[<prev] [next>] [day] [month] [year] [list]
Message-ID: <20140313092933.GA31360@localhost>
Date: Thu, 13 Mar 2014 17:29:33 +0800
From: Fengguang Wu <fengguang.wu@...el.com>
To: Daniel Borkmann <dborkman@...hat.com>
Cc: "David S. Miller" <davem@...emloft.net>,
LKML <linux-kernel@...r.kernel.org>, lkp@...org,
netdev@...r.kernel.org
Subject: [loopback] b17c706987f: +91.0% qperf.sctp_bw.bw.MB_sec
Hi Daniel,
We are glad to notice this big performance gain on
git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next.git master
commit b17c706987fa6f28bdc1771c8266e7a69e22adcb ("loopback: sctp: add NETIF_F_SCTP_CSUM to device features")
test case: lkp-a06/micro/qperf/600s
72f8e06f3ea022d b17c706987fa6f28bdc1771c8
--------------- -------------------------
39.30 ~ 3% +91.0% 75.06 ~11% TOTAL qperf.sctp_bw.bw.MB_sec
126 ~ 0% -3.2% 122 ~ 0% TOTAL qperf.sctp_lat.latency.us
216270 ~ 2% -46.5% 115740 ~ 4% TOTAL cpuidle.C4.usage
48722971 ~ 5% +45.1% 70681678 ~ 7% TOTAL cpuidle.C2.time
370655 ~ 2% +46.8% 543952 ~ 7% TOTAL cpuidle.C2.usage
1.00 ~13% -22.8% 0.77 ~15% TOTAL perf-profile.cpu-cycles.acpi_processor_ffh_cstate_enter.acpi_idle_enter_bm.cpuidle_enter_state.cpuidle_idle_call.arch_cpu_idle
15233974 ~ 0% +14.2% 17397187 ~ 3% TOTAL proc-vmstat.pgalloc_normal
24268359 ~ 0% +14.2% 27716949 ~ 3% TOTAL proc-vmstat.pgfree
9034872 ~ 0% +14.2% 10321019 ~ 3% TOTAL proc-vmstat.pgalloc_dma32
51262 ~ 2% -10.0% 46151 ~ 3% TOTAL time.involuntary_context_switches
13874 ~ 1% +4.8% 14540 ~ 0% TOTAL vmstat.system.cs
812 ~ 0% -3.4% 784 ~ 1% TOTAL time.system_time
4125867 ~ 1% +3.9% 4285302 ~ 0% TOTAL time.voluntary_context_switches
Legend:
~XX% - stddev percent
[+-]XX% - change percent
qperf.sctp_bw.bw.MB_sec
90 ++------------------------------------------------------------O-------+
| O O |
80 ++ O O O O O O |
O O O O O O O O |
| O O O O O |
70 ++ O O O
| O |
60 ++ O |
| |
50 ++ |
| |
| .*.. .*.. .*.. .*. .*.. |
40 *+.*.*. *.*..*..*..*.*. *.*..*..* *. *..*. *.*..*..* |
| |
30 ++--------------------------------------------------------------------+
[O] bisect-bad sample
[*] bisect-good sample
Thanks,
Fengguang
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists