaped |
+                    (if you want to use system piping instead of python piping)
+        :param pipe: return CmdPipe instead of executing it. (pipe this into another run() command via inp=...)
+        :param inp: Can be None, a string or a CmdPipe that was previously returned.
+        :param tab_split: split tabbed files in output into a list
+        :param valid_exitcodes: list of valid exit codes for this command. Use [] to accept all exit codes. Default [0]
+        :param readonly: make this True if the command doesn't make any changes and is safe to execute in testmode
+        :param hide_errors: don't show stderr output as error, instead show it as debugging output (use to hide expected errors)
+        :param return_stderr: return both stdout and stderr as a tuple. (normally only returns stdout)
+        :param return_all: return both stdout and stderr and exit_code as a tuple. (normally only returns stdout)
+        :param cwd: Change current working directory before executing command.
+
+        """
+
+        # create new pipe?
+        if not isinstance(inp, CmdPipe):
+            cmd_pipe = CmdPipe(self.readonly, inp)
+        else:
+            # add stuff to existing pipe
+            cmd_pipe = inp
+
+        # stderr parser
+        error_lines = []
+        returned_exit_code=None
+
+        def stderr_handler(line):
+            if tab_split:
+                error_lines.append(line.rstrip().split('\t'))
+            else:
+                error_lines.append(line.rstrip())
+            self._parse_stderr(line, hide_errors)
+
+        # exit code hanlder
+        if valid_exitcodes is None:
+            valid_exitcodes = [0]
+
+        def exit_handler(exit_code):
+            if self.debug_output:
+                self.debug("EXIT   > {}".format(exit_code))
+
+            if (valid_exitcodes != []) and (exit_code not in valid_exitcodes):
+                self.error("Command \"{}\" returned exit code {} (valid codes: {})".format(cmd_item, exit_code, valid_exitcodes))
+                return False
+
+            return True
+
+        # stdout parser
+        output_lines = []
+
+        if pipe:
+            # dont specify output handler, so it will get piped to next process
+            stdout_handler=None
+        else:
+            # handle output manually, dont pipe it
+            def stdout_handler(line):
+                if tab_split:
+                    output_lines.append(line.rstrip().split('\t'))
+                else:
+                    output_lines.append(line.rstrip())
+                self._parse_stdout(line)
+
+        # add shell command and handlers to pipe
+        cmd_item=CmdItem(cmd=self._shell_cmd(cmd, cwd), readonly=readonly, stderr_handler=stderr_handler, exit_handler=exit_handler, shell=self.is_local(), stdout_handler=stdout_handler)
+        cmd_pipe.add(cmd_item)
+
+        # return CmdPipe instead of executing?
+        if pipe:
+            return cmd_pipe
+
+        if cmd_pipe.should_execute():
+            self.debug("CMD    > {}".format(cmd_pipe))
+        else:
+            self.debug("CMDSKIP> {}".format(cmd_pipe))
+
+        # execute and calls handlers in CmdPipe
+        if not cmd_pipe.execute():
+            raise(ExecuteError("Last command returned error"))
+
+        if return_all:
+            return output_lines, error_lines, cmd_item.process and cmd_item.process.returncode
+        elif return_stderr:
+            return output_lines, error_lines
+        else:
+            return output_lines
+
+    def script(self, lines, inp=None, stdout_handler=None, stderr_handler=None, exit_handler=None, valid_exitcodes=None, readonly=False, hide_errors=False, pipe=False):
+        """Run a multiline script on the node.
+
+        This is much more low level than run() and allows for finer grained control.
+
+        Either uses a local shell (sh -c) or remote shell (ssh) to execute the command.
+        You need to do your own escaping/quoting.
+        It will do logging of stderr and exit codes, but you should
+        specify your stdout handler when calling CmdPipe.execute.
+        Also specify the optional stderr/exit code handlers if you need them.
+        Handlers are called for each line.
+        It wont collect lines internally like run() does, so streams of data can be of unlimited size.
+
+        :param lines: list of lines of the actual script.
+        :param inp: Can be None, a string or a CmdPipe that was previously returned.
+        :param readonly: make this True if the command doesn't make any changes and is safe to execute in testmode
+        :param valid_exitcodes: list of valid exit codes for this command. Use [] to accept all exit codes. Default [0]
+        :param hide_errors: don't show stderr output as error, instead show it as debugging output (use to hide expected errors)
+        :param pipe: return CmdPipe instead of executing it. (pipe this into another run() command via inp=...)
+
+        """
+
+        # create new pipe?
+        if not isinstance(inp, CmdPipe):
+            cmd_pipe = CmdPipe(self.readonly, inp)
+        else:
+            # add stuff to existing pipe
+            cmd_pipe = inp
+
+        internal_stdout_handler=None
+        if stdout_handler is not None:
+            if self.debug_output:
+                def internal_stdout_handler(line):
+                    self.debug("STDOUT > " + line.rstrip())
+                    stdout_handler(line)
+            else:
+                internal_stdout_handler=stdout_handler
+
+        def internal_stderr_handler(line):
+            self._parse_stderr(line, hide_errors)
+            if stderr_handler is not None:
+                stderr_handler(line)
+
+        # exit code hanlder
+        if valid_exitcodes is None:
+            valid_exitcodes = [0]
+
+        def internal_exit_handler(exit_code):
+            if self.debug_output:
+                self.debug("EXIT   > {}".format(exit_code))
+
+            if exit_handler is not None:
+                exit_handler(exit_code)
+
+            if (valid_exitcodes != []) and (exit_code not in valid_exitcodes):
+                self.error("Script returned exit code {} (valid codes: {})".format(exit_code, valid_exitcodes))
+                return False
+
+            return True
+
+        #build command
+        cmd=[]
+
+        #add remote shell
+        if not self.is_local():
+            #note: dont escape this part (executed directly without shell)
+            cmd.append("ssh")
+
+            if self.ssh_config is not None:
+                cmd.append(["-F", self.ssh_config])
+
+            cmd.append(self.ssh_to)
+
+        # convert to script
+        cmd.append("\n".join(lines))
+
+        # add shell command and handlers to pipe
+        cmd_item=CmdItem(cmd=cmd, readonly=readonly, stderr_handler=internal_stderr_handler, exit_handler=internal_exit_handler, stdout_handler=internal_stdout_handler, shell=self.is_local())
+        cmd_pipe.add(cmd_item)
+
+        self.debug("SCRIPT > {}".format(cmd_pipe))
+
+        if pipe:
+            return cmd_pipe
+        else:
+            return cmd_pipe.execute()

zfs_autobackup/LogConsole.py

@@ -0,0 +1,74 @@
+# python 2 compatibility
+from __future__ import print_function
+
+import sys
+
+class LogConsole:
+    """Log-class that outputs to console, adding colors if needed"""
+
+    def __init__(self, show_debug, show_verbose, color):
+        self.last_log = ""
+        self.show_debug = show_debug
+        self.show_verbose = show_verbose
+        self._progress_uncleared=False
+
+        if color:
+            # try to use color, failback if colorama not available
+            self.colorama=False
+            try:
+                import colorama
+                global colorama
+                self.colorama = True
+            except ImportError:
+                pass
+
+        else:
+            self.colorama=False
+
+    def error(self, txt):
+        self.clear_progress()
+        if self.colorama:
+            print(colorama.Fore.RED + colorama.Style.BRIGHT + "! " + txt + colorama.Style.RESET_ALL, file=sys.stderr)
+        else:
+            print("! " + txt, file=sys.stderr)
+        sys.stderr.flush()
+
+    def warning(self, txt):
+        self.clear_progress()
+        if self.colorama:
+            print(colorama.Fore.YELLOW + colorama.Style.BRIGHT + "  NOTE: " + txt + colorama.Style.RESET_ALL)
+        else:
+            print("  NOTE: " + txt)
+        sys.stdout.flush()
+
+    def verbose(self, txt):
+        if self.show_verbose:
+            self.clear_progress()
+            if self.colorama:
+                print(colorama.Style.NORMAL + "  " + txt + colorama.Style.RESET_ALL)
+            else:
+                print("  " + txt)
+            sys.stdout.flush()
+
+    def debug(self, txt):
+        if self.show_debug:
+            self.clear_progress()
+            if self.colorama:
+                print(colorama.Fore.GREEN + "# " + txt + colorama.Style.RESET_ALL)
+            else:
+                print("# " + txt)
+            sys.stdout.flush()
+
+    def progress(self, txt):
+        """print progress output to stderr (stays on same line)"""
+        self.clear_progress()
+        self._progress_uncleared=True
+        print(">>> {}\r".format(txt), end='', file=sys.stderr)
+        sys.stderr.flush()
+
+    def clear_progress(self):
+        if self._progress_uncleared:
+            import colorama
+            print(colorama.ansi.clear_line(), end='', file=sys.stderr)
+            # sys.stderr.flush()
+            self._progress_uncleared=False

zfs_autobackup/LogStub.py

@@ -0,0 +1,18 @@
+#Used for baseclasses that dont implement their own logging (Like ExecuteNode)
+#Usually logging is implemented in subclasses (Like ZfsNode thats a subclass of ExecuteNode), but for regression testing its nice to have these stubs.
+
+class LogStub:
+    """Just a stub, usually overriden in subclasses."""
+
+    # simple logging stubs
+    def debug(self, txt):
+        print("DEBUG  : " + txt)
+
+    def verbose(self, txt):
+        print("VERBOSE: " + txt)
+
+    def warning(self, txt):
+        print("WARNING: " + txt)
+
+    def error(self, txt):
+        print("ERROR  : " + txt)

