Merge branch 'master' of github.com:psy0rz/zfs_autobackup

usefull -> useful

README.md

@@ -84,7 +84,7 @@ On older servers you might have to use easy_install
 
 Its also possible to just download <https://raw.githubusercontent.com/psy0rz/zfs_autobackup/master/bin/zfs-autobackup> and run it directly.
 
-The only requirement that is sometimes missing is the `argparse` python module. Optionally you can install `colorma` for colors.
+The only requirement that is sometimes missing is the `argparse` python module. Optionally you can install `colorama` for colors.
 
 It should work with python 2.7 and higher.
 
@@ -324,7 +324,7 @@ Snapshots on the source that still have to be send to the target wont be destroy
 ## Tips
 
 * Use ```--debug``` if something goes wrong and you want to see the commands that are executed. This will also stop at the first error.
-* You can split up the snapshotting and sending tasks by creating two cronjobs. Use ```--no-send``` for the snapshotter-cronjob and use ```--no-snapshot``` for the send-cronjob. This is usefull if you only want to send at night or if your send take too long.
+* You can split up the snapshotting and sending tasks by creating two cronjobs. Use ```--no-send``` for the snapshotter-cronjob and use ```--no-snapshot``` for the send-cronjob. This is useful if you only want to send at night or if your send take too long.
 * Set the ```readonly``` property of the target filesystem to ```on```. This prevents changes on the target side. (Normally, if there are changes the next backup will fail and will require a zfs rollback.) Note that readonly means you cant change the CONTENTS of the dataset directly. Its still possible to receive new datasets and manipulate properties etc.
 * 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.
@@ -409,9 +409,9 @@ optional arguments:
                         10,1d1w,1w1m,1m1y
   --other-snapshots     Send over other snapshots as well, not just the ones
                         created by this tool.
-  --no-snapshot         Dont create new snapshots (usefull for finishing
+  --no-snapshot         Dont create new snapshots (useful for finishing
                         uncompleted backups, or cleanups)
-  --no-send             Dont send snapshots (usefull for cleanups, or if you
+  --no-send             Dont send snapshots (useful for cleanups, or if you
                         want a separate send-cronjob)
   --min-change MIN_CHANGE
                         Number of bytes written after which we consider a
@@ -419,9 +419,9 @@ optional arguments:
   --allow-empty         If nothing has changed, still create empty snapshots.
                         (same as --min-change=0)
   --ignore-replicated   Ignore datasets that seem to be replicated some other
-                        way. (No changes since lastest snapshot. Usefull for
+                        way. (No changes since lastest snapshot. Useful for
                         proxmox HA replication)
-  --no-holds            Dont lock snapshots on the source. (Usefull to allow
+  --no-holds            Dont lock snapshots on the source. (Useful to allow
                         proxmox HA replication to switches nodes)
   --resume              Support resuming of interrupted transfers by using the
                         zfs extensible_dataset feature (both zpools should
@@ -454,7 +454,7 @@ optional arguments:
                         care! (implies --rollback)
   --ignore-transfer-errors
                         Ignore transfer errors (still checks if received
-                        filesystem exists. usefull for acltype errors)
+                        filesystem exists. useful 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

bin/zfs-autobackup

@@ -26,7 +26,7 @@ if sys.stdout.isatty():
     except ImportError:
         pass
 
-VERSION="3.0-rc9"
+VERSION="3.0-rc10"
 HEADER="zfs-autobackup v{} - Copyright 2020 E.H.Eefting (edwin@datux.nl)\n".format(VERSION)
 
 class Log:
@@ -40,6 +40,7 @@ class Log:
             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 verbose(self, txt):
         if self.show_verbose:
@@ -47,6 +48,7 @@ class Log:
                 print(colorama.Style.NORMAL+ "  "+txt+colorama.Style.RESET_ALL)
             else:
                 print("  "+txt)
+            sys.stdout.flush()
 
     def debug(self, txt):
         if self.show_debug:
@@ -54,6 +56,7 @@ class Log:
                 print(colorama.Fore.GREEN+ "# "+txt+colorama.Style.RESET_ALL)
             else:
                 print("# "+txt)
+            sys.stdout.flush()
 
 
 
@@ -308,7 +311,7 @@ class ExecuteNode:
     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 (usefull for testing-runs)
+           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.
         """
 
