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
126 lines
4.0 KiB
Diff
126 lines
4.0 KiB
Diff
From ad89da1e00919c510596dac78741c98052b1e2f7 Mon Sep 17 00:00:00 2001
|
|
From: =?UTF-8?q?Zbigniew=20J=C4=99drzejewski-Szmek?= <zbyszek@in.waw.pl>
|
|
Date: Tue, 10 Nov 2020 10:38:37 +0100
|
|
Subject: [PATCH 14/20] sd-event: update state at the end in
|
|
event_source_enable
|
|
|
|
Coverity in CID#1435966 was complaining that s->enabled is not "restored" in
|
|
all cases. But the code was actually correct, since it should only be
|
|
"restored" in the error paths. But let's still make this prettier by not setting
|
|
the state before all operations that may fail are done.
|
|
|
|
We need to set .enabled for the prioq reshuffling operations, so move those down.
|
|
|
|
No functional change intended.
|
|
|
|
(cherry picked from commit d2eafe61ca07f8300dc741a0491a914213fa2b6b)
|
|
|
|
Related: #1819868
|
|
|
|
[commit deb9e6ad3a1d7cfbc3b53d1e74cda6ae398a90fd from
|
|
https://github.com/systemd-rhel/rhel-8/]
|
|
|
|
Signed-off-by: Li Zhou <li.zhou@windriver.com>
|
|
---
|
|
src/libsystemd/sd-event/sd-event.c | 51 +++++++++++++++++-------------
|
|
1 file changed, 29 insertions(+), 22 deletions(-)
|
|
|
|
diff --git a/src/libsystemd/sd-event/sd-event.c b/src/libsystemd/sd-event/sd-event.c
|
|
index 82cb9ad..3ff15a2 100644
|
|
--- a/src/libsystemd/sd-event/sd-event.c
|
|
+++ b/src/libsystemd/sd-event/sd-event.c
|
|
@@ -1691,11 +1691,11 @@ static int event_source_disable(sd_event_source *s) {
|
|
return 0;
|
|
}
|
|
|
|
-static int event_source_enable(sd_event_source *s, int m) {
|
|
+static int event_source_enable(sd_event_source *s, int enable) {
|
|
int r;
|
|
|
|
assert(s);
|
|
- assert(IN_SET(m, SD_EVENT_ON, SD_EVENT_ONESHOT));
|
|
+ assert(IN_SET(enable, SD_EVENT_ON, SD_EVENT_ONESHOT));
|
|
assert(s->enabled == SD_EVENT_OFF);
|
|
|
|
/* Unset the pending flag when this event source is enabled */
|
|
@@ -1705,31 +1705,16 @@ static int event_source_enable(sd_event_source *s, int m) {
|
|
return r;
|
|
}
|
|
|
|
- s->enabled = m;
|
|
-
|
|
switch (s->type) {
|
|
-
|
|
case SOURCE_IO:
|
|
- r = source_io_register(s, m, s->io.events);
|
|
- if (r < 0) {
|
|
- s->enabled = SD_EVENT_OFF;
|
|
+ r = source_io_register(s, enable, s->io.events);
|
|
+ if (r < 0)
|
|
return r;
|
|
- }
|
|
-
|
|
- break;
|
|
-
|
|
- case SOURCE_TIME_REALTIME:
|
|
- case SOURCE_TIME_BOOTTIME:
|
|
- case SOURCE_TIME_MONOTONIC:
|
|
- case SOURCE_TIME_REALTIME_ALARM:
|
|
- case SOURCE_TIME_BOOTTIME_ALARM:
|
|
- event_source_time_prioq_reshuffle(s);
|
|
break;
|
|
|
|
case SOURCE_SIGNAL:
|
|
r = event_make_signal_data(s->event, s->signal.sig, NULL);
|
|
if (r < 0) {
|
|
- s->enabled = SD_EVENT_OFF;
|
|
event_gc_signal_data(s->event, &s->priority, s->signal.sig);
|
|
return r;
|
|
}
|
|
@@ -1750,10 +1735,12 @@ static int event_source_enable(sd_event_source *s, int m) {
|
|
|
|
break;
|
|
|
|
+ case SOURCE_TIME_REALTIME:
|
|
+ case SOURCE_TIME_BOOTTIME:
|
|
+ case SOURCE_TIME_MONOTONIC:
|
|
+ case SOURCE_TIME_REALTIME_ALARM:
|
|
+ case SOURCE_TIME_BOOTTIME_ALARM:
|
|
case SOURCE_EXIT:
|
|
- prioq_reshuffle(s->event->exit, s, &s->exit.prioq_index);
|
|
- break;
|
|
-
|
|
case SOURCE_DEFER:
|
|
case SOURCE_POST:
|
|
break;
|
|
@@ -1762,6 +1749,26 @@ static int event_source_enable(sd_event_source *s, int m) {
|
|
assert_not_reached("Wut? I shouldn't exist.");
|
|
}
|
|
|
|
+ s->enabled = enable;
|
|
+
|
|
+ /* Non-failing operations below */
|
|
+ switch (s->type) {
|
|
+ case SOURCE_TIME_REALTIME:
|
|
+ case SOURCE_TIME_BOOTTIME:
|
|
+ case SOURCE_TIME_MONOTONIC:
|
|
+ case SOURCE_TIME_REALTIME_ALARM:
|
|
+ case SOURCE_TIME_BOOTTIME_ALARM:
|
|
+ event_source_time_prioq_reshuffle(s);
|
|
+ break;
|
|
+
|
|
+ case SOURCE_EXIT:
|
|
+ prioq_reshuffle(s->event->exit, s, &s->exit.prioq_index);
|
|
+ break;
|
|
+
|
|
+ default:
|
|
+ break;
|
|
+ }
|
|
+
|
|
return 0;
|
|
}
|
|
|
|
--
|
|
2.17.1
|
|
|