* Re: 回复: [RFC PATCH V3] raid1: rewrite the iobarrier ― Linux RAID Storage
[not found] ` <2013091214210358767013@gmail.com>
@ 2013-09-12 6:37 ` NeilBrown
0 siblings, 0 replies; only message in thread
From: NeilBrown @ 2013-09-12 6:37 UTC (permalink / raw)
To: majianpeng; +Cc: linux-raid
[-- Attachment #1: Type: text/plain, Size: 3338 bytes --]
On Thu, 12 Sep 2013 14:21:05 +0800 majianpeng <majianpeng@gmail.com> wrote:
> Hi Neil,
> How about this patchset?
> Thanks!
> Jianpeng Ma
Sorry - it fell of my todo list. I might not be able to look at it properly
for a few weeks (due to leave) but I'll make sure it stays on my list.
NeilBrown
> >Patch1/2/3 are only to easy implemented for patch4.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
> >
> >V3:
> > patch1: rename a paramter make it more understandable.
> > patch2: not change.
> > patch3 draw from patch3 of V2.
> > patch4: reconstruct some code
> > rename some parameters make it more understandable.
> > modify some trivial bugs.
> >
> >V2:http://www.spinics.net/lists/raid/msg44138.html
> >
> >V1:http://www.spinics.net/lists/raid/msg41710.html
> >
> >
> >Jianpeng Ma (4):
> > raid1: Add a filed array_frozen to indicate whether raid in freeze
> > state.
> > radi1: Relace raise_barrier/lower_barrrier with
> > freeze_array/unfreeze_array for reconfigure the array.
> > raid1: Add some macros to make code clearly.
> > raid1: Rewrite the implementation of iobarrier.
> >
> > drivers/md/raid1.c | 151 +++++++++++++++++++++++++++++++++++++++++++----------
> > drivers/md/raid1.h | 15 ++++++
> > 2 files changed, 137 insertions(+), 29 deletions(-)
> >
> >--
> >1.8.1.2
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 828 bytes --]
^ permalink raw reply [flat|nested] only message in thread
only message in thread, other threads:[~2013-09-12 6:37 UTC | newest]
Thread overview: (only message) (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
[not found] <201308281940028090534@gmail.com>
[not found] ` <2013091214210358767013@gmail.com>
2013-09-12 6:37 ` 回复: [RFC PATCH V3] raid1: rewrite the iobarrier ― Linux RAID Storage NeilBrown
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).