Archive Home arrow Reviews: arrow Storage arrow ADATA S599 SSD AS599S-128GM-C
ADATA S599 SSD AS599S-128GM-C E-mail
Reviews - Featured Reviews: Storage
Written by Olin Coles   
Tuesday, 30 March 2010
Table of Contents: Page Index
ADATA S599 SSD AS599S-128GM-C
Features and Specifications
First Look: ADATA S599
SandForce SF-1200 SSD Controller
SSD Testing Methodology
AS-SSD Benchmark
ATTO Disk Benchmark
Iometer IOPS Performance
EVEREST Disk Benchmark
CrystalDiskMark Tests
SSD vs Hard Disk Drive
ADATA AS599S-128GM-C Conclusion

Iometer IOPS Performance

Iometer is an I/O subsystem measurement and characterization tool for single and clustered systems. Iometer does for a computer's I/O subsystem what a dynamometer does for an engine: it measures performance under a controlled load. Iometer was originally developed by the Intel Corporation and formerly known as "Galileo". Intel has discontinued work on Iometer, and has gifted it to the Open Source Development Lab (OSDL).

Iometer is both a workload generator (that is, it performs I/O operations in order to stress the system) and a measurement tool (that is, it examines and records the performance of its I/O operations and their impact on the system). It can be configured to emulate the disk or network I/O load of any program or benchmark, or can be used to generate entirely synthetic I/O loads. It can generate and measure loads on single or multiple (networked) systems.

To measure random I/O response time as well as total I/O's per second, Iometer is set to use 4KB file size chunks over a 100% random sequential distribution at a queue depth of 32 outstanding I/O's per target. The tests are given a 50% read and 50% write distribution. While this pattern may not match traditional 'server' or 'workstation' profiles, it illustrates a single point of reference relative to our product field.

The chart below illustrates combined random read and write IOPS over a 120-second Iometer test phase, where highest I/O total is preferred:

Iometer_Random_4K-IOPS_30QD_Results.png

From the onset, SandForce SSDs clearly outperform the competition when tested which a larger queue depth. While G.Skill's product website displays an image of their Iometer results reaching nearly 50,118 IOPS, there's no telling what settings were used for this test. In our own Iometer tests, which use 32 outstanding I/O's per target and a random 50/50 read/write distribution, only the 'unrestricted' SandForce SSDs approach 50,000 IOPS. These SSDs demonstrate a much higher performance level due to the custom firmware they've implemented, whereas the others each use 'locked' standard-release SandForce firmware that offers consistently identical results. Benchmark Reviews discusses this topic in more detail in our SandForce SF-1200 SSD Firmware Comparison article.

Drive Hardware

In our next section, we test linear read and write bandwidth performance and compare its speed against several other top storage products using EVEREST Disk Benchmark. Benchmark Reviews feels that linear tests are excellent for rating SSDs, however HDDs are put at a disadvantage with these tests whenever capacity is high.



 

Comments 

 
# I fail to see the subject under test in most of the chartsGreg 2010-03-30 16:21
Maybe the wrong charts were published.
Out of the 13 SSDs in the charts, none is the ADATA S599.
What gives?
Report Comment
 
 
# The ADATA S599 is in the charts.Olin Coles 2010-03-30 17:07
I don't know what you're referring to, but the charts include the ADATA S599 SSD test results.
Report Comment
 
 
# RE: The ADATA S599 is in the charts.Stas 2010-03-30 23:24
In CrystalDiskMark Tests too?
Report Comment
 
 
# Read the article...Olin Coles 2010-03-31 06:46
If you actually READ THE ARTICLE, you'll notice the lengthy explanations for these two tests.
Report Comment
 
 
# Updated Test ResultsOlin Coles 2010-04-21 16:01
The AS-SSD Benchmark and CrystalDiskMark 3.0 results have been updated, and comparison charts are now included. The new data reflects test results with 4K IOPS performance in mind. I have also removed HD-Tune entirely, since we've discovered that the random IOPS portion of this tool is not useful for SSDs.
Report Comment
 
 
# RE: ADATA S599 SandForce SF-1200 SSDJustin 2010-03-31 04:54
The Crystal DiskMark and the HDTune Random IOPS charts are missing the ADATA S599.
Report Comment
 
 
# re: ADATA S599 SSDLogan 2010-03-31 11:22
Oi Olin!

You ARE missing the ADATA S599 from the DiskMark AND the HDTune IOPS charts.

