linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Sergey Senozhatsky <senozhatsky@chromium.org>
To: Yosry Ahmed <yosry.ahmed@linux.dev>
Cc: Sergey Senozhatsky <senozhatsky@chromium.org>,
	 Andrew Morton <akpm@linux-foundation.org>,
	Minchan Kim <minchan@kernel.org>,
	linux-mm@kvack.org,  linux-kernel@vger.kernel.org,
	Kairui Song <ryncsn@gmail.com>
Subject: Re: [PATCHv4 14/17] zsmalloc: make zspage lock preemptible
Date: Fri, 14 Feb 2025 12:33:33 +0900	[thread overview]
Message-ID: <sio5jxzi5fsdcfpgbifna6d6ipwvbrxftogeyxpqim74yeptd4@gaqzwxsrkoud> (raw)
In-Reply-To: <Z64O3w2p1NrXoicl@google.com>

On (25/02/13 15:25), Yosry Ahmed wrote:
> On Thu, Feb 13, 2025 at 05:22:20PM +0900, Sergey Senozhatsky wrote:
> > On (25/02/13 16:21), Sergey Senozhatsky wrote:
> > > BASE
> > > ====
> > > 
> > > 1363.64user 157.08system 1:30.89elapsed 1673%CPU (0avgtext+0avgdata 825692maxresident)k
> > > 
> > > lock stats
> > > 
> > >                               class name    con-bounces    contentions   waittime-min   waittime-max waittime-total   waittime-avg    acq-bounces   acquisitions   holdtime-min   holdtime-max holdtime-total   holdtime-avg
> > >                    &pool->migrate_lock-R:             0              0           0.00           0.00           0.00           0.00          10001         702081           0.14         104.74      125571.64           0.18
> > >                             &class->lock:             1              1           0.25           0.25           0.25           0.25           6320         840542           0.06         809.72      191214.87           0.23
> > >                          &zspage->lock-R:             0              0           0.00           0.00           0.00           0.00           6452         664129           0.12         660.24      201888.61           0.30
> > >                 &zram->table[index].lock:             0              0           0.00           0.00           0.00           0.00        1716362        3096466           0.07         811.10      365551.24           0.12
> > >                             &zstrm->lock:             0              0           0.00           0.00           0.00           0.00              0         664129           1.68        1004.80    14853571.32          22.37
> > > 
> > > PATCHED
> > > =======
> > > 
> > > 1366.50user 154.89system 1:30.33elapsed 1684%CPU (0avgtext+0avgdata 825692maxresident)k
> > > 
> > > lock stats
> > > 
> > >                               class name    con-bounces    contentions   waittime-min   waittime-max waittime-total   waittime-avg    acq-bounces   acquisitions   holdtime-min   holdtime-max holdtime-total   holdtime-avg
> > >                          &pool->lock#3-R:             0              0           0.00           0.00           0.00           0.00           3648         701979           0.12          44.09      107333.02           0.15
> > >                             &class->lock:             0              0           0.00           0.00           0.00           0.00           5038         840434           0.06        1245.90      211814.60           0.25
> > >                          zsmalloc-page-R:             0              0           0.00           0.00           0.00           0.00              0         664078           0.05         699.35      236641.75           0.36
> > >                         zram-entry->lock:             0              0           0.00           0.00           0.00           0.00              0        3098328           0.06        2987.02      313339.11           0.10
> > >    &per_cpu_ptr(comp->stream, cpu)->lock:             0              0           0.00           0.00           0.00           0.00             23         664078           1.77        7071.30    14838397.61          22.34
> > 
> > So...
> > 
> > I added lock-stat handling to zspage->lock and to zram (in zram it's only
> > trylock that we can track, but it doesn't really bother me).  I also
> > renamed zsmalloc-page-R to old zspage->lock-R and zram-entry->lock to
> > old zram->table[index].lock, just in case if anyone cares.
> > 
> > Now bounces stats for zspage->lock and zram->table[index].lock look
> > pretty much like in BASE case.
> > 
> > PATCHED
> > =======
> > 
> >                               class name    con-bounces    contentions   waittime-min   waittime-max waittime-total   waittime-avg    acq-bounces   acquisitions   holdtime-min   holdtime-max holdtime-total   holdtime-avg
> >                          &pool->lock#3-R:             0              0           0.00           0.00           0.00           0.00           2702         703841           0.22         873.90      197110.49           0.28
> >                             &class->lock:             0              0           0.00           0.00           0.00           0.00           4590         842336           0.10        3329.63      256595.70           0.30
> >                           zspage->lock-R:             0              0           0.00           0.00           0.00           0.00           4750         665011           0.08        3360.60      258402.21           0.39
> >                  zram->table[index].lock:             0              0           0.00           0.00           0.00           0.00        1722291        3099346           0.12        6943.09      721282.34           0.23
> >    &per_cpu_ptr(comp->stream, cpu)->lock:             0              0           0.00           0.00           0.00           0.00             23         665011           2.84        7062.18    14896206.16          22.40
> > 
> 
> holdtime-max and holdtime-total are higher in the patched kernel. Not
> sure if this is just an artifact of lock holders being preemtible. 