zfs_autobackup/Thinner.py

@@ -0,0 +1,99 @@
+import time
+
+from .ThinnerRule import ThinnerRule
+
+
+class Thinner:
+    """progressive thinner (universal, used for cleaning up snapshots)"""
+
+    def __init__(self, schedule_str=""):
+        """
+        Args:
+            schedule_str: comma seperated list of ThinnerRules. A plain number specifies how many snapshots to always keep.
+        """
+
+        self.rules = []
+        self.always_keep = 0
+
+        if schedule_str == "":
+            return
+
+        rule_strs = schedule_str.split(",")
+        for rule_str in rule_strs:
+            if rule_str.lstrip('-').isdigit():
+                self.always_keep = int(rule_str)
+                if self.always_keep < 0:
+                    raise (Exception("Number of snapshots to keep cant be negative: {}".format(self.always_keep)))
+            else:
+                self.rules.append(ThinnerRule(rule_str))
+
+    def human_rules(self):
+        """get list of human readable rules"""
+        ret = []
+        if self.always_keep:
+            ret.append("Keep the last {} snapshot{}.".format(self.always_keep, self.always_keep != 1 and "s" or ""))
+        for rule in self.rules:
+            ret.append(rule.human_str)
+
+        return ret
+
+    def thin(self, objects, keep_objects=None, now=None):
+        """thin list of objects with current schedule rules. objects: list of
+        objects to thin. every object should have timestamp attribute.
+
+            return( keeps, removes )
+
+        Args:
+            objects: list of objects to check (should have a timestamp attribute)
+            keep_objects: objects to always keep (if they also are in the in the normal objects list)
+            now: if specified, use this time as current time
+        """
+
+        if not keep_objects:
+            keep_objects = []
+
+        # always keep a number of the last objets?
+        if self.always_keep:
+            # all of them
+            if len(objects) <= self.always_keep:
+                return objects, []
+
+            # determine which ones
+            always_keep_objects = objects[-self.always_keep:]
+        else:
+            always_keep_objects = []
+
+        # determine time blocks
+        time_blocks = {}
+        for rule in self.rules:
+            time_blocks[rule.period] = {}
+
+        if not now:
+            now = int(time.time())
+
+        keeps = []
+        removes = []
+
+        # traverse objects
+        for thisobject in objects:
+            # important they are ints!
+            timestamp = int(thisobject.timestamp)
+            age = int(now) - timestamp
+
+            # store in the correct time blocks, per period-size, if not too old yet
+            # e.g.: look if there is ANY timeblock that wants to keep this object
+            keep = False
+            for rule in self.rules:
+                if age <= rule.ttl:
+                    block_nr = int(timestamp / rule.period)
+                    if block_nr not in time_blocks[rule.period]:
+                        time_blocks[rule.period][block_nr] = True
+                        keep = True
+
+            # keep it according to schedule, or keep it because it is in the keep_objects list
+            if keep or thisobject in keep_objects or thisobject in always_keep_objects:
+                keeps.append(thisobject)
+            else:
+                removes.append(thisobject)
+
+        return keeps, removes

zfs_autobackup/ThinnerRule.py

@@ -0,0 +1,71 @@
+import re
+
+
+class ThinnerRule:
+    """a thinning schedule rule for Thinner"""
+
+    TIME_NAMES = {
+        'y': 3600 * 24 * 365.25,
+        'm': 3600 * 24 * 30,
+        'w': 3600 * 24 * 7,
+        'd': 3600 * 24,
+        'h': 3600,
+        'min': 60,
+        's': 1,
+    }
+
+    TIME_DESC = {
+        'y': 'year',
+        'm': 'month',
+        'w': 'week',
+        'd': 'day',
+        'h': 'hour',
+        'min': 'minute',
+        's': 'second',
+    }
+
+    def __init__(self, rule_str):
+        """parse scheduling string
+            example:
+                daily snapshot, remove after a week:     1d1w
+                weekly snapshot, remove after a month:   1w1m
+                monthly snapshot, remove after 6 months: 1m6m
+                yearly snapshot, remove after 2 year:    1y2y
+                keep all snapshots, remove after a day   1s1d
+                keep nothing:                            1s1s
+
+        """
+
+        rule_str = rule_str.lower()
+        matches = re.findall("([0-9]*)([a-z]*)([0-9]*)([a-z]*)", rule_str)[0]
+
+        if '' in matches:
+            raise (Exception("Invalid schedule string: '{}'".format(rule_str)))
+
+        period_amount = int(matches[0])
+        period_unit = matches[1]
+        ttl_amount = int(matches[2])
+        ttl_unit = matches[3]
+
+        if period_unit not in self.TIME_NAMES:
+            raise (Exception("Invalid period string in schedule: '{}'".format(rule_str)))
+
+        if ttl_unit not in self.TIME_NAMES:
+            raise (Exception("Invalid ttl string in schedule: '{}'".format(rule_str)))
+
+        self.period = period_amount * self.TIME_NAMES[period_unit]
+        self.ttl = ttl_amount * self.TIME_NAMES[ttl_unit]
+
+        if self.period > self.ttl:
+            raise (Exception("Period cant be longer than ttl in schedule: '{}'".format(rule_str)))
+
+        self.rule_str = rule_str
+
+        self.human_str = "Keep every {} {}{}, delete after {} {}{}.".format(
+            period_amount, self.TIME_DESC[period_unit], period_amount != 1 and "s" or "", ttl_amount,
+            self.TIME_DESC[ttl_unit], ttl_amount != 1 and "s" or "")
+
+    def __str__(self):
+        """get schedule as a schedule string"""
+
+        return self.rule_str

zfs_autobackup/TreeHasher.py

@@ -0,0 +1,60 @@
+import itertools
+import os
+
+
+class TreeHasher():
+    """uses BlockHasher recursively on a directory tree
+
+    Input and output generators are in the format: ( relative-filepath, chunk_nr, hexdigest)
+
+    """
+
+    def __init__(self, block_hasher):
+        """
+
+        :type block_hasher: BlockHasher
+        """
+        self.block_hasher=block_hasher
+
+    def generate(self, start_path):
+        """Use BlockHasher on every file in a tree, yielding the results
+
+        note that it only checks the contents of actual files. It ignores metadata like permissions and mtimes.
+        It also ignores empty directories, symlinks and special files.
+        """
+
+        def walkerror(e):
+            raise e
+
+        for (dirpath, dirnames, filenames) in os.walk(start_path, onerror=walkerror):
+            for f in filenames:
+                file_path=os.path.join(dirpath, f)
+
+                if (not os.path.islink(file_path)) and os.path.isfile(file_path):
+                    for (chunk_nr, hash) in self.block_hasher.generate(file_path):
+                        yield ( os.path.relpath(file_path,start_path), chunk_nr, hash )
+
+
+    def compare(self, start_path, generator):
+        """reads from generator and compares blocks
+
+        yields mismatches in the form: ( relative_filename, chunk_nr, compare_hexdigest, actual_hexdigest )
+        yields errors in the form:     ( relative_filename, chunk_nr, compare_hexdigest, "message" )
+
+        """
+
+        count=0
+
+        def filter_file_name( file_name, chunk_nr, hexdigest):
+                return ( chunk_nr, hexdigest )
+
+
+        for file_name, group_generator in itertools.groupby(generator, lambda x: x[0]):
+            count=count+1
+            block_generator=itertools.starmap(filter_file_name, group_generator)
+            for ( chunk_nr, compare_hexdigest, actual_hexdigest) in self.block_hasher.compare(os.path.join(start_path,file_name), block_generator):
+                yield ( file_name, chunk_nr, compare_hexdigest, actual_hexdigest )
+
+
+
+

zfs_autobackup/ZfsAuto.py

@@ -0,0 +1,117 @@
+import argparse
+import sys
+
+from .CliBase import CliBase
+
+
+class ZfsAuto(CliBase):
+    """Common Base class for ZfsAutobackup and ZfsAutoverify ."""
+
+    def __init__(self, argv, print_arguments=True):
+
+        self.hold_name = None
+        self.snapshot_time_format = None
+        self.property_name = None
+        self.exclude_paths = None
+
+        super(ZfsAuto, self).__init__(argv, print_arguments)
+
+    def parse_args(self, argv):
+        """parse common arguments, setup logging, check and adjust parameters"""
+
+        args = super(ZfsAuto, self).parse_args(argv)
+
+        if args.backup_name == None:
+            self.parser.print_usage()
+            self.log.error("Please specify BACKUP-NAME")
+            sys.exit(255)
+
+        if args.target_path is not None and args.target_path[0] == "/":
+            self.log.error("Target should not start with a /")
+            sys.exit(255)
+
+        if args.ignore_replicated:
+            self.warning("--ignore-replicated has been renamed, using --exclude-unchanged")
+            args.exclude_unchanged = True
+
+        # Note: Before version v3.1-beta5, we always used exclude_received. This was a problem if you wanted to
+        # replicate an existing backup to another host and use the same backupname/snapshots. However, exclude_received
+        # may still need to be used to explicitly exclude a backup with the 'received' source property to avoid accidental
+        # recursive replication of a zvol that is currently being received in another session (as it will have changes).
+
+        self.exclude_paths = []
+        if args.ssh_source == args.ssh_target:
+            if args.target_path:
+                # target and source are the same, make sure to exclude target_path
+                self.verbose("NOTE: Source and target are on the same host, excluding target-path from selection.")
+                self.exclude_paths.append(args.target_path)
+            else:
+                if not args.exclude_received:
+                    self.verbose("NOTE: Source and target are on the same host, adding --exclude-received to commandline.")
+                    args.exclude_received = True
+
+        if args.test:
+            self.warning("TEST MODE - SIMULATING WITHOUT MAKING ANY CHANGES")
+
+        #format all the names
+        self.property_name = args.property_format.format(args.backup_name)
+        self.snapshot_time_format = args.snapshot_format.format(args.backup_name)
+        self.hold_name = args.hold_format.format(args.backup_name)
+
+        self.verbose("")
+        self.verbose("Selecting dataset property : {}".format(self.property_name))
+        self.verbose("Snapshot format            : {}".format(self.snapshot_time_format))
+        self.verbose("Timezone                   : {}".format("UTC" if args.utc else "Local"))
+
+        return args
+
+    def get_parser(self):
+
+        parser = super(ZfsAuto, self).get_parser()
+
+        #positional arguments
+        parser.add_argument('backup_name', metavar='BACKUP-NAME', default=None, nargs='?',
+                            help='Name of the backup to select')
+
+        parser.add_argument('target_path', metavar='TARGET-PATH', default=None, nargs='?',
+                            help='Target ZFS filesystem (optional)')
+
+
+
+        # SSH options
+        group=parser.add_argument_group("SSH options")
+        group.add_argument('--ssh-config', metavar='CONFIG-FILE', default=None, help='Custom ssh client config')
+        group.add_argument('--ssh-source', metavar='USER@HOST', default=None,
+                            help='Source host to pull backup from.')
+        group.add_argument('--ssh-target', metavar='USER@HOST', default=None,
+                            help='Target host to push backup to.')
+
+        group=parser.add_argument_group("String formatting options")
+        group.add_argument('--property-format', metavar='FORMAT', default="autobackup:{}",
+                            help='Dataset selection string format. Default: %(default)s')
+        group.add_argument('--snapshot-format', metavar='FORMAT', default="{}-%Y%m%d%H%M%S",
+                            help='ZFS Snapshot string format. Default: %(default)s')
+        group.add_argument('--hold-format', metavar='FORMAT', default="zfs_autobackup:{}",
+                            help='ZFS hold string format. Default: %(default)s')
+        group.add_argument('--strip-path', metavar='N', default=0, type=int,
+                           help='Number of directories to strip from target path.')
+
+        group=parser.add_argument_group("Selection options")
+        group.add_argument('--ignore-replicated', action='store_true', help=argparse.SUPPRESS)
+        group.add_argument('--exclude-unchanged', metavar='BYTES', default=0, type=int,
+                            help='Exclude datasets that have less than BYTES data changed since any last snapshot. (Use with proxmox HA replication)')
+        group.add_argument('--exclude-received', action='store_true',
+                            help='Exclude datasets that have the origin of their autobackup: property as "received". '
+                                 'This can avoid recursive replication between two backup partners.')
+
+        return parser
+
+    def print_error_sources(self):
+        self.error(
+            "No source filesystems selected, please do a 'zfs set autobackup:{0}=true' on the source datasets "
+            "you want to select.".format(
+                self.args.backup_name))
+
+    def make_target_name(self, source_dataset):
+        """make target_name from a source_dataset"""
+        return self.args.target_path + "/" + source_dataset.lstrip_path(self.args.strip_path)

zfs_autobackup/ZfsAutobackup.py

@@ -0,0 +1,547 @@
+import time
+
+import argparse
+from datetime import datetime
+from signal import signal, SIGPIPE
+from .util import output_redir, sigpipe_handler
+
+from .ZfsAuto import ZfsAuto
+
+from . import compressors
+from .ExecuteNode import ExecuteNode
+from .Thinner import Thinner
+from .ZfsDataset import ZfsDataset
+from .ZfsNode import ZfsNode
+from .ThinnerRule import ThinnerRule
+
+class ZfsAutobackup(ZfsAuto):
+    """The main zfs-autobackup class. Start here, at run() :)"""
+
+    def __init__(self, argv, print_arguments=True):
+
+        # NOTE: common options and parameters are in ZfsAuto
+        super(ZfsAutobackup, self).__init__(argv, print_arguments)
+
+    def parse_args(self, argv):
+        """do extra checks on common args"""
+
+        args = super(ZfsAutobackup, self).parse_args(argv)
+
+        if not args.no_holds:
+            self.verbose("Hold name                  : {}".format(self.hold_name))
+
+        if args.allow_empty:
+            args.min_change = 0
+
+        if args.destroy_incompatible:
+            args.rollback = True
+
+        if args.resume:
+            self.warning("The --resume option isn't needed anymore (it's autodetected now)")
+
+        if args.raw:
+            self.warning(
+                "The --raw option isn't needed anymore (it's autodetected now). Also see --encrypt and --decrypt.")
+
+        if args.compress and args.ssh_source is None and args.ssh_target is None:
+            self.warning("Using compression, but transfer is local.")
+
+        if args.compress and args.zfs_compressed:
+            self.warning("Using --compress with --zfs-compressed, might be inefficient.")
+
+        return args
+
+    def get_parser(self):
+        """extend common parser with  extra stuff needed for zfs-autobackup"""
+
+        parser = super(ZfsAutobackup, self).get_parser()
+
+        group = parser.add_argument_group("Snapshot options")
+        group.add_argument('--no-snapshot', action='store_true',
+                           help='Don\'t create new snapshots (useful for finishing uncompleted backups, or cleanups)')
+        group.add_argument('--pre-snapshot-cmd', metavar="COMMAND", default=[], action='append',
+                           help='Run COMMAND before snapshotting (can be used multiple times.')
+        group.add_argument('--post-snapshot-cmd', metavar="COMMAND", default=[], action='append',
+                           help='Run COMMAND after snapshotting (can be used multiple times.')
+        group.add_argument('--min-change', metavar='BYTES', type=int, default=1,
+                           help='Only create snapshot if enough bytes are changed. (default %('
+                                'default)s)')
+        group.add_argument('--allow-empty', action='store_true',
+                           help='If nothing has changed, still create empty snapshots. (Same as --min-change=0)')
+        group.add_argument('--other-snapshots', action='store_true',
+                           help='Send over other snapshots as well, not just the ones created by this tool.')
+        group.add_argument('--set-snapshot-properties', metavar='PROPERTY=VALUE,...', type=str,
+                           help='List of properties to set on the snapshot.')
+
+
+        group = parser.add_argument_group("Transfer options")
+        group.add_argument('--no-send', action='store_true',
+                           help='Don\'t transfer snapshots (useful for cleanups, or if you want a separate send-cronjob)')
+        group.add_argument('--no-holds', action='store_true',
+                           help='Don\'t hold snapshots. (Faster. Allows you to destroy common snapshot.)')
+        group.add_argument('--clear-refreservation', action='store_true',
+                           help='Filter "refreservation" property. (recommended, saves space. same as '
+                                '--filter-properties refreservation)')
+        group.add_argument('--clear-mountpoint', action='store_true',
+                           help='Set property canmount=noauto for new datasets. (recommended, prevents mount '
+                                'conflicts. same as --set-properties canmount=noauto)')
+        group.add_argument('--filter-properties', metavar='PROPERTY,...', type=str,
+                           help='List of properties to "filter" when receiving filesystems. (you can still restore '
+                                'them with zfs inherit -S)')
+        group.add_argument('--set-properties', metavar='PROPERTY=VALUE,...', type=str,
+                           help='List of propererties to override when receiving filesystems. (you can still restore '
+                                'them with zfs inherit -S)')
+        group.add_argument('--rollback', action='store_true',
+                           help='Rollback changes to the latest target snapshot before starting. (normally you can '
+                                'prevent changes by setting the readonly property on the target_path to on)')
+        group.add_argument('--force', '-F', action='store_true',
+                           help='Use zfs -F option to force overwrite/rollback. (Useful with --strip-path=1, but use with care)')
+        group.add_argument('--destroy-incompatible', action='store_true',
+                           help='Destroy incompatible snapshots on target. Use with care! (implies --rollback)')
+        group.add_argument('--ignore-transfer-errors', action='store_true',
+                           help='Ignore transfer errors (still checks if received filesystem exists. useful for '
+                                'acltype errors)')
+
+        group.add_argument('--decrypt', action='store_true',
+                           help='Decrypt data before sending it over.')
+        group.add_argument('--encrypt', action='store_true',
+                           help='Encrypt data after receiving it.')
+
+        group.add_argument('--zfs-compressed', action='store_true',
+                           help='Transfer blocks that already have zfs-compression as-is.')
+
+        group = parser.add_argument_group("Data transfer options")
+        group.add_argument('--compress', metavar='TYPE', default=None, nargs='?', const='zstd-fast',
+                           choices=compressors.choices(),
+                           help='Use compression during transfer, defaults to zstd-fast if TYPE is not specified. ({})'.format(
+                               ", ".join(compressors.choices())))
+        group.add_argument('--rate', metavar='DATARATE', default=None,
+                           help='Limit data transfer rate in Bytes/sec (e.g. 128K. requires mbuffer.)')
+        group.add_argument('--buffer', metavar='SIZE', default=None,
+                           help='Add zfs send and recv buffers to smooth out IO bursts. (e.g. 128M. requires mbuffer)')
+        group.add_argument('--send-pipe', metavar="COMMAND", default=[], action='append',
+                           help='pipe zfs send output through COMMAND (can be used multiple times)')
+        group.add_argument('--recv-pipe', metavar="COMMAND", default=[], action='append',
+                           help='pipe zfs recv input through COMMAND (can be used multiple times)')
+
+        group = parser.add_argument_group("Thinner options")
+        group.add_argument('--no-thinning', action='store_true', help="Do not destroy any snapshots.")
+        group.add_argument('--keep-source', metavar='SCHEDULE', type=str, default="10,1d1w,1w1m,1m1y",
+                           help='Thinning schedule for old source snapshots. Default: %(default)s')
+        group.add_argument('--keep-target', metavar='SCHEDULE', type=str, default="10,1d1w,1w1m,1m1y",
+                           help='Thinning schedule for old target snapshots. Default: %(default)s')
+        group.add_argument('--destroy-missing', metavar="SCHEDULE", type=str, default=None,
+                           help='Destroy datasets on target that are missing on the source. Specify the time since '
+                                'the last snapshot, e.g: --destroy-missing 30d')
+
+        # obsolete
+        parser.add_argument('--resume', action='store_true', help=argparse.SUPPRESS)
+        parser.add_argument('--raw', action='store_true', help=argparse.SUPPRESS)
+
+        return parser
+
+    # NOTE: this method also uses self.args. args that need extra processing are passed as function parameters:
+    def thin_missing_targets(self, target_dataset, used_target_datasets):
+        """thin target datasets that are missing on the source."""
+
+        self.debug("Thinning obsolete datasets")
+        missing_datasets = [dataset for dataset in target_dataset.recursive_datasets if
+                            dataset not in used_target_datasets]
+
+        count = 0
+        for dataset in missing_datasets:
+
+            count = count + 1
+            if self.args.progress:
+                self.progress("Analysing missing {}/{}".format(count, len(missing_datasets)))
+
+            try:
+                dataset.debug("Missing on source, thinning")
+                dataset.thin()
+
+            except Exception as e:
+                dataset.error("Error during thinning of missing datasets ({})".format(str(e)))
+
+        # if self.args.progress:
+        #     self.clear_progress()
+
+    # NOTE: this method also uses self.args. args that need extra processing are passed as function parameters:
+    def destroy_missing_targets(self, target_dataset, used_target_datasets):
+        """destroy target datasets that are missing on the source and that meet the requirements"""
+
+        self.debug("Destroying obsolete datasets")
+
+        missing_datasets = [dataset for dataset in target_dataset.recursive_datasets if
+                            dataset not in used_target_datasets]
+
+        count = 0
+        for dataset in missing_datasets:
+
+            count = count + 1
+            if self.args.progress:
+                self.progress("Analysing destroy missing {}/{}".format(count, len(missing_datasets)))
+
+            try:
+                # cant do anything without our own snapshots
+                if not dataset.our_snapshots:
+                    if dataset.datasets:
+                        # its not a leaf, just ignore
+                        dataset.debug("Destroy missing: ignoring")
+                    else:
+                        dataset.verbose(
+                            "Destroy missing: has no snapshots made by us (please destroy manually).")
+                else:
+                    # past the deadline?
+                    deadline_ttl = ThinnerRule("0s" + self.args.destroy_missing).ttl
+                    now = int(time.time())
+                    if dataset.our_snapshots[-1].timestamp + deadline_ttl > now:
+                        dataset.verbose("Destroy missing: Waiting for deadline.")
+                    else:
+
+                        dataset.debug("Destroy missing: Removing our snapshots.")
+
+                        # remove all our snaphots, except last, to safe space in case we fail later on
+                        for snapshot in dataset.our_snapshots[:-1]:
+                            snapshot.destroy(fail_exception=True)
+
+                        # does it have other snapshots?
+                        has_others = False
+                        for snapshot in dataset.snapshots:
+                            if not snapshot.is_ours():
+                                has_others = True
+                                break
+
+                        if has_others:
+                            dataset.verbose("Destroy missing: Still in use by other snapshots")
+                        else:
+                            if dataset.datasets:
+                                dataset.verbose("Destroy missing: Still has children here.")
+                            else:
+                                dataset.verbose("Destroy missing.")
+                                dataset.our_snapshots[-1].destroy(fail_exception=True)
+                                dataset.destroy(fail_exception=True)
+
+            except Exception as e:
+                # if self.args.progress:
+                #     self.clear_progress()
+
+                dataset.error("Error during --destroy-missing: {}".format(str(e)))
+
+        # if self.args.progress:
+        #     self.clear_progress()
+
+    def get_send_pipes(self, logger):
+        """determine the zfs send pipe"""
+
+        ret = []
+
+        # IO buffer
+        if self.args.buffer:
+            logger("zfs send buffer        : {}".format(self.args.buffer))
+            ret.extend([ExecuteNode.PIPE, "mbuffer", "-q", "-s128k", "-m" + self.args.buffer])
+
+        # custom pipes
+        for send_pipe in self.args.send_pipe:
+            ret.append(ExecuteNode.PIPE)
+            ret.extend(send_pipe.split(" "))
+            logger("zfs send custom pipe   : {}".format(send_pipe))
+
+        # compression
+        if self.args.compress != None:
+            ret.append(ExecuteNode.PIPE)
+            cmd = compressors.compress_cmd(self.args.compress)
