64 lines
2.6 KiB
Diff
64 lines
2.6 KiB
Diff
|
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
|