* Linux 3.3.1 resync speed
@ 2012-04-02 21:21 Mathias Burén
2012-04-02 21:23 ` Mathias Burén
2012-04-02 21:28 ` Larkin Lowrey
0 siblings, 2 replies; 4+ messages in thread
From: Mathias Burén @ 2012-04-02 21:21 UTC (permalink / raw)
To: Linux-RAID
Hi mailing list,
On my old
model name : Intel(R) Atom(TM) CPU 330 @ 1.60GHz
I'm currently seeing a resync speed of around 200MB/s!
~ $ cat /proc/mdstat
Personalities : [raid6] [raid5] [raid4]
md0 : active raid6 sdg1[0] sde1[7] sdh1[8] sdf1[5] sdc1[3] sdd1[4] sdb1[9]
9751756800 blocks super 1.2 level 6, 64k chunk, algorithm 2
[7/7] [UUUUUUU]
[======>..............] check = 32.6% (636923520/1950351360)
finish=111.2min speed=196740K/sec
unused devices: <none>
This ia almost 10 times higher than what I used to see on 3.2 and
earlier. What's that about? The array is a 7 drive RAID6:
$ sudo mdadm -D /dev/md0
/dev/md0:
Version : 1.2
Creation Time : Tue Oct 19 08:58:41 2010
Raid Level : raid6
Array Size : 9751756800 (9300.00 GiB 9985.80 GB)
Used Dev Size : 1950351360 (1860.00 GiB 1997.16 GB)
Raid Devices : 7
Total Devices : 7
Persistence : Superblock is persistent
Update Time : Mon Apr 2 22:18:14 2012
State : clean, checking
Active Devices : 7
Working Devices : 7
Failed Devices : 0
Spare Devices : 0
Layout : left-symmetric
Chunk Size : 64K
Check Status : 32% complete
Name : ion:0 (local to host ion)
UUID : e6595c64:b3ae90b3:f01133ac:3f402d20
Events : 6773811
Number Major Minor RaidDevice State
0 8 97 0 active sync /dev/sdg1
9 8 17 1 active sync /dev/sdb1
4 8 49 2 active sync /dev/sdd1
3 8 33 3 active sync /dev/sdc1
5 8 81 4 active sync /dev/sdf1
8 8 113 5 active sync /dev/sdh1
7 8 65 6 active sync /dev/sde1
Best regards,
Mathias
^ permalink raw reply [flat|nested] 4+ messages in thread* Re: Linux 3.3.1 resync speed
2012-04-02 21:21 Linux 3.3.1 resync speed Mathias Burén
@ 2012-04-02 21:23 ` Mathias Burén
2012-04-02 21:28 ` Larkin Lowrey
1 sibling, 0 replies; 4+ messages in thread
From: Mathias Burén @ 2012-04-02 21:23 UTC (permalink / raw)
To: Linux-RAID
On 2 April 2012 22:21, Mathias Burén <mathias.buren@gmail.com> wrote:
> Hi mailing list,
>
> On my old
>
> model name : Intel(R) Atom(TM) CPU 330 @ 1.60GHz
>
> I'm currently seeing a resync speed of around 200MB/s!
>
> ~ $ cat /proc/mdstat
> Personalities : [raid6] [raid5] [raid4]
> md0 : active raid6 sdg1[0] sde1[7] sdh1[8] sdf1[5] sdc1[3] sdd1[4] sdb1[9]
> 9751756800 blocks super 1.2 level 6, 64k chunk, algorithm 2
> [7/7] [UUUUUUU]
> [======>..............] check = 32.6% (636923520/1950351360)
> finish=111.2min speed=196740K/sec
>
> unused devices: <none>
>
> This ia almost 10 times higher than what I used to see on 3.2 and
> earlier. What's that about? The array is a 7 drive RAID6:
>
> $ sudo mdadm -D /dev/md0
> /dev/md0:
> Version : 1.2
> Creation Time : Tue Oct 19 08:58:41 2010
> Raid Level : raid6
> Array Size : 9751756800 (9300.00 GiB 9985.80 GB)
> Used Dev Size : 1950351360 (1860.00 GiB 1997.16 GB)
> Raid Devices : 7
> Total Devices : 7
> Persistence : Superblock is persistent
>
> Update Time : Mon Apr 2 22:18:14 2012
> State : clean, checking
> Active Devices : 7
> Working Devices : 7
> Failed Devices : 0
> Spare Devices : 0
>
> Layout : left-symmetric
> Chunk Size : 64K
>
> Check Status : 32% complete
>
> Name : ion:0 (local to host ion)
> UUID : e6595c64:b3ae90b3:f01133ac:3f402d20
> Events : 6773811
>
> Number Major Minor RaidDevice State
> 0 8 97 0 active sync /dev/sdg1
> 9 8 17 1 active sync /dev/sdb1
> 4 8 49 2 active sync /dev/sdd1
> 3 8 33 3 active sync /dev/sdc1
> 5 8 81 4 active sync /dev/sdf1
> 8 8 113 5 active sync /dev/sdh1
> 7 8 65 6 active sync /dev/sde1
>
> Best regards,
> Mathias
It was actually capped at 200000 KB/s in
/sys/block/md0/md/sync_speed_max . I raised that by a factor of 100,
and I am now seeing:
$ cat /proc/mdstat
Personalities : [raid6] [raid5] [raid4]
md0 : active raid6 sdg1[0] sde1[7] sdh1[8] sdf1[5] sdc1[3] sdd1[4] sdb1[9]
9751756800 blocks super 1.2 level 6, 64k chunk, algorithm 2
[7/7] [UUUUUUU]
[======>..............] check = 34.8% (679312336/1950351360)
finish=70.2min speed=301438K/sec
unused devices: <none>
I'm not complaining, just very surprised and I'm wondering if
everything is OK. Usually a check takes around 20-24 hours.
Mathias
--
To unsubscribe from this list: send the line "unsubscribe linux-raid" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply [flat|nested] 4+ messages in thread* Re: Linux 3.3.1 resync speed
2012-04-02 21:21 Linux 3.3.1 resync speed Mathias Burén
2012-04-02 21:23 ` Mathias Burén
@ 2012-04-02 21:28 ` Larkin Lowrey
2012-04-02 21:30 ` Mathias Burén
1 sibling, 1 reply; 4+ messages in thread
From: Larkin Lowrey @ 2012-04-02 21:28 UTC (permalink / raw)
To: Mathias Burén; +Cc: Linux-RAID
This is a known issue and a patch has been submitted. I'm not sure when
it is scheduled to appear in the kernel.
There will be no actual disk I/O during the raid check and the array
will not actually be checked.
--Larkin
On 4/2/2012 4:21 PM, Mathias Burén wrote:
> Hi mailing list,
>
> On my old
>
> model name : Intel(R) Atom(TM) CPU 330 @ 1.60GHz
>
> I'm currently seeing a resync speed of around 200MB/s!
>
> ~ $ cat /proc/mdstat
> Personalities : [raid6] [raid5] [raid4]
> md0 : active raid6 sdg1[0] sde1[7] sdh1[8] sdf1[5] sdc1[3] sdd1[4] sdb1[9]
> 9751756800 blocks super 1.2 level 6, 64k chunk, algorithm 2
> [7/7] [UUUUUUU]
> [======>..............] check = 32.6% (636923520/1950351360)
> finish=111.2min speed=196740K/sec
>
> unused devices: <none>
>
> This ia almost 10 times higher than what I used to see on 3.2 and
> earlier. What's that about? The array is a 7 drive RAID6:
>
> $ sudo mdadm -D /dev/md0
> /dev/md0:
> Version : 1.2
> Creation Time : Tue Oct 19 08:58:41 2010
> Raid Level : raid6
> Array Size : 9751756800 (9300.00 GiB 9985.80 GB)
> Used Dev Size : 1950351360 (1860.00 GiB 1997.16 GB)
> Raid Devices : 7
> Total Devices : 7
> Persistence : Superblock is persistent
>
> Update Time : Mon Apr 2 22:18:14 2012
> State : clean, checking
> Active Devices : 7
> Working Devices : 7
> Failed Devices : 0
> Spare Devices : 0
>
> Layout : left-symmetric
> Chunk Size : 64K
>
> Check Status : 32% complete
>
> Name : ion:0 (local to host ion)
> UUID : e6595c64:b3ae90b3:f01133ac:3f402d20
> Events : 6773811
>
> Number Major Minor RaidDevice State
> 0 8 97 0 active sync /dev/sdg1
> 9 8 17 1 active sync /dev/sdb1
> 4 8 49 2 active sync /dev/sdd1
> 3 8 33 3 active sync /dev/sdc1
> 5 8 81 4 active sync /dev/sdf1
> 8 8 113 5 active sync /dev/sdh1
> 7 8 65 6 active sync /dev/sde1
>
> Best regards,
> Mathias
> --
> To unsubscribe from this list: send the line "unsubscribe linux-raid" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
>
--
To unsubscribe from this list: send the line "unsubscribe linux-raid" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: Linux 3.3.1 resync speed
2012-04-02 21:28 ` Larkin Lowrey
@ 2012-04-02 21:30 ` Mathias Burén
0 siblings, 0 replies; 4+ messages in thread
From: Mathias Burén @ 2012-04-02 21:30 UTC (permalink / raw)
To: Larkin Lowrey; +Cc: Linux-RAID
On 2 April 2012 22:28, Larkin Lowrey <llowrey@nuclearwinter.com> wrote:
> This is a known issue and a patch has been submitted. I'm not sure when
> it is scheduled to appear in the kernel.
>
> There will be no actual disk I/O during the raid check and the array
> will not actually be checked.
>
> --Larkin
>
Ok, thanks for letting me know. I thought it looked too good to be
true. I'm actually observing this on 3.3.0, not 3.3.1 as I originally
reported.
Mathias
^ permalink raw reply [flat|nested] 4+ messages in thread
end of thread, other threads:[~2012-04-02 21:30 UTC | newest]
Thread overview: 4+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2012-04-02 21:21 Linux 3.3.1 resync speed Mathias Burén
2012-04-02 21:23 ` Mathias Burén
2012-04-02 21:28 ` Larkin Lowrey
2012-04-02 21:30 ` Mathias Burén
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox