pool/sysstat
SHA256
2
0
Fork 1
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Accepting request 835448 from home:pmonrealgonzalez:branches:Base:System

Browse Source 
- Fix average iowait output of sar [bsc#1174227]
  * The iowait value reported by the kernel can also decrement as
    a result of inaccurate iowait tracking. Waiting on IO can be
    first accounted as iowait but then instead as idle. Therefore
    if the idle value during the same period did not decrease then
    consider this is a problem with the iowait reporting and correct
    the previous value according to the new reading. Otherwise, treat
    this as CPU coming back online.
- Add patch sysstat-iowait-decr.patch

OBS-URL: https://build.opensuse.org/request/show/835448
OBS-URL: https://build.opensuse.org/package/show/Base:System/sysstat?expand=0&rev=115
This commit is contained in:
Marcus Meissner 2020-09-21 10:50:06 +00:00 committed by Git OBS Bridge
parent e0378284ad
commit dd230d294a
3 changed files with 79 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

63
sysstat-iowait-decr.patch Normal file
View File

@ -0,0 +1,63 @@
From 1f5949d4a6fcb33065dbb1d509f356db039998ed Mon Sep 17 00:00:00 2001
From: Sebastien GODARD <sysstat@users.noreply.github.com>
Date: Wed, 2 Sep 2020 19:04:04 +0200
Subject: [PATCH] Workaround for iowait being decremented
The iowait value reported by the kernel on NO_HZ systems can decrement
as a result of inaccurate iowait tracking. Waiting on IO can be first
accounted as iowait but then instead as idle.
Function get_per_cpu_interval() considers iowait going backwards between
two readings as a CPU coming back online and resets the iowait value of
the first reading to 0. If iowait is decremented only because of
inaccurate tracking, this causes that almost all time between the two
readings is incorrectly recognized by sar as being spent in iowait.
The patch updates the code in get_per_cpu_interval() to recognize this
situation. If the iowait value between two readings decremented but the
idle value did not then the code now considers it as a problem with the
iowait reporting and corrects the first value according to the second
reading. Otherwise, the code remains treating decremented iowait as a
CPU coming back online.
Fixes #14.
Signed-off-by: Sebastien GODARD <sysstat@users.noreply.github.com>
---
rd_stats.c | 20 +++++++++++++++++---
1 file changed, 17 insertions(+), 3 deletions(-)
diff --git a/rd_stats.c b/rd_stats.c
index 56d42d00..fb93f23f 100644
--- a/rd_stats.c
+++ b/rd_stats.c
@@ -440,12 +440,26 @@ unsigned long long get_per_cpu_interval(struct stats_cpu *scc,
* value was greater than ULLONG_MAX - 0x7ffff (the counter probably
* overflew).
*/
+ if ((scc->cpu_iowait < scp->cpu_iowait) && (scp->cpu_iowait < (ULLONG_MAX - 0x7ffff))) {
+ /*
+ * The iowait value reported by the kernel can also decrement as
+ * a result of inaccurate iowait tracking. Waiting on IO can be
+ * first accounted as iowait but then instead as idle.
+ * Therefore if the idle value during the same period did not
+ * decrease then consider this is a problem with the iowait
+ * reporting and correct the previous value according to the new
+ * reading. Otherwise, treat this as CPU coming back online.
+ */
+ if ((scc->cpu_idle > scp->cpu_idle) || (scp->cpu_idle >= (ULLONG_MAX - 0x7ffff))) {
+ scp->cpu_iowait = scc->cpu_iowait;
+ }
+ else {
+ scp->cpu_iowait = 0;
+ }
+ }
if ((scc->cpu_idle < scp->cpu_idle) && (scp->cpu_idle < (ULLONG_MAX - 0x7ffff))) {
scp->cpu_idle = 0;
}
- if ((scc->cpu_iowait < scp->cpu_iowait) && (scp->cpu_iowait < (ULLONG_MAX - 0x7ffff))) {
- scp->cpu_iowait = 0;
- }
/*
* Don't take cpu_guest and cpu_guest_nice into account

13
sysstat.changes
View File

@ -1,3 +1,16 @@
-------------------------------------------------------------------
Fri Sep 18 14:47:02 UTC 2020 - Pedro Monreal <pmonreal@suse.com>
- Fix average iowait output of sar [bsc#1174227]
* The iowait value reported by the kernel can also decrement as
a result of inaccurate iowait tracking. Waiting on IO can be
first accounted as iowait but then instead as idle. Therefore
if the idle value during the same period did not decrease then
consider this is a problem with the iowait reporting and correct
the previous value according to the new reading. Otherwise, treat
this as CPU coming back online.
- Add patch sysstat-iowait-decr.patch
-------------------------------------------------------------------
Mon Aug 31 11:43:51 UTC 2020 - Dirk Mueller <dmueller@suse.com>

3
sysstat.spec
View File

@ -35,6 +35,8 @@ Patch2: sysstat-8.0.4-pagesize.diff
Patch3: sysstat-service.patch
# PATCH-FIX-OPENSUSE Temporarily disable failing tests on s390x and ppc64
Patch4: sysstat-disable-test-failures.patch
# PATCH-FIX-OPENSUSE bsc#1174227 Workaround for iowait being decremented
Patch5: sysstat-iowait-decr.patch
BuildRequires: findutils
BuildRequires: gettext-runtime
BuildRequires: pkgconfig
@ -77,6 +79,7 @@ from a sysstat package.
%ifarch s390x ppc64
%patch4 -p1
%endif
%patch5 -p1
cp %{S:1} .
# remove date and time from objects
find ./ -name \*.c -exec sed -i -e 's: " compiled " __DATE__ " " __TIME__::g' {} \;