Ubuntu Servers :: Raid1 Reads At Single Disk Speed?
May 3, 2011
im on 10.10(desktop) and mdadm was v2.8.1 from 2008, very out of date so i tried 3.2.1 -> no change. mdadm raid1 read speeds are the same as single disk. note i used the tests in the disk utility benchmarking tool at first --these showed raid 5 atleast to be much better but when i tried dd reads raid5 dropped off with larger data to almost the same (slow) speed as raid1. compare:
[code]....
using two partitions will be enough to show raid1 performs at single disk speed. I dont really want to use a 4 disk raid0 just to get the read speed i should be able to get with raid1 as i dont really care about the size loss. I would of course use raid10 but i have found this suffers from the same problem (achieve same read speed as 2 disk stripe). So whilst im shocked others aren't reporting this, unless there is some obscure reason why my system would give these results i think raid1 in not behaving as it should.
View 6 Replies
ADVERTISEMENT
May 5, 2010
I have an Ubuntu Server on (8.10) running under Citrix XenServer (though that shouldn't make a difference).
I installed on a single disk:
xvda1 - 200 MB - /boot
xvda2 - 9.8 GB - LVM (ubuntu-base)
The LVM is:
swap - 1.0 GB
root - 8.8 GB - /
I have successfully gotten this converted to RAID1 by adding a new drive (xvdb) and following the Debian howtoforge article [URL]
What I have not been able to do, is get grub working properly.
If I fail xvdb and reboot the system, everything comes up and I can reboot and run.
If I fail xvda and reboot the system, XenServer gives me a bootloader error. i.e.: no grub
If someone has done this, can they tell me what grub commands to run to get a successful boot of the primary disk fails?
View 1 Replies
View Related
Apr 5, 2011
I recently had an issue where one of my RAID1 configured drives died on a Debian box. By die, I mean after post, I am presented with a black screen and flashing cursor, nothing more. I booted into a knoppix shell and did:
mdadm --assemble /dev/md0 --run -u <UUID of the only working drive> /dev/sda1
I could then 'mount /dev/sda1 /mnt/' and see all the contents as I should be able to. However, I cannot boot from this device by itself for some reason. I have reinstalled grub 'grub-install --recheck --rootdirectory=/mnt /dev/sda1' #something like that, can't remember the exact --rootdirectory command without the switch. I restarted, with the failed drive unplugged, and again, I'm faced with the black screen, flashing cursor.
View 1 Replies
View Related
Jul 13, 2011
I was analyzing the Disk read using hdparm utility. This is what i got as a result.
Code:
# hdparm -t /dev/sda
/dev/sda:
Timing buffered disk reads: 108 MB in 3.04 seconds = 35.51 MB/sec
Code:
# hdparm -T /dev/sda
/dev/sda:
Timing cached reads: 3496 MB in 1.99 seconds = 1756.56 MB/sec I m not sure what does Cache read and buffered disk read mean.
View 1 Replies
View Related
Jul 2, 2010
We are graphing various system parameters using Cacti. One of our graphs shows hard drive reads and writes. A question came up: why do we need this graph?
View 3 Replies
View Related
Mar 27, 2011
i have amd athlon x2 3gb RAM ddr2 two hdd one 80gb other 1tb in this computer i got only ubuntu all disk in EXT4.i want to copy 10gb many file of 700mb or 1gb ( many linux ISO )the transfer is 1mb/s this is SOOO SLOW.i did a touch /forcefsck just in case but nothing happen it is still slow!!what might be the problem ??
View 1 Replies
View Related
Aug 1, 2010
I had done a new lucid install to a 1 TB RAID 1 array using the alternate CD a few weeks back. I messed up that system trying to some hardware working that lucid doesn't have drivers for yet, so I gave up on it and reinstalled to a single 80 GB disk that I now want to move over to the RAID array.
I moved all of the existing files on the array to a single folder, then copied all of the folders from the 80 GB disk over to the array with permissions and symlinks (minus the contents of /proc and /sys, which I created empty).
These are the commands I used:
Quote:
p -a -d -R -v -t /media/raid_array /b*
cp -a -d -R -v -t /media/raid_array /d*
cp -a -d -R -v -t /media/raid_array /e*
cp -a -d -R -v -t /media/raid_array /h*
[Code]....
