ccfeeef59d
Backport the patches for this issue: https://bugzilla.redhat.com/show_bug.cgi?id=1819868 We met such an issue: When testing a large number of pods (> 230), occasionally observed a number of issues related to systemd process: systemd ran continually 90-100% cpu usage systemd memory usage started increasing rapidly (20GB/hour) systemctl commands would always timeout (Failed to get properties: Connection timed out) sm services failed and can't recover: open-ldap, registry-token-server, docker-distribution, etcd new pods can't start, and got stuck in state ContainerCreating Those patches work to prevent excessive /proc/1/mountinfo reparsing. It has been verified that those patches can improve this performance greatly. 16 commits are listed in sequence (from [1] to [16]) at below link for the issue: https://github.com/systemd-rhel/rhel-8/pull/154/commits [16](10)core: prevent excessive /proc/self/mountinfo parsing [15][Dropped-6]test: add ratelimiting test [14](9)sd-event: add ability to ratelimit event sources [13](8)sd-event: increase n_enabled_child_sources just once [12](7)sd-event: update state at the end in event_source_enable [11](6)sd-event: remove earliest_index/latest_index into common part of event source objects [10][Dropped-5]sd-event: follow coding style with naming return parameter [9] [Dropped-4]sd-event: ref event loop while in sd_event_prepare() ot sd_event_run() [8] (5)sd-event: refuse running default event loops in any other thread than the one they are default for [7] [Dropped-3]sd-event: let's suffix last_run/last_log with "_usec" [6] [Dropped-2]sd-event: fix delays assert brain-o (#17790) [5] (4)sd-event: split out code to add/remove timer event sources to earliest/latest prioq [4] (3)sd-event: split clock data allocation out of sd_event_add_time() [3] [Dropped-1]sd-event: mention that two debug logged events are ignored [2] (2)sd-event: split out enable and disable codepaths from sd_event_source_set_enabled() [1] (1)sd-event: split out helper functions for reshuffling prioqs I ported 10 of them back (from (1) to (10)) to fix this issue and dropped the other 6 (from [Dropped-1] to [Dropped-6]) for those reasons: [Dropped-1]Only changes error log. [Dropped-2]Fixes a bug introduced in a commit which doesn't exist in this version. [Dropped-3]Only changes vars' names and there is no functional change. [Dropped-4]More commits are needed for merging it, while I don't see any help on adding the rate-limiting ability. [Dropped-5]Change coding style for a function which isn't really used by anyone. [Dropped-6]Add test cases. Closes-Bug: #1924686 Signed-off-by: Li Zhou <li.zhou@windriver.com> Change-Id: Ia4c8f162cb1a47b40d1b26cf4d604976b97e92d6
80 lines
2.4 KiB
Diff
80 lines
2.4 KiB
Diff
From 77b772bce846db28dc447420fd380a51eadcde15 Mon Sep 17 00:00:00 2001
|
|
From: Lennart Poettering <lennart@poettering.net>
|
|
Date: Mon, 23 Nov 2020 11:40:24 +0100
|
|
Subject: [PATCH 09/20] sd-event: split clock data allocation out of
|
|
sd_event_add_time()
|
|
|
|
Just some simple refactoring, that will make things easier for us later.
|
|
But it looks better this way even without the later function reuse.
|
|
|
|
(cherry picked from commit 41c63f36c3352af8bebf03b6181f5d866431d0af)
|
|
|
|
Related: #1819868
|
|
|
|
[commit 6cc0022115afbac9ac66c456b140601d90271687 from
|
|
https://github.com/systemd-rhel/rhel-8/]
|
|
|
|
Signed-off-by: Li Zhou <li.zhou@windriver.com>
|
|
---
|
|
src/libsystemd/sd-event/sd-event.c | 34 ++++++++++++++++++++----------
|
|
1 file changed, 23 insertions(+), 11 deletions(-)
|
|
|
|
diff --git a/src/libsystemd/sd-event/sd-event.c b/src/libsystemd/sd-event/sd-event.c
|
|
index 7074520..8e6536f 100644
|
|
--- a/src/libsystemd/sd-event/sd-event.c
|
|
+++ b/src/libsystemd/sd-event/sd-event.c
|
|
@@ -1065,6 +1065,28 @@ static int time_exit_callback(sd_event_source *s, uint64_t usec, void *userdata)
|
|
return sd_event_exit(sd_event_source_get_event(s), PTR_TO_INT(userdata));
|
|
}
|
|
|
|
+static int setup_clock_data(sd_event *e, struct clock_data *d, clockid_t clock) {
|
|
+ int r;
|
|
+
|
|
+ assert(d);
|
|
+
|
|
+ if (d->fd < 0) {
|
|
+ r = event_setup_timer_fd(e, d, clock);
|
|
+ if (r < 0)
|
|
+ return r;
|
|
+ }
|
|
+
|
|
+ r = prioq_ensure_allocated(&d->earliest, earliest_time_prioq_compare);
|
|
+ if (r < 0)
|
|
+ return r;
|
|
+
|
|
+ r = prioq_ensure_allocated(&d->latest, latest_time_prioq_compare);
|
|
+ if (r < 0)
|
|
+ return r;
|
|
+
|
|
+ return 0;
|
|
+}
|
|
+
|
|
_public_ int sd_event_add_time(
|
|
sd_event *e,
|
|
sd_event_source **ret,
|
|
@@ -1094,20 +1116,10 @@ _public_ int sd_event_add_time(
|
|
d = event_get_clock_data(e, type);
|
|
assert(d);
|
|
|
|
- r = prioq_ensure_allocated(&d->earliest, earliest_time_prioq_compare);
|
|
- if (r < 0)
|
|
- return r;
|
|
-
|
|
- r = prioq_ensure_allocated(&d->latest, latest_time_prioq_compare);
|
|
+ r = setup_clock_data(e, d, clock);
|
|
if (r < 0)
|
|
return r;
|
|
|
|
- if (d->fd < 0) {
|
|
- r = event_setup_timer_fd(e, d, clock);
|
|
- if (r < 0)
|
|
- return r;
|
|
- }
|
|
-
|
|
s = source_new(e, !ret, type);
|
|
if (!s)
|
|
return -ENOMEM;
|
|
--
|
|
2.17.1
|
|
|