@@ -622,7 +625,7 @@ class ZfsDataset():
     @cached_property
     def exists(self):
         """check if dataset exists.
-        Use force to force a specific value to be cached, if you already know. Usefull for performance reasons"""
+        Use force to force a specific value to be cached, if you already know. Useful for performance reasons"""
 
 
         if self.force_exists!=None:
@@ -1024,9 +1027,7 @@ class ZfsDataset():
         return(None)
 
 
-
-
-    def thin(self, keeps=[], ignores=[]):
+    def thin_list(self, keeps=[], ignores=[]):
         """determines list of snapshots that should be kept or deleted based on the thinning schedule. cull the herd!
         keep: list of snapshots to always keep (usually the last)
         ignores: snapshots to completely ignore (usually incompatible target snapshots that are going to be destroyed anyway)
@@ -1039,6 +1040,15 @@ class ZfsDataset():
         return(self.zfs_node.thinner.thin(snapshots, keep_objects=keeps))
 
 
+    def thin(self):
+        """destroys snapshots according to thin_list, except last snapshot"""
+
+        (keeps, obsoletes)=self.thin_list(keeps=self.our_snapshots[-1:])
+        for obsolete in obsoletes:
+            obsolete.destroy()
+            self.snapshots.remove(obsolete)
+
+
     def find_common_snapshot(self, target_dataset):
         """find latest common snapshot between us and target
         returns None if its an initial transfer
@@ -1137,13 +1147,13 @@ class ZfsDataset():
         #now let thinner decide what we want on both sides as final state (after all transfers are done)
         self.debug("Create thinning list")
         if self.our_snapshots:
-            (source_keeps, source_obsoletes)=self.thin(keeps=[self.our_snapshots[-1]])
+            (source_keeps, source_obsoletes)=self.thin_list(keeps=[self.our_snapshots[-1]])
         else:
             source_keeps=[]
             source_obsoletes=[]
 
         if target_dataset.our_snapshots:
-            (target_keeps, target_obsoletes)=target_dataset.thin(keeps=[target_dataset.our_snapshots[-1]], ignores=incompatible_target_snapshots)
+            (target_keeps, target_obsoletes)=target_dataset.thin_list(keeps=[target_dataset.our_snapshots[-1]], ignores=incompatible_target_snapshots)
         else:
             target_keeps=[]
             target_obsoletes=[]
@@ -1226,10 +1236,10 @@ class ZfsDataset():
 
                 # we may now destroy the previous source snapshot if its obsolete
                 if prev_source_snapshot in source_obsoletes:
-                    prev_source_snapshot.destroy()
+                    prev_source_snapshot.destroy()                    
 
                 # destroy the previous target snapshot if obsolete (usually this is only the common_snapshot, the rest was already destroyed or will not be send)
-                prev_target_snapshot=target_dataset.find_snapshot(common_snapshot)
+                prev_target_snapshot=target_dataset.find_snapshot(prev_source_snapshot)
                 if prev_target_snapshot in target_obsoletes:
                     prev_target_snapshot.destroy()
 
@@ -1302,7 +1312,7 @@ class ZfsNode(ExecuteNode):
                 #always output for debugging offcourse
                 self.debug(prefix+line.rstrip())
 
-                #actual usefull info
+                #actual useful info
                 if len(progress_fields)>=3:
                     if progress_fields[0]=='full' or progress_fields[0]=='size':
                         self._progress_total_bytes=int(progress_fields[2])
@@ -1317,8 +1327,8 @@ class ZfsNode(ExecuteNode):
                             bytes_left=self._progress_total_bytes-bytes
                             minutes_left=int((bytes_left/(bytes/(time.time()-self._progress_start_time)))/60)
 
-                            print(">>> {}% {}MB/s (total {}MB, {} minutes left)  \r".format(percentage, speed, int(self._progress_total_bytes/(1024*1024)), minutes_left), end='')
-                            sys.stdout.flush()
+                            print(">>> {}% {}MB/s (total {}MB, {} minutes left)     \r".format(percentage, speed, int(self._progress_total_bytes/(1024*1024)), minutes_left), end='', file=sys.stderr)
+                            sys.stderr.flush()
 
                 return
 
@@ -1370,7 +1380,7 @@ class ZfsNode(ExecuteNode):
 
             pools[pool].append(snapshot)
 
