Hello,
For a RAID1 array built of two disks on two separate SCSI controllers,
are the reads balanced between the two controllers (for higher speed) ?
--
Petru Paler, mailto:[email protected]
http://www.ppetru.net - ICQ: 41817235
In article <[email protected]> you wrote:
> For a RAID1 array built of two disks on two separate SCSI controllers,
> are the reads balanced between the two controllers (for higher speed) ?
With the current RAID1 setup, you will NOT get a speed increase for
single-threaded, sequential reading programs (read: benchmarks like hdparm
and tiobench)[1]. You will get improvents in all other cases.
Greetings,
Arjan van de Ven
[1] This can be fix by a 10 line patch, however this changes the on-disk
layout.
Hi!
Could you provide an URL to that patch? I would like to test it.
Regards.
-Jorge
==============================================================
Jorge Boncompte - T?cnico de sistemas
DTI2 - Desarrollo de la Tecnolog?a de las Comunicaciones
--------------------------------------------------------------
C/ Abogado Enriquez Barrios, 5 14004 CORDOBA (SPAIN)
Tlf: +34 957 761395 / FAX: +34 957 450380
--------------------------------------------------------------
[email protected] _-_-_-_-_-_-_-_-_-_-_-_-_-_ http://www.dti2.net
==============================================================
Without wicker a basket cannot be done.
==============================================================
----- Mensaje original -----
De: "Arjan van de Ven" <[email protected]>
Para: "Petru Paler" <[email protected]>
CC: <[email protected]>
Enviado: lunes, 12 de febrero de 2001 10:34
Asunto: Re: RAID1 read balancing
> In article <[email protected]> you wrote:
>
> > For a RAID1 array built of two disks on two separate SCSI controllers,
> > are the reads balanced between the two controllers (for higher speed) ?
>
> With the current RAID1 setup, you will NOT get a speed increase for
> single-threaded, sequential reading programs (read: benchmarks like hdparm
> and tiobench)[1]. You will get improvents in all other cases.
>
> Greetings,
> Arjan van de Ven
>
>
> [1] This can be fix by a 10 line patch, however this changes the on-disk
> layout.
> -
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to [email protected]
> Please read the FAQ at http://www.tux.org/lkml/
>