On Wed, Dec 19, 2007 at 10:31:12AM -0500, Justin Piszcz wrote:
> Some nice graphs found here:
> http://sqlblog.com/blogs/linchi_shea/archive/2007/02/01/performance-impact-of-disk-misalignment.aspx
Again, this is a HW RAID, and the partitioning is done _on top of_ the
RAID.
Gabor
--
--
On Wed, Dec 19, 2007 at 04:01:43PM +0100, Mattias Wadenstein wrote:
> From that setup it seems simple, scrap the partition table and use the disk
> device for raid. This is what we do for all data storage disks (hw raid)
> and sw raid members.
And _exactly_ that's when you run into the alignmen
On Wed, Dec 19, 2007 at 12:55:16PM -0500, Justin Piszcz wrote:
> unligned, just fdisk /dev/sdc, mkpartition, fd raid.
> aligned, fdisk, expert, start at 512 as the off-set
No, that won't show any difference. You need to partition _the RAID
device_. If the partitioning is below the RAID level, th
On Thu, Dec 13, 2007 at 06:24:15AM -0500, Justin Piszcz wrote:
> Sequential:
> Output of CFQ: (horrid): 311,683 KiB/s
> Output of AS: 443,103 KiB/s
OTOH AS had worse latencies than CFQ AFAIR (it was quite some time ago I
last experimented). So it depends on what do you want to optimize for.
Gab
On Wed, Dec 05, 2007 at 03:31:14PM -0500, Bill Davidsen wrote:
> BTW: if this can be done in a user program, mdadm, rather than by code in
> the kernel, that might well make everyone happy. Okay, realistically "less
> unhappy."
I start to like the idea. Of course you can't repair a running arra
On Tue, Oct 30, 2007 at 12:08:07AM -0500, Alberto Alonso wrote:
> > > * Internal serverworks PATA controller on a netengine server. The
> > > server if off waiting to get picked up, so I can't get the important
> > > details.
> >
> > 1 PATA failure.
>
> I was surprised on this one, I did hav
On Mon, Oct 29, 2007 at 08:41:39AM +0100, Luca Berra wrote:
> consider a storage with 64 spt, an io size of 4k and partition starting
> at sector 63.
> first io request will require two ios from the storage (1 for sector 63,
> and one for sectors 64 to 70)
> the next 7 io (71-78,79-86,97-94,95-102
On Sat, Oct 27, 2007 at 09:50:55AM +0200, Luca Berra wrote:
>> Because you didn't stripe align the partition, your bad.
> :)
> by default fdisk misalignes partition tables
> and aligning them is more complex than just doing without.
Why use fdisk then? Use parted instead. It's not the kernel's fa
On Fri, Oct 26, 2007 at 02:52:59PM -0400, Doug Ledford wrote:
> In fact, no you can't. I know, because I've created a device that had
> both but wasn't a raid device. And it's matching partner still existed
> too. What you are talking about would have misrecognized this
> situation, guaranteed.
On Fri, Oct 26, 2007 at 02:41:56PM -0400, Doug Ledford wrote:
> * When using lilo to boot from a raid device, it automatically installs
> itself to the mbr, not to the partition. This can not be changed. Only
> 0.90 and 1.0 superblock types are supported because lilo doesn't
> understand the off
On Fri, Oct 26, 2007 at 06:22:27PM +0200, Gabor Gombas wrote:
> You got the ordering wrong. You should get userspace support ready and
> accepted _first_, and then you can start the
> flamew^H^H^H^H^H^Hdiscussion to make the in-kernel partitioning code
> configurable.
Oh wait that
On Fri, Oct 26, 2007 at 11:15:13AM +0200, Luca Berra wrote:
> on a pc maybe, but that is 20 years old design.
> partition table design is limited because it is still based on C/H/S,
> which do not exist anymore.
The MS-DOS format is not the only possible partition table layout. Other
formats such
On Fri, Oct 26, 2007 at 11:54:18AM +0200, Luca Berra wrote:
> but the fix is easy.
