Re: [PATCH] Documentation: statistics about nested locks

[Yong Zhang]

On Mon, May 16, 2011 at 6:01 PM, Juri Lelli <juri.lelli@xxxxxxxxx> wrote:
> Hi all,
> just a little patch to the Documentation. I had some trouble understanding
> the trailing "/1" on some lock class names of lock_stat output, so I added
> something on this inside lockstat documentation.
>
> Signed-off-by: Juri Lelli <juri.lelli@xxxxxxxxx>
>
> ---
> ÂDocumentation/lockstat.txt | Â 36 ++++++++++++++++++++++++++++++++++--
> Â1 files changed, 34 insertions(+), 2 deletions(-)
>
> diff --git a/Documentation/lockstat.txt b/Documentation/lockstat.txt
> index 65f4c79..75eeb65 100644
> --- a/Documentation/lockstat.txt
> +++ b/Documentation/lockstat.txt
> @@ -12,8 +12,9 @@ Because things like lock contention can severely impact
> performance.
> Â- HOW
>
> ÂLockdep already has hooks in the lock functions and maps lock instances to
> -lock classes. We build on that. The graph below shows the relation between
> -the lock functions and the various hooks therein.
> +lock classes. We build on that (see Documentation/lockdep-design.txt).
> +The graph below shows the relation between the lock functions and the
> various
> +hooks therein.
>
> Â Â Â Â __acquire
> Â Â Â Â Â Â |
> @@ -128,6 +129,37 @@ points are the points we're contending with.
>
> ÂThe integer part of the time values is in us.
>
> +Dealing with nested locks, subclasses may appear:
> +
> +32...............................................................................................................................................................................................
> +33
> +34 Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â &rq->lock: Â Â Â Â 13128 13128
> 0.43 Â Â Â Â 190.53 Â Â Â103881.26 Â Â Â Â Â97454 Â3453404 Â Â Â Â Â 0.00
> Â Â Â 401.11 Â Â13224683.11
> +35 Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â ---------
> +36                &rq->lock      Â645
> [<ffffffff8103bfc4>] task_rq_lock+0x43/0x75
> +37                &rq->lock      Â297
> [<ffffffff8104ba65>] try_to_wake_up+0x127/0x25a
> +38                &rq->lock      Â360
> [<ffffffff8103c4c5>] select_task_rq_fair+0x1f0/0x74a
> +39                &rq->lock      Â428
> [<ffffffff81045f98>] scheduler_tick+0x46/0x1fb
> +40 Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â ---------
> +41                &rq->lock       77
> [<ffffffff8103bfc4>] task_rq_lock+0x43/0x75
> +42                &rq->lock      Â174
> [<ffffffff8104ba65>] try_to_wake_up+0x127/0x25a
> +43                &rq->lock      4715
> [<ffffffff8103ed4b>] double_rq_lock+0x42/0x54
> +44                &rq->lock      Â893
> [<ffffffff81340524>] schedule+0x157/0x7b8
> +45
> +46...............................................................................................................................................................................................
> +47
> +48 Â Â Â Â Â Â Â Â Â Â Â Â Â Â &rq->lock/1: Â Â Â Â 11526 11488
> 0.33 Â Â Â Â 388.73 Â Â Â136294.31 Â Â Â Â Â21461 Â Â38404 Â Â Â Â Â 0.00
> Â Â Â Â37.93 Â Â Â109388.53
> +49 Â Â Â Â Â Â Â Â Â Â Â Â Â Â -----------
> +50 Â Â Â Â Â Â Â Â Â Â Â Â Â Â &rq->lock/1 Â Â Â Â Â11526
> [<ffffffff8103ed58>] double_rq_lock+0x4f/0x54
> +51 Â Â Â Â Â Â Â Â Â Â Â Â Â Â -----------
> +52 Â Â Â Â Â Â Â Â Â Â Â Â Â Â &rq->lock/1 Â Â Â Â Â 5645
> [<ffffffff8103ed4b>] double_rq_lock+0x42/0x54
> +53 Â Â Â Â Â Â Â Â Â Â Â Â Â Â &rq->lock/1 Â Â Â Â Â 1224
> [<ffffffff81340524>] schedule+0x157/0x7b8
> +54 Â Â Â Â Â Â Â Â Â Â Â Â Â Â &rq->lock/1 Â Â Â Â Â 4336
> [<ffffffff8103ed58>] double_rq_lock+0x4f/0x54
> +55 Â Â Â Â Â Â Â Â Â Â Â Â Â Â &rq->lock/1 Â Â Â Â Â Â181
> [<ffffffff8104ba65>] try_to_wake_up+0x127/0x25a
> +
> +Line 48 shows statistics for the first subclass (/1) of &rq->lock class,

Actually it's the second subclass because subclass starts from 0.

Thanks,
Yong

> since
> +in this case, as line 50 suggests, double_rq_lock actually acquires a
> nested
> +lock of two spinlocks.
> +
> ÂView the top contending locks:
>
> Â# grep : /proc/lock_stat | head
> --
> 1.7.4.1
>



-- 
Only stand for myself
N‹§²æìr¸›yúèšØb²X¬¶ÇvØ^–)Þ{.nÇ+‰·¥Š{±‘êçzX§¶›¡Ü}©ž²ÆzÚ&j:+v‰¨¾«‘êçzZ+€Ê+zf£¢·hšˆ§~†­†Ûiÿûàz¹®w¥¢¸?™¨è­Ú&¢)ßf”ù^jÇy§m…á@A«a¶Úÿ0¶ìh®å’i