News for hackers. Stuff that matters.
Re:Many SSD Benchmark Reviews Contain Flaws by mrb on Monday September 13, 2010 @06:38AM (#1686131)
Anandtech seems to come out of the pack.

For example they are the only ones who seem to benchmark SandForce-based SSDs (from OCZ, Crucial, ADATA, etc) correctly by taking care of defeating the transparent compression and deduplication features of this controller. They did that by patching IOMeter to use blocks of random bytes instead of constant bytes.

Re:Many SSD Benchmark Reviews Contain Flaws by avar on Monday September 13, 2010 @01:16PM (#1687281)
On the other hand the SSD is probably doing transparent compression and de-duplication because it helps with real-word workloads.

If you only test the pathological it isn't informative if your real workloads could benefit from compression and de-duplication.

Re:Many SSD Benchmark Reviews Contain Flaws by mrb on Monday September 13, 2010 @02:49PM (#1687740)
Anandtech takes care of testing the 2 cases, 100% random data and non-random data, to give a range of expected performance on real-world workloads.

However they only do this for tests run with IOMeter, because most other benchmarking tools are unable to write random data. Which brings me back to one of my points that many benchmarking tools are flawed in the sense they don't take into account potential deduplication.

Re:Many SSD Benchmark Reviews Contain Flaws by wmf on Monday September 13, 2010 @12:19PM (#1687043)
OTOH, Anand appears to use misaligned partitions for some benchmarks, which is only representative of Windows XP but not newer OSes.