I tried to change fstab to use the 689a... for root, but when I try to boot, it's still trying to open /dev/disk/by-uuid/412d...
So then I booted from the single disk again and chrooted into the array, then ran update-initramfs -u. I got 3 "grep: /proc/modules: No such file or directory" errors, and "cat: /proc/cmdline: No such file or directory"- so I created directory /proc/modules, created an empty file /proc/cmdline, and ran the initramfs update again. Then I tried to shut down, which hung (probably because I was doing all of this from a terminal window in Gnome), so I killed the power after a couple of minutes.
It's still trying to use /dev/disk/by-uuid/412d... to boot.
What am I missing? I assume I just have to change the UUID to mount as root, but I don't know how.
View 2 Replies
View Related
Oct 27, 2010
I have a hypothetical situation in which I installed my operating system using a RAID1 mirror. At some point I decided that this setup was overkill, my machine isn't system critical, I value doubling my storage space more than speedy recovery, I'm doing routine backups, etc...
Short of backing up my system volume and repartitioning, or otherwise starting over, is there a way I can reconfigure my RAID1 array to only expect one disk so that mdadm no longer reports a Degraded state?
View 3 Replies
View Related
Oct 16, 2009
my Fedora 11 system is not starting anylonger. It stops with the message:
Code:
VFS: Can't find ext4 filesystem on dev dm-0
The system told me since a while, that a lot of the sectors of one disk of the (software) RAID compound are failed already. So tried to disconnect each of the disks and start them separately. Unfortunaltly this is not working (for one its is not working at all, the other wents the same far as with both), when I tried to recover the system with the Fedora DVD, it said no distribution found. I am quite new and do not know so much about linux system, so i do not know what further information you could need. Maybe it can be important, that both disks are encryped (the system wents so far, that I can type in the password).
View 2 Replies
View Related
Jun 9, 2010
I have two 80 GB IDE hard disk. I have create raid1 partition in both drive using [URL] ink. raid is working fine. But i have copy some data on one hard disk (md0) but this data is not autometically copy in second hard disk(md1). I want when data is write on one hard disk, this data autometically write in second hard disk.
View 11 Replies
View Related
Dec 7, 2010
Just finished installing F14 with RAID1 setup for 2 hdd (SATA''s). Entire drives are mirrored, including SWAP. As I had done in the past, I was planning on installing grub on MBR of 2nd hdd. In prep for this I did the following to locate the grub setup files:
grub> find /grub/stage1
find /grub/stage1
(hd0,1)
[code]....
I was surprised, expected to get (hd0,0) & (hd1,0), not (hd0,1) & (hd1,1)
running "fdisk -l" I get:
Disk /dev/sda: 120.0 GB, 120034123776 bytes
255 heads, 63 sectors/track, 14593 cylinders, total 234441648 sectors
Units = sectors of 1 * 512 = 512 bytes
[code]....
MBR is the first 512 bytes of the drive. Each partition has a boot sector. In my case grub stage 1 is on 2nd partition of sda & 2nd partition of sdb. What i dont understand is how grub stage 1 can be on sda2 & sdb2, since I am assuming that sda1 & sdb1 would be the first partitions of the drives & therefore contain the MBR's. Maybe this might be because sda1 & sdb1 are SWAP partitions?
View 5 Replies
View Related
Mar 23, 2010
Recently i am trying to check on the rsync speed for single file(2.4GB iso) directory ( 900MB directory with files inside ) When i run the rsync for single file: the speed i get is average 50MBps However, for a directory: average speed is 10MBps Is there any reason behind this ? i tried to google but unable to get the concept.
View 2 Replies
View Related
Apr 22, 2010
I'm planing to copy a productive mysql innodb file from one server to another, and the file size is around 300GB. As the file is keeping changing all the time, I have to shutdown mysql instance and copy the large data file to other server as quickly as possible.I should have to find a way to speed up file copying ... I'm wondering whether there's a way to copy file block by block.If the destination side block has same content, then bypass it.
View 4 Replies
View Related
Jun 8, 2011
Is there a difference between raid1 and ordinary hard disk?
