[Date Prev][Date Next] [Thread Prev][Thread Next] [Date Index] [Thread Index]

Bug#637406: marked as done (linux-2.6: Slow lvm performance with raid1 and 1 missing device)

Your message dated Thu, 11 Aug 2011 15:42:08 +0100
with message-id <1313073728.2591.1285.camel@deadeye>
and subject line Re: Bug#637406: Problem solved
has caused the Debian Bug report #637406,
regarding linux-2.6: Slow lvm performance with raid1 and 1 missing device
to be marked as done.

This means that you claim that the problem has been dealt with.
If this is not the case it is now your responsibility to reopen the
Bug report if necessary, and/or fix the problem forthwith.

(NB: If you are a system administrator and have no idea what this
message is talking about, this may indicate a serious mail system
misconfiguration somewhere. Please contact owner@bugs.debian.org
immediately.)


-- 
637406: http://bugs.debian.org/cgi-bin/bugreport.cgi?bug=637406
Debian Bug Tracking System
Contact owner@bugs.debian.org with problems
--- Begin Message --- 
Package: linux-2.6
Severity: important

I've set up a raid1 device with one missing device and created a lvm logical volume on it (pvcreate, vgcreate, lvcreate). Disk IO is significantly slower than when I do the same set-up using the onde device directly and no raid1. I've tested this with different hard drives and on different machines. According to 'top' the [kdmflush] hogs the CPU at 99-100% during any access to the filesystem on logical volume. I've also tested this with an earlier kernel (2.6.26 lenny) and got the same problem. According to iostat when using the device disk utilisation of the underlying device is constantly 100%.
   
Thanks,

Michael
-- System Information:
Debian Release: 6.0.2
  APT prefers stable
  APT policy: (900, 'stable'), (500, 'stable-updates'), (100, 'oldstable')
Architecture: i386 (i686)

Kernel: Linux 2.6.32-5-686 (SMP w/4 CPU cores)
Locale: LANG=en_GB.UTF-8, LC_CTYPE=en_GB.UTF-8 (charmap=UTF-8)
Shell: /bin/sh linked to /bin/bash

--- End Message ---
--- Begin Message --- 
On Thu, 2011-08-11 at 14:43 +0100, Michael Moritz wrote:
> This is not related to the linux-kernel. Thanks to people on the
> debian-isp list I found out the problem has to do with partitioning
> and 4K sector size. See this thread for more details
> http://lists.debian.org/debian-isp/2011/08/msg00011.html

Thanks for letting us know.

Ben.

Attachment: signature.asc
Description: This is a digitally signed message part


--- End Message ---
Reply to: