Do Intel's new RST AHCI/RAID drivers support TRIM?

[DZand]

Win7 users with an Intel chipset mainboard and Intel X25-M 2G SSD's, who successfully have flashed the actually withdrawn Postville SSD Firmware, want to take advantage of the TRIM command support, but there still are some restrictions:

1. Intel's Matrix Storage Manager drivers (last official v8.9.0.1023) do not support the TRIM command. The only available SATA drivers, which do fully support the TRIM command, are the Win7 generic MS IDE/AHCI drivers.

2. SSD's running in "RAID Mode" neither do support the TRIM command nor can be "cleaned" by Intel's new SSD Toolbox.

So here is my question:

Do or will the upcoming Intel AHCI/RAID drivers of the Intel(R) Rapid Storage Technology (RST) support the TRIM command?

I ask this, because I am already running the brandnew and WHQL certified RST driver v9.5.0.1037 (available at Station-drivers since 13th October) with my 2x160 GB Intel Postville SSD RAID0 system and got a really amazing performance boost.

Thanks in advance!

Fernando

My system:

MB: Gigabyte GA-EP45-UD3R (P45 with Intel ICH10R Southbridge)

CPU: Intel Core2Duo E8400 (no OC)

HDD's: 2x160 GB Intel X25-M G2 as RAID0

RAM: 4x2 GB J.Skill PC2-8500

[idata]

A short question offtopic...

To install the new Firmware, are these the right settings for the bios ?

PCH SATA Control Mode (IDE; AHCI; RAID) = AHCI

SATA Port 0-3 Native Mode = Disabled ("allows the controller to work at Legacy IDE (???) mode")

Because the fw manual mentioned something about configuring the SATA port mode to "Legacy" or "Compatibility"

[DZand]

@ Arcticus:

The best preparation for the firmware update is to set the PCH SATA Control Mode to "IDE". Furthermore it will be a good idea to connect the SSD with one of the first SATA ports (SATA0 or SATA1).

It is not necessary to disable the SATA Port 0-3 Native Mode.

[idata]

@Fernando.

You have seen my benchmark results - I have shown no benefit to the RST drivers over the default MS AHCI drivers nor the MSM drivers. Will you please elaborate on the benfit you have claim to have witnessed with your system in RAID 0? Benchmark results will be apreciated vs. your abject claims of "improvement".

[DZand]

Here are the benchmark results of my 2x160 GB Intel Postville SSD's as RAID0 (in both cases with disabled "Write Caching")

1. with Intel MSM RAID driver v8.9.0.1023:

2. with Intel RST RAID driver v9.5.0.1037:

If you compare both results, you can see, that the Read Speeds of small files have been drastically improved by the RST drivers.

Just to show you the performance of my current RAID0 by using the RST driver, I add the recent CrystalDiskMark rates after having flashed the Trim firmware:

Regards

Fernando

[idata]

dokh22, Just read your earlier post and agree but left Pagefile on SSD, based on this: http://blogs.msdn.com/e7/archive/2009/05/05/support-and-q-a-for-solid-state-drives-and.aspx "...Should the pagefile be placed on SSDs? Yes. Most pagefile operations are small random reads or larger sequential writes, both of which are types of operations that SSDs handle well. In looking at telemetry data from thousands of traces and focusing on pagefile reads and writes, we find that Pagefile.sys reads outnumber pagefile.sys writes by about 40 to 1, Pagefile.sys read sizes are typically quite small, with 67% less than or equal to 4 KB, and 88% less than 16 KB. Pagefile.sys writes are relatively large, with 62% greater than or equal to 128 KB and 45% being exactly 1 MB in size. In fact, given typical pagefile reference patterns and the favorable performance characteristics SSDs have on those patterns, there are few files better than the pagefile to place on an SSD..." Here's a good article with advice on optimizing storage on SSDs: http://www.maximumpc.com/article/howtos/howto_optimize_your_windows_profile_and_media_storage_ssd Try this for finding how file storage fills your drives: http://www.uderzo.it/main_products/space_sniffer regards, sgibson