Ken Price wrote: > > > Thanks Ken.That's a good thing to know that software > striping won't > > really boost performance, i then won't waste money on that > avenue. > > I cannot explain why as i don't know about Linux drivers > > architecture and general system low level behavior but maybe > > somebody on this list could give us a > > It's not specific to Linux, but RAID in general. You need more than > two disks to get any significant increase in performance. In fact, > you may get better performance with Linux software RAID than > hardware > RAID. Linux software RAID is really quite robust. > > > clue.As i said on my previous post, i found that the server is > > inside a rack that has a VTRAK 15100 SCSI to SATA Enclosure > with a > > free SCSI bus (the unit has 2 independant bus) and hard > disk slots. > > I think we have a spare Adaptec 39160 so if it's the case, > i could > > go with this solution and buy 4 x WD 250 Gigs "YS" (RAID) serie > > drives @ about 75$ each and put all this in RAID 10. The unit > > supports NCQ. It remains to be seen how well it can > perform even if > > they are talking about "up to 200 MBps".Regards,Guy Boisvert > > I've used both the Promise UltraTrak SX8000 (8-disk RAID50) and > UltraTrak SX4000 > (4-disk Raid10). Performance was adequate, but I was using Dell > PERC2/3 RAID cards. In testing, a plain-jane Adaptec SCSI card > coupled with software RAID gave "significantly" better results. The PERC2/3 cards were junk. These days the PERC 5e and newer provide performance levels as good or better then Linux software RAID, plus onboard write-back cache which software RAID doesn't provide. -Ross ______________________________________________________________________ This e-mail, and any attachments thereto, is intended only for use by the addressee(s) named herein and may contain legally privileged and/or confidential information. If you are not the intended recipient of this e-mail, you are hereby notified that any dissemination, distribution or copying of this e-mail, and any attachments thereto, is strictly prohibited. If you have received this e-mail in error, please immediately notify the sender and permanently delete the original and any copy or printout thereof.