Hmm, pool->lock shouldn't be affected at all, however BASE holds it much
longer than PATCHED

        holdtime-max            holdtime-total
BASE    104.74                  125571.64
PATCHED 44.09                   107333.02

Doesn't make sense.  I can understand zspage->lock and
zram->table[index].lock, but for zram->table[index] things look
strange (comparing run #1 and #2)

        holdtime-total
BASE    365551.24
PATCHED 313339.11

And run #3 is in its own league.



Very likely just a very very bad way to test things.


Re-based on 6.14.0-rc2-next-20250213.


BASE
====

PREEMPT_NONE

                              class name    con-bounces    contentions   waittime-min   waittime-max waittime-total   waittime-avg    acq-bounces   acquisitions   holdtime-min   holdtime-max holdtime-total   holdtime-avg
                   &pool->migrate_lock-R:             0              0           0.00           0.00           0.00           0.00           3624         702276           0.15          35.96      126562.90           0.18
                            &class->lock:             0              0           0.00           0.00           0.00           0.00           5084         840733           0.06         795.26      183238.22           0.22
                         &zspage->lock-R:             0              0           0.00           0.00           0.00           0.00           5358         664228           0.12          43.71      192732.71           0.29
                &zram->table[index].lock:             0              0           0.00           0.00           0.00           0.00        1528645        3095862           0.07         764.76      370881.23           0.12
                            &zstrm->lock:             0              0           0.00           0.00           0.00           0.00              0         664228           2.52        2033.81    14605911.45          21.99

PREEMPT_VOLUNTARY

                              class name    con-bounces    contentions   waittime-min   waittime-max waittime-total   waittime-avg    acq-bounces   acquisitions   holdtime-min   holdtime-max holdtime-total   holdtime-avg
                   &pool->migrate_lock-R:             0              0           0.00           0.00           0.00           0.00           3039         699556           0.14          50.78      125553.59           0.18
                            &class->lock:             0              0           0.00           0.00           0.00           0.00           5259         838005           0.06         943.43      177108.05           0.21
                         &zspage->lock-R:             0              0           0.00           0.00           0.00           0.00           5581         664096           0.12          81.56      190235.48           0.29
                &zram->table[index].lock:             0              0           0.00           0.00           0.00           0.00        1731706        3098570           0.07         796.87      366934.54           0.12
                            &zstrm->lock:             0              0           0.00           0.00           0.00           0.00              0         664096           3.38        5074.72    14472697.91          21.79

PREEMPT

                              class name    con-bounces    contentions   waittime-min   waittime-max waittime-total   waittime-avg    acq-bounces   acquisitions   holdtime-min   holdtime-max holdtime-total   holdtime-avg
                   &pool->migrate_lock-R:             0              0           0.00           0.00           0.00           0.00           2545         701827           0.14         773.56      125463.37           0.18
                            &class->lock:             0              0           0.00           0.00           0.00           0.00           4697         840281           0.06        1701.18      231657.38           0.28
                         &zspage->lock-R:             0              0           0.00           0.00           0.00           0.00           4778         664002           0.12         755.62      181215.17           0.27
                &zram->table[index].lock:             0              0           0.00           0.00           0.00           0.00        1731737        3096937           0.07        1703.92      384633.29           0.12
                            &zstrm->lock:             0              0           0.00           0.00           0.00           0.00              0         664002           2.85        3603.20    14586900.58          21.97


So somehow holdtime-max for per-CPU stream is 2.5x higher for PREEMPT_VOLUNTARY
than for PREEMPT_NONE.  And class->lock holdtime-total is much much higher for
PREEMPT than for any other preemption models.  And that's BASE kernel, which
runs fully atomic zsmalloc and zram.  I call this rubbish.


  reply	other threads:[~2025-02-14  3:33 UTC|newest]

