Wednesday, July 15, 2009

Solid-State Drive Benchmarks With Latency Measurements

After my previous round of SSD benchmarks, I was asked to repeat the tests with a newer bonnie version to get some latency measurements. Here are the results:
Version      1.96   ------Sequential Output------ --Sequential Input- --Random-
-Per Chr- --Block-- -Rewrite- -Per Chr- --Block-- --Seeks--
Machine Size K/sec %CP K/sec %CP K/sec %CP K/sec %CP K/sec %CP /sec %CP
hdd 64G 13939 2 10973 2 56604 5 42.0 1
Latency 20356ms 3310ms 60419us 593ms
hdd 64G 13957 2 10933 2 56628 5 42.7 1
Latency 4956ms 2243ms 66937us 523ms
hdd 64G 13938 2 10958 2 56613 5 42.7 1
Latency 5259ms 2577ms 94416us 609ms
hdd 64G 13906 2 10976 2 56602 5 42.5 2
Latency 20689ms 2510ms 56957us 593ms
hdd 64G 13914 2 10990 2 56635 5 42.2 2
Latency 5266ms 2357ms 94285us 518ms
ssd 48G 106763 19 63722 12 254350 21 1825 72
Latency 15396ms 421ms 53517us 7830us
ssd 48G 110696 19 63812 10 254238 21 1971 69
Latency 12050ms 456ms 10615us 1334us
ssd 48G 107193 19 64260 11 254179 21 1823 79
Latency 14950ms 789ms 10542us 8046us
ssd 48G 108723 19 63380 11 254226 21 1801 74
Latency 14118ms 1720ms 40106us 1477us
ssd 48G 108848 19 63363 9 254035 21 1960 75
Latency 15320ms 1717ms 10895us 1387us
hdraid 64G 280086 58 115494 21 450230 40 552.0 49
Latency 1685ms 1325ms 619ms 33518us
hdraid 64G 283360 55 115566 20 467900 45 589.1 42
Latency 1738ms 1109ms 298ms 33042us
hdraid 64G 285003 56 115642 20 460394 43 571.2 37
Latency 1890ms 1272ms 759ms 46262us
hdraid 64G 286838 56 115059 20 453657 43 570.1 43
Latency 1808ms 1065ms 513ms 65779us
hdraid 64G 291125 57 116871 21 445977 43 589.4 40
Latency 1081ms 1057ms 577ms 97685us
I have posted an HTML version of this table at http://wiki.postgresql.org/wiki/User:Petere/SSD_benchmarks, for easier viewing.

Legend: hdd = single hard disk, ssd = Intel X25-E, hdraid = 8 hard disk RAID 10 array

The random seek numbers aren't quite the same as in the last test. I have at times noticed deviations of up to 50% over many measurements.

So the SSD beats everything else in latency, but not by much in the sequential tests. It's difficult to say, however, what exactly these numbers might mean in practice.

A side observation is the 75% or so CPU utilization during the random seek test on the SSD. With multiple disks, you might actually end up exhausting the CPUs before the disks!?!

3 comments:

  1. "Peter Eisentraut published solid-state drive benchmarks with latency measurements, following up and earlier item on SSD benchmarks and the write cache. [...]"

    Log Buffer #154

    ReplyDelete
  2. Peter, it's very interesting but it seems that critical system etc info needed to interpret those results is missing:
    1) which controller(s) were used for RAID10 and SSD; how cache on the controller (if any) was set
    2) was write cache ON or OFF for HD and/or SSD
    3) which FS were used, created with what params (if known) and mounted with which options
    4) what IO scheduler was used for RAID10 and/or SSD?
    5) what's the CPU and RAM size and version of Linux kernel
    6) what drive model was used in 10-disk RAID10 array (or at least it's type and RPM)
    Thanks.
    Igor

    ReplyDelete
  3. I suspect something is wrong? Here is a bonnie result from a ocz drive (prevailing wisdom is that it's slower at random than the intel) and it's booking 9k seeks:

    http://www.finalcog.com/ssd-bonnie-benchmark-ocz-vertex-samsung

    Considering that bonnie is doing 10:1 ratio read/write, something is not adding up here...maybe there is contention in bonnie or some other config problem.

    That said, IMNSHO your results, if confirmed, would absolutely crush any expectations that the intel drives are going to make any short term inroads into production enterprise databases except in niche cases.

    ReplyDelete