> remove the partition detection code from the kernel and start working on
> a smart userspace replacement for device detection. we already have
> vol_id from udev and blkid from ext3 which support detection of many
On Wed, Jul 18, 2007 at 01:51:16PM +0100, Robin Hill wrote:
> Just to pick up on this one (as I'm about to reformat my array as XFS) -
> does this actually work with a hardware controller? Is there any
> assurance that the XFS stripes align with the hardware RAID stripes? Or
> could you just end
On Wed, Jul 18, 2007 at 06:23:25AM -0400, Justin Piszcz wrote:
> I recently got a chance to test SW RAID5 using 750GB disks (10) in a RAID5
> on a 3ware card, model no: 9550SXU-12
>
> The bottom line is the controller is doing some weird caching with writes
> on SW RAID5 which makes it not worth
On Wed, Jun 06, 2007 at 04:24:31PM +0200, Peter Rabbitson wrote:
> So I was asking if the component _number_, which is unique to a specific
> device regardless of the assembly mechanism, can be reported in case of a
> failure.
So you need to write an event-handling script and pass it to mdadm
(
On Wed, Jun 06, 2007 at 02:23:31PM +0200, Peter Rabbitson wrote:
> This would not work as arrays are assembled by the kernel at boot time, at
> which point there is no udev or anything else for that matter other than
> /dev/sdX. And I am pretty sure my OS (debian) does not support udev in
> ini
On Thu, May 24, 2007 at 09:29:04AM +1000, lewis shobbrook wrote:
> I've noted that device allocation can change with the generation of
> new initrd's and installation of new kernels; i.e. /dev/sdc becomes
> /dev/sda depending upon what order the modules load etc.
> I'm wondering if one could send
On Mon, Mar 05, 2007 at 06:32:32PM -0500, Mike Accetta wrote:
> Yes, we actually have a separate (smallish) boot partition at the front of
> the array. This does reduce the at-risk window substantially. I'll have to
> ponder whether it reduces it close enough to negligible to then ignore, but
>
On Fri, Mar 02, 2007 at 10:40:32AM -0500, Justin Piszcz wrote:
> AFAIK mdadm/kernel raid can handle this, I had a number of occaisons when
> my UPS shut my machine down when I was rebuilding a RAID5 array, when the
> box came back up, the rebuild picked up where it left off.
_If_ the resync got
On Fri, Mar 02, 2007 at 09:04:40AM -0500, Mike Accetta wrote:
> Thoughts or other suggestions anyone?
This is a case where a very small /boot partition is still a very good
idea... 50-100MB is a good choice (some initramfs generators require
quite a bit of space under /boot while generating the i
On Thu, Dec 07, 2006 at 10:51:25AM -0500, Bill Davidsen wrote:
> I also suspect that write are not being combined, since writing the 2GB
> test runs at one-drive speed writing 1MB blocks, but floppy speed
> writing 2k blocks. And no, I'm not running out of CPU to do the
> overhead, it jumps fro
On Fri, Nov 10, 2006 at 12:55:57PM +0100, Mogens Kjaer wrote:
> If one of your disks fails, and you have pages in the swapfile
> on the failing disk, your machine will crash when the pages are
> needed again.
IMHO the machine will not crash just the application which the page
belongs to will be k
On Thu, Nov 09, 2006 at 03:30:55PM +0100, Dexter Filmore wrote:
> 195 Hardware_ECC_Recovered 3344107
For some models that's perfectly normal.
> Looking at a 5 year old 40GB Maxtor that's not been cooled too well I see "3"
> as the raw value.
Different technology, different vendor, different m
On Fri, Nov 03, 2006 at 02:39:31PM +1100, Neil Brown wrote:
> mdadm could probably be changed to be able to remove the device
> anyway. The only difficulty is: how do you tell it which device to
> remove", given that there is no name in /dev to use.
> Suggestions?
Major:minor? If /sys/block stil
On Tue, Oct 17, 2006 at 10:07:07AM +0200, Gabor Gombas wrote:
> Vanilla 2.6.18 kernel. In fact, all the /sys/block/*/holders directories
> are empty here.
