From caded41823c820f43a46f329c7e40d3780e8a38a Mon Sep 17 00:00:00 2001 From: Fiona Ebner Date: Thu, 11 Apr 2024 13:16:03 +0200 Subject: [PATCH] blockjob: anticipate jobs with auto-dismiss=false for better error messages and detection When auto-dismiss=true (the default), a failed job can disappear very quickly from the job list and there might not be any chance to see the error in the result of 'query-block-jobs'. For jobs with $completion being 'auto', like 'block-stream', it couldn't even be detected that the job failed. Jobs with auto-dismiss=false on the other hand, will wait in 'concluded' state until manually dismissed. For those, it will be possible to query the error if the job failed. There doesn't seem to be a way to have only failed jobs stay around, e.g. something like auto-dismiss=on-success. Planned to be used for the 'drive-mirror' and 'block-stream' jobs initially. Signed-off-by: Fiona Ebner --- PVE/QemuServer.pm | 24 +++++++++++++++++++++++- 1 file changed, 23 insertions(+), 1 deletion(-) diff --git a/PVE/QemuServer.pm b/PVE/QemuServer.pm index 1d1b211d..f8972146 100644 --- a/PVE/QemuServer.pm +++ b/PVE/QemuServer.pm @@ -8019,6 +8019,9 @@ sub qemu_drive_mirror_monitor { die "$job_id: '$op' has been cancelled\n" if !defined($job); + qemu_handle_concluded_blockjob($vmid, $job_id, $job) + if $job && $job->{status} eq 'concluded'; + my $busy = $job->{busy}; my $ready = $job->{ready}; if (my $total = $job->{len}) { @@ -8119,6 +8122,19 @@ sub qemu_drive_mirror_monitor { } } +# If the job was started with auto-dismiss=false, it's necessary to dismiss it manually. Using this +# option is useful to get the error for failed jobs here. QEMU's job lock should make it impossible +# to see a job in 'concluded' state when auto-dismiss=true. +# $info is the 'BlockJobInfo' for the job returned by query-block-jobs. +sub qemu_handle_concluded_blockjob { + my ($vmid, $job_id, $info) = @_; + + eval { mon_cmd($vmid, 'job-dismiss', id => $job_id); }; + log_warn("$job_id: failed to dismiss job - $@") if $@; + + die "$job_id: $info->{error} (io-status: $info->{'io-status'})\n" if $info->{error}; +} + sub qemu_blockjobs_cancel { my ($vmid, $jobs) = @_; @@ -8137,8 +8153,14 @@ sub qemu_blockjobs_cancel { } foreach my $job (keys %$jobs) { + my $info = $running_jobs->{$job}; + eval { + qemu_handle_concluded_blockjob($vmid, $job, $info) + if $info && $info->{status} eq 'concluded'; + }; + log_warn($@) if $@; # only warn and proceed with canceling other jobs - if (defined($jobs->{$job}->{cancel}) && !defined($running_jobs->{$job})) { + if (defined($jobs->{$job}->{cancel}) && !defined($info)) { print "$job: Done.\n"; delete $jobs->{$job}; }