Re: Raid5 reads and cpu

2006-09-03 Thread Neil Brown
On Monday August 28, [EMAIL PROTECTED] wrote: > This might be a dumb question, but what causes md to use a large amount of > cpu resources when reading a large amount of data from a raid1 array? I assume you meant raid5 there. md/raid5 shouldn't use that much CPU when reading. It does use more th

Re: RAID6 Problem (in conjunction with nested LVM and encryption)

2006-09-03 Thread Neil Brown
On Monday September 4, [EMAIL PROTECTED] wrote: > Neil Brown <[EMAIL PROTECTED]> wrote: > > > On Sunday September 3, [EMAIL PROTECTED] wrote: > > > >> I have a really really big problem. In fact, the problem is the output of > >> mdadm --examine as shown on > >> http://nomorepasting.com/paste.ph

Re: RAID6 Problem (in conjunction with nested LVM and encryption)

2006-09-03 Thread Bodo Thiesen
Neil Brown <[EMAIL PROTECTED]> wrote: > On Sunday September 3, [EMAIL PROTECTED] wrote: > >> I have a really really big problem. In fact, the problem is the output of >> mdadm --examine as shown on http://nomorepasting.com/paste.php?pasteID=68021 > > Please explain why you think that output is a

Re: Newbie: Kernel panic during RAID1 test & reboot loses one disk

2006-09-03 Thread Neil Brown
On Monday August 28, [EMAIL PROTECTED] wrote: > Neil Brown wrote: > > On Saturday August 26, [EMAIL PROTECTED] wrote: > >> All, > >> > >> [...] > >> > >> * Problem 1: Since moving from 2.4 -> 2.6 kernel, a reboot kicks one > >> device out of the array (c.f. post by Andreas Pelzner on 24th Aug 2006

Re: [PATCH 001 of 4] md: Define backing_dev_info.congested_fn for raid0 and linear

2006-09-03 Thread Neil Brown
On Monday August 28, [EMAIL PROTECTED] wrote: > On Tue, 29 Aug 2006 15:39:24 +1000 > NeilBrown <[EMAIL PROTECTED]> wrote: > > > > > Each backing_dev needs to be able to report whether it is congested, > > either by modulating BDI_*_congested in ->state, or by > > defining a ->congested_fn. > > md

Re: Strange IO stats on RAID1?

2006-09-03 Thread Neil Brown
On Wednesday August 30, [EMAIL PROTECTED] wrote: > Hi all, > > I have an IMAP mail server where mail messages are stored on a RAID1 array. > The access on that array (/dev/md3) has seemed slow, so I did some > investigating. > "iostat -x /dev/hd[bd] /dev/md3" shows this: > > avg-cpu: %user

Re: mdadm dynamic multipathing

2006-09-03 Thread Neil Brown
On Thursday August 31, [EMAIL PROTECTED] wrote: > Hi all, > > Just wondering if there is any way to get mdadm created multipath devices > to re-activate a previously disabled path? > > I know I can > > mdadm /dev/md0 -f /dev/sdx -r /dev/sdx -a /dev/sdx > > to re-activate it, but I want mdadm t

Re: Superblock checksum problems

2006-09-03 Thread Neil Brown
On Saturday September 2, [EMAIL PROTECTED] wrote: > > Attempting to build a new raid5 md array across 4 hard drives. At the > exact moment that the drive finishes rebuilding, the superblock checksum > changes to an invalid value. During the rebuild, mdadm -E for the 4 > drives shows: > >

Re: RAID6 Problem (in conjunction with nested LVM and encryption)

2006-09-03 Thread Neil Brown
On Sunday September 3, [EMAIL PROTECTED] wrote: > Hello GABELN > > I have a really really big problem. In fact, the problem is the output of > mdadm --examine as shown on http://nomorepasting.com/paste.php?pasteID=68021 Please explain why you think that output is a problem. It looks fine to me.

Re: RAID-5 recovery

2006-09-03 Thread Neil Brown
On Sunday September 3, [EMAIL PROTECTED] wrote: > On Sun, 3 Sep 2006, Clive Messer wrote: > > > This leads me to a question. I understand from reading the linux-raid > > archives > > that the current behaviour when rebuilding with a single badblock on > > another > > disk is for that disk to a

RAID-0 on the Intel ICH7R chipset and swap configuration...