Thread overview: 73+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-01-31  9:05 [PATCHv4 00/17] zsmalloc/zram: there be preemption Sergey Senozhatsky
2025-01-31  9:06 ` [PATCHv4 01/17] zram: switch to non-atomic entry locking Sergey Senozhatsky
2025-01-31 11:41   ` Hillf Danton
2025-02-03  3:21     ` Sergey Senozhatsky
2025-02-03  3:52       ` Sergey Senozhatsky
2025-02-03 12:39       ` Sergey Senozhatsky
2025-01-31 22:55   ` Andrew Morton
2025-02-03  3:26     ` Sergey Senozhatsky
2025-02-03  7:11       ` Sergey Senozhatsky
2025-02-03  7:33         ` Sergey Senozhatsky
2025-02-04  0:19       ` Andrew Morton
2025-02-04  4:22         ` Sergey Senozhatsky
2025-02-06  7:01     ` Sergey Senozhatsky
2025-02-06  7:38       ` Sebastian Andrzej Siewior
2025-02-06  7:47         ` Sergey Senozhatsky
2025-02-06  8:13           ` Sebastian Andrzej Siewior
2025-02-06  8:17             ` Sergey Senozhatsky
2025-02-06  8:26               ` Sebastian Andrzej Siewior
2025-02-06  8:29                 ` Sergey Senozhatsky
2025-01-31  9:06 ` [PATCHv4 02/17] zram: do not use per-CPU compression streams Sergey Senozhatsky
2025-02-01  9:21   ` Kairui Song
2025-02-03  3:49     ` Sergey Senozhatsky
2025-02-03 21:00       ` Yosry Ahmed
2025-02-06 12:26         ` Sergey Senozhatsky
2025-02-06  6:55       ` Kairui Song
2025-02-06  7:22         ` Sergey Senozhatsky
2025-02-06  8:22           ` Sergey Senozhatsky
2025-02-06 16:16           ` Yosry Ahmed
2025-02-07  2:56             ` Sergey Senozhatsky
2025-02-07  6:12               ` Sergey Senozhatsky
2025-02-07 21:07                 ` Yosry Ahmed
2025-02-08 16:20                   ` Sergey Senozhatsky
2025-02-08 16:41                     ` Sergey Senozhatsky
2025-02-09  6:22                     ` Sergey Senozhatsky
2025-02-09  7:42                       ` Sergey Senozhatsky
2025-01-31  9:06 ` [PATCHv4 03/17] zram: remove crypto include Sergey Senozhatsky
2025-01-31  9:06 ` [PATCHv4 04/17] zram: remove max_comp_streams device attr Sergey Senozhatsky
2025-01-31  9:06 ` [PATCHv4 05/17] zram: remove two-staged handle allocation Sergey Senozhatsky
2025-01-31  9:06 ` [PATCHv4 06/17] zram: permit reclaim in zstd custom allocator Sergey Senozhatsky
2025-01-31  9:06 ` [PATCHv4 07/17] zram: permit reclaim in recompression handle allocation Sergey Senozhatsky
2025-01-31  9:06 ` [PATCHv4 08/17] zram: remove writestall zram_stats member Sergey Senozhatsky
2025-01-31  9:06 ` [PATCHv4 09/17] zram: limit max recompress prio to num_active_comps Sergey Senozhatsky
2025-01-31  9:06 ` [PATCHv4 10/17] zram: filter out recomp targets based on priority Sergey Senozhatsky
2025-01-31  9:06 ` [PATCHv4 11/17] zram: unlock slot during recompression Sergey Senozhatsky
2025-01-31  9:06 ` [PATCHv4 12/17] zsmalloc: factor out pool locking helpers Sergey Senozhatsky
2025-01-31 15:46   ` Yosry Ahmed
2025-02-03  4:57     ` Sergey Senozhatsky
2025-01-31  9:06 ` [PATCHv4 13/17] zsmalloc: factor out size-class " Sergey Senozhatsky
2025-01-31  9:06 ` [PATCHv4 14/17] zsmalloc: make zspage lock preemptible Sergey Senozhatsky
2025-01-31 15:51   ` Yosry Ahmed
2025-02-03  3:13     ` Sergey Senozhatsky
2025-02-03  4:56       ` Sergey Senozhatsky
2025-02-03 21:11       ` Yosry Ahmed
2025-02-04  6:59         ` Sergey Senozhatsky
2025-02-04 17:19           ` Yosry Ahmed
2025-02-05  2:43             ` Sergey Senozhatsky
2025-02-05 19:06               ` Yosry Ahmed
2025-02-06  3:05                 ` Sergey Senozhatsky
2025-02-06  3:28                   ` Sergey Senozhatsky
2025-02-06 16:19                   ` Yosry Ahmed
2025-02-07  2:48                     ` Sergey Senozhatsky
2025-02-07 21:09                       ` Yosry Ahmed
2025-02-12  5:00                         ` Sergey Senozhatsky
2025-02-12 15:35                           ` Yosry Ahmed
2025-02-13  2:18                             ` Sergey Senozhatsky
2025-02-13  2:57                               ` Yosry Ahmed
2025-02-13  7:21                                 ` Sergey Senozhatsky
2025-02-13  8:22                                   ` Sergey Senozhatsky
2025-02-13 15:25                                     ` Yosry Ahmed
2025-02-14  3:33                                       ` Sergey Senozhatsky [this message]
2025-01-31  9:06 ` [PATCHv4 15/17] zsmalloc: introduce new object mapping API Sergey Senozhatsky
2025-01-31  9:06 ` [PATCHv4 16/17] zram: switch to new zsmalloc " Sergey Senozhatsky
2025-01-31  9:06 ` [PATCHv4 17/17] zram: add might_sleep to zcomp API Sergey Senozhatsky

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=sio5jxzi5fsdcfpgbifna6d6ipwvbrxftogeyxpqim74yeptd4@gaqzwxsrkoud \
    --to=senozhatsky@chromium.org \
    --cc=akpm@linux-foundation.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=minchan@kernel.org \
    --cc=ryncsn@gmail.com \
    --cc=yosry.ahmed@linux.dev \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox