Re: Help recreating a raid5
Neil Brown wrote: On Sunday April 2, [EMAIL PROTECTED] wrote: From some archive reading I understand that I can recreate the array using mdadm --create /dev/md1 -l5 -n3 /dev/sdd1 /dev/sdb1 missing but that I need to specify the correct order for the drives. I've not used --assume-clean, --force or --run; should I? I assume that since it's only got 2 of 3 then it won't need the assume-clean. The detail and dmesg data suggests that the order in the command above is correct. Can anyone confirm this? Yes, that all looks correct. Thanks Neil That seemed to work. Now I need to find out if I have bad hardware or if there is something (else) wrong with libata :) David - To unsubscribe from this list: send the line unsubscribe linux-raid in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html
How is an IO size are determnied ?
Neil/Jens Hello.
Hope is this not too much bother for you.
Question: how does the psuedo device ( /dev/md ) change the
IOs sizes going down into the disks ?
Explanation:
I am using software raid5 , chunk size is 1024K, 4 disks.
I have made a hook in make_request inorder to bypass
the raid5 IO methodology .I need to control the amount of IOs
going down into the disk and their sizes.
the hook looks like this.
static int make_request (request_queue_t *q, struct bio * bi){
...
if ( bypass_raid5 bio_data_dir(bi) == READ )
{
new_sector = raid5_compute_sector(bi-bi_sector,
raid_disks,
data_disks,
dd_idx,
pd_idx,
conf);
bi-bi_sector = new_sector;
bi-bi_bdev = conf-disks[dd_idx].rdev-bdev;
return 1;
}
...
}
I have compared the IOs sizes and numbers in the deadline elevator.
it seems that an a single direct IO read of 1MB to a disk
is divided into two 1/2 MB request_t ( though max_hw_sectors=2048)
and when I go through the raid i am getting three request_t's
992 sectors followed by 64 sectors followed by 992 sectors.
I have also recorded the IOs going in make_request in this
scenario, it is composed of 8 124K and an additional 32K
request.
the test:
My test is simple . I am reading the device in direct io mode
and no file system in involved.
could you explain this ? why I am not getting two 1/2 MB ?
Could it be the slab cache ? ( biovec256)
Thank you
--
Raz
-
To unsubscribe from this list: send the line unsubscribe linux-raid in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
RAID rebuild I/O bandwidth
Hi Folks, I am doing some research on calculating I/O performance of a raid array. I want to test the RAID rebuild. Can anyone specify what raid rebuild I/O bandwidth is? How should I set 10MB/sec of rebuild I/O bandwidth? How should I measure time to rebuild a disk? Thanks in advance, Thanks, Yogesh - To unsubscribe from this list: send the line unsubscribe linux-raid in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html
Cheap Motherboards and Linux RAID
If you happen to be unfortunate enough to have also purchased a cheap ASUS K8N VM with the Nforce410 chipset in order to get the software RAID (or anything for that matter) to work you have to disable APIC . This means APIC modules must not be loaded. Joe Olstad, Solid Computing Corp Edmonton, Canada 780-710-FAST - Original Message - From: Jeff Garzik [EMAIL PROTECTED] Date: Monday, April 3, 2006 4:28 am Subject: Re: Softraid controllers and Linux Jim Klimov wrote: Hello linux-raid, I have tried several cheap RAID controllers recently (namely, VIA VT6421, Intel 6300ESB and Adaptec/Marvell 885X6081). VIA one is a PCI card, the second two are built in a Supermicro motherboard (E7520/X6DHT-G). The intent was to let the BIOS of the controllers make a RAID1 mirror of two disks independently of an OS to make redundant multi-OS booting transparent. While DOS and Windows saw their mirrors as a singular block device, Linux (FC5) accessed the two drives separately on all adapters. You did not buy a RAID controller. http://linux-ata.org/faq-sata-raid.html If you really want to use proprietary RAID on Linux, you may use dmraid, but using MD for software RAID is much more robust. Jeff - To unsubscribe from this list: send the line unsubscribe linux- raid in the body of a message to [EMAIL PROTECTED] 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 [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: I dropped 42 Lbs in 4 days