View 11 Replies
View Related
Mar 12, 2011
I've read many of the postings on ICH10R and grub but none seem to give me the info I need. Here's the situation: I've got an existing server on which I was running my RAID1 pair boot/root drive on an LSI based RAID chip; however there are system design issues I won't bore you with that mean I need to shift this RAID pair to the fakeraid (which happens to most reliably come up sda, etc). So far I've been able to configure the fakeraid pair as 'Adaptec' and build the RAID1 mirror with new drives; it shows up just fine in the BIOS where I want it.
Using a pre-prepared 'rescue' disk with lots of space, I dd'd the partitions from the old RAID device; then I rewired things, rebooted, fired up dmraid -ay and got the /dev/mapper/ddf1_SYS device. Using cfdisk, I set up three extended partitions to match the ones on the old RAID; mounted them; loopback mounted the images of the old partitions; then used rsync -aHAX to dup the system and home to the new RAID1 partitions. I then edited the /etc/fstab to change the UUID's; likewise the grub/menu.list (This is an older system that does not have the horror that is grub2 installed) I've taken a look at the existing initrd and believe it is all set up to deal with dmraid at boot. So that leaves only the grub install. Paranoid that I am, I tried to deal with this:
dmraid -ay
mount /dev/mapper/ddf1_SYS5 /newsys
cd /newsys
[code]....
and I get messages about 'does not have any corresponding BIOS drive'. I tried editing grub/device.conf, tried --recheck and any thing else I could think of, to no avail. I have not tried dd'ing an mbr to sector 0 yet as I am not really sure whether that will kill info set up by the fakeraid in the BIOS. I might also add that the two constituent drives show up as /dev/sda and /dev/sdb and trying to use either of those directly results in the same error messages from grub. Obviously this sort of thing is in the category of 'kids don't try this at home', but I have more than once manually put a unix disk together one file at a time, so much of the magic is not new to me.
View 2 Replies
View Related
Dec 18, 2010
I have an external sata dock for hdd that give me a lot of error till linux decided to lower the speed of it to 1.5 then it start work well
View 2 Replies
View Related
Jul 22, 2011
I have SLES10-SP3 running on an Intel SR1600URHS board with 3 hot-swap SATA disks configured using mdadm as Raid1 with hot spare. If I pull one of the active disks, all file i/o will stop for about 2.5 minutes after which it will start again and the raid array will be rebuilt using the spare disk. Is there any way I can reduce this 2.5 minutes of inactivity? I've tried setting /sys/block/sdX/device/timeout and /sys/block/sdX/device/retries to 1 for all disks, but this hasn't made any difference. The output from messages is:
12:11:56: ata2.00: exception Emask 0x0 SAct 0x0 SErr 0x0 action 0x2 frozen
12:11:56: ata2.00: cmd ea/00:00:00:00:00/00:00:00:00:00/a0 tag 0 cdb 0x1e data 0
12:11:56: res 40/00:03:00:00:20/00:00:00:00:00/b0 Emask 0x4 (timeout)
[code]....
View 1 Replies
View Related
Aug 11, 2010
intending to set up an all-in-one server, i threw in the ubuntu server 10.04 (amd64) cd. during the text-install, i set up the device-topology below, and it worked.
[Code]....
then i tested my raid by hot-pulling off the sda wire (ouch). worked fine, system still worked, and it also managed rebooting from the left sdb (which of course showed up being sda, lacking the first drive). now i am trying to recover this pre-crash state. adding the first disk (showing up as sdb), i can add it to md0 and let it start syncronizing for 2 hours. but... i can?t boot anymore with the recovered first disk being sda...
at first, booting got stuck in an initrd-prompt after complaining it couldn?t find my sys-logical volume. after a lot of trial and error i don?t even get any complaints, just a black screen which would let me wait for a boot for weeks... so, my system does not boot from my first disk, whether i plug in the second or not. my second disk still boots. my last attempt to get booting fine again has been: zero sda?s first and last gigabyte to kill any ids duplicate sdb?s first cylinder to sda to make it bootable reinitialize sdb?s part.table using command o in fdisk for a new disk-id recreate sda1 partition add sda1 to md0
View 1 Replies
View Related
Jan 5, 2011
I had a thread earlier asking for help installing Ubuntu Server to my homemade atom based NAS, but I gave up on that (GUI's are more helpful to me ) and so now I'm running Ubuntu 10.10 Desktop 64bit edition.Last night I was finally able to get mdadm set up. I have two 1TB disks set up in RAID1 config. I used
Code:
sudo mdadm --create /dev/md0 --level=1 --raid-devices=2 /dev/sdb1 /dev/sdc1
to create the array, and then waited until it finished assembling. Then I used System>Administration>Disk
[code]....
View 1 Replies
View Related
Feb 1, 2011
We have had a hardisk crash in our RAID1 webhosting server running CentOS5 and Plesk. We first realized something was wrong when our main site didn't load but showed MySQL errors. We then found out that the system was in read-only state. Something that also happened the day before yesterday, but we could fix with a FSCK. Then the system worked well til around 18 hours later when it crashed with the same sympoms. So, we rebooted the server and wanted to do a filesystem check again. But the HDD wouldnt even load. It was gone. Unfortunatelly it was not realized that the second disk in the system was also not working any more for some time now. Fortunatelly we had our main site backed up externally though. So we could re-install a fresh box and mounted the two drives to the system. We checked the harddisk. One is practically empty (the older one), the other has almost only files in 'lost + found' but these are all "numbered", no real filenames or so.
View 2 Replies
View Related
Jul 29, 2010
I have built a small test server. I am planing on using this machine a an email and web server to test out its hosting capacities. in the future I will build a larger and more well equipped version.
AMD Athlon x2 2.0ghz
2 160gb SATA drives (hardware raid 1, done through the Motherboard)
2 gb ram (dual channel)
Like I said small test server. I am trying to install 10.04 server edition. When I get to the point of partitioning it asks me to activate the raid so I do. I get through the guided partitioning and get ready to write the file system to the drives and the screen goes red and says that it has failed. On a side note, this works if i install it on the same drives without any raid configuration.
View 6 Replies
View Related
Feb 7, 2011
I have a RAID1 array, where mdadm states that one of the disks is "removed." Naturally, I assume one of the drives has failed. The mdadm --detail command tells me that the sda drive has failed. However, further inspection from the mdadm -E /dev/sdb1 command says that sdb1 disk has been removed. I am a bit confused. Can someone clarify which drive is failed? Am I misreading the command outputs?
Code:
sudo fdisk -l
Disk /dev/sda: 500.1 GB, 500107862016 bytes
255 heads, 63 sectors/track, 60801 cylinders
Units = cylinders of 16065 * 512 = 8225280 bytes
Sector size (logical/physical): 512 bytes / 512 bytes
[Code]...
View 3 Replies
View Related
Nov 14, 2010
One of the hard drives in my server failed the other day, backups saved the day and downtime was only a few hours, but when setting up the new drive I went ahead and migrated to software RAID, in the hopes it may give me less downtime in the future when a drive fails. It all went rather well, but my main root partition won't finish syncing for some reason.
sda was the original drive with sda4 as /, sda1 as /boot, and sda2 as swap. sdb was the drive that failed and was replaced with the new drive. So I set up sdb with the same partitions of sda, added it to a RAID1 array, copied files from sda, and reboot to md4 as /, md1 as /boot, and md2 as swap. I added the sda partitions to the array, and the sync went off without a hitch on md1 and md2, md4 progresses well, but after a few hours /proc/mdstat just shows this:
Code:
root@d668:~# cat /proc/mdstat
Personalities : [linear] [multipath] [raid0] [raid1] [raid6] [raid5] [raid4] [raid10]
md2 : active raid1 sdb2[1] sda2[0]
9767424 blocks [2/2] [UU]
[Code]...
View 3 Replies
View Related
Feb 4, 2011
I have a ubuntu sever with a raid1 data drive formated in native linux ext3. I have searched for answers to my question but most likely I'm not asking it correctly. I want to use the data drive to store backups of files from various ubuntu and windows machines. Do I need to reformat the drive as ntfs to enable windows use or can it remain as ext3? For that matter can I reformat as ext4 as a soultion? Again, I wish to use the data drive as a backup storage.
View 3 Replies
View Related
Apr 10, 2011
I accidentally rm -rf 'ed /etc directory from the main server. The server has raid1 soft-raid. Is there a way to recover the directory.
