From: Theodore Ts'o <tytso@mit.edu>
To: Alexey Lyashkov <alexey.lyashkov@gmail.com>
Cc: Andreas Dilger <adilger@dilger.ca>,
Artem Blagodarenko <artem.blagodarenko@gmail.com>,
linux-ext4 <linux-ext4@vger.kernel.org>,
Yang Sheng <yang.sheng@intel.com>,
Zhen Liang <liang.zhen@intel.com>,
Artem Blagodarenko <artem.blagodarenko@seagate.com>
Subject: Re: [PATCH] Add largedir feature
Date: Mon, 20 Mar 2017 10:20:30 -0400 [thread overview]
Message-ID: <20170320142030.s2acios7q2qytzak@thunk.org> (raw)
In-Reply-To: <AC9DD60D-37A5-458B-AFA2-5EDDAAFD5E9E@gmail.com>
On Mon, Mar 20, 2017 at 02:34:31PM +0300, Alexey Lyashkov wrote:
>
> To make picture clean. OST side is regular FS with 32 directories where a stripe objects is live.
> With current 4G inodes limit each directory will filled with up 100k regular files.
> Files allocated in batch, up to 20k files per batch. Allocated object used on MDT side to make mapping between metadata objects and data for such file.
> I worry about it part, not about MDT. these directories have a large number creations/unlinks and performance degradation started after 3M-5M creations/unlinks.
> With Large dir feature i think this performance problems may deeper.
This makes no sense. On the Object Store side, if the maximum
directory size is 100k regular files, you're never going to run into
two-levle htree limit, so the presense (or absense) of largedir is
largely irrelevant. So how can it make the performance problem worse?
- Ted
next prev parent reply other threads:[~2017-03-20 14:20 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-03-16 9:51 [PATCH] Add largedir feature Artem Blagodarenko
2017-03-16 21:44 ` Andreas Dilger
2017-03-17 6:15 ` Alexey Lyashkov
2017-03-17 20:51 ` Andreas Dilger
2017-03-18 8:16 ` Alexey Lyashkov
2017-03-18 16:29 ` Theodore Ts'o
2017-03-18 17:17 ` Alexey Lyashkov
2017-03-19 0:39 ` Theodore Ts'o
2017-03-19 4:19 ` Alexey Lyashkov
2017-03-19 6:13 ` Andreas Dilger
2017-03-19 5:38 ` Andreas Dilger
2017-03-19 13:34 ` Theodore Ts'o
2017-03-19 23:54 ` Andreas Dilger
2017-03-20 11:34 ` Alexey Lyashkov
2017-03-20 14:20 ` Theodore Ts'o [this message]
2017-03-21 15:38 ` Andreas Dilger
2017-03-20 11:42 ` Theodore Ts'o
2017-04-30 0:59 ` Theodore Ts'o
2017-05-01 18:58 ` Eric Biggers
2017-05-01 23:39 ` Andreas Dilger
2017-05-02 2:44 ` Theodore Ts'o
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=20170320142030.s2acios7q2qytzak@thunk.org \
--to=tytso@mit.edu \
--cc=adilger@dilger.ca \
--cc=alexey.lyashkov@gmail.com \
--cc=artem.blagodarenko@gmail.com \
--cc=artem.blagodarenko@seagate.com \
--cc=liang.zhen@intel.com \
--cc=linux-ext4@vger.kernel.org \
--cc=yang.sheng@intel.com \
/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).