2006-09-03 Thread Julio Meca Hansen
Hi, I would like to ask for advice on the following subject: I've recently acquired a FOXCONN 945G7MA-8EKRS2 mATX board, which comes with an Intel ICH7R chipset, and I would like to make a RAID-0 array with 3 disks of equal size (750GB in this case) with an XFS filesystem (system configuration is

Re: RAID-5 recovery

2006-09-03 Thread Martin Schröder
2006/9/4, Clive Messer <[EMAIL PROTECTED]>: Does anyone have a preference for cards other than 3ware if purchasing a 'hardware' raid card? From what have read the 3ware cards are very well regarded and the driver is open source. OpenBSD recommends LSI MegaRaid. Best Martin -- VGER BF report

Re: RAID-5 recovery

2006-09-03 Thread Clive Messer
On Sunday 03 September 2006 14:11, you wrote: > On Sun, 3 Sep 2006, Clive Messer wrote: > > This leads me to a question. I understand from reading the linux-raid > > archives that the current behaviour when rebuilding with a single > > badblock on another disk is for that disk to also be kicked fro

Re: RAID-5 recovery

2006-09-03 Thread Clive Messer
On Sunday 03 September 2006 23:32, you wrote: > On Sun, 3 Sep 2006, Clive Messer wrote: > > This leads me to a question. I understand from reading the linux-raid > > archives that the current behaviour when rebuilding with a single > > badblock on another disk is for that disk to also be kicked fro

Re: RAID-5 recovery

2006-09-03 Thread dean gaudet
On Sun, 3 Sep 2006, Clive Messer wrote: > This leads me to a question. I understand from reading the linux-raid > archives > that the current behaviour when rebuilding with a single badblock on another > disk is for that disk to also be kicked from the array. that's not quite the current behav

Re: serious trouble - raid5 won't assemble properly, vgscan sees no volumes - solved

2006-09-03 Thread Dexter Filmore
Array is online, degraded for the moment but I can access the file systems for backups. I passed -A --force to mdadm, seems that did the trick. What puzzles me still is that I had a degraded array for the third time now and never could tell why it happened in the first place. This time the mac

Re: Feature Request/Suggestion - "Drive Linking"

2006-09-03 Thread Michael Tokarev
Tuomas Leikola wrote: [] > Here's an alternate description. On first 'unrecoverable' error, the > disk is marked as FAILING, which means that a spare is immediately > taken into use to replace the failing one. The disk is not kicked, and > readable blocks can still be used to rebuild other blocks (

Re: RAID6 fallen apart

2006-09-03 Thread Tuomas Leikola
On 9/3/06, Tuomas Leikola <[EMAIL PROTECTED]> wrote: > Possibly safer to recreate with two missing if you aren't sure of the > order. That way you can look in the array to see if it looks right, > or if you have to try a different order. I'd say it's safer to recreate with all disks, in order t

Re: RAID6 fallen apart

2006-09-03 Thread Tuomas Leikola
Possibly safer to recreate with two missing if you aren't sure of the order. That way you can look in the array to see if it looks right, or if you have to try a different order. I'd say it's safer to recreate with all disks, in order to get the resync. Otherwise you risk the all so famous sile

Re: Feature Request/Suggestion - "Drive Linking"

2006-09-03 Thread Tuomas Leikola
This way I could get the replacement in and do the resync without actually having to degrade the array first. 2) This sort of brings up a subject I'm getting increasingly paranoid about. It seems to me that if disk 1 develops a unrecoverable error at block 500 and disk 4 develops one at 55,00

Re: RAID-5 recovery

2006-09-03 Thread Mikael Abrahamsson
On Sun, 3 Sep 2006, Clive Messer wrote: This leads me to a question. I understand from reading the linux-raid archives that the current behaviour when rebuilding with a single badblock on another disk is for that disk to also be kicked from the array. For some time I have considered buying a 3

Re: Kernel RAID support

2006-09-03 Thread John Stoffel
For 2.6.18-rc5-mm1, just edit drivers/md/Kconfig and change the 'if CONFIG_BLOCK' to 'if BLOCK' and you'll be all set. You can then run 'make oldconfig' and you should be all set. It's a simple change, and easier than hunting down and applying a patch at this point. :] -- VGER BF report: U 0.

Re: Kernel RAID support

2006-09-03 Thread David Greaves
Richard Scobie wrote: > Josh Litherland wrote: >> On Sun, 2006-09-03 at 15:56 +1200, Richard Scobie wrote: >> >>> I am building 2.6.18rc5-mm1 and I cannot find the entry under "make >>> config", to enable the various RAID options. >> >> >> Under "Device Drivers", switch on "Multi-device support".

RAID-5 recovery

2006-09-03 Thread Clive Messer
Hi, I lost a disk from a 4 disk RAID-5 array; usually not a problem, investigate and add it back in. Normally nothing wrong with the disk, possibly a ICH6 libata bug when heavy IO is taking place. Yesterday when adding it back to the array, I run into a problem with 3 badblocks on one of the o