[<prev] [next>] [day] [month] [year] [list]
Message-ID: <20140930080557.GE9561@wfg-t540p.sh.intel.com>
Date: Tue, 30 Sep 2014 16:05:57 +0800
From: Fengguang Wu <fengguang.wu@...el.com>
To: "Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>
Cc: Dave Hansen <dave.hansen@...el.com>,
LKML <linux-kernel@...r.kernel.org>, lkp@...org
Subject: [LKP] [mm] f1820361f83: -53.5% proc-vmstat.pgfault
Hi Kirill,
FYI, we noticed 53.5% reduction of page faults and more mmap pages on
commit f1820361f83d556a7f0a9f629100f3825e594328 ("mm: implement ->map_pages for page cache")
testbox/testcase/testparams: lituya/will-it-scale/brk1
8c6e50b0290c4c7 f1820361f83d556a7f0a9f629
--------------- -------------------------
1111649 ± 0% -53.5% 517160 ± 0% proc-vmstat.pgfault
42 ±15% -39.6% 25 ±22% sched_debug.cpu#0.load
21 ±23% +45.3% 30 ±20% sched_debug.cfs_rq[3]:/.runnable_load_avg
1907 ± 0% +56.4% 2983 ± 0% proc-vmstat.nr_mapped
7631 ± 0% +56.4% 11938 ± 0% meminfo.Mapped
5002 ± 0% +42.3% 7119 ± 0% time.maximum_resident_set_size
38824 ±17% +40.3% 54478 ±19% sched_debug.cpu#4.nr_load_updates
572834 ±18% +32.3% 757713 ±10% sched_debug.cpu#4.sched_count
563679 ±18% +32.3% 745714 ±11% sched_debug.cpu#4.nr_switches
280478 ±18% +32.3% 371078 ±11% sched_debug.cpu#4.sched_goidle
67648 ± 0% +25.6% 84935 ± 0% meminfo.Active(file)
16911 ± 0% +25.6% 21233 ± 0% proc-vmstat.nr_active_file
21 ± 9% +27.5% 27 ±17% sched_debug.cfs_rq[2]:/.runnable_load_avg
331375 ±18% +31.0% 434139 ± 9% sched_debug.cpu#4.ttwu_count
104185 ± 0% +16.6% 121516 ± 0% meminfo.Active
2716 ± 0% +15.5% 3138 ± 0% proc-vmstat.pgactivate
22227 ± 0% -40.5% 13227 ± 0% time.minor_page_faults
14852144 ± 3% +7.5% 15967380 ± 4% time.voluntary_context_switches
103047 ± 3% +7.1% 110336 ± 4% vmstat.system.cs
time.minor_page_faults
3000 ++------------------------------------------------------------------+
2800 *+*..*.*..*.*..*.*.*..*.*..*.*..*.*.*..*.*..*.*..*.*.*..*.*..*.*..*.*
| |
2600 ++ |
2400 ++ |
| |
2200 ++ |
2000 ++ |
1800 ++ |
| |
1600 ++ |
1400 ++ |
| |
1200 O+O O O O O O O O O O O O O O O O O O O O O O O O O O O |
1000 ++------------------------------------------------------------------+
[*] bisect-good sample
[O] bisect-bad sample
To reproduce:
apt-get install ruby ruby-oj
git clone git://git.kernel.org/pub/scm/linux/kernel/git/wfg/lkp-tests.git
cd lkp-tests
bin/setup-local job.yaml # the job file attached in this email
bin/run-local job.yaml
Disclaimer:
Results have been estimated based on internal Intel analysis and are provided
for informational purposes only. Any difference in system hardware or software
design or configuration may affect actual performance.
Thanks,
Fengguang
View attachment "job.yaml" of type "text/plain" (1292 bytes)
View attachment "reproduce" of type "text/plain" (31 bytes)
_______________________________________________
LKP mailing list
LKP@...ux.intel.com
Powered by blists - more mailing lists