Never mind, I just found the per-partition holders directories. Argh.
On Tue, Oct 17, 2006 at 11:58:03AM +1000, Neil Brown wrote:
> udev can find out what needs to be done by looking at
> /sys/block/whatever/holders.
Are you sure?
$ cat /proc/mdstat
[...]
md0 : active raid1 sdd1[1] sdc1[0] sdb1[2] sda1[3]
393472 blocks [4/4] []
[...]
$ ls -l /sys/block/
On Tue, Oct 10, 2006 at 01:47:56PM -0400, Doug Ledford wrote:
> Not at all true. Every filesystem, no matter where it stores its
> metadata blocks, still writes to every single metadata block it
> allocates to initialize that metadata block. The same is true for
> directory blocks...they are cre
On Mon, Oct 09, 2006 at 12:32:00PM -0400, Doug Ledford wrote:
> You don't really need to. After a clean install, the operating system
> has no business reading any block it didn't write to during the install
> unless you are just reading disk blocks for the fun of it.
What happens if you have a
On Sat, Aug 19, 2006 at 09:05:39AM +0200, Luca Berra wrote:
> please, can we try not to resurrect again the kernel-level autodetection
> flamewar on this list.
There is no need for a flame war. In some situations one is better, in
other situations the other is better.
Gabor
--
---
On Thu, Aug 17, 2006 at 08:28:07AM +0200, Peter T. Breuer wrote:
> 1) if the network disk device has decided to shut down wholesale
>(temporarily) because of lack of contact over the net, then
>retries and writes are _bound_ to fail for a while, so there
>is no point in sending them no
On Wed, Aug 16, 2006 at 06:06:24AM -0400, andy liebman wrote:
> There is absolutely NO PROBLEM making images of single disks and
> restoring them to new disks (thus, creating clones). And it is very
> fast. For an OS drive with about 4 GBs of data, it only takes about 5
> minutes to make the im
On Wed, Aug 16, 2006 at 09:38:54AM +0200, Luca Berra wrote:
> The only risk is if you ever move one disk from one machine to another.
> To work around this you can change the uuid by recreating the array with
> mdadm,
No need to re-create, --update=uuid should be enough according to the
man page.
On Thu, Jul 06, 2006 at 08:12:14PM +0200, Dexter Filmore wrote:
> How can I tell if the discs on the new controller will become sd[e-h] or if
> they'll be the new a-d and push the existing ones back?
If they are the same type (or more precisely, if they use the same
driver), then their order on
On Tue, Jun 20, 2006 at 08:00:13AM -0700, Mr. James W. Laferriere wrote:
> At least one can do a ls of the /sys/block area & then do an
> automated
> echo cfq down the tree . Does anyone know of a method to set a
> default
> scheduler ?
RTFM: Documentation/kernel-
On Tue, Jun 20, 2006 at 03:08:59PM +0200, Niccolo Rigacci wrote:
> Do you know if it is possible to switch the scheduler at runtime?
echo cfq > /sys/block//queue/scheduler
Gabor
--
-
MTA SZTAKI Computer and Automation Research I
On Wed, Jun 14, 2006 at 10:46:09AM -0500, Bill Cizek wrote:
> I was able to work around this by lowering
> /proc/sys/dev/raid/speed_limit_max to a value
> below my disk thruput value (~ 50 MB/s) as follows:
IMHO a much better fix is to use the cfq I/O scheduler during the
rebuild. The default an
On Wed, Apr 19, 2006 at 02:16:10PM -0400, Ming Zhang wrote:
> is this possible?
> * stop RAID5
> * set a mirror between current disk X and a new added disk Y, and X as
> primary one (which means copy X to Y to full sync, and before this ends,
> only read from X); also this mirror will not have an
On Mon, Apr 17, 2006 at 09:30:32AM +1000, Neil Brown wrote:
> It is arguable that for a read error on a degraded raid5, that may not
> be the best thing to do, but I'm not completely convinced.
My opinion would be that in the degraded case md should behave as if it
was a single physical drive, an
39 matches
Mail list logo