[Gluster-devel] GlusterFS performance for random file acess

[Amar S. Tumballi]

Hi,
 With read-ahead 'option page-size 16kB' you may not achieve maximum
throughput, so, better try 'option page-size 128kB' (Note that 16K is just
treated as 16bytes, as the parser needs 'KB' 'MB' 'GB' as the unit, not K,
M, or G respectively).

Regards,
Amar

On Dec 21, 2007 3:20 PM, Grigory Shamov <gas at knc.ru> wrote:

> Dear Sam,
>
> Thank you for the quick reply.
>
> Sam Douglas ?????:
> > As I understand it, read and write calls in GlusterFS (and FUSE) are
> > done with supplied offsets (for example read 8192 bytes at position
> > 9024 of the file). This is why seek performance is pretty consistent.
> > The rewrite performance with read-ahead and write-behind drops because
> > writing to the file changes the modification time and invalidates the
> > read-ahead cache. Thus the data that was read was copied needlessly.
>
> So, is there a way to tune it somehow? For now I couldn't think of
> anything except using very small values for the read-ahead cache. With
> page-size of 16K and page-count 1 I get Rewrite of about 7000 K/sec but
> the Sequential Read only about 26000 K/sec which is only a half of the
> best possible value.
>
> --
> WBR, Grigory Shamov
>
>
>
> >
> >    Sam Douglas
> >
> > On Dec 19, 2007 10:56 PM, Grigory Shamov <gas at knc.ru> wrote:
> >> Dear GlusterFS developers,
> >>
> >> So I did a Bonnie++ benchmark using one of the servers (Dual Opteron,
> >> 4GB RAM, SATA disk, CentOS Linux 5) and a client (old P4 2.4GHz box,
> >> 512MB RAM, Gigabit Ethernet, CentOS 4.5). I used 8Gb size for the
> >> Bonnie++ tests, and tried either forced flush IO or not (-b option; the
> >> data below are for the latter case). Some of the Bonnie++ results are
> >> like this:
> >>
> >> ===============================================
> >>   FileSystem:     Sequential Output , K/sec
> >>                   Per-char    Block     Rewrite
> >> ===============================================
> >>   NFS               14442      30419     7710
> >>   Lustre            16012      35228     19018
> >>   GlusterFS         16582      15833      8358
> >>   GlusterFS, wb     17988      43774      8409
> >>   GlusterFS, ra     18414      15863      1804
> >>   GlusterFS, ra, wb 22403      41821       355
> >> ===============================================
> >> FileSystem:     Sequential Input, K/sec Random
> >>                   Per-char    Block      seeks, #/s
> >> ===============================================
> >>   NFS               20229      49510      178.8
> >>   Lustre            17284      47753       53.0
> >>   GlusterFS         16791      16815      161.4
> >>   GlusterFS, wb     15304      17438      174.1
> >>   GlusterFS, ra     19420      54803      143.3
> >>   GlusterFS, ra, wb 19900      54427      144.4
> >> ===============================================
>
>
>
> _______________________________________________
> Gluster-devel mailing list
> Gluster-devel at nongnu.org
> http://lists.nongnu.org/mailman/listinfo/gluster-devel
>



-- 
Amar Tumballi
Gluster/GlusterFS Hacker
[bulde on #gluster/irc.gnu.org]
http://www.zresearch.com - Commoditizing Supercomputing and Superstorage!