Re: [Xen-users] very slow disk access

[Randy Katz <rkatz@xxxxxxxxxxxxxxxxxxxxx>]

On 2/27/2011 2:25 AM, Fajar A. Nugraha wrote:
> On Sun, Feb 27, 2011 at 9:11 AM, Randy Katz<rkatz@xxxxxxxxxxxxxxxxxxxxx>  wrote:
> > it seems I am using tap:aio on what appears to be quite slow:
> >
> > disk = [ "tap:aio:/disk0/server3.img,xvda,w" ]
> >
> > Is there a good way to convert from tap:aio to lvm? I tried stop vm, dd
> > if=server3.img of=/dev/vg1/newlv3
> > but it is very very slow, much quicker to blow away the whole thing (vm) and
> > reinstall and then add data
> > from backups.
> dd is the generic way. You might want to use dd_rescue (available as
> rpm from EPEL), which should at least show you what it's doing and how
> fast it's doing it. 6 - 10MBps is quite normal if you only have one
> disk.
>
> If your image is still empty-ish (e.g 20GB file image with only 2GB
> used), it might be faster to copy MBR first (which includes partition
> table), setup your system so you could access the partition on LVM
> (using something like kpartx), and use something like partclone or
> clone2fs to copy only used blocks.
Cool stuff Fajar, thank you much!

Regards,
Randy

_______________________________________________
Xen-users mailing list
Xen-users@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-users