From: Al Viro <viro@ZenIV.linux.org.uk>
To: lkp@lists.01.org
Subject: Re: [dcache_{readdir, dir_lseek}() users] 4e82901cd6: reaim.jobs_per_min -49.1% regression
Date: Thu, 02 Jun 2016 17:29:56 +0100 [thread overview]
Message-ID: <20160602162956.GH14480@ZenIV.linux.org.uk> (raw)
In-Reply-To: <87h9dchzor.fsf@yhuang-dev.intel.com>
[-- Attachment #1: Type: text/plain, Size: 790 bytes --]
On Thu, Jun 02, 2016 at 02:28:36PM +0800, Huang, Ying wrote:
> "Huang, Ying" <ying.huang@intel.com> writes:
> Here is the comparison result with perf profile information. You can
> find it via searching 'perf-profile'.
[snip]
Looks like this load is hitting the arseloads of contention cases of
spin_lock() on various ->d_lock inside dcache_readdir(). With exclusive
lock on directory most of them end up uncontended...
I'll try to see what can be done there; quite a bit of those are actually
due to moving the cursor on every step. I wonder if we could do the list
traversals with something less drastic - the real contents changes are
prevented by the shared lock on directory being held, after all...
I'll play with that and post when I get somewhere with it...
WARNING: multiple messages have this Message-ID (diff)
From: Al Viro <viro@ZenIV.linux.org.uk>
To: "Huang, Ying" <ying.huang@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>,
lkp@01.org, LKML <linux-kernel@vger.kernel.org>
Subject: Re: [LKP] [lkp] [dcache_{readdir, dir_lseek}() users] 4e82901cd6: reaim.jobs_per_min -49.1% regression
Date: Thu, 2 Jun 2016 17:29:56 +0100 [thread overview]
Message-ID: <20160602162956.GH14480@ZenIV.linux.org.uk> (raw)
In-Reply-To: <87h9dchzor.fsf@yhuang-dev.intel.com>
On Thu, Jun 02, 2016 at 02:28:36PM +0800, Huang, Ying wrote:
> "Huang, Ying" <ying.huang@intel.com> writes:
> Here is the comparison result with perf profile information. You can
> find it via searching 'perf-profile'.
[snip]
Looks like this load is hitting the arseloads of contention cases of
spin_lock() on various ->d_lock inside dcache_readdir(). With exclusive
lock on directory most of them end up uncontended...
I'll try to see what can be done there; quite a bit of those are actually
due to moving the cursor on every step. I wonder if we could do the list
traversals with something less drastic - the real contents changes are
prevented by the shared lock on directory being held, after all...
I'll play with that and post when I get somewhere with it...
next prev parent reply other threads:[~2016-06-02 16:29 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-05-31 8:15 [dcache_{readdir, dir_lseek}() users] 4e82901cd6: reaim.jobs_per_min -49.1% regression kernel test robot
2016-05-31 8:15 ` [lkp] [dcache_{readdir,dir_lseek}() " kernel test robot
2016-05-31 13:40 ` [dcache_{readdir, dir_lseek}() " Al Viro
2016-05-31 13:40 ` [lkp] [dcache_{readdir,dir_lseek}() " Al Viro
2016-06-01 1:03 ` [dcache_{readdir, dir_lseek}() " Huang, Ying
2016-06-01 1:03 ` [LKP] [lkp] " Huang, Ying
2016-06-02 6:28 ` Huang, Ying
2016-06-02 6:28 ` [LKP] [lkp] " Huang, Ying
2016-06-02 16:29 ` Al Viro [this message]
2016-06-02 16:29 ` Al Viro
2016-06-26 9:50 ` Thorsten Leemhuis
2016-06-26 17:13 ` Linus Torvalds
2016-06-26 17:13 ` [LKP] [lkp] " Linus Torvalds
2016-06-26 18:06 ` Al Viro
2016-06-26 18:06 ` [LKP] [lkp] " Al Viro
2016-06-26 21:20 ` Linus Torvalds
2016-06-26 21:20 ` [LKP] [lkp] " Linus Torvalds
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=20160602162956.GH14480@ZenIV.linux.org.uk \
--to=viro@zeniv.linux.org.uk \
--cc=lkp@lists.01.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 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.