40 lines
1.4 KiB
Diff
40 lines
1.4 KiB
Diff
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
|
|
From: Stefan Reiter <s.reiter@proxmox.com>
|
|
Date: Mon, 4 Jan 2021 14:49:14 +0100
|
|
Subject: [PATCH] PVE: fix aborting multiple 'CREATED' jobs in sequential
|
|
transaction
|
|
|
|
Deadlocks could occur in the AIO_WAIT_WHILE loop in job_finish_sync,
|
|
which would wait for CREATED but not running jobs to complete, even
|
|
though job_enter is a no-op in that scenario. Mark offending jobs as
|
|
ABORTING immediately via job_update_rc if required.
|
|
|
|
Manifested itself in cancelling or failing backups with more than 2
|
|
drives.
|
|
|
|
Signed-off-by: Stefan Reiter <s.reiter@proxmox.com>
|
|
Tested-by: Mira Limbeck <m.limbeck@proxmox.com>
|
|
Signed-off-by: Wolfgang Bumiller <w.bumiller@proxmox.com>
|
|
---
|
|
job.c | 7 +++++++
|
|
1 file changed, 7 insertions(+)
|
|
|
|
diff --git a/job.c b/job.c
|
|
index 8f06e05fbf..05b7797e82 100644
|
|
--- a/job.c
|
|
+++ b/job.c
|
|
@@ -1035,6 +1035,13 @@ int job_finish_sync(Job *job, void (*finish)(Job *, Error **errp), Error **errp)
|
|
return -EBUSY;
|
|
}
|
|
|
|
+ /* in a sequential transaction jobs with status CREATED can appear at time
|
|
+ * of cancelling, these have not begun work so job_enter won't do anything,
|
|
+ * let's ensure they are marked as ABORTING if required */
|
|
+ if (job->status == JOB_STATUS_CREATED && job->txn->sequential) {
|
|
+ job_update_rc(job);
|
|
+ }
|
|
+
|
|
AIO_WAIT_WHILE(job->aio_context,
|
|
(job_enter(job), !job_is_completed(job)));
|
|
|