diff options
| author | Waiman Long <longman@redhat.com> | 2018-10-16 16:45:06 +0300 |
|---|---|---|
| committer | Ingo Molnar <mingo@kernel.org> | 2018-10-17 09:37:31 +0300 |
| commit | 1222109a53637f96c581224198b86856d503f892 (patch) | |
| tree | e144300a8e2e0d4121f02571097e43d49e45bf4a | |
| parent | 7aa54be2976550f17c11a1c3e3630002dea39303 (diff) | |
| download | linux-1222109a53637f96c581224198b86856d503f892.tar.xz | |
locking/qspinlock_stat: Count instances of nested lock slowpaths
Queued spinlock supports up to 4 levels of lock slowpath nesting -
user context, soft IRQ, hard IRQ and NMI. However, we are not sure how
often the nesting happens.
So add 3 more per-CPU stat counters to track the number of instances where
nesting index goes to 1, 2 and 3 respectively.
On a dual-socket 64-core 128-thread Zen server, the following were the
new stat counter values under different circumstances:
State slowpath index1 index2 index3
----- -------- ------ ------ -------
After bootup 1,012,150 82 0 0
After parallel build + perf-top 125,195,009 82 0 0
So the chance of having more than 2 levels of nesting is extremely low.
[ mingo: Minor changelog edits. ]
Signed-off-by: Waiman Long <longman@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will.deacon@arm.com>
Link: http://lkml.kernel.org/r/1539697507-28084-1-git-send-email-longman@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
| -rw-r--r-- | kernel/locking/qspinlock.c | 5 | ||||
| -rw-r--r-- | kernel/locking/qspinlock_stat.h | 6 |
2 files changed, 11 insertions, 0 deletions
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c index 341ca666bc60..ce6af1ee2cac 100644 --- a/kernel/locking/qspinlock.c +++ b/kernel/locking/qspinlock.c @@ -397,6 +397,11 @@ pv_queue: node += idx; /* + * Keep counts of non-zero index values: + */ + qstat_inc(qstat_lock_idx1 + idx - 1, idx); + + /* * Ensure that we increment the head node->count before initialising * the actual node. If the compiler is kind enough to reorder these * stores, then an IRQ could overwrite our assignments. diff --git a/kernel/locking/qspinlock_stat.h b/kernel/locking/qspinlock_stat.h index 6bd78c0740fc..42d3d8dc8f49 100644 --- a/kernel/locking/qspinlock_stat.h +++ b/kernel/locking/qspinlock_stat.h @@ -55,6 +55,9 @@ enum qlock_stats { qstat_pv_wait_node, qstat_lock_pending, qstat_lock_slowpath, + qstat_lock_idx1, + qstat_lock_idx2, + qstat_lock_idx3, qstat_num, /* Total number of statistical counters */ qstat_reset_cnts = qstat_num, }; @@ -82,6 +85,9 @@ static const char * const qstat_names[qstat_num + 1] = { [qstat_pv_wait_node] = "pv_wait_node", [qstat_lock_pending] = "lock_pending", [qstat_lock_slowpath] = "lock_slowpath", + [qstat_lock_idx1] = "lock_index1", + [qstat_lock_idx2] = "lock_index2", + [qstat_lock_idx3] = "lock_index3", [qstat_reset_cnts] = "reset_counters", }; |