From: Vitaly Wool <vitalywool@gmail.com>
To: Linux-MM <linux-mm@kvack.org>, linux-kernel@vger.kernel.org
Cc: Dan Streetman <ddstreet@ieee.org>,
Andrew Morton <akpm@linux-foundation.org>,
Dave Chinner <david@fromorbit.com>
Subject: [PATCH v5] z3fold: add shrinker
Date: Sat, 15 Oct 2016 13:56:32 +0200 [thread overview]
Message-ID: <20161015135632.541010b55bec496e2cae056e@gmail.com> (raw)
This patch set implements shrinker for z3fold, preceded by some
code optimizations and preparations that I thought would be
reasonable to have as separate patches.
This patch set has been verified on x86 and on Qemu emulating
Versatile Express. fio results for the resulting code are:
Run status group 0 (all jobs):
WRITE: io=3200.0MB, aggrb=13095KB/s, minb=3273KB/s, maxb=3284KB/s, mint=249447msec, maxt=250214msec
Run status group 1 (all jobs):
READ: io=3200.0MB, aggrb=28992KB/s, minb=7248KB/s, maxb=7273KB/s, mint=112623msec, maxt=113021msec
Run status group 2 (all jobs):
READ: io=1595.2MB, aggrb=8825KB/s, minb=2194KB/s, maxb=2224KB/s, mint=184517msec, maxt=185077msec
WRITE: io=1604.9MB, aggrb=8879KB/s, minb=2207KB/s, maxb=2245KB/s, mint=184519msec, maxt=185079msec
Run status group 3 (all jobs):
READ: io=1600.6MB, aggrb=8413KB/s, minb=2084KB/s, maxb=2132KB/s, mint=193286msec, maxt=194803msec
WRITE: io=1599.5MB, aggrb=8406KB/s, minb=2099KB/s, maxb=2120KB/s, mint=193290msec, maxt=194825msec
Disk stats (read/write):
zram0: ios=1636792/1638952, merge=0/0, ticks=169250/462410, in_queue=633700, util=85.33%
Just for comparison, zsmalloc gives slightly worse results:
Run status group 0 (all jobs):
WRITE: io=3200.0MB, aggrb=12827KB/s, minb=3206KB/s, maxb=3230KB/s, mint=253603msec, maxt=255450msec
Run status group 1 (all jobs):
READ: io=3200.0MB, aggrb=26184KB/s, minb=6546KB/s, maxb=6556KB/s, mint=124940msec, maxt=125144msec
Run status group 2 (all jobs):
READ: io=1595.2MB, aggrb=8549KB/s, minb=2123KB/s, maxb=2162KB/s, mint=190151msec, maxt=191049msec
WRITE: io=1604.9MB, aggrb=8601KB/s, minb=2145KB/s, maxb=2172KB/s, mint=190153msec, maxt=191051msec
Run status group 3 (all jobs):
READ: io=1600.6MB, aggrb=8147KB/s, minb=2026KB/s, maxb=2049KB/s, mint=200339msec, maxt=201154msec
WRITE: io=1599.5MB, aggrb=8142KB/s, minb=2023KB/s, maxb=2062KB/s, mint=200343msec, maxt=201158msec
Disk stats (read/write):
zram0: ios=1637032/1639304, merge=0/0, ticks=175840/458740, in_queue=637140, util=82.48%
Signed-off-by: Vitaly Wool <vitalywool@gmail.com>
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next reply other threads:[~2016-10-15 11:56 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-10-15 11:56 Vitaly Wool [this message]
2016-10-15 11:58 ` [PATCH v5 1/3] z3fold: make counters atomic Vitaly Wool
2016-10-17 20:37 ` Dan Streetman
2016-10-15 11:59 ` [PATCH v5 2/3] z3fold: remove redundant locking Vitaly Wool
2016-10-17 20:48 ` Dan Streetman
2016-10-18 2:55 ` Vitaly Wool
2016-10-15 12:05 ` [PATCH v5 3/3] z3fold: add shrinker Vitaly Wool
2016-10-18 2:06 ` Dan Streetman
2016-10-18 2:45 ` Vitaly Wool
2016-10-18 14:27 ` Dan Streetman
2016-10-18 14:51 ` Vitaly Wool
2016-10-18 15:29 ` Dan Streetman
2016-10-18 16:26 ` [PATCH v5] " Vitaly Wool
2016-10-18 17:35 ` Dan Streetman
2016-10-18 18:36 ` Vitaly Wool
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=20161015135632.541010b55bec496e2cae056e@gmail.com \
--to=vitalywool@gmail.com \
--cc=akpm@linux-foundation.org \
--cc=david@fromorbit.com \
--cc=ddstreet@ieee.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
/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;
as well as URLs for NNTP newsgroup(s).