+            ret.extend(cmd)
+            logger("zfs send compression   : {}".format(" ".join(cmd)))
+
+        # transfer rate
+        if self.args.rate:
+            logger("zfs send transfer rate : {}".format(self.args.rate))
+            ret.extend([ExecuteNode.PIPE, "mbuffer", "-q", "-s128k", "-m16M", "-R" + self.args.rate])
+
+        return ret
+
+    def get_recv_pipes(self, logger):
+
+        ret = []
+
+        # decompression
+        if self.args.compress != None:
+            cmd = compressors.decompress_cmd(self.args.compress)
+            ret.extend(cmd)
+            ret.append(ExecuteNode.PIPE)
+            logger("zfs recv decompression : {}".format(" ".join(cmd)))
+
+        # custom pipes
+        for recv_pipe in self.args.recv_pipe:
+            ret.extend(recv_pipe.split(" "))
+            ret.append(ExecuteNode.PIPE)
+            logger("zfs recv custom pipe   : {}".format(recv_pipe))
+
+        # IO buffer
+        if self.args.buffer:
+            # only add second buffer if its usefull. (e.g. non local transfer or other pipes active)
+            if self.args.ssh_source != None or self.args.ssh_target != None or self.args.recv_pipe or self.args.send_pipe or self.args.compress != None:
+                logger("zfs recv buffer        : {}".format(self.args.buffer))
+                ret.extend(["mbuffer", "-q", "-s128k", "-m" + self.args.buffer, ExecuteNode.PIPE])
+
+        return ret
+
+    def make_target_name(self, source_dataset):
+        """make target_name from a source_dataset"""
+        stripped=source_dataset.lstrip_path(self.args.strip_path)
+        if stripped!="":
+            return self.args.target_path + "/" + stripped
+        else:
+            return self.args.target_path
+
+    def check_target_names(self, source_node, source_datasets, target_node):
+        """check all target names for collesions etc due to strip-options"""
+
+        self.debug("Checking target names:")
+        target_datasets={}
+        for source_dataset in source_datasets:
+
+            target_name = self.make_target_name(source_dataset)
+            source_dataset.debug("-> {}".format(target_name))
+
+            if target_name in target_datasets:
+                raise Exception("Target collision: Target path {} encountered twice, due to: {} and {}".format(target_name, source_dataset, target_datasets[target_name]))
+
+            target_datasets[target_name]=source_dataset
+
+    # NOTE: this method also uses self.args. args that need extra processing are passed as function parameters:
+    def sync_datasets(self, source_node, source_datasets, target_node):
+        """Sync datasets, or thin-only on both sides
+        :type target_node: ZfsNode
+        :type source_datasets: list of ZfsDataset
+        :type source_node: ZfsNode
+        """
+
+        send_pipes = self.get_send_pipes(source_node.verbose)
+        recv_pipes = self.get_recv_pipes(target_node.verbose)
+
+        fail_count = 0
+        count = 0
+        target_datasets = []
+        for source_dataset in source_datasets:
+
+            # stats
+            if self.args.progress:
+                count = count + 1
+                self.progress("Analysing dataset {}/{} ({} failed)".format(count, len(source_datasets), fail_count))
+
+            try:
+                # determine corresponding target_dataset
+                target_name = self.make_target_name(source_dataset)
+                target_dataset = target_node.get_dataset(target_name)
+                target_datasets.append(target_dataset)
+
+                # ensure parents exists
+                # TODO: this isnt perfect yet, in some cases it can create parents when it shouldn't.
+                if not self.args.no_send \
+                        and target_dataset.parent \
+                        and target_dataset.parent not in target_datasets \
+                        and not target_dataset.parent.exists:
+                    target_dataset.parent.create_filesystem(parents=True)
+
+                # determine common zpool features (cached, so no problem we call it often)
+                source_features = source_node.get_pool(source_dataset).features
+                target_features = target_node.get_pool(target_dataset).features
+                common_features = source_features and target_features
+
+                # sync the snapshots of this dataset
+                source_dataset.sync_snapshots(target_dataset, show_progress=self.args.progress,
+                                              features=common_features, filter_properties=self.filter_properties_list(),
+                                              set_properties=self.set_properties_list(),
+                                              ignore_recv_exit_code=self.args.ignore_transfer_errors,
+                                              holds=not self.args.no_holds, rollback=self.args.rollback,
+                                              also_other_snapshots=self.args.other_snapshots,
+                                              no_send=self.args.no_send,
+                                              destroy_incompatible=self.args.destroy_incompatible,
+                                              send_pipes=send_pipes, recv_pipes=recv_pipes,
+                                              decrypt=self.args.decrypt, encrypt=self.args.encrypt,
+                                              zfs_compressed=self.args.zfs_compressed, force=self.args.force)
+            except Exception as e:
+                # if self.args.progress:
+                #     self.clear_progress()
+
+                fail_count = fail_count + 1
+                source_dataset.error("FAILED: " + str(e))
+                if self.args.debug:
+                    self.verbose("Debug mode, aborting on first error")
+                    raise
+
+        # if self.args.progress:
+        #     self.clear_progress()
+
+        target_path_dataset = target_node.get_dataset(self.args.target_path)
+        if not self.args.no_thinning:
+            self.thin_missing_targets(target_dataset=target_path_dataset, used_target_datasets=target_datasets)
+
+        if self.args.destroy_missing is not None:
+            self.destroy_missing_targets(target_dataset=target_path_dataset, used_target_datasets=target_datasets)
+
+        return fail_count
+
+    def thin_source(self, source_datasets):
+
+        self.set_title("Thinning source")
+
+        for source_dataset in source_datasets:
+            source_dataset.thin(skip_holds=True)
+
+    def filter_properties_list(self):
+
+        if self.args.filter_properties:
+            filter_properties = self.args.filter_properties.split(",")
+        else:
+            filter_properties = []
+
+        if self.args.clear_refreservation:
+            filter_properties.append("refreservation")
+
+        return filter_properties
+
+    def set_properties_list(self):
+
+        if self.args.set_properties:
+            set_properties = self.args.set_properties.split(",")
+        else:
+            set_properties = []
+
+        if self.args.clear_mountpoint:
+            set_properties.append("canmount=noauto")
+
+        return set_properties
+
+    def set_snapshot_properties_list(self):
+
+        if self.args.set_snapshot_properties:
+            set_snapshot_properties = self.args.set_snapshot_properties.split(",")
+        else:
+            set_snapshot_properties = []
+
+        return set_snapshot_properties
+
+    def run(self):
+
+        try:
+
+            ################ create source zfsNode
+            self.set_title("Source settings")
+
+            description = "[Source]"
+            if self.args.no_thinning:
+                source_thinner = None
+            else:
+                source_thinner = Thinner(self.args.keep_source)
+            source_node = ZfsNode(utc=self.args.utc,
+                                  snapshot_time_format=self.snapshot_time_format, hold_name=self.hold_name, logger=self,
+                                  ssh_config=self.args.ssh_config,
+                                  ssh_to=self.args.ssh_source, readonly=self.args.test,
+                                  debug_output=self.args.debug_output, description=description, thinner=source_thinner)
+
+            ################# select source datasets
+            self.set_title("Selecting")
+            ( source_datasets, excluded_datasets) = source_node.selected_datasets(property_name=self.property_name,
+                                                            exclude_received=self.args.exclude_received,
+                                                            exclude_paths=self.exclude_paths,
+                                                            exclude_unchanged=self.args.exclude_unchanged)
+            if not source_datasets and not excluded_datasets:
+                self.print_error_sources()
+                return 255
+
+            ################# snapshotting
+            if not self.args.no_snapshot:
+                self.set_title("Snapshotting")
+                dt = datetime.utcnow() if self.args.utc else datetime.now()
+                snapshot_name = dt.strftime(self.snapshot_time_format)
+                source_node.consistent_snapshot(source_datasets, snapshot_name,
+                                                min_changed_bytes=self.args.min_change,
+                                                pre_snapshot_cmds=self.args.pre_snapshot_cmd,
+                                                post_snapshot_cmds=self.args.post_snapshot_cmd,
+                                                set_snapshot_properties=self.set_snapshot_properties_list())
+
+            ################# sync
+            # if target is specified, we sync the datasets, otherwise we just thin the source. (e.g. snapshot mode)
+            if self.args.target_path:
+
+                # create target_node
+                self.set_title("Target settings")
+                if self.args.no_thinning:
+                    target_thinner = None
+                else:
+                    target_thinner = Thinner(self.args.keep_target)
+                target_node = ZfsNode(utc=self.args.utc,
+                                      snapshot_time_format=self.snapshot_time_format, hold_name=self.hold_name,
+                                      logger=self, ssh_config=self.args.ssh_config,
+                                      ssh_to=self.args.ssh_target,
+                                      readonly=self.args.test, debug_output=self.args.debug_output,
+                                      description="[Target]",
+                                      thinner=target_thinner)
+                target_node.verbose("Receive datasets under: {}".format(self.args.target_path))
+
+                self.set_title("Synchronising")
+
+                # check if exists, to prevent vague errors
+                target_dataset = target_node.get_dataset(self.args.target_path)
+                if not target_dataset.exists:
+                    raise (Exception(
+                        "Target path '{}' does not exist. Please create this dataset first.".format(target_dataset)))
+
+                # check for collisions due to strip-path
+                self.check_target_names(source_node, source_datasets, target_node)
+
+                # do the actual sync
+                # NOTE: even with no_send, no_thinning and no_snapshot it does a usefull thing because it checks if the common snapshots and shows incompatible snapshots
+                fail_count = self.sync_datasets(
+                    source_node=source_node,
+                    source_datasets=source_datasets,
+                    target_node=target_node)
+
+            # no target specified, run in snapshot-only mode
+            else:
+                if not self.args.no_thinning:
+                    self.thin_source(source_datasets)
+                fail_count = 0
+
+            if not fail_count:
+                if self.args.test:
+                    self.set_title("All tests successful.")
+                else:
+                    self.set_title("All operations completed successfully")
+                    if not self.args.target_path:
+                        self.verbose("(No target_path specified, only operated as snapshot tool.)")
+
+            else:
+                if fail_count != 255:
+                    self.error("{} dataset(s) failed!".format(fail_count))
+
+            if self.args.test:
+                self.verbose("")
+                self.warning("TEST MODE - DID NOT MAKE ANY CHANGES!")
+
+            self.clear_progress()
+            return fail_count
+
+        except Exception as e:
+            self.error("Exception: " + str(e))
+            if self.args.debug:
+                raise
+            return 255
+        except KeyboardInterrupt:
+            self.error("Aborted")
+            return 255
+
+
+def cli():
+    import sys
+
+    signal(SIGPIPE, sigpipe_handler)
+
+    failed_datasets=ZfsAutobackup(sys.argv[1:], False).run()
+    sys.exit(min(failed_datasets, 255))
+
+
+if __name__ == "__main__":
+    cli()

zfs_autobackup/ZfsAutoverify.py

@@ -0,0 +1,316 @@
+# from util import activate_volume_snapshot, create_mountpoints, cleanup_mountpoint
+from signal import signal, SIGPIPE
+from .util import output_redir, sigpipe_handler
+
+from .ZfsAuto import ZfsAuto
+from .ZfsNode import ZfsNode
+import sys
+
+
+# # try to be as unix compatible as possible, while still having decent performance
+# def compare_trees_find(source_node, source_path, target_node, target_path):
+#     # find /tmp/zfstmp_pve1_1993135target/ -xdev -type f -print0 | xargs -0 md5sum | md5sum -c
+#
+#     #verify tree has atleast one file
+#
+#     stdout=source_node.run(["find", ".", "-type", "f",
+#                           ExecuteNode.PIPE, "head", "-n1",
+#                           ], cwd=source_path)
+#
+#     if not stdout:
+#         source_node.debug("No files, skipping check")
+#     else:
+#         pipe=source_node.run(["find", ".", "-type", "f", "-print0",
+#                               ExecuteNode.PIPE, "xargs", "-0", "md5sum"
+#                               ], pipe=True, cwd=source_path)
+#         stdout=target_node.run([ "md5sum", "-c", "--quiet"], inp=pipe, cwd=target_path, valid_exitcodes=[0,1])
+#
+#         if len(stdout):
+#             for line in stdout:
+#                 target_node.error("md5sum: "+line)
+#
+#             raise(Exception("Some files have checksum errors"))
+#
+#
+# def compare_trees_rsync(source_node, source_path, target_node, target_path):
+#     """use rsync to compare two trees.
+#      Advantage is that we can see which individual files differ.
+#      But requires rsync and cant do remote to remote."""
+#
+#     cmd = ["rsync", "-rcnq", "--info=COPY,DEL,MISC,NAME,SYMSAFE", "--msgs2stderr", "--delete" ]
+#
+#     #local
+#     if source_node.ssh_to is None and target_node.ssh_to is None:
+#         cmd.append("{}/".format(source_path))
+#         cmd.append("{}/".format(target_path))
+#         source_node.debug("Running rsync locally, on source.")
+#         stdout, stderr = source_node.run(cmd, return_stderr=True)
+#
+#     #source is local
+#     elif source_node.ssh_to is None and target_node.ssh_to is not None:
+#         cmd.append("{}/".format(source_path))
+#         cmd.append("{}:{}/".format(target_node.ssh_to, target_path))
+#         source_node.debug("Running rsync locally, on source.")
+#         stdout, stderr = source_node.run(cmd, return_stderr=True)
+#
+#     #target is local
+#     elif source_node.ssh_to is not None and target_node.ssh_to is None:
+#         cmd.append("{}:{}/".format(source_node.ssh_to, source_path))
+#         cmd.append("{}/".format(target_path))
+#         source_node.debug("Running rsync locally, on target.")
+#         stdout, stderr=target_node.run(cmd, return_stderr=True)
+#
+#     else:
+#         raise Exception("Source and target cant both be remote when verifying. (rsync limitation)")
+#
+#     if stderr:
+#         raise Exception("Dataset verify failed, see above list for differences")
+
+
+def verify_filesystem(source_snapshot, source_mnt, target_snapshot, target_mnt, method):
+    """Compare the contents of two zfs filesystem snapshots """
+
+    try:
+
+        # mount the snapshots
+        source_snapshot.mount(source_mnt)
+        target_snapshot.mount(target_mnt)
+
+        if method=='rsync':
+            compare_trees_rsync(source_snapshot.zfs_node, source_mnt, target_snapshot.zfs_node, target_mnt)
+        # elif method == 'tar':
+        #     compare_trees_tar(source_snapshot.zfs_node, source_mnt, target_snapshot.zfs_node, target_mnt)
+        elif method == 'find':
+            compare_trees_find(source_snapshot.zfs_node, source_mnt, target_snapshot.zfs_node, target_mnt)
+        else:
+            raise(Exception("program errror, unknown method"))
+
+    finally:
+        source_snapshot.unmount()
+        target_snapshot.unmount()
+
+
+# def hash_dev(node, dev):
+#     """calculate md5sum of a device on a node"""
+#
+#     node.debug("Hashing volume {} ".format(dev))
+#
+#     cmd = [ "md5sum", dev ]
+#
+#     stdout = node.run(cmd)
+#
+#     if node.readonly:
+#         hashed=None
+#     else:
+#         hashed = stdout[0].split(" ")[0]
+#
+#     node.debug("Hash of volume {} is {}".format(dev, hashed))
+#
+#     return hashed
+
+
+
+# def deacitvate_volume_snapshot(snapshot):
+#     clone_name=get_tmp_clone_name(snapshot)
+#     clone=snapshot.zfs_node.get_dataset(clone_name)
+#     clone.destroy(deferred=True, verbose=False)
+
+def verify_volume(source_dataset, source_snapshot, target_dataset, target_snapshot):
+    """compare the contents of two zfs volume snapshots"""
+
+    # try:
+    source_dev= activate_volume_snapshot(source_snapshot)
+    target_dev= activate_volume_snapshot(target_snapshot)
+
+    source_hash= hash_dev(source_snapshot.zfs_node, source_dev)
+    target_hash= hash_dev(target_snapshot.zfs_node, target_dev)
+
+    if source_hash!=target_hash:
+        raise Exception("md5hash difference: {} != {}".format(source_hash, target_hash))
+
+    # finally:
+    #     deacitvate_volume_snapshot(source_snapshot)
+    #     deacitvate_volume_snapshot(target_snapshot)
+
+
+# class ZfsAutoChecksumVolume(ZfsAuto):
+#     def __init__(self, argv, print_arguments=True):
+#
+#         # NOTE: common options and parameters are in ZfsAuto
+#         super(ZfsAutoverify, self).__init__(argv, print_arguments)
+
+class ZfsAutoverify(ZfsAuto):
+    """The zfs-autoverify class, default agruments and stuff come from ZfsAuto"""
+
+    def __init__(self, argv, print_arguments=True):
+
+        # NOTE: common options and parameters are in ZfsAuto
+        super(ZfsAutoverify, self).__init__(argv, print_arguments)
+
+    def parse_args(self, argv):
+        """do extra checks on common args"""
+
+        args=super(ZfsAutoverify, self).parse_args(argv)
+
+        if args.target_path == None:
+            self.log.error("Please specify TARGET-PATH")
+            sys.exit(255)
+
+        return args
+
+    def get_parser(self):
+        """extend common parser with  extra stuff needed for zfs-autobackup"""
+
+        parser=super(ZfsAutoverify, self).get_parser()
+
+        group=parser.add_argument_group("Verify options")
+        group.add_argument('--fs-compare', metavar='METHOD', default="find", choices=["find", "rsync"],
+                            help='Compare method to use for filesystems. (find, rsync) Default: %(default)s ')
+
+        return parser
+
+    def verify_datasets(self, source_mnt, source_datasets, target_node, target_mnt):
+
+        fail_count=0
+        count = 0
+        for source_dataset in source_datasets:
+
+            # stats
+            if self.args.progress:
+                count = count + 1
+                self.progress("Analysing dataset {}/{} ({} failed)".format(count, len(source_datasets), fail_count))
+
+            try:
+                # determine corresponding target_dataset
+                target_name = self.make_target_name(source_dataset)
+                target_dataset = target_node.get_dataset(target_name)
+
+                # find common snapshots to  verify
+                source_snapshot = source_dataset.find_common_snapshot(target_dataset)
+                target_snapshot = target_dataset.find_snapshot(source_snapshot)
+
+                if source_snapshot is None or target_snapshot is None:
+                    raise(Exception("Cant find common snapshot"))
+
+                target_snapshot.verbose("Verifying...")
+
+                if source_dataset.properties['type']=="filesystem":
+                    verify_filesystem(source_snapshot, source_mnt, target_snapshot, target_mnt, self.args.fs_compare)
+                elif source_dataset.properties['type']=="volume":
+                    verify_volume(source_dataset, source_snapshot, target_dataset, target_snapshot)
+                else:
+                    raise(Exception("{} has unknown type {}".format(source_dataset, source_dataset.properties['type'])))
+
+
+            except Exception as e:
+                # if self.args.progress:
+                #     self.clear_progress()
+
+                fail_count = fail_count + 1
+                target_dataset.error("FAILED: " + str(e))
+                if self.args.debug:
+                    self.verbose("Debug mode, aborting on first error")
+                    raise
+
+        # if self.args.progress:
+        #     self.clear_progress()
+
+        return fail_count
+
+    def run(self):
+
+        source_node=None
+        source_mnt=None
+        target_node=None
+        target_mnt=None
+
+
+        try:
+
+            ################ create source zfsNode
+            self.set_title("Source settings")
+
+            description = "[Source]"
+            source_node = ZfsNode(utc=self.args.utc,
+                                  snapshot_time_format=self.snapshot_time_format, hold_name=self.hold_name, logger=self,
+                                  ssh_config=self.args.ssh_config,
+                                  ssh_to=self.args.ssh_source, readonly=self.args.test,
+                                  debug_output=self.args.debug_output, description=description)
+
+            ################# select source datasets
+            self.set_title("Selecting")
+            ( source_datasets, excluded_datasets) = source_node.selected_datasets(property_name=self.property_name,
+                                                            exclude_received=self.args.exclude_received,
+                                                            exclude_paths=self.exclude_paths,
+                                                            exclude_unchanged=self.args.exclude_unchanged)
+            if not source_datasets and not excluded_datasets:
+                self.print_error_sources()
+                return 255
+
+            # create target_node
+            self.set_title("Target settings")
+            target_node = ZfsNode(utc=self.args.utc,
+                                  snapshot_time_format=self.snapshot_time_format, hold_name=self.hold_name,
+                                  logger=self, ssh_config=self.args.ssh_config,
+                                  ssh_to=self.args.ssh_target,
+                                  readonly=self.args.test, debug_output=self.args.debug_output,
+                                  description="[Target]")
+            target_node.verbose("Verify datasets under: {}".format(self.args.target_path))
+
+            self.set_title("Verifying")
+
+            source_mnt, target_mnt= create_mountpoints(source_node, target_node)
+
+            fail_count = self.verify_datasets(
+                source_mnt=source_mnt,
+                source_datasets=source_datasets,
+                target_mnt=target_mnt,
+                target_node=target_node)
+
+            if not fail_count:
+                if self.args.test:
+                    self.set_title("All tests successful.")
+                else:
+                    self.set_title("All datasets verified ok")
+
+            else:
+                if fail_count != 255:
+                    self.error("{} dataset(s) failed!".format(fail_count))
+
+            if self.args.test:
+                self.verbose("")
+                self.warning("TEST MODE - DID NOT VERIFY ANYTHING!")
+
+            return fail_count
+
+        except Exception as e:
+            self.error("Exception: " + str(e))
+            if self.args.debug:
+                raise
+            return 255
+        except KeyboardInterrupt:
+            self.error("Aborted")
+            return 255
+        finally:
+
+            # cleanup
+            if source_mnt is not None:
+                cleanup_mountpoint(source_node, source_mnt)
+
+            if target_mnt is not None:
+                cleanup_mountpoint(target_node, target_mnt)
+
+
+
+
+def cli():
+    import sys
+
+    raise(Exception("This program is incomplete, dont use it yet."))
+    signal(SIGPIPE, sigpipe_handler)
+    failed = ZfsAutoverify(sys.argv[1:], False).run()
+    sys.exit(min(failed,255))
+
+
+if __name__ == "__main__":
+    cli()

