What are you using to measure your performance? Are these numbers read
or write numbers? You should be getting better performance, but real
world, I wouldn't expect anything sustained over 250, even in very
extreme circumstances. I've used multi-channel VERY high end RAID cards
from both LSI and Adaptec with as many as 15 drives striped, and had
trouble getting over 250 MB/sec, sustained. You might get bursts as
high as 300, but bursts would be it. I would not expect sustained much
higher than 100 with only 4 drives.
Ed
J. Sokalski wrote:
> I am trying to debug and setup an X5DA8 board and have been extremely
> disappointed in the slow SCSI drive speeds when using an Adaptec 2010S in
> the green PCI-X slot. 4 Seagate ST336607LW drives only give 72.2 MB/s
> (across the whole 140GB) through put in a Raid 0 array. Software Raid 0
> (Win2K Server) with the 2010S still in the system gives 104 MB/s over the
> whole 140GB array (a 44% improvement). That indicates there is still a SCSI
> bottle neck when a 2010S is in the system. Each drive (according to
> Seagate's specs.) should provide 78-43 MB/s through put from the outside to
> inside tracks. I expected the outer 20GB in a Raid 0 array to show over 300
> MS/s. The data comes from WinBench 99 v.2's disk inspection tests.
>
> My next tests will be without the 2010S in the system and Win2K Server's
> software Raid 0. The system board and 2010S have been flashed to the latest
> versions and drivers are the latest versions also.
>
> I don't understand why Supermicro would have anything to do with Adaptec
> when the recommended Raid controller slows the performance of the hard
> drives.
>
><!-- ~MESSAGE_AFTER~ -->
>> Stay informed about: X5DA8 + 2010S = slow SCSI performance