The SSD Improv: Intel & Indilinx get TRIM, Kingston Brings Intel Down to $115

jmke · 26th October 2009, 19:58 [**jmke**]

There’s a major problem with TRIM today. The only Windows storage drivers to support it are written by Microsoft. The Intel Matrix Storage Manager (IMSM) driver will not pass the TRIM instruction to your SSD. This means you can't use anything but the drivers that ship with Windows 7. To make matters worse, if you enable non-member RAID on an Intel motherboard the default Windows 7 driver is an older version of IMSM so TRIM won't work there either - even if you don't have a RAID array created. Your best bet is to install Windows 7 with your I/O controller in AHCI mode (for Intel chipsets) and don't install any storage drivers. Intel is working on an updated IMSM that will pass the TRIM instruction to SSDs but it won't be ready for at least a couple of months.

http://www.anandtech.com/storage/sho...spx?i=3667&p=1

jmke · 26th October 2009, 20:21 [**jmke**]

I so want this soft

Quote:

Recently we’ve been able to get our hands on a piece of software that allows us to record all disk activity on a machine and then play it back on any other machine.

Kougar · 27th October 2009, 13:59 [**Kougar**]

Sounds like useful software I agree, but how is playing the recorded IOPS back as fast as possible "real world"?

Buying the fastest drive in the results doesn't make individual tasks like browsing the web, replying to email or viewing a powerpoint presentation go any faster since the user can only focus on one at a time. Is an interesting metric to have though, nonetheless.

jmke · 27th October 2009, 14:30 [**jmke**]

the higher the IOPs, the better your PC will be at multitasking without slowdown

Kougar · 27th October 2009, 17:24 [**Kougar**]

That's true, but you can measure that with IOMeter.I don't see how this is any more directly applicable, the only thing changed was how the IOP's were generated.

I don't know of anyone that reads a powerpoint presentation while writing an email while reading/emailing a PDF while playing 30 minutes of 3D games all at once. My issue is more about the types of IOPS recorded, should've recorded actual multitasking scenarios before claiming "real world".

jmke · 27th October 2009, 19:09 [**jmke**]

Quote:

but you can measure that with IOMeter.

AHA, but those IOPs are not real-world

Quote:

should've recorded actual multitasking scenarios before claiming "real world".

we can make a few suggestions to Anand, but I also like to know what soft he's using

Kougar · 27th October 2009, 19:42 [**Kougar**]

I agree, would certainly like to know what that software is... far, far easier to "reverse-IOMeter" programs than to build an IOMeter regimen that gets the same effect.