zfs_autobackup/ZfsCheck.py

@@ -0,0 +1,310 @@
+from __future__ import print_function
+
+import time
+from signal import signal, SIGPIPE
+
+from . import util
+from .TreeHasher import TreeHasher
+from .BlockHasher import BlockHasher
+from .ZfsNode import ZfsNode
+from .util import *
+from .CliBase import CliBase
+
+
+class ZfsCheck(CliBase):
+
+    def __init__(self, argv, print_arguments=True):
+
+        # NOTE: common options argument parsing are in CliBase
+        super(ZfsCheck, self).__init__(argv, print_arguments)
+
+        self.node = ZfsNode(self.log, utc=self.args.utc, readonly=self.args.test, debug_output=self.args.debug_output)
+
+        self.block_hasher = BlockHasher(count=self.args.count, bs=self.args.block_size, skip=self.args.skip)
+
+    def get_parser(self):
+
+        parser = super(ZfsCheck, self).get_parser()
+
+        # positional arguments
+        parser.add_argument('target', metavar='TARGET', default=None, nargs='?', help='Target to checkum. (can be blockdevice, directory or ZFS snapshot)')
+
+        group = parser.add_argument_group('Checker options')
+
+        group.add_argument('--block-size', metavar="BYTES", default=4096, help="Read block-size, default %(default)s",
+                           type=int)
+        group.add_argument('--count', metavar="COUNT", default=int((100 * (1024 ** 2)) / 4096),
+                           help="Hash chunks of COUNT blocks. Default %(default)s . (CHUNK size is BYTES * COUNT) ", type=int)  # 100MiB
+
+        group.add_argument('--check', '-c', metavar="FILE", default=None, const=True, nargs='?',
+                           help="Read hashes from STDIN (or FILE) and compare them")
+
+        group.add_argument('--skip', '-s', metavar="NUMBER", default=0, type=int,
+                           help="Skip this number of chunks after every hash. %(default)s")
+
+        return parser
+
+    def parse_args(self, argv):
+        args = super(ZfsCheck, self).parse_args(argv)
+
+        if args.test:
+            self.warning("TEST MODE - WILL ONLY DO READ-ONLY STUFF")
+
+        if args.target is None:
+            self.error("Please specify TARGET")
+            sys.exit(1)
+
+        self.verbose("Target               : {}".format(args.target))
+        self.verbose("Block size           : {} bytes".format(args.block_size))
+        self.verbose("Block count          : {}".format(args.count))
+        self.verbose("Effective chunk size : {} bytes".format(args.count*args.block_size))
+        self.verbose("Skip chunk count     : {} (checks {:.2f}% of data)".format(args.skip, 100/(1+args.skip)))
+        self.verbose("")
+
+
+        return args
+
+    def prepare_zfs_filesystem(self, snapshot):
+
+        mnt = "/tmp/" + tmp_name()
+        self.debug("Create temporary mount point {}".format(mnt))
+        self.node.run(["mkdir", mnt])
+        snapshot.mount(mnt)
+        return mnt
+
+    def cleanup_zfs_filesystem(self, snapshot):
+        mnt = "/tmp/" + tmp_name()
+        snapshot.unmount()
+        self.debug("Cleaning up temporary mount point")
+        self.node.run(["rmdir", mnt], hide_errors=True, valid_exitcodes=[])
+
+    # NOTE: https://www.google.com/search?q=Mount+Path+Limit+freebsd
+    # Freebsd has limitations regarding path length, so we have to clone it so the part stays sort
+    def prepare_zfs_volume(self, snapshot):
+        """clone volume, waits and tries to findout /dev path to the volume, in a compatible way. (linux/freebsd/smartos)"""
+
+        clone_name = get_tmp_clone_name(snapshot)
+        clone = snapshot.clone(clone_name)
+
+        # TODO: add smartos location to this list as well
+        locations = [
+            "/dev/zvol/" + clone_name
+        ]
+
+        clone.debug("Waiting for /dev entry to appear in: {}".format(locations))
+        time.sleep(0.1)
+
+        start_time = time.time()
+        while time.time() - start_time < 10:
+            for location in locations:
+                if os.path.exists(location):
+                    return location
+
+                # fake it in testmode
+                if self.args.test:
+                    return location
+
+            time.sleep(1)
+
+        raise (Exception("Timeout while waiting for /dev entry to appear. (looking in: {}). Hint: did you forget to load the encryption key?".format(locations)))
+
+    def cleanup_zfs_volume(self, snapshot):
+        """destroys temporary volume snapshot"""
+        clone_name = get_tmp_clone_name(snapshot)
+        clone = snapshot.zfs_node.get_dataset(clone_name)
+        clone.destroy(deferred=True, verbose=False)
+
+    def generate_tree_hashes(self, prepared_target):
+
+        tree_hasher = TreeHasher(self.block_hasher)
+        self.debug("Hashing tree: {}".format(prepared_target))
+        for i in tree_hasher.generate(prepared_target):
+            yield i
+
+    def generate_tree_compare(self, prepared_target, input_generator=None):
+
+        tree_hasher = TreeHasher(self.block_hasher)
+        self.debug("Comparing tree: {}".format(prepared_target))
+        for i in tree_hasher.compare(prepared_target, input_generator):
+            yield i
+
+    def generate_file_hashes(self, prepared_target):
+
+        self.debug("Hashing file: {}".format(prepared_target))
+        for i in self.block_hasher.generate(prepared_target):
+            yield i
+
+    def generate_file_compare(self, prepared_target, input_generator=None):
+
+        self.debug("Comparing file: {}".format(prepared_target))
+        for i in self.block_hasher.compare(prepared_target, input_generator):
+            yield i
+
+    def generate_input(self):
+        """parse input lines and yield items to use in compare functions"""
+
+        if self.args.check is True:
+            input_fh=sys.stdin
+        else:
+            input_fh=open(self.args.check, 'r')
+
+        last_progress_time = time.time()
+        progress_checked = 0
+        progress_skipped = 0
+
+        line=input_fh.readline()
+        skip=0
+        while line:
+            i=line.rstrip().split("\t")
+            #ignores lines without tabs
+            if (len(i)>1):
+
+                if skip==0:
+                    progress_checked=progress_checked+1
+                    yield i
+                    skip=self.args.skip
+                else:
+                    skip=skip-1
+                    progress_skipped=progress_skipped+1
+
+                if self.args.progress and time.time() - last_progress_time > 1:
+                    last_progress_time = time.time()
+                    self.progress("Checked {} hashes (skipped {})".format(progress_checked, progress_skipped))
+
+            line=input_fh.readline()
+
+        self.verbose("Checked {} hashes (skipped {})".format(progress_checked, progress_skipped))
+
+    def print_hashes(self, hash_generator):
+        """prints hashes that are yielded by the specified hash_generator"""
+
+        last_progress_time = time.time()
+        progress_count = 0
+
+        for i in hash_generator:
+
+            if len(i) == 3:
+                print("{}\t{}\t{}".format(*i))
+            else:
+                print("{}\t{}".format(*i))
+            progress_count = progress_count + 1
+
+            if self.args.progress and time.time() - last_progress_time > 1:
+                last_progress_time = time.time()
+                self.progress("Generated {} hashes.".format(progress_count))
+
+            sys.stdout.flush()
+
+        self.verbose("Generated {} hashes.".format(progress_count))
+        self.clear_progress()
+
+        return 0
+
+    def print_errors(self, compare_generator):
+        """prints errors that are yielded by the specified compare_generator"""
+        errors = 0
+        for i in compare_generator:
+            errors = errors + 1
+
+            if len(i) == 4:
+                (file_name, chunk_nr, compare_hexdigest, actual_hexdigest) = i
+                print("{}: Chunk {} failed: {} {}".format(file_name, chunk_nr, compare_hexdigest, actual_hexdigest))
+            else:
+                (chunk_nr, compare_hexdigest, actual_hexdigest) = i
+                print("Chunk {} failed: {} {}".format(chunk_nr, compare_hexdigest, actual_hexdigest))
+
+            sys.stdout.flush()
+
+        self.verbose("Total errors: {}".format(errors))
+        self.clear_progress()
+
+        return errors
+
+    def prepare_target(self):
+
+        if "@" in self.args.target:
+            # zfs snapshot
+            snapshot=self.node.get_dataset(self.args.target)
+            if not snapshot.exists:
+                raise Exception("ZFS snapshot {} does not exist!".format(snapshot))
+            dataset_type = snapshot.parent.properties['type']
+
+            if dataset_type == 'volume':
+                return self.prepare_zfs_volume(snapshot)
+            elif dataset_type == 'filesystem':
+                return self.prepare_zfs_filesystem(snapshot)
+            else:
+                raise Exception("Unknown dataset type")
+        return self.args.target
+
+    def cleanup_target(self):
+        if "@" in self.args.target:
+            # zfs snapshot
+            snapshot=self.node.get_dataset(self.args.target)
+            if not snapshot.exists:
+                return
+
+            dataset_type = snapshot.parent.properties['type']
+
+            if dataset_type == 'volume':
+                self.cleanup_zfs_volume(snapshot)
+            elif dataset_type == 'filesystem':
+                self.cleanup_zfs_filesystem(snapshot)
+
+    def run(self):
+
+        compare_generator=None
+        hash_generator=None
+        try:
+            prepared_target=self.prepare_target()
+            is_dir=os.path.isdir(prepared_target)
+
+            #run as compare
+            if self.args.check is not None:
+                input_generator=self.generate_input()
+                if is_dir:
+                    compare_generator = self.generate_tree_compare(prepared_target, input_generator)
+                else:
+                    compare_generator=self.generate_file_compare(prepared_target, input_generator)
+                errors=self.print_errors(compare_generator)
+            #run as generator
+            else:
+                if is_dir:
+                    hash_generator = self.generate_tree_hashes(prepared_target)
+                else:
+                    hash_generator=self.generate_file_hashes(prepared_target)
+
+                errors=self.print_hashes(hash_generator)
+
+        except Exception as e:
+            self.error("Exception: " + str(e))
+            if self.args.debug:
+                raise
+            return 255
+        except KeyboardInterrupt:
+            self.error("Aborted")
+            return 255
+
+        finally:
+            #important to call check_output so that cleanup still functions in case of a broken pipe:
+            # util.check_output()
+
+            #close generators, to make sure files are not in use anymore when cleaning up
+            if hash_generator is not None:
+                hash_generator.close()
+            if compare_generator is not None:
+                compare_generator.close()
+            self.cleanup_target()
+
+        return errors
+
+
+def cli():
+    import sys
+    signal(SIGPIPE, sigpipe_handler)
+    failed=ZfsCheck(sys.argv[1:], False).run()
+    sys.exit(min(failed,255))
+
+
+if __name__ == "__main__":
+    cli()

