From: Jaegeuk Kim <jaegeuk@kernel.org>
To: Marc Lehmann <schmorp@schmorp.de>
Cc: linux-f2fs-devel@lists.sourceforge.net
Subject: Re: write performance difference 3.18.21/4.2.1
Date: Thu, 24 Sep 2015 11:28:36 -0700 [thread overview]
Message-ID: <20150924182836.GD40291@jaegeuk-mac02> (raw)
In-Reply-To: <20150923231103.GA3463@schmorp.de>
On Thu, Sep 24, 2015 at 01:11:03AM +0200, Marc Lehmann wrote:
> I tried twice with the same options, on linux 3.8.21 and 4.2.1, and write
> performance is very different on these kernels (I rebooted every time in
> between).
>
> On 3.18.21, the source raid is hardly able to keep up with the write
> speed, f2fs basically writes at more or less full disk speed, for extended
> periods of time. As mentiopned earlier, average write speed was 103MB/s
> over the whole 2.1TB, with f2fs being idle a lot of that time, so actual
> write speed would be higher.
>
> On 4.2.1, same mkfs+mount options, performance is 5-10 times less, i.e.
> <<100MB/s (and more like 20MB/s for extendesd stretches):
>
> http://ue.tst.eu/43a8f7ae96ac770dc45ac8f1e3b0c479.txt
> (see the dsk/sde columns)
>
> First there is a "good" stretch with >100MB/s, then it starts to degrade.
> Another difference is the frequent read activity, which is mostly absent on
> 3.18.21.
>
> The log starts after only 20GB had been written. Here is the status output
> at 25GB:
>
> http://ue.tst.eu/734f7883107ee4dabff77602db92310b.txt
It seems about 700MB were moved by background GC.
>
> Any idea why 4.2.1 performs so much worse than 3.8.21?
One thing that we can try is to run the latest f2fs source in v3.18.
This branch supports f2fs for v3.18.
http://git.kernel.org/cgit/linux/kernel/git/jaegeuk/f2fs.git/log/?h=linux-3.18
Could you check out this branch and then copy the following files into your
v3.18 kernel?
- fs/f2fs/*
- include/linux/f2fs_fs.h
- include/trace/event/f2fs.h
And, if possible, could you share the status output of both of v3.18 and v4.2?
Thanks,
>
> (Note, if that is the difference between "filesystem works" (4.2.1?) and
> "filesystem doesn't work" (3.18.21) then that might be it - still, that
> would mean f2fs performs worse than traditional filesystems on these
> disks).
>
> --
> The choice of a Deliantra, the free code+content MORPG
> -----==- _GNU_ http://www.deliantra.net
> ----==-- _ generation
> ---==---(_)__ __ ____ __ Marc Lehmann
> --==---/ / _ \/ // /\ \/ / schmorp@schmorp.de
> -=====/_/_//_/\_,_/ /_/\_\
>
> ------------------------------------------------------------------------------
> Monitor Your Dynamic Infrastructure at Any Scale With Datadog!
> Get real-time metrics from all of your servers, apps and tools
> in one place.
> SourceForge users - Click here to start your Free Trial of Datadog now!
> http://pubads.g.doubleclick.net/gampad/clk?id=241902991&iu=/4140
> _______________________________________________
> Linux-f2fs-devel mailing list
> Linux-f2fs-devel@lists.sourceforge.net
> https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel
------------------------------------------------------------------------------
next prev parent reply other threads:[~2015-09-24 18:28 UTC|newest]
Thread overview: 74+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-09-23 21:58 sync/umount hang on 3.18.21, 1.4TB gone after crash Marc Lehmann
2015-09-23 23:11 ` write performance difference 3.18.21/4.2.1 Marc Lehmann
2015-09-24 18:28 ` Jaegeuk Kim [this message]
2015-09-24 23:20 ` Marc Lehmann
2015-09-24 23:27 ` Marc Lehmann
2015-09-25 6:50 ` Marc Lehmann
2015-09-25 9:47 ` Chao Yu
2015-09-25 18:20 ` Jaegeuk Kim
2015-09-26 3:22 ` Marc Lehmann
2015-09-26 5:25 ` write performance difference 3.18.21/git f2fs Marc Lehmann
2015-09-26 5:57 ` Marc Lehmann
2015-09-26 7:52 ` Jaegeuk Kim
2015-09-26 13:59 ` Marc Lehmann
2015-09-28 17:59 ` Jaegeuk Kim
2015-09-29 11:02 ` Marc Lehmann
2015-09-29 23:13 ` Jaegeuk Kim
2015-09-30 9:02 ` Chao Yu
2015-10-01 12:11 ` Marc Lehmann
2015-10-01 18:51 ` Marc Lehmann
2015-10-02 8:53 ` 100% system time hang with git f2fs Marc Lehmann
2015-10-02 16:51 ` Jaegeuk Kim
2015-10-03 6:29 ` Marc Lehmann
2015-10-02 16:46 ` write performance difference 3.18.21/git f2fs Jaegeuk Kim
2015-10-04 9:40 ` near disk full performance (full 8TB) Marc Lehmann
2015-09-26 7:48 ` write performance difference 3.18.21/4.2.1 Jaegeuk Kim
2015-09-25 18:26 ` Jaegeuk Kim
2015-09-24 18:50 ` sync/umount hang on 3.18.21, 1.4TB gone after crash Jaegeuk Kim
2015-09-25 6:00 ` Marc Lehmann
2015-09-25 6:01 ` Marc Lehmann
2015-09-25 18:42 ` Jaegeuk Kim
2015-09-26 3:08 ` Marc Lehmann
2015-09-26 7:27 ` Jaegeuk Kim
2015-09-25 9:13 ` Chao Yu
2015-09-25 18:30 ` Jaegeuk Kim
-- strict thread matches above, loose matches on Subject: below --
2015-08-08 20:50 general stability of f2fs? Marc Lehmann
2015-08-10 20:31 ` Jaegeuk Kim
2015-08-10 20:53 ` Marc Lehmann
2015-08-10 21:58 ` Jaegeuk Kim
2015-08-13 0:26 ` Marc Lehmann
2015-08-14 23:07 ` Jaegeuk Kim
2015-09-20 23:59 ` finally testing with SMR drives Marc Lehmann
2015-09-21 8:17 ` SMR drive test 1; 512GB partition; very slow + unfixable corruption Marc Lehmann
2015-09-21 8:19 ` Marc Lehmann
2015-09-21 9:58 ` SMR drive test 2; 128GB partition; no obvious corruption, much more sane behaviour, weird overprovisioning Marc Lehmann
2015-09-22 20:22 ` SMR drive test 3: full 8TB partition, mount problems, fsck error after delete Marc Lehmann
2015-09-22 23:08 ` Jaegeuk Kim
2015-09-23 3:50 ` Marc Lehmann
2015-09-23 1:12 ` SMR drive test 2; 128GB partition; no obvious corruption, much more sane behaviour, weird overprovisioning Jaegeuk Kim
2015-09-23 4:15 ` Marc Lehmann
2015-09-23 6:00 ` Marc Lehmann
2015-09-23 8:55 ` Chao Yu
2015-09-23 23:30 ` Marc Lehmann
2015-09-23 23:43 ` Marc Lehmann
2015-09-24 17:21 ` Jaegeuk Kim
2015-09-25 8:28 ` Chao Yu
2015-09-25 8:05 ` Chao Yu
2015-09-26 3:42 ` Marc Lehmann
2015-09-23 22:08 ` Jaegeuk Kim
2015-09-23 23:39 ` Marc Lehmann
2015-09-24 17:27 ` Jaegeuk Kim
2015-09-25 5:42 ` Marc Lehmann
2015-09-25 17:45 ` Jaegeuk Kim
2015-09-26 3:32 ` Marc Lehmann
2015-09-26 7:36 ` Jaegeuk Kim
2015-09-26 13:53 ` Marc Lehmann
2015-09-28 18:33 ` Jaegeuk Kim
2015-09-29 7:36 ` Marc Lehmann
2015-09-23 6:06 ` Marc Lehmann
2015-09-23 9:10 ` Chao Yu
2015-09-23 21:30 ` Jaegeuk Kim
2015-09-23 23:11 ` Marc Lehmann
2015-09-23 21:29 ` Jaegeuk Kim
2015-09-23 23:24 ` Marc Lehmann
2015-09-24 17:51 ` Jaegeuk Kim
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=20150924182836.GD40291@jaegeuk-mac02 \
--to=jaegeuk@kernel.org \
--cc=linux-f2fs-devel@lists.sourceforge.net \
--cc=schmorp@schmorp.de \
/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).