-            #add snapshot to cache (also usefull in testmode)
+            #add snapshot to cache (also useful in testmode)
             dataset.snapshots.append(snapshot) #NOTE: this will trigger zfs list
 
         if not pools:
@@ -1394,6 +1404,9 @@ class ZfsNode(ExecuteNode):
 
            returns: list of 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", "-s", "local,inherited", "-H", "autobackup:"+self.backup_name
@@ -1429,11 +1442,6 @@ class ZfsNode(ExecuteNode):
         return(selected_filesystems)
 
 
-
-
-
-
-
 class ZfsAutobackup:
     """main class"""
     def __init__(self):
@@ -1451,13 +1459,13 @@ class ZfsAutobackup:
         parser.add_argument('target_path',    help='Target ZFS filesystem')
 
         parser.add_argument('--other-snapshots', action='store_true', help='Send over other snapshots as well, not just the ones created by this tool.')
-        parser.add_argument('--no-snapshot', action='store_true', help='Don\'t create new snapshots (usefull for finishing uncompleted backups, or cleanups)')
-        parser.add_argument('--no-send', action='store_true', help='Don\'t send snapshots (usefull for cleanups, or if you want a serperate send-cronjob)')
+        parser.add_argument('--no-snapshot', action='store_true', help='Don\'t create new snapshots (useful for finishing uncompleted backups, or cleanups)')
+        parser.add_argument('--no-send', action='store_true', help='Don\'t send snapshots (useful for cleanups, or if you want a serperate send-cronjob)')
         parser.add_argument('--min-change', type=int, default=1, help='Number of bytes written after which we consider a dataset changed (default %(default)s)')
         parser.add_argument('--allow-empty', action='store_true', help='If nothing has changed, still create empty snapshots. (same as --min-change=0)')
-        parser.add_argument('--ignore-replicated', action='store_true',  help='Ignore datasets that seem to be replicated some other way. (No changes since lastest snapshot. Usefull for proxmox HA replication)')
-        parser.add_argument('--no-holds', action='store_true',  help='Don\'t lock snapshots on the source. (Usefull to allow proxmox HA replication to switches nodes)')
-        #not sure if this ever was usefull:
+        parser.add_argument('--ignore-replicated', action='store_true',  help='Ignore datasets that seem to be replicated some other way. (No changes since lastest snapshot. Useful for proxmox HA replication)')
+        parser.add_argument('--no-holds', action='store_true',  help='Don\'t lock snapshots on the source. (Useful to allow proxmox HA replication to switches nodes)')
+        #not sure if this ever was useful:
         # parser.add_argument('--ignore-new', action='store_true',  help='Ignore filesystem if there are already newer snapshots for it on the target (use with caution)')
 
         parser.add_argument('--resume', action='store_true', help='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.')
@@ -1472,7 +1480,7 @@ class ZfsAutobackup:
         parser.add_argument('--set-properties', type=str, help='List of propererties to override when receiving filesystems. (you can still restore them with zfs inherit -S)')
         parser.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)')
         parser.add_argument('--destroy-incompatible', action='store_true', help='Destroy incompatible snapshots on target. Use with care! (implies --rollback)')
-        parser.add_argument('--ignore-transfer-errors', action='store_true', help='Ignore transfer errors (still checks if received filesystem exists. usefull for acltype errors)')
+        parser.add_argument('--ignore-transfer-errors', action='store_true', help='Ignore transfer errors (still checks if received filesystem exists. useful for acltype errors)')
         parser.add_argument('--raw', action='store_true', help='For encrypted datasets, send data exactly as it exists on disk.')
 
 
@@ -1480,13 +1488,16 @@ class ZfsAutobackup:
         parser.add_argument('--verbose', action='store_true', help='verbose output')
         parser.add_argument('--debug', action='store_true', help='Show zfs commands that are executed, stops after an exception.')
         parser.add_argument('--debug-output', action='store_true', help='Show zfs commands and their output/exit codes. (noisy)')
-        parser.add_argument('--progress', action='store_true', help='show zfs progress output (to stderr)')
+        parser.add_argument('--progress', action='store_true', help='show zfs progress output (to stderr). Enabled by default on ttys.')
 
         #note args is the only global variable we use, since its a global readonly setting anyway
         args = parser.parse_args()
 
         self.args=args
 
+        if sys.stderr.isatty():
+            args.progress=True
+       
         if args.debug_output:
             args.debug=True
 
@@ -1517,105 +1528,126 @@ class ZfsAutobackup:
 
     def run(self):
 
-        self.verbose (HEADER)
+        try:
+            self.verbose (HEADER)
 
-        if self.args.test:
-            self.verbose("TEST MODE - SIMULATING WITHOUT MAKING ANY CHANGES")
+            if self.args.test:
+                self.verbose("TEST MODE - SIMULATING WITHOUT MAKING ANY CHANGES")
 
-        self.set_title("Settings summary")
+            self.set_title("Settings summary")
 
-        description="[Source]"
-        source_thinner=Thinner(self.args.keep_source)
-        source_node=ZfsNode(self.args.backup_name, 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)
-        source_node.verbose("Send all datasets that have 'autobackup:{}=true' or 'autobackup:{}=child'".format(self.args.backup_name, self.args.backup_name))
+            description="[Source]"
+            source_thinner=Thinner(self.args.keep_source)
+            source_node=ZfsNode(self.args.backup_name, 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)
+            source_node.verbose("Send all datasets that have 'autobackup:{}=true' or 'autobackup:{}=child'".format(self.args.backup_name, self.args.backup_name))
 
-        self.verbose("")
+            self.verbose("")
 
-        description="[Target]"
-        target_thinner=Thinner(self.args.keep_target)
-        target_node=ZfsNode(self.args.backup_name, self, ssh_config=self.args.ssh_config, ssh_to=self.args.ssh_target, readonly=self.args.test, debug_output=self.args.debug_output, description=description, thinner=target_thinner)
-        target_node.verbose("Receive datasets under: {}".format(self.args.target_path))
+            description="[Target]"
+            target_thinner=Thinner(self.args.keep_target)
+            target_node=ZfsNode(self.args.backup_name, self, ssh_config=self.args.ssh_config, ssh_to=self.args.ssh_target, readonly=self.args.test, debug_output=self.args.debug_output, description=description, thinner=target_thinner)
+            target_node.verbose("Receive datasets under: {}".format(self.args.target_path))
 
-        self.set_title("Selecting")
-        selected_source_datasets=source_node.selected_datasets
-        if not selected_source_datasets:
-            self.error("No source filesystems selected, please do a 'zfs set autobackup:{0}=true' on the source datasets you want to backup.".format(self.args.backup_name))
+
+            self.set_title("Selecting")
+            selected_source_datasets=source_node.selected_datasets
+            if not selected_source_datasets:
+                self.error("No source filesystems selected, please do a 'zfs set autobackup:{0}=true' on the source datasets you want to backup.".format(self.args.backup_name))
+                return(255)
+
+            source_datasets=[]
+
+
+            #filter out already replicated stuff?
+            if not self.args.ignore_replicated:
+                source_datasets=selected_source_datasets
+            else:
+                self.set_title("Filtering already replicated filesystems")
+                for selected_source_dataset in selected_source_datasets:
+                    if selected_source_dataset.is_changed(self.args.min_change):
+                        source_datasets.append(selected_source_dataset)
+                    else:
+                        selected_source_dataset.verbose("Ignoring, already replicated")
+
+
+            if not self.args.no_snapshot:
+                self.set_title("Snapshotting")
+                source_node.consistent_snapshot(source_datasets, source_node.new_snapshotname(), min_changed_bytes=self.args.min_change)
+
+
+            if self.args.no_send:        
+                self.set_title("Thinning")
+            else:
+                self.set_title("Sending and thinning")
+
+            if self.args.filter_properties:
+                filter_properties=self.args.filter_properties.split(",")
+            else:
+                filter_properties=[]
+
+            if self.args.set_properties:
+                set_properties=self.args.set_properties.split(",")
+            else:
+                set_properties=[]
+
+            if self.args.clear_refreservation:
+                filter_properties.append("refreservation")
+
+            if self.args.clear_mountpoint:
+                set_properties.append("canmount=noauto")
+
+            #sync datasets
+            fail_count=0
+            target_datasets=[]
+            for source_dataset in source_datasets:
+
+                try:
+                    #determine corresponding target_dataset
+                    target_name=self.args.target_path + "/" + source_dataset.lstrip_path(self.args.strip_path)
+                    target_dataset=ZfsDataset(target_node, target_name)
+                    target_datasets.append(target_dataset)
+
+                    #ensure parents exists
+                    if not self.args.no_send and not target_dataset.parent.exists:
+                        target_dataset.parent.create_filesystem(parents=True)
+
+                    source_dataset.sync_snapshots(target_dataset, show_progress=self.args.progress, resume=self.args.resume, filter_properties=filter_properties, set_properties=set_properties, ignore_recv_exit_code=self.args.ignore_transfer_errors, source_holds= not self.args.no_holds, rollback=self.args.rollback, raw=self.args.raw, other_snapshots=self.args.other_snapshots, no_send=self.args.no_send, destroy_incompatible=self.args.destroy_incompatible)
+                except Exception as e:
+                    fail_count=fail_count+1
+                    self.error("DATASET FAILED: "+str(e))
+                    if self.args.debug:
+                        raise
+
+            #also thin target_datasets that are not on the source any more
+            self.debug("Thinning obsolete datasets")
+            for dataset in ZfsDataset(target_node, self.args.target_path).recursive_datasets:
+                if dataset not in target_datasets:
+                    dataset.verbose("Missing on source")
+                    dataset.thin()
+
+
+            if not fail_count:
+                if self.args.test:
+                    self.set_title("All tests successfull.")
+                else:
+                    self.set_title("All backups completed successfully")
+            else:
+                self.error("{} datasets failed!".format(fail_count))
+
+            if self.args.test:
+                self.verbose("TEST MODE - DID NOT MAKE ANY BACKUPS!")
+
+            return(fail_count)
+
+        except Exception as e:
+            self.error("Exception: "+str(e))
+            if self.args.debug:
+                raise
+            return(255)
+        except KeyboardInterrupt as e:
+            self.error("Aborted")
             return(255)
 
-        source_datasets=[]
-
-        #filter out already replicated stuff?
-        if not self.args.ignore_replicated:
-            source_datasets=selected_source_datasets
-        else:
-            self.set_title("Filtering already replicated filesystems")
-            for selected_source_dataset in selected_source_datasets:
-                if selected_source_dataset.is_changed(self.args.min_change):
-                    source_datasets.append(selected_source_dataset)
-                else:
-                    selected_source_dataset.verbose("Ignoring, already replicated")
-
-
-        if not self.args.no_snapshot:
-            self.set_title("Snapshotting")
-            source_node.consistent_snapshot(source_datasets, source_node.new_snapshotname(), min_changed_bytes=self.args.min_change)
-
-
-
-        if self.args.no_send:        
-            self.set_title("Thinning")
-        else:
-            self.set_title("Sending and thinning")
-
-        if self.args.filter_properties:
-            filter_properties=self.args.filter_properties.split(",")
-        else:
-            filter_properties=[]
-
-        if self.args.set_properties:
-            set_properties=self.args.set_properties.split(",")
-        else:
-            set_properties=[]
-
-        if self.args.clear_refreservation:
-            filter_properties.append("refreservation")
-
-        if self.args.clear_mountpoint:
-            set_properties.append("canmount=noauto")
-
-        fail_count=0
-        for source_dataset in source_datasets:
-
-            try:
-                #determine corresponding target_dataset
-                target_name=self.args.target_path + "/" + source_dataset.lstrip_path(self.args.strip_path)
-                target_dataset=ZfsDataset(target_node, target_name)
-
-                #ensure parents exists
-                if not self.args.no_send and not target_dataset.parent.exists:
-                    target_dataset.parent.create_filesystem(parents=True)
-
-                source_dataset.sync_snapshots(target_dataset, show_progress=self.args.progress, resume=self.args.resume, filter_properties=filter_properties, set_properties=set_properties, ignore_recv_exit_code=self.args.ignore_transfer_errors, source_holds= not self.args.no_holds, rollback=self.args.rollback, raw=self.args.raw, other_snapshots=self.args.other_snapshots, no_send=self.args.no_send, destroy_incompatible=self.args.destroy_incompatible)
-            except Exception as e:
-                fail_count=fail_count+1
-                self.error("DATASET FAILED: "+str(e))
-                if self.args.debug:
-                    raise
-
-
-
-        if not fail_count:
-            if self.args.test:
-                self.set_title("All tests successfull.")
-            else:
-                self.set_title("All backups completed successfully")
-        else:
-            self.error("{} datasets failed!".format(fail_count))
-
-        if self.args.test:
-            self.verbose("TEST MODE - DID NOT MAKE ANY BACKUPS!")
-
-        return(fail_count)
 
 if __name__ == "__main__":
     zfs_autobackup=ZfsAutobackup()