[pve-devel] [PATCH pve-guest-common v3 1/1] partial fix #2530: snapshots: add pre/post/failed-snapshot hooks

[Stefan Hanreich <s.hanreich@proxmox.com>]

This commit adds hooks to the snapshotting process, which can be used to
run additional setup scripts to prepare the VM for snapshotting.

Examples for use cases include:
- forcing processes to flush their writes
- blocking processes from writing
- altering the configuration of the VM to make snapshotting possible

The prepare step has been split into two parts, so the configuration can
be locked a bit earlier during the snapshotting process. Doing it this
way ensures that the configuration is already locked during the
pre-snapshot hook. Because of this split, the VM config gets written in
two stages now, rather than one.

In case of failure during the preparation step - after the lock is
written - error handling has been added so the lock gets released
properly. The failed-snapshot hook runs when the snapshot or a snapshot
hook fails, but only if the pre-snapshot hook ran already. This enables
users to revert any changes done during the pre-snapshot hookscript.

The preparation step assumes that the hook does not convert the current
VM into a template, which is why the basic checks are not re-run after
the pre-snapshot hook. The storage check runs after the pre-snapshot
hook, because the hook might get used to setup the storage for
snapshotting. If the hook would run after the storage checks, this
becomes impossible.

cfs_update() gets called after every invocation of a hookscript, since
it is impossible to know which changes get made by the hookscript.
Doing this ensures that we see the updated state of the CFS after the
hookscript got invoked.

Signed-off-by: Stefan Hanreich <s.hanreich@proxmox.com>
---
 src/PVE/AbstractConfig.pm | 76 +++++++++++++++++++++++++++++++++++----
 1 file changed, 70 insertions(+), 6 deletions(-)

diff --git a/src/PVE/AbstractConfig.pm b/src/PVE/AbstractConfig.pm
index a0c0bc6..9763c0c 100644
--- a/src/PVE/AbstractConfig.pm
+++ b/src/PVE/AbstractConfig.pm
@@ -704,14 +704,28 @@ sub __snapshot_apply_config {
     return $newconf;
 }
 
+sub __snapshot_failed {
+    my ($class, $vmid, $phase) = @_;
+
+    my $conf = $class->load_config($vmid);
+
+    return if !$conf->{hookscript};
+
+    {
+	local $ENV{'PVE_SNAPSHOT_PHASE'} = $phase;
+	PVE::GuestHelpers::exec_hookscript($conf, $vmid, "failed-snapshot");
+    }
+
+    PVE::Cluster::cfs_update();
+}
+
 # Prepares the configuration for snapshotting.
 sub __snapshot_prepare {
     my ($class, $vmid, $snapname, $save_vmstate, $comment) = @_;
 
     my $snap;
 
-    my $updatefn =  sub {
-
+    my $run_checks = sub {
 	my $conf = $class->load_config($vmid);
 
 	die "you can't take a snapshot if it's a template\n"
@@ -721,15 +735,21 @@ sub __snapshot_prepare {
 
 	$conf->{lock} = 'snapshot';
 
-	my $snapshots = $conf->{snapshots};
-
 	die "snapshot name '$snapname' already used\n"
-	    if defined($snapshots->{$snapname});
+	    if defined($conf->{snapshots}->{$snapname});
 
+	$class->write_config($vmid, $conf);
+    };
+
+    my $updatefn = sub {
+	my $conf = $class->load_config($vmid);
 	my $storecfg = PVE::Storage::config();
+
 	die "snapshot feature is not available\n"
 	    if !$class->has_feature('snapshot', $conf, $storecfg, undef, undef, $snapname eq 'vzdump');
 
+	my $snapshots = $conf->{snapshots};
+
 	for my $snap (sort keys %$snapshots) {
 	    my $parent_name = $snapshots->{$snap}->{parent} // '';
 	    if ($snapname eq $parent_name) {
@@ -753,7 +773,33 @@ sub __snapshot_prepare {
 	$class->write_config($vmid, $conf);
     };
 
-    $class->lock_config($vmid, $updatefn);
+    $class->lock_config($vmid, $run_checks);
+
+    my $conf = $class->load_config($vmid);
+
+    if ($conf->{hookscript}) {
+	eval {
+	    PVE::GuestHelpers::exec_hookscript($conf, $vmid, "pre-snapshot", 1);
+	};
+	my $err = $@;
+
+	PVE::Cluster::cfs_update();
+
+	if ($err) {
+	    $class->__snapshot_failed($vmid, 'pre-snapshot');
+	    $class->remove_lock($vmid, 'snapshot');
+	    die $err;
+	}
+    }
+
+    eval {
+	$class->lock_config($vmid, $updatefn);
+    };
+    if (my $err = $@) {
+	$class->__snapshot_failed($vmid, 'prepare');
+	$class->remove_lock($vmid, 'snapshot');
+	die $err;
+    }
 
     return $snap;
 }
@@ -837,11 +883,29 @@ sub snapshot_create {
 
     if ($err) {
 	warn "snapshot create failed: starting cleanup\n";
+
 	eval { $class->snapshot_delete($vmid, $snapname, 1, $drivehash); };
 	warn "$@" if $@;
+
+	$class->__snapshot_failed($vmid, 'snapshot');
+
 	die "$err\n";
     }
 
+    if ($conf->{hookscript}) {
+	eval {
+	    PVE::GuestHelpers::exec_hookscript($conf, $vmid, "post-snapshot", 1);
+	};
+	$err = $@;
+
+	PVE::Cluster::cfs_update();
+
+	if ($err) {
+	    warn $err;
+	    $class->__snapshot_failed($vmid, 'post-snapshot');
+	}
+    }
+
     $class->__snapshot_commit($vmid, $snapname);
 }
 
-- 
2.30.2