From: majianpeng <majianpeng@gmail.com>
To: NeilBrown <neilb@suse.de>
Cc: linux-raid <linux-raid@vger.kernel.org>
Subject: [RFC PATCH 0/3 V2] Rewrite the implementation of iobarrier for raid1.
Date: Mon, 19 Aug 2013 19:57:39 +0800 [thread overview]
Message-ID: <201308191957351897533@gmail.com> (raw)
Hi Neil,
I rewrite the implementation of iobarrier for raid1.
Patch1/2 are only to easy implemented for patch3.They don't effect the performance.
Performance Result:
Requirement:
A: sync_speed_max = sync_speed_min = 200000
B: echo repair > sync_action
Without the patch3:
TestA:
fio --rw=read --bs=512k --filename=/dev/md0 --offset=1000199467008 --rate=50M --ratemin=30M --name=test --runtime=600s
>>READ: io=8861.6MB, aggrb=15123KB/s, minb=15123KB/s, maxb=15123KB/s, mint=600012msec, maxt=600012msec
cat /proc/mdstat
>>speed=25522K/sec
TestB:
fio --rw=write --bs=512k --filename=/dev/md0 --offset=1000199467008 --rate=50M --name=test --runtime=600s
>>WRITE: io=1939.6MB, aggrb=3309KB/s, minb=3309KB/s, maxb=3309KB/s, mint=600033msec, maxt=600033msec
cat /proc/mdstat
>>speed=7732K/sec
With the patch3:
TestA:(Make sure the position of read after resync)
fio --rw=read --bs=512k --filename=/dev/md0 --offset=1000199467008 --rate=50m --name=test
>>READ: io=12547MB, aggrb=40810KB/s, minb=40810KB/s, maxb=40810KB/s, mint=314815msec, maxt=314815msec
cat /proc/mdstat:
>>speed=43745K/sec
TestB:(Make sure the position of write after resync)
fio --rw=write --bs=512k --filename=/dev/md0 --offset=1000199467008 --rate=50m --name=test --runtime=600
>>WRITE: io=30001MB, aggrb=51200KB/s, minb=51200KB/s, maxb=51200KB/s, mint=600001msec, maxt=600001msec
cat /proc/mdstat
>>speed=26686K/sec
TestC:(Make sure the position of read before resync)
fio --rw=read --bs=512k --filename=/dev/md0 --offset=0 --rate=50m --name=test --runtime=600
>>READ: io=29725MB, aggrb=50729KB/s, minb=50729KB/s, maxb=50729KB/s, mint=600004msec, maxt=600004msec
cat /proc/mdstat
>>speed=44839K/sec
TestD:(Make sure the positon of write before resync)
fio --rw=write --bs=512k --filename=/dev/md0 --offset=0 --rate=50m --name=test --runtime=600
>> WRITE: io=30001MB, aggrb=51200KB/s, minb=51200KB/s, maxb=51200KB/s, mint=600001msec, maxt=600001msec
cat /proc/mdstat
>>speed=30884K/sec
V1:http://www.spinics.net/lists/raid/msg41710.html
Jianpeng Ma (3):
raid1: Add a filed freeze_array to indicate whether raid in freeze
state.
radi1: Relace raise_barrier/lower_barrrier with
freeze_array/unfreeze_array for reconfigure the array.
raid1: Rewrite the implementation of iobarrier.
drivers/md/raid1.c | 174 ++++++++++++++++++++++++++++++++++++++++++-----------
drivers/md/raid1.h | 5 ++
2 files changed, 145 insertions(+), 34 deletions(-)
--
1.8.1.2
reply other threads:[~2013-08-19 11:57 UTC|newest]
Thread overview: [no followups] expand[flat|nested] mbox.gz Atom feed
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=201308191957351897533@gmail.com \
--to=majianpeng@gmail.com \
--cc=linux-raid@vger.kernel.org \
--cc=neilb@suse.de \
/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).