Re: About Hardware Raid ...

1999-04-22 Thread Paul Jakma
On 22 Apr 1999, Osma Ahvenlampi wrote: Andy Poling <[EMAIL PROTECTED]> writes: > If you'll be doing alot of writing, the controller can use it's memory to > coalesce the writes and optimize the parity calculations for writing. I believe the Linux buffer-cache will try to do the same.

Re: About Hardware Raid ...

1999-04-22 Thread Osma Ahvenlampi
Andy Poling <[EMAIL PROTECTED]> writes: > If you'll be doing alot of writing, the controller can use it's memory to > coalesce the writes and optimize the parity calculations for writing. I believe the Linux buffer-cache will try to do the same. -- Osma Ahvenlampi

Re: About Hardware Raid ...

1999-04-21 Thread Andy Poling
On Wed, 21 Apr 1999, Sebastien Koechlin wrote: > We are going to buy an Hardware PCI-SCSI Raid Controller > (because we need to run SCO for 3-4 months) (probably an > ICP-Vortex which is enought for 2x 9Go) and most of them have > Cache RAM. > > Is there any improvement using a large amount of Ca

About Hardware Raid ...

1999-04-21 Thread Sebastien Koechlin
We are going to buy an Hardware PCI-SCSI Raid Controller (because we need to run SCO for 3-4 months) (probably an ICP-Vortex which is enought for 2x 9Go) and most of them have Cache RAM. Is there any improvement using a large amount of Cache on the controller? I think Linux uses RAM better than