I read your article and it was ok but you really have to make sure that all tested items are on the charts if you expect consumers to make informed choices... I'm sure that ADATA would appreciate that most of all because at least on paper, they seem to have a smoking fast product.

Cheers..
Report Comment
 
 
# RE: re: ADATA S599 SSDOlin Coles 2010-03-31 11:28
If you had read the article, you'd know that these two tests produced abnormal results. I explain this in full detail, and also reveal all of my results.
Report Comment
 
 
# Intel ...Christopher27 2010-04-01 03:52
Intel has TRIM (and I suppose X-25E serie has GC also).
Report Comment
 
 
# Sector alignment issuesAllan Stirling 2010-04-01 07:12
HDDs can suffer from sector misalignment as well. ##g-loaded.eu/2010/03/29/partition-misalignment-slows-4096-byte-sector-hard-drives/
Report Comment
 
 
# RE: ADATA S599 SandForce SF-1200 SSDBen 2010-04-06 04:56
Although the details are listed, the missing chart information is misleading to people who just scan through the article. I suggest you publish all of your data in the chart with a footnote stating "abnormal results". Thanks for including it in the written review, but it would be eye-opening to see it compared instead of just referred to.
Report Comment
 
 
# Which storage controller was used?gaspard leon 2010-06-21 07:25
In the "Test System" section it says: "Storage HBA: Integrated Marvell SE9128 3rd-Generation SATA-6.0Gbps Controller"

But in the tests it says the ICH10 was used... which is it?

This makes quite a difference... Also if you want to get the least lag, you need an H55 or P55 based board, the storage controller on those is really quick
Report Comment
 
 
# RE: Which storage controller was used?Olin Coles 2010-06-21 07:29
ICH10 is used on SATA-3GB SSDs, and the Marvell SE9128 is used on SATA-6GB SSDs (currently only Crucial C300).

As for the H/P55 platform having less 'lag' than X58, you are basing this on what evidence? I'm disregarding this remark, since I've tested on both.
Report Comment
 
 
# thanks for the quick replygaspard leon 2010-06-21 18:56
Yeah that makes sense, so only the Crucial was on the Marvell.

Re H/P55 I have not done a lot of checks but I noticed a little bit faster access times, and slightly higher scores under AS SSD Benchmark, which I attribute to the H/P55 design being newer, and not a "Separate" chip, since the north and south bridge are both in the one chip, so the latency is a litttle lower...

Overall the difference between ICH10R and 55 series is fairly slight, just thought you should know that it's probably the best platform I've seen so far for SSD latency.

You can disregard this if you like, just trying to keep up awareness of different platforms
Report Comment
 
 
# iometer resultsChristian 2011-01-24 02:17
guys, i'm not able to reproduce your scores, can you send me your iometer's config. file? this will be very appreciated ... :)
Report Comment
 
 
# RE: iometer resultsOlin Coles 2011-01-24 09:40
Sure thing! I've emailed you our Iometer configuration file. Make sure that you use the same version as we did in our article for best results.
Report Comment
 
 
# Thanks!!!Christian 2011-01-24 09:55
Thanks mate! i'll try it soon ...
Report Comment
 
 
# RE: ADATA S599 SSD AS599S-128GM-CAMOCO 2011-07-05 22:30
So I sent Adata an email about firmware updates:
Me;So,When is the new updated firmware for this drive coming out?I've and others
have been waiting months for it.As the 3.4.6 firmware has heat issues.

Adata;The firmware updates are released by Sandforce and we have not gotten any update on new firmware. However, if you are experiencing issues please let us know we can replace for a new S599, or exchange for S596 Turbo.

So what gives?Is there an update for this drive other than 3.4.6?
Report Comment
 

Comments have been disabled by the administrator.

Search Benchmark Reviews
QNAP Network Storage Servers

Follow Benchmark Reviews on FacebookReceive Tweets from Benchmark Reviews on Twitter