replied on this one privately. :) for the rest, I handle 300 spams a day (once you are someones list, getting off is hard work). still, to see it here... I found that rather unusual (hence the comment). sorry bout that (and yeah, I am fairly conversant with netiquette. this one just took me by surprise is all. :) On Monday 03 April 2006 11:23, David Greaves wrote: This would be a phenomenon known as 'spam' - if you don't recognise it yet, don't worry, you soon will :) Netiquette says you ignore it, not reply to all. Mind you, netiquette says a lot of things that fewer and fewer people seem to heed... Google for netiquette if you are interested. David (Who knows he shouldn't have replied) - To unsubscribe from this list: send the line unsubscribe linux-raid in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: Cheap Motherboards and Linux RAID
If you happen to be unfortunate enough to have also purchased a cheap ASUS K8N VM with the Nforce410 chipset in order to get the software RAID And if you are also unfortunate enough to have bought some newer Maxtor SATA harddrives, use the jumper on the drive to revert to SATA150 instead of SATA300 ; this will prevent your drives from randomly failing (and losing all data) every 2-5 days. If your drive has no jumper, you (should) be safe (hopefully). This bug is agnostic and hits windows and linux, with nforce 3 and 4 chipsets. On the SATA150 position, the machine has been running smoothly for a few months with no problem whatsoever. (or anything for that matter) to work you have to disable APIC . This means APIC modules must not be loaded. - To unsubscribe from this list: send the line unsubscribe linux-raid in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: [PATCH] mdadm: monitor event argument passing
Neil Brown wrote: On Friday March 31, [EMAIL PROTECTED] wrote: I've been looking at the mdadm monitor, and thought it might be useful if it allowed extra context information (in the form of command line arguments) to be sent to the event program, so instead of just: # mdadm -F /dev/md0 -p md_event you could do something like: # mdadm -F /dev/md0 -p md_event -i some_info And the -i some_info will be passed on the command line to the event program. Of course you can usually figure out what the extra context should be in the event program itself, but it may take more work. I would recommend the use of environment variables for this: md_event_context=some_info mdadm -F /dev/md0 -p md_event Does that work for you? Yes, that would work. Thanks, Paul - To unsubscribe from this list: send the line unsubscribe linux-raid in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: I dropped 42 Lbs in 4 days
On Mon, Apr 03, 2006 at 11:04:48AM -0700, Technomage wrote: pardon my asking but... HUH?!?!? Sometimes spams do leak thru to the lists. How and why is explained in LKML-FAQ. On Monday 03 April 2006 17:46, Alice wrote: I lost 30lbs in w eeks snip url /Matti Aarnio - To unsubscribe from this list: send the line unsubscribe linux-raid in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html
Help needed - RAID5 recovery from Power-fail
I wonder if you could help a Raid Newbie with a problem I had a power fail, and now I can't access my RAID array. It has been working fine for months until I lost power... Being a fool, I don't have a full backup, so I really need to get this data back. I run FC4 (64bit). I have an array of two disks /dev/sda1 and /dev/sdb1 as a raid5 array /dev/md0 on top of which I run lvm and mount the whole lot as /home. My intention was always to add another disk to this array, and I purchased one yesterday. When I boot, I get: md0 is not clean Cannot start dirty degraded array failed to run raid set md0 I can provide the following extra information: # cat /proc/mdstat Personalities : [raid5] unused devices: none # mdadm --query /dev/md0 /dev/md0: is an md device which is not active # mdadm --query /dev/md0 /dev/md0: is an md device which is not active /dev/md0: is too small to be an