| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20230511181931.869812-8-tj@kernel.org>
Date: Thu, 11 May 2023 08:19:31 -1000
From: Tejun Heo <tj@...nel.org>
To: jiangshanlai@...il.com
Cc: torvalds@...ux-foundation.org, peterz@...radead.org,
linux-kernel@...r.kernel.org, kernel-team@...a.com,
Tejun Heo <tj@...nel.org>
Subject: [PATCH 7/7] workqueue: Track and monitor per-workqueue CPU time usage
Now that wq_worker_tick() is there, we can easily track the rough CPU time
consumption of each workqueue by charging the whole tick whenever a tick
hits an active workqueue. While not super accurate, it provides reasonable
visibility into the workqueues that consume a lot of CPU cycles.
wq_monitor.py is updated to report the per-workqueue CPU times.
Signed-off-by: Tejun Heo <tj@...nel.org>
---
Documentation/core-api/workqueue.rst | 38 ++++++++++++++--------------
kernel/workqueue.c | 3 +++
tools/workqueue/wq_monitor.py | 9 ++++++-
3 files changed, 30 insertions(+), 20 deletions(-)
diff --git a/Documentation/core-api/workqueue.rst b/Documentation/core-api/workqueue.rst
index a389f31b025c..a4c9b9d1905f 100644
--- a/Documentation/core-api/workqueue.rst
+++ b/Documentation/core-api/workqueue.rst
@@ -354,25 +354,25 @@ Monitoring
Use tools/workqueue/wq_monitor.py to monitor workqueue operations: ::
$ tools/workqueue/wq_monitor.py events
- total infl CPUitsv CMwake mayday rescued
- events 18545 0 0 5 - -
- events_highpri 8 0 0 0 - -
- events_long 3 0 0 0 - -
- events_unbound 38306 0 - - - -
- events_freezable 0 0 0 0 - -
- events_power_efficient 29598 0 0 0 - -
- events_freezable_power_ 10 0 0 0 - -
- sock_diag_events 0 0 0 0 - -
-
- total infl CPUitsv CMwake mayday rescued
- events 18548 0 0 5 - -
- events_highpri 8 0 0 0 - -
- events_long 3 0 0 0 - -
- events_unbound 38322 0 - - - -
- events_freezable 0 0 0 0 - -
- events_power_efficient 29603 0 0 0 - -
- events_freezable_power_ 10 0 0 0 - -
- sock_diag_events 0 0 0 0 - -
+ total infl CPUtime CPUhog CMwake mayday rescued
+ events 18545 0 6.1 0 5 - -
+ events_highpri 8 0 0.0 0 0 - -
+ events_long 3 0 0.0 0 0 - -
+ events_unbound 38306 0 0.1 - - - -
+ events_freezable 0 0 0.0 0 0 - -
+ events_power_efficient 29598 0 0.2 0 0 - -
+ events_freezable_power_ 10 0 0.0 0 0 - -
+ sock_diag_events 0 0 0.0 0 0 - -
+
+ total infl CPUtime CPUhog CMwake mayday rescued
+ events 18548 0 6.1 0 5 - -
+ events_highpri 8 0 0.0 0 0 - -
+ events_long 3 0 0.0 0 0 - -
+ events_unbound 38322 0 0.1 - - - -
+ events_freezable 0 0 0.0 0 0 - -
+ events_power_efficient 29603 0 0.2 0 0 - -
+ events_freezable_power_ 10 0 0.0 0 0 - -
+ sock_diag_events 0 0 0.0 0 0 - -
...
