Re: GlusterFS performance for random file acess

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

 



Grigory,
 currently read-ahead intelligently stops doing read-ahead when file is
being read randomly. (except it has the overhead of always reading in terms
of the page-size with the backend). I am also thinking of makng read-ahead
stop reading ahead when file is IO is detected to be read/writes interleaved
(to save on the read-ahead losses)

16KB is a very small value. please try out 64KB and 32KB page-sizes, with a
page-count of 1 (read ahead just 1 page).

with what block size does your application perform IO?

avati

2007/12/21, Grigory Shamov <gas@xxxxxx>:
>
> Dear Amar,
>
> Thank you for the advice.
>
> (Actually, I used byte units, like, 16384 for 16KB)
>
> The thing is, 128KB page-size, while gives full throughput, seems to
> kill Rewrite completely, as one could see from the Table down below in
> the quote. There I used page-size 128KB and page-count of 2.
>
> --
> Best regards,
> Grigory Shamov
> Kazan Science Centre of RAS,
> Kazan, Russian Federation
>
>
> Amar wrote:
> > 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 19, 2007 10:56 PM, Grigory Shamov <gas@xxxxxx> wrote:
> >> Dear GlusterFS developers,
> >>
> 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@xxxxxxxxxx
> http://lists.nongnu.org/mailman/listinfo/gluster-devel
>



-- 
If I traveled to the end of the rainbow
As Dame Fortune did intend,
Murphy would be there to tell me
The pot's at the other end.


[Index of Archives]     [Gluster Users]     [Ceph Users]     [Linux ARM Kernel]     [Linux ARM]     [Linux Omap]     [Fedora ARM]     [IETF Annouce]     [Security]     [Bugtraq]     [Linux]     [Linux OMAP]     [Linux MIPS]     [eCos]     [Asterisk Internet PBX]     [Linux API]

  Powered by Linux