md component. # mdadm --query /dev/sda1 /dev/sda1: is not an md array /dev/sda1: device 0 in 2 device undetected raid5 md0. Use mdadm --examine for more detail. #mdadm --query /dev/sdb1 /dev/sdb1: is not an md array /dev/sdb1: device 1 in 2 device undetected raid5 md0. Use mdadm --examine for more detail. # mdadm --examine /dev/md0 mdadm: /dev/md0 is too small for md # mdadm --examine /dev/sda1 /dev/sda1: Magic : a92b4efc Version : 00.90.02 UUID : c57d50aa:1b3bcabd:ab04d342:6049b3f1 Creation Time : Thu Dec 15 15:29:36 2005 Raid Level : raid5 Raid Devices : 2 Total Devices : 2 Preferred Minor : 0 Update Time : Tue Mar 21 06:25:52 2006 State : active Active Devices : 1 Working Devices : 1 Failed Devices : 2 Spare Devices : 0 Checksum : 2ba99f09 - correct Events : 0.1498318 Layout : left-symmetric Chunk Size : 128K Number Major Minor RaidDevice State this 0 810 active sync /dev/sda1 0 0 810 active sync /dev/sda1 1 1 001 faulty removed #mdadm --examine /dev/sdb1 /dev/sdb1: Magic : a92b4efc Version : 00.90.02 UUID : c57d50aa:1b3bcabd:ab04d342:6049b3f1 Creation Time : Thu Dec 15 15:29:36 2005 Raid Level : raid5 Raid Devices : 2 Total Devices : 2 Preferred Minor : 0 Update Time : Tue Mar 21 06:23:57 2006 State : active Active Devices : 2 Working Devices : 2 Failed Devices : 0 Spare Devices : 0 Checksum : 2ba99e95 - correct Events : 0.1498307 Layout : left-symmetric Chunk Size : 128K Number Major Minor RaidDevice State this 1 8 171 active sync /dev/sdb1 0 0 810 active sync /dev/sda1 1 1 8 171 active sync /dev/sdb1 It looks to me like there is no hardware problem, but maybe I am wrong. I cannot find any file /etc/mdadm.confnor /etc/raidtab. How would you suggest I proceed? I'm wary of doing anything (assemble, build, create) until I am sure it won't reset everything. Many Thanks Nigel - To unsubscribe from this list: send the line unsubscribe linux-raid in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: Help needed - RAID5 recovery from Power-fail
On Monday April 3, [EMAIL PROTECTED] wrote: I wonder if you could help a Raid Newbie with a problem I had a power fail, and now I can't access my RAID array. It has been working fine for months until I lost power... Being a fool, I don't have a full backup, so I really need to get this data back. I run FC4 (64bit). I have an array of two disks /dev/sda1 and /dev/sdb1 as a raid5 array /dev/md0 on top of which I run lvm and mount the whole lot as /home. My intention was always to add another disk to this array, and I purchased one yesterday. 2 devices in a raid5?? Doesn't seem a lot of point it being raid5 rather than raid1. When I boot, I get: md0 is not clean Cannot start dirty degraded array failed to run raid set md0 This tells use that the array is degraded. A dirty degraded array can have undetectable data corruption. That is why it won't start it for you. However with only two devices, data corruption from this cause isn't actually possible. The kernel parameter md_mod.start_dirty_degraded=1 will bypass this message and start the array anyway. Alternately: mdadm -A --force /dev/md0 /dev/sd[ab]1 # mdadm --examine /dev/sda1 /dev/sda1: Magic : a92b4efc Version : 00.90.02 UUID : c57d50aa:1b3bcabd:ab04d342:6049b3f1 Creation Time : Thu Dec 15 15:29:36 2005 Raid Level : raid5 Raid Devices : 2 Total Devices : 2 Preferred Minor : 0 Update Time : Tue Mar 21 06:25:52 2006 State : active Active Devices : 1 So at 06:25:52, there was only one working devices, while... #mdadm --examine /dev/sdb1 /dev/sdb1: Magic : a92b4efc Version : 00.90.02 UUID : c57d50aa:1b3bcabd:ab04d342:6049b3f1 Creation Time : Thu Dec 15 15:29:36 2005 Raid Level : raid5 Raid Devices : 2 Total Devices : 2 Preferred Minor : 0 Update Time : Tue Mar 21 06:23:57 2006 State : active Active Devices : 2 at 06:23:57 there were two. It looks like you lost a drive a while ago. Did you notice? Anyway, the 'mdadm' command I gave above should get the array working again for you. Then you might want to mdadm /dev/md0 -a /dev/sdb1 is you trust /dev/sdb NeilBrown - To unsubscribe from this list: send the line unsubscribe linux-raid in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html