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index b85d70f133f7..42c41d5368dc 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -212,6 +212,7 @@ struct worker_pool {
enum pool_workqueue_stats {
PWQ_STAT_STARTED, /* work items started execution */
PWQ_STAT_COMPLETED, /* work items completed execution */
+ PWQ_STAT_CPU_TIME, /* total CPU time consumed */
PWQ_STAT_CPU_INTENSIVE, /* wq_cpu_intensive_thresh_us violations */
PWQ_STAT_CM_WAKEUP, /* concurrency-management worker wakeups */
PWQ_STAT_MAYDAY, /* maydays to rescuer */
@@ -1170,6 +1171,8 @@ void wq_worker_tick(struct task_struct *task)
if (!pwq)
return;
+ pwq->stats[PWQ_STAT_CPU_TIME] += TICK_USEC;
+
/*
* If the current worker is concurrency managed and hogged the CPU for
* longer than wq_cpu_intensive_thresh_us, it's automatically marked
diff --git a/tools/workqueue/wq_monitor.py b/tools/workqueue/wq_monitor.py
index 5dc0b61b36e8..3c35239d50c4 100644
--- a/tools/workqueue/wq_monitor.py
+++ b/tools/workqueue/wq_monitor.py
@@ -12,6 +12,10 @@ https://github.com/osandov/drgn.
infl The number of currently in-flight work items.
+ CPUtime Total CPU time consumed by the workqueue in seconds. This is
+ sampled from scheduler ticks and only provides ballpark
+ measurement. "nohz_full=" CPUs are excluded from measurement.
+
CPUitsv The number of times a concurrency-managed work item hogged CPU
longer than the threshold (workqueue.cpu_intensive_thresh_us)
and got excluded from concurrency management to avoid stalling
@@ -59,6 +63,7 @@ WQ_MEM_RECLAIM = prog['WQ_MEM_RECLAIM']
PWQ_STAT_STARTED = prog['PWQ_STAT_STARTED'] # work items started execution
PWQ_STAT_COMPLETED = prog['PWQ_STAT_COMPLETED'] # work items completed execution
+PWQ_STAT_CPU_TIME = prog['PWQ_STAT_CPU_TIME'] # total CPU time consumed
PWQ_STAT_CPU_INTENSIVE = prog['PWQ_STAT_CPU_INTENSIVE'] # wq_cpu_intensive_thresh_us violations
PWQ_STAT_CM_WAKEUP = prog['PWQ_STAT_CM_WAKEUP'] # concurrency-management worker wakeups
PWQ_STAT_MAYDAY = prog['PWQ_STAT_MAYDAY'] # maydays to rescuer
@@ -82,13 +87,14 @@ PWQ_NR_STATS = prog['PWQ_NR_STATS']
'mem_reclaim' : self.mem_reclaim,
'started' : self.stats[PWQ_STAT_STARTED],
'completed' : self.stats[PWQ_STAT_COMPLETED],
+ 'cputime' : self.stats[PWQ_STAT_CPU_TIME],
'cpu_intensive' : self.stats[PWQ_STAT_CPU_INTENSIVE],
'cm_wakeup' : self.stats[PWQ_STAT_CM_WAKEUP],
'mayday' : self.stats[PWQ_STAT_MAYDAY],
'rescued' : self.stats[PWQ_STAT_RESCUED], }
def table_header_str():
- return f'{"":>24} {"total":>8} {"infl":>5} {"CPUitsv":>7} '\
+ return f'{"":>24} {"total":>8} {"infl":>5} {"CPUtime":>8} {"CPUitsv":>7} '\
f'{"CMwake":>7} {"mayday":>7} {"rescued":>7}'
def table_row_str(self):
@@ -108,6 +114,7 @@ PWQ_NR_STATS = prog['PWQ_NR_STATS']
out = f'{self.name[-24:]:24} ' \
f'{self.stats[PWQ_STAT_STARTED]:8} ' \
f'{max(self.stats[PWQ_STAT_STARTED] - self.stats[PWQ_STAT_COMPLETED], 0):5} ' \
+ f'{self.stats[PWQ_STAT_CPU_TIME] / 1000000:8.1f} ' \
f'{cpu_intensive:>7} ' \
f'{cm_wakeup:>7} ' \
f'{mayday:>7} ' \
--
2.40.1
Powered by blists - more mailing lists