up vote 2 down vote favorite
share [g+] share [fb]

Do these results look right for a RAID-10 consisting of 4x1TB Samsung F3 SATA drives connected via a Dell Precision T3500's integrated RAID controller (which I believe is an Intel-based "FakeRAID")?

I understand speeds will vary based on the controller, but I was surprised to see that the writes were consistently faster than the reads - which seemed counter-intuitive.

Screenshot of benchmark from ATTO Disk Benchmark 2.46: http://imageshack.us/f/851/drivebenchmark3.jpg/

RAID Settings (from Intel Rapid Storage Technology applet): Raid Level: 1+0 (RAID 10) Stripe Size: 64KB Write-back cache: Enabled

Physical Disk Settings (from Intel Rapid Storage Technology applet): NCQ: Yes Disk data cache: Enabled

link|improve this question
60% accept rate
Disable the write-back cache (write through) and run the test again. I think you'll find that is what's contributing to the high write throughput. – murisonc Sep 20 '11 at 22:26
feedback

1 Answer

up vote 1 down vote

As the commenter mentioned, I think you are seeing the amazing effects of cache on your controller or disks themselves. This is one of the reasons I always make sure that my test is writing more data than the cache sizes and the RAM available on the system combined (e.g. run a MUCH larger test than just 256MB, and you'll see things level out over the long run).

link|improve this answer
feedback

Your Answer

 
or
required, but never shown
discard

Not the answer you're looking for? Browse other questions tagged or ask your own question.