View 4 Replies
View Related
May 10, 2010
I have what seems to be a hard disk Write speed problems with my first hard drive. Timing the cp command of a 700 Meg file takes about 8 secs from disk 2 to 3 but takes 25 minutes from disk 2 to disk 1.
Here are the details:
Kubuntu 9.04 (Kernel 2.6.28-15-generic)
Hard Disk 1 : /dev/sda (WDC WD2500KS-00MJB0)
Partitioned
/dev/sda1 ext3 / 10 Gigs
/dev/sda2 extended 222 Gigs
/dev/sda5 linux-swap 2 Gigs
/dev/sda6 ext /home 220 Gigs
Hard Disk 2 : /dev/sdb (WDC WD2500AAKS-00F0A0)
Partitioned :
/dev/sdb1 ntfs 16 gigs
/dev/sdb2 xfs /home/eric/data_drive 216 Gigs
Hard Disk 2 : /dev/sdc (ST3500320AS)
Partitioned:
/dev/sdc1 xfs /home/eric/data_drive2 465 Gigs
By doing 'time cp ...sdb1/test.avi ...sdc1' takes about 8 seconds and same vice-versa. the command 'time cp ...sdb1/test.avi ...sdb1/test1.avi takes about 11 seconds and the same holds true if sdc1 is used But copy sdb1 or sdc1/test.avi to either sda1 or sda6 and it takes 25 minutes. Same problem if I copy from the same drive partition (sda). I have booted a livecd Knoppix 6.2 and the same problems happens.. So safe to say it's not Kubuntu. The only thing that is left to do is backup and reformat the partitions as XFS and try again. I also did a full smartcontrol Extended test and no errors. Checked all the various logs and nothing found.
View 8 Replies
View Related
Aug 23, 2010
On a modern system--Lucid, SATA 3.0--does the location of a file on the physical disk make an appreciable difference to its access speed? If so, is there a (safe) way to put a file in a particular place on the disk?
I ask because I would like to reserve some space on disk to remain unused without messing with the partition table. My thought was to do this by using dd to create some large files (4 Gb each, or so) containing zeros.But obviously I would like to put them on the slowest part of the disk, as they won't be used for anything.
View 2 Replies
View Related
Jun 10, 2011
I have a big problem my hard drive is works fast all the time and now i hear clicks and scratching and weird stuff from so how can i make it slow down. i cant buy a new one if it breaks down ...
View 6 Replies
View Related
Jan 3, 2010
I am running Ubuntu 9.10 x64 on a relatively old laptop and I find Grub is taking about 20 seconds to initially load before booting the system. The laptop only has a single 120GB hard drive, and I chose the "use entire disk" option when installing, so I do not have any fancy partitioning scheme.When the system boots I get the "LOADING GRUB" text displayed and then shortly after it just shows the flashing cursor with no text, and stays there for about 20 seconds. After that it finally starts loading the system.All the searching I have done only turned up solutions relevant to people with multiple hard drives. This was not an issue on Grub 1.
View 1 Replies
View Related
Feb 2, 2010
Recently, one the SMART utility said that one of the drives had failed and another drive was about to fail. I downed the box and hooked them up to my windows machine to run sea tools on them (They are all seagate drives). Sea Tools said that the drives were fine, while ubuntu said they were failing/dead. Yesterday I decided to try to fix one of the drives in the raid. I turned the server off, took the failed drive out, and restarted. Of course the raid didn't work because only 2 of the 3 drives were there, however it had been working w/ only 2 of the 3 drives for a couple months now (I'm a lazy college student). I turned it back off and back on with the drive there just to see if I could get the raid up again, but I havn't been able to get it to go. So far I've tried:
Code:
mdadm --assemble /dev/md0 /dev/sd[b,c,d]
mdadm: no recogniseable superblock on /dev/sdb
mdadm: /dev/sdb has no superblock - assembly aborted
[code]....
I'm looking for a way to trick the raid into working with just 2 drives until I can warranty the seagate and buy an external 1.5 TB drive to use as another backup. how to remove the bad drive from the array and replace it with a fresh drive, without data loss.
View 3 Replies
View Related
