Tell me more ×
Server Fault is a question and answer site for professional system and network administrators. It's 100% free, no registration required.
up vote 2 down vote favorite

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

share|improve this question
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

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).

share|improve this answer

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

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