zfs_autobackup/ZfsNode.py

@@ -0,0 +1,285 @@
+# python 2 compatibility
+from __future__ import print_function
+import re
+import shlex
+import subprocess
+import sys
+import time
+
+from .ExecuteNode import ExecuteNode
+from .Thinner import Thinner
+from .CachedProperty import CachedProperty
+from .ZfsPool import ZfsPool
+from .ZfsDataset import ZfsDataset
+from .ExecuteNode import ExecuteError
+
+
+class ZfsNode(ExecuteNode):
+    """a node that contains zfs datasets. implements global (systemwide/pool wide) zfs commands"""
+
+    def __init__(self, logger, utc=False, snapshot_time_format="", hold_name="", ssh_config=None, ssh_to=None, readonly=False,
+                 description="",
+                 debug_output=False, thinner=None):
+
+        self.utc = utc
+        self.snapshot_time_format = snapshot_time_format
+        self.hold_name = hold_name
+
+        self.description = description
+
+        self.logger = logger
+
+        if ssh_config:
+            self.verbose("Using custom SSH config: {}".format(ssh_config))
+
+        if ssh_to:
+            self.verbose("SSH to: {}".format(ssh_to))
+        # else:
+        #     self.verbose("Datasets are local")
+
+        if thinner is not None:
+            rules = thinner.human_rules()
+            if rules:
+                for rule in rules:
+                    self.verbose(rule)
+            else:
+                self.verbose("Keep no old snaphots")
+
+        self.__thinner = thinner
+
+        # list of ZfsPools
+        self.__pools = {}
+        self.__datasets = {}
+
+        self._progress_total_bytes = 0
+        self._progress_start_time = time.time()
+
+        ExecuteNode.__init__(self, ssh_config=ssh_config, ssh_to=ssh_to, readonly=readonly, debug_output=debug_output)
+
+    def thin(self, objects, keep_objects):
+        # NOTE: if thinning is disabled with --no-thinning, self.__thinner will be none.
+        if self.__thinner is not None:
+            return self.__thinner.thin(objects, keep_objects)
+        else:
+            return (keep_objects, [])
+
+    @CachedProperty
+    def supported_send_options(self):
+        """list of supported options, for optimizing sends"""
+        # not every zfs implementation supports them all
+
+        ret = []
+        for option in ["-L", "-e", "-c"]:
+            if self.valid_command(["zfs", "send", option, "zfs_autobackup_option_test"]):
+                ret.append(option)
+        return ret
+
+    @CachedProperty
+    def supported_recv_options(self):
+        """list of supported options"""
+        # not every zfs implementation supports them all
+
+        ret = []
+        for option in ["-s"]:
+            if self.valid_command(["zfs", "recv", option, "zfs_autobackup_option_test"]):
+                ret.append(option)
+        return ret
+
+    def valid_command(self, cmd):
+        """test if a specified zfs options are valid exit code. use this to determine support options"""
+
+        try:
+            self.run(cmd, hide_errors=True, valid_exitcodes=[0, 1])
+        except ExecuteError:
+            return False
+
+        return True
+
+    def get_pool(self, dataset):
+        """get a ZfsPool() object from dataset. stores objects internally to enable caching"""
+
+        if not isinstance(dataset, ZfsDataset):
+            raise (Exception("{} is not a ZfsDataset".format(dataset)))
+
+        zpool_name = dataset.name.split("/")[0]
+
+        return self.__pools.setdefault(zpool_name, ZfsPool(self, zpool_name))
+
+    def get_dataset(self, name, force_exists=None):
+        """get a ZfsDataset() object from name. stores objects internally to enable caching"""
+
+        return self.__datasets.setdefault(name, ZfsDataset(self, name, force_exists))
+
+    # def reset_progress(self):
+    #     """reset progress output counters"""
+    #     self._progress_total_bytes = 0
+    #     self._progress_start_time = time.time()
+
+    def parse_zfs_progress(self, line, hide_errors, prefix):
+        """try to parse progress output of zfs recv -Pv, and don't show it as error to the user """
+
+        # is it progress output?
+        progress_fields = line.rstrip().split("\t")
+
+        if (line.find("nvlist version") == 0 or
+                line.find("resume token contents") == 0 or
+                len(progress_fields) != 1 or
+                line.find("skipping ") == 0 or
+                re.match("send from .*estimated size is ", line)):
+
+            # always output for debugging offcourse
+            self.debug(prefix + line.rstrip())
+
+            # actual useful info
+            if len(progress_fields) >= 3:
+                if progress_fields[0] == 'full' or progress_fields[0] == 'size':
+                    # Reset the total bytes and start the timer again (otherwise the MB/s
+                    # counter gets confused)
+                    self._progress_total_bytes = int(progress_fields[2])
+                    self._progress_start_time = time.time()
+                elif progress_fields[0] == 'incremental':
+                    # Reset the total bytes and start the timer again (otherwise the MB/s
+                    # counter gets confused)
+                    self._progress_total_bytes = int(progress_fields[3])
+                    self._progress_start_time = time.time()
+                elif progress_fields[1].isnumeric():
+                    bytes_ = int(progress_fields[1])
+                    if self._progress_total_bytes:
+                        percentage = min(100, int(bytes_ * 100 / self._progress_total_bytes))
+                        speed = int(bytes_ / (time.time() - self._progress_start_time) / (1024 * 1024))
+                        bytes_left = self._progress_total_bytes - bytes_
+                        minutes_left = int((bytes_left / (bytes_ / (time.time() - self._progress_start_time))) / 60)
+
+                        self.logger.progress(
+                            "Transfer {}% {}MB/s (total {}MB, {} minutes left)".format(percentage, speed, int(
+                                self._progress_total_bytes / (1024 * 1024)), minutes_left))
+
+            return
+
+        # still do the normal stderr output handling
+        if hide_errors:
+            self.debug(prefix + line.rstrip())
+        else:
+            self.error(prefix + line.rstrip())
+
+    # def _parse_stderr_pipe(self, line, hide_errors):
+    #     self.parse_zfs_progress(line, hide_errors, "STDERR|> ")
+
+    def _parse_stderr(self, line, hide_errors):
+        self.parse_zfs_progress(line, hide_errors, "STDERR > ")
+
+    def verbose(self, txt):
+        self.logger.verbose("{} {}".format(self.description, txt))
+
+    def error(self, txt):
+        self.logger.error("{} {}".format(self.description, txt))
+
+    def warning(self, txt):
+        self.logger.warning("{} {}".format(self.description, txt))
+
+    def debug(self, txt):
+        self.logger.debug("{} {}".format(self.description, txt))
+
+    def consistent_snapshot(self, datasets, snapshot_name, min_changed_bytes, pre_snapshot_cmds=[],
+                            post_snapshot_cmds=[], set_snapshot_properties=[]):
+        """create a consistent (atomic) snapshot of specified datasets, per pool.
+        """
+
+        pools = {}
+
+        # collect snapshots that we want to make, per pool
+        # self.debug(datasets)
+        for dataset in datasets:
+            if not dataset.is_changed_ours(min_changed_bytes):
+                dataset.verbose("No changes since {}".format(dataset.our_snapshots[-1].snapshot_name))
+                continue
+
+            # force_exist, since we're making it
+            snapshot = self.get_dataset(dataset.name + "@" + snapshot_name, force_exists=True)
+
+            pool = dataset.split_path()[0]
+            if pool not in pools:
+                pools[pool] = []
+
+            pools[pool].append(snapshot)
+
+            # update cache, but try to prevent an unneeded zfs list
+            if self.readonly or CachedProperty.is_cached(dataset, 'snapshots'):
+                dataset.snapshots.append(snapshot)  # NOTE: this will trigger zfs list if its not cached
+
+        if not pools:
+            self.verbose("No changes anywhere: not creating snapshots.")
+            return
+
+        try:
+            for cmd in pre_snapshot_cmds:
+                self.verbose("Running pre-snapshot-cmd")
+                self.run(cmd=shlex.split(cmd), readonly=False)
+
+            # create consistent snapshot per pool
+            for (pool_name, snapshots) in pools.items():
+                cmd = ["zfs", "snapshot"]
+                for snapshot_property in set_snapshot_properties:
+                    cmd += ['-o', snapshot_property]
+
+                cmd.extend(map(lambda snapshot_: str(snapshot_), snapshots))
+
+                self.verbose("Creating snapshots {} in pool {}".format(snapshot_name, pool_name))
+                self.run(cmd, readonly=False)
+
+        finally:
+            for cmd in post_snapshot_cmds:
+                self.verbose("Running post-snapshot-cmd")
+                try:
+                    self.run(cmd=shlex.split(cmd), readonly=False)
+                except Exception as e:
+                    pass
+
+    def selected_datasets(self, property_name, exclude_received, exclude_paths, exclude_unchanged):
+        """determine filesystems that should be backed up by looking at the special autobackup-property, systemwide
+
+           returns: ( list of selected ZfsDataset, list of excluded ZfsDataset)
+        """
+
+        self.debug("Getting selected datasets")
+
+        # get all source filesystems that have the backup property
+        lines = self.run(tab_split=True, readonly=True, cmd=[
+            "zfs", "get", "-t", "volume,filesystem", "-o", "name,value,source", "-H",
+            property_name
+        ])
+
+
+        # The returnlist of selected ZfsDataset's:
+        selected_filesystems = []
+        excluded_filesystems = []
+
+        # list of sources, used to resolve inherited sources
+        sources = {}
+
+        for line in lines:
+            (name, value, raw_source) = line
+            dataset = self.get_dataset(name, force_exists=True)
+
+            # "resolve" inherited sources
+            sources[name] = raw_source
+            if raw_source.find("inherited from ") == 0:
+                inherited = True
+                inherited_from = re.sub("^inherited from ", "", raw_source)
+                source = sources[inherited_from]
+            else:
+                inherited = False
+                source = raw_source
+
+            # determine it
+            selected=dataset.is_selected(value=value, source=source, inherited=inherited, exclude_received=exclude_received,
+                                   exclude_paths=exclude_paths, exclude_unchanged=exclude_unchanged)
+
+            if selected==True:
+                selected_filesystems.append(dataset)
+            elif selected==False:
+                excluded_filesystems.append(dataset)
+            #returns None when no property is set.
+
+
+        return ( selected_filesystems, excluded_filesystems)

zfs_autobackup/ZfsPool.py

@@ -0,0 +1,63 @@
+from .CachedProperty import CachedProperty
+
+
+class ZfsPool():
+    """a zfs pool"""
+
+    def __init__(self, zfs_node, name):
+        """name: name of the pool
+        """
+
+        self.zfs_node = zfs_node
+        self.name = name
+
+    def __repr__(self):
+        return "{}: {}".format(self.zfs_node, self.name)
+
+    def __str__(self):
+        return self.name
+
+    def __eq__(self, obj):
+        if not isinstance(obj, ZfsPool):
+            return False
+
+        return self.name == obj.name
+
+    def verbose(self, txt):
+        self.zfs_node.verbose("zpool {}: {}".format(self.name, txt))
+
+    def error(self, txt):
+        self.zfs_node.error("zpool {}: {}".format(self.name, txt))
+
+    def debug(self, txt):
+        self.zfs_node.debug("zpool {}: {}".format(self.name, txt))
+
+    @CachedProperty
+    def properties(self):
+        """all zpool properties"""
+
+        self.debug("Getting zpool properties")
+
+        cmd = [
+            "zpool", "get", "-H", "-p", "all", self.name
+        ]
+
+        ret = {}
+
+        for pair in self.zfs_node.run(tab_split=True, cmd=cmd, readonly=True, valid_exitcodes=[0]):
+            ret[pair[1]] = pair[2]
+
+        return ret
+
+    @property
+    def features(self):
+        """get list of active zpool features"""
+
+        ret = []
+        for (key, value) in self.properties.items():
+            if key.startswith("feature@"):
+                feature = key.split("@")[1]
+                if value == 'enabled' or value == 'active':
+                    ret.append(feature)
+
+        return ret

zfs_autobackup/__init__.py

@@ -0,0 +1,3 @@
+
+
+

zfs_autobackup/__main__.py

@@ -0,0 +1,7 @@
+# (c)edwin@datux.nl  - Released under GPL V3
+#
+# Greetings from eth0 2019 :)
+
+import sys
+
+

zfs_autobackup/compressors.py

@@ -0,0 +1,75 @@
+# Adopted from Syncoid :)
+
+# this software is licensed for use under the Free Software Foundation's GPL v3.0 license, as retrieved
+# from http://www.gnu.org/licenses/gpl-3.0.html on 2014-11-17.  A copy should also be available in this
+# project's Git repository at https://github.com/jimsalterjrs/sanoid/blob/master/LICENSE.
+
+COMPRESS_CMDS = {
+    'gzip': {
+        'cmd': 'gzip',
+        'args': [ '-3' ],
+        'dcmd': 'zcat',
+        'dargs': [],
+    },
+    'pigz-fast': {
+        'cmd': 'pigz',
+        'args': [ '-3' ],
+        'dcmd': 'pigz',
+        'dargs': [ '-dc' ],
+    },
+    'pigz-slow': {
+        'cmd': 'pigz',
+        'args': [ '-9' ],
+        'dcmd': 'pigz',
+        'dargs': [ '-dc' ],
+    },
+    'zstd-fast': {
+        'cmd': 'zstdmt',
+        'args': [ '-3' ],
+        'dcmd': 'zstdmt',
+        'dargs': [ '-dc' ],
+    },
+    'zstd-slow': {
+        'cmd': 'zstdmt',
+        'args': [ '-19' ],
+        'dcmd': 'zstdmt',
+        'dargs': [ '-dc' ],
+    },
+    'zstd-adapt': {
+        'cmd': 'zstdmt',
+        'args': [ '--adapt' ],
+        'dcmd': 'zstdmt',
+        'dargs': [ '-dc' ],
+    },
+    'xz': {
+        'cmd': 'xz',
+        'args': [],
+        'dcmd': 'xz',
+        'dargs': [ '-d' ],
+    },
+    'lzo': {
+        'cmd': 'lzop',
+        'args': [],
+        'dcmd': 'lzop',
+        'dargs': [ '-dfc' ],
+    },
+    'lz4': {
+        'cmd': 'lz4',
+        'args': [],
+        'dcmd': 'lz4',
+        'dargs': [ '-dc' ],
+    },
+}
+
+def compress_cmd(compressor):
+    ret=[ COMPRESS_CMDS[compressor]['cmd'] ]
+    ret.extend( COMPRESS_CMDS[compressor]['args'])
+    return ret
+
+def decompress_cmd(compressor):
+    ret= [ COMPRESS_CMDS[compressor]['dcmd'] ]
+    ret.extend(COMPRESS_CMDS[compressor]['dargs'])
+    return ret
+
+def choices():
+    return COMPRESS_CMDS.keys()

zfs_autobackup/test.py

@@ -0,0 +1,129 @@
+import os.path
+import os
+import subprocess
+import sys
+import time
+from signal import signal, SIGPIPE
+
+import util
+
+signal(SIGPIPE, util.sigpipe_handler)
+
+
+try:
+    print ("voor eerste")
+    raise Exception("eerstre")
+except Exception as e:
+    print ("voor tweede")
+    raise Exception("tweede")
+finally:
+    print ("JO")
+
+def generator():
+
+    try:
+        util.deb('in generator')
+        print ("TRIGGER SIGPIPE")
+        sys.stdout.flush()
+        util.deb('after trigger')
+
+        # if False:
+        yield ("bla")
+        # yield ("bla")
+
+    except GeneratorExit as e:
+        util.deb('GENEXIT '+str(e))
+        raise
+
+    except Exception as e:
+        util.deb('EXCEPT '+str(e))
+    finally:
+        util.deb('FINALLY')
+        print("nog iets")
+        sys.stdout.flush()
+        util.deb('after print in finally WOOP!')
+
+
+util.deb('START')
+g=generator()
+util.deb('after generator')
+for bla in g:
+    # print ("heb wat ontvangen")
+    util.deb('ontvangen van gen')
+    break
+    # raise Exception("moi")
+
+    pass
+raise Exception("moi")
+
+util.deb('after for')
+
+while True:
+    pass
+
+#
+# with open('test.py', 'rb') as fh:
+#
+#     # fsize = fh.seek(10000, os.SEEK_END)
+#     # print(fsize)
+#
+#     start=time.time()
+#     for i in range(0,1000000):
+#         # fh.seek(0, 0)
+#         fsize=fh.seek(0, os.SEEK_END)
+#         # fsize=fh.tell()
+#         # os.path.getsize('test.py')
+#     print(time.time()-start)
+#
+#
+#     print(fh.tell())
+#
+# sys.exit(0)
+#
+#
+#
+# checked=1
+# skipped=1
+# coverage=0.1
+#
+# max_skip=0
+#
+#
+# skipinarow=0
+# while True:
+#     total=checked+skipped
+#
+#     skip=coverage<random()
+#     if skip:
+#         skipped = skipped + 1
+#         print("S {:.2f}%".format(checked * 100 / total))
+#
+#         skipinarow = skipinarow+1
+#         if skipinarow>max_skip:
+#             max_skip=skipinarow
+#     else:
+#         skipinarow=0
+#         checked=checked+1
+#         print("C {:.2f}%".format(checked * 100 / total))
+#
+#     print(max_skip)
+#
+# skip=0
+# while True:
+#
+#     total=checked+skipped
+#     if skip>0:
+#         skip=skip-1
+#         skipped = skipped + 1
+#         print("S {:.2f}%".format(checked * 100 / total))
+#     else:
+#         checked=checked+1
+#         print("C {:.2f}%".format(checked * 100 / total))
+#
+#         #calc new skip
+#         skip=skip+((1/coverage)-1)*(random()*2)
+#         # print(skip)
+#         if skip> max_skip:
+#             max_skip=skip
+#
+#     print(max_skip)

zfs_autobackup/util.py

@@ -0,0 +1,65 @@
+# root@psyt14s:/home/psy/zfs_autobackup# ls -lh /home/psy/Downloads/carimage.zip
+# -rw-rw-r-- 1 psy psy 990M Nov 26  2020 /home/psy/Downloads/carimage.zip
+# root@psyt14s:/home/psy/zfs_autobackup# time sha1sum /home/psy/Downloads/carimage.zip
+# a682e1a36e16fe0d0c2f011104f4a99004f19105  /home/psy/Downloads/carimage.zip
+#
+# real	0m2.558s
+# user	0m2.105s
+# sys	0m0.448s
+# root@psyt14s:/home/psy/zfs_autobackup# time python3 -m zfs_autobackup.ZfsCheck
+#
+# real	0m1.459s
+# user	0m0.993s
+# sys	0m0.462s
+
+# NOTE: surprisingly sha1 in via python3 is faster than the native sha1sum utility, even in the way we use below!
+import os
+import platform
+import sys
+
+
+def tmp_name(suffix=""):
+    """create temporary name unique to this process and node. always retruns the same result during the same execution"""
+
+    #we could use uuids but those are ugly and confusing
+    name="{}-{}-{}".format(
+        os.path.basename(sys.argv[0]).replace(" ","_"),
+        platform.node(),
+        os.getpid())
+    name=name+suffix
+    return name
+
+
+def get_tmp_clone_name(snapshot):
+    pool=snapshot.zfs_node.get_pool(snapshot)
+    return pool.name+"/"+tmp_name()
+
+
+
+def output_redir():
+    """use this after a BrokenPipeError to prevent further exceptions.
+    Redirects stdout/err to /dev/null
+    """
+
+    devnull = os.open(os.devnull, os.O_WRONLY)
+    os.dup2(devnull, sys.stdout.fileno())
+    os.dup2(devnull, sys.stderr.fileno())
+
+def sigpipe_handler(sig, stack):
+    #redir output so we dont get more SIGPIPES during cleanup. (which my try to write to stdout)
+    output_redir()
+    deb('redir')
+
+# def check_output():
+#     """make sure stdout still functions. if its broken, this will trigger a SIGPIPE which will be handled by the sigpipe_handler."""
+#     try:
+#         print(" ")
+#         sys.stdout.flush()
+#     except Exception as e:
+#         pass
+
+# def deb(txt):
+#     with open('/tmp/debug.log', 'a') as fh:
+#         fh.write("DEB: "+txt+"\n")
+
+