Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > linux.kernel > #1412422

Re: [LKP] [lkp] [dcache_{readdir, dir_lseek}() users] 4e82901cd6: reaim.jobs_per_min -49.1% regression

From Al Viro <viro@ZenIV.linux.org.uk>
Newsgroups linux.kernel
Subject Re: [LKP] [lkp] [dcache_{readdir, dir_lseek}() users] 4e82901cd6: reaim.jobs_per_min -49.1% regression
Date 2016-06-02 18:40 +0200
Message-ID <rFDP3-8ex-13@gated-at.bofh.it> (permalink)
References <rEN46-b2-13@gated-at.bofh.it> <rESds-3nT-13@gated-at.bofh.it> <rF2Pv-1CU-1@gated-at.bofh.it> <rFuiK-2lh-25@gated-at.bofh.it>
Organization linux.* mail to news gateway

Show all headers | View raw


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...

Back to linux.kernel | Previous | NextPrevious in thread | Find similar | Unroll thread


Thread

Re: [lkp] [dcache_{readdir,dir_lseek}() users] 4e82901cd6:  reaim.jobs_per_min -49.1% regression Al Viro <viro@ZenIV.linux.org.uk> - 2016-05-31 15:50 +0200
  Re: [LKP] [lkp] [dcache_{readdir, dir_lseek}() users] 4e82901cd6: reaim.jobs_per_min -49.1% regression "Huang\, Ying" <ying.huang@intel.com> - 2016-06-01 03:10 +0200
    Re: [LKP] [lkp] [dcache_{readdir, dir_lseek}() users] 4e82901cd6: reaim.jobs_per_min -49.1% regression "Huang\, Ying" <ying.huang@intel.com> - 2016-06-02 08:30 +0200
      Re: [LKP] [lkp] [dcache_{readdir, dir_lseek}() users] 4e82901cd6:  reaim.jobs_per_min -49.1% regression Al Viro <viro@ZenIV.linux.org.uk> - 2016-06-02 18:40 +0200

csiph-web