All of lore.kernel.org
 help / color / mirror / Atom feed
From: Marc Lehmann <schmorp@schmorp.de>
To: Jaegeuk Kim <jaegeuk@kernel.org>
Cc: linux-f2fs-devel@lists.sourceforge.net
Subject: Re: write performance difference 3.18.21/4.2.1
Date: Fri, 25 Sep 2015 08:50:57 +0200	[thread overview]
Message-ID: <20150925065057.GA2638@schmorp.de> (raw)
In-Reply-To: <20150924175131.GC40291@jaegeuk-mac02> <20150924182836.GD40291@jaegeuk-mac02>

On Thu, Sep 24, 2015 at 11:28:36AM -0700, Jaegeuk Kim <jaegeuk@kernel.org> wrote:
> One thing that we can try is to run the latest f2fs source in v3.18.
> This branch supports f2fs for v3.18.

Ok, please bear with me, the last time I built my own kernel was during
the 2.4 timeframe, and this is a ubuntu kernel. What I did is this:

   git clone -b linux-3.18 git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs.git
   cd f2fs/fs/f2fs
   rsync -avPR include/linux/f2fs_fs.h include/trace/events/f2fs.h /usr/src/linux-headers-3.18.21-031821/.
   make -C /lib/modules/3.18.21-031821-generic/build/ M=$PWD modules modules_install

I then rmmod f2fs/insmod the resulting module, and tried to mount my
existing f2fs fs for a quick test, but got a null ptr exception on "mount":

http://ue.tst.eu/e4628dcee97324e580da1bafad938052.txt

Probably caused me not building a full kernel, but recreating how ubuntu
build their kernels on a debian system isn't something I look forward to.

> For example, if I can represent blocks like:
[number of logs discussion]

Thanks for this explanation - two logs doesn't look so bad, from a
locality viewpoint (not a big issue for flash, but a big issue for
rotational devices - I also realised I can't use dmcache as dmcache, even
in writethrough mode, writes back all data after an unclean shutdown,
which would positively kill the disk).

Since whatever speed difference I saw with two logs wasn't big, you
completely sold me on 6 logs, or 4 (especially if it seepds up the gc,
which I haven't much tested yet). Two logs was merely a test anyway (the
same with no_heap, I don't know what it does, but I thought it is worth
a try, as metadata + data nearer together is better than having them at
opposite ends of the log or so).

-- 
                The choice of a       Deliantra, the free code+content MORPG
      -----==-     _GNU_              http://www.deliantra.net
      ----==-- _       generation
      ---==---(_)__  __ ____  __      Marc Lehmann
      --==---/ / _ \/ // /\ \/ /      schmorp@schmorp.de
      -=====/_/_//_/\_,_/ /_/\_\

------------------------------------------------------------------------------

  parent reply	other threads:[~2015-09-25  6:51 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
2015-09-24 23:20     ` Marc Lehmann
2015-09-24 23:27       ` Marc Lehmann
2015-09-25  6:50     ` Marc Lehmann [this message]
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=20150925065057.GA2638@schmorp.de \
    --to=schmorp@schmorp.de \
    --cc=jaegeuk@kernel.org \
    --cc=linux-f2fs-devel@lists.sourceforge.net \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.