v5.10 kernel workqueue rescuer threads have unexpected CPU affinitie
Affects | Status | Importance | Assigned to | Milestone | |
---|---|---|---|---|---|
StarlingX |
Fix Released
|
High
|
Jiping Ma |
Bug Description
Brief Description
-----------------
here are numerous kernel threads that have unexpected CPU affinities.
Quoting from Gerry's e-mail, which I trimmed a bit for length:
I did setup some application-
that there’s a lot of kernel threads that are floating across all cpus based
on ps-sched.sh dump.
[sysadmin@
PID TID PPID S PO NICE RTPRIO PR AFFINITY P COMM COMMAND
3 3 2 I TS -20 - 0 0xfffffffff 0 rcu_gp [rcu_gp]
4 4 2 I TS -20 - 0 0xfffffffff 0 rcu_par_gp [rcu_par_gp]
8 8 2 I TS -20 - 0 0xfffffffff 0 mm_percpu_wq [mm_percpu_wq]
280 280 2 I TS -20 - 0 0xfffffffff 0 netns [netns]
288 288 2 I TS -20 - 0 0xfffffffff 0 writeback [writeback]
301 301 2 I TS -20 - 0 0xfffffffff 0 cryptd [cryptd]
344 344 2 I TS -20 - 0 0xfffffffff 0 kintegrityd [kintegrityd]
345 345 2 I TS -20 - 0 0xfffffffff 0 kblockd [kblockd]
346 346 2 I TS -20 - 0 0xfffffffff 0 blkcg_punt_bio [blkcg_punt_bio]
...
controller-
BOOT_IMAGE=
module_
selinux=0 enforcing=0 nmi_watchdog=0 softlockup_panic=0 softdog.
user_
default_
audit=1 audit_backlog_
In summary, the kernel workqueue rescuer threads have their CPU affinities set to "all possible CPUs", which may negatively impact cyclictest measurements.
Severity
--------
Major
Steps to Reproduce
-------------------
Expected Behavior
-----------------
Actual Behavior
---------------
Reproducibility
----------------
reproducible (happened 2/2)
System Configuration
-------
Branch/Pull Time/Commit
-------
recent stx master load after the 5.10 kernel merged
Last Pass
----------
Timestamp/Logs
--------------
Test Activity
Workaround
----------
Unknown
Changed in starlingx: | |
assignee: | nobody → Jiping Ma (jma11) |
Fix proposed to branch: master /review. opendev. org/c/starlingx /kernel/ +/815226
Review: https:/