46 lines
2.2 KiB
Diff
46 lines
2.2 KiB
Diff
From 1656ad6fd17e5be6504785bf94495437bcf453cb Mon Sep 17 00:00:00 2001
|
|
From: Anita Zhang <the.anitazha@gmail.com>
|
|
Date: Wed, 19 Jan 2022 10:40:46 -0800
|
|
Subject: [PATCH] oomd: fix race with path unavailability when killing cgroups
|
|
|
|
There can be a situation where systemd-oomd would kill all of the processes
|
|
in a cgroup, pid1 would clean up that cgroup, and systemd-oomd would get
|
|
ENODEV trying to iterate the cgroup a final time to ensure it was empty.
|
|
systemd-oomd sees this as an error and immediately picks a new candidate even
|
|
though pressure may have recovered. To counter this, check and handle
|
|
path unavailability errnos specially.
|
|
|
|
Fixes: #22030
|
|
(cherry picked from commit 2ee209466bb51f39ae9df7fec4d5594ce8cfa3f0)
|
|
(cherry picked from commit 0456e3aaaae7c21a037f4d3c758463c3ba4d167c)
|
|
|
|
Conflict:NA
|
|
Reference:https://github.com/systemd/systemd/commit/1656ad6fd17e5be6504785bf94495437bcf453cb
|
|
---
|
|
src/oom/oomd-util.c | 9 ++++++++-
|
|
1 file changed, 8 insertions(+), 1 deletion(-)
|
|
|
|
diff --git a/src/oom/oomd-util.c b/src/oom/oomd-util.c
|
|
index b2a48acb1f..503ede9a9f 100644
|
|
--- a/src/oom/oomd-util.c
|
|
+++ b/src/oom/oomd-util.c
|
|
@@ -196,7 +196,14 @@ int oomd_cgroup_kill(const char *path, bool recurse, bool dry_run) {
|
|
r = cg_kill_recursive(SYSTEMD_CGROUP_CONTROLLER, path, SIGKILL, CGROUP_IGNORE_SELF, pids_killed, log_kill, NULL);
|
|
else
|
|
r = cg_kill(SYSTEMD_CGROUP_CONTROLLER, path, SIGKILL, CGROUP_IGNORE_SELF, pids_killed, log_kill, NULL);
|
|
- if (r < 0)
|
|
+
|
|
+ /* The cgroup could have been cleaned up after we have sent SIGKILL to all of the processes, but before
|
|
+ * we could do one last iteration of cgroup.procs to check. Or the service unit could have exited and
|
|
+ * was removed between picking candidates and coming into this function. In either case, let's log
|
|
+ * about it let the caller decide what to do once they know how many PIDs were killed. */
|
|
+ if (IN_SET(r, -ENOENT, -ENODEV))
|
|
+ log_debug_errno(r, "Error when sending SIGKILL to processes in cgroup path %s, ignoring: %m", path);
|
|
+ else if (r < 0)
|
|
return r;
|
|
|
|
r = increment_oomd_xattr(path, "user.oomd_kill", set_size(pids_killed));
|
|
--
|
|
2.33.0
|
|
|