AnandTech Storage Bench 2011 - Light Workload

Our new light workload actually has more write operations than read operations. The split is as follows: 372,630 reads and 459,709 writes. The relatively close read/write ratio does better mimic a typical light workload (although even lighter workloads would be far more read centric).

The I/O breakdown is similar to the heavy workload at small IOs, however you'll notice that there are far fewer large IO transfers:

AnandTech Storage Bench 2011 - Light Workload IO Breakdown
IO Size % of Total
4KB 27%
16KB 8%
32KB 6%
64KB 5%

Despite the reduction in large IOs, over 60% of all operations are perfectly sequential. Average queue depth is a lighter 2.2029 IOs.

Light Workload 2011 - Average Data Rate

The performance advantage over the RevoDrive 3 X2 drops to around 29% in our lighter workload. The narrowing gap makes sense given the workload here. There's less to break up and distribute among all of the controllers and thus we see less of a speedup.

Light Workload 2011 - Average Read Speed

Light Workload 2011 - Average Write Speed

Light Workload 2011 - Disk Busy Time

Light Workload 2011 - Disk Busy Time (Reads)

Light Workload 2011 - Disk Busy Time (Writes)

AnandTech Storage Bench 2011 Enterprise Storage Bench - Oracle Swingbench
Comments Locked

57 Comments

View All Comments

  • squashmeister99 - Tuesday, September 27, 2011 - link

    You teased us with your video reviews. Now we cant go back... :-)
  • G-Man - Tuesday, September 27, 2011 - link

    I miss the video reviews already :-)
  • vol7ron - Tuesday, September 27, 2011 - link

    hahaha. they are a good addition aren't they?
  • Rasterman - Wednesday, September 28, 2011 - link

    Comparing a single Vertex 3 240GB to a 1.6TB doesn't seem quite valid. Someone considering the R4 would be asking what is the performance difference between the R4 and 4 to 16 Vertex 3s in RAID 0. Especially considering the massive cost savings per GB using the Vertex 3s.
  • MrBungle123 - Wednesday, September 28, 2011 - link

    I'd like to see some RAID 5/6/10 arrays of 15K RPM SCSI drives in the benchmarks too.
  • marraco - Wednesday, September 28, 2011 - link

    No. I don't want video reviews, unless they have English subtitles.
  • SilthDraeth - Wednesday, September 28, 2011 - link

    I have trouble hearing and use subs for all my movies, yet Anand speaks quite clearly, and I have no trouble understanding him.

    Also, he posts the video review in conjunction with the written review, and not as a stand alone feature, so you really don't need it subtitled. So you would still get to enjoy the reviews as you always have.
  • Lonbjerg - Thursday, September 29, 2011 - link

    You can write english but not understand it when it's spoken? *shakes head*
  • connor4312 - Thursday, September 29, 2011 - link

    I'm guessing you never learned a second language?
  • arthur449 - Wednesday, September 28, 2011 - link

    Not all information provided is specifically relevant to everyone's interests in a review of a product. Similarly, information provided in a video review follows a linear arbitrary organizational structure that cannot possibly align with everyone's preferred method of learning. Also, it's easier to skim / search / quote / share a text-based review.

Log in

Don't have an account? Sign up now