Testing TRIM

A firmware update gives you TRIM support, but we should probably test to make sure it's actually working.

First up, the Intel X25-M G2 with the TRIM firmware. I ran a 4KB random write test across the entire 80GB LBA space for five minutes. I ran the test again afterwards and recorded the average transfer rate for each run:

4KB Random Write, IOQ=16 Run 1 Run 2
Intel X25-M 80GB TRIM Firmware 37.9 MB/s 13.8 MB/s

 

As expected, performance goes down as the drive fills up. The second run is much slower than the first.

Now look at the two runs if we format the drive in between. The format under Windows 7 triggers a TRIM of all invalid data, meaning all the jibberish we generated in the first run is gone and the second run now runs at full speed:

4KB Random Write, IOQ=16 Run 1 Run 2 after Format
Intel X25-M 80GB TRIM Firmware 37.9 MB/s 38.0 MB/s

 

Obviously you don’t usually write a bunch of garbage to your drive then format and repeat, but we’re trying to confirm that TRIM works here; it does. Windows 7 will actually take noticeably longer to format a drive that supports TRIM and has data on it. It still completes in less than 30 seconds on these SSDs, but it's a lot longer than the few seconds it used to take before TRIM.

This confirms that TRIM works on a format, but what about if you delete a partition? To find out I created a partition on my X25-M G2, filled it with data, deleted the partition and ran my 4KB random write test across all LBAs. If deleting a partition forces TRIM I should see new-performance out of the G2:

4KB Random Write, IOQ=16 Run 1 Run 2 after Deleting Partition
Intel X25-M 80GB TRIM Firmware 37.9 MB/s 17.9 MB/s

 

Performance drop. Formatting a partition causes the contents to be TRIMed, but just deleting a partition doesn’t. This means if you accidentally delete a partition you can still retrieve your data, however there’s no way to go back from a format.

What about file deletion? I performed the same test. Created a partition, filled it with garbage but then deleted the garbage before deleting the partition and running my 4KB random write test. Deleting data should force a TRIM:

4KB Random Write, IOQ=16 Run 1 Run 2 after Deleting All Files
Intel X25-M 80GB TRIM Firmware 37.9 MB/s 40.4 MB/s

 

Indeed it does. You no longer have to worry about performance dropping over time. When you delete a file it’ll eventually be nixed on the SSD as well. Below we have the actions that will force a TRIM of data under Windows 7:

Windows 7 File Delete Partition Format Partition Delete
TRIM? Yes Yes No

 

Formatting your drive now actually does something. You no longer have to boot to DOS and secure erase your SSD before installing Windows, just quick format the partition before installing Windows 7.

I performed the same tests on an Indilinx MLC based SSD, this time a SuperTalent UltraDrive GX with the 1819 TRIM-enabled firmware. The results were identical:

4KB Random Write, IOQ=16 Run 1 Run 2 After Format After File Delete
SuperTalent (Indilinx) UltraDrive GX TRIM Firmware v1819 17.8 MB/s 14.1 MB/s 17.8 MB/s 17.8 MB/s

 

We have TRIM working on both Indilinx (from SuperTalent/OCZ) and Intel drives. Sweet.

Index Wipe When You Can’t TRIM
POST A COMMENT

163 Comments

View All Comments

  • Tuvok86 - Wednesday, October 28, 2009 - link

    oops, I meant
    40GB - (Intel Controller, 34nm Intel MLC NAND, 32MB Cache)
    Reply
  • Tuvok86 - Tuesday, October 27, 2009 - link

    I don't like how Kingston labelled this drive as v-series, this may lead people to think that v-series 64gb and 128gb are good as well, while they end up buying a JMicron crap...I know that the v-series stands for value but I'd expect a kind of consistancy in series parts.
    I'd expect 64 and 128 drives to perform equally or better than the 40gb part, but it wouldn't...perhaps kingston had to find a sloppy way to get rid of those unsold "value" drives...

    Regarding ssd reliabilty brought up in the recent posts, I'd be pretty confident to put an SSD in a home pc anytime.
    Man, they are used for SERVERS (well, SLC drives actually, but the story is the same), one of the most mission critical environment out there.
    Dangers are ahead only if you want to mess trying TRIM, fw updates or any other topic brought up every now and then, but if you wait a while and resist early-adopting new features for a couple days, problems are issued quickly. Anyway backup is just a click away.
    Reply
  • clarkn0va - Wednesday, October 28, 2009 - link

    I would like to see tests on the JMicron-based Kinston V Series. Supposedly their newer controller resolves the stuttering and random access bottleneck of the gen-1 SSDs.

    I installed one in a budget build for a customer and was very impressed with performance in a modest use case scenario (with Windows xp and an Atom 330). I would have no reservations using these drives in future builds, although the new 40GB model is an interesting proposition.
    Reply
  • clarkn0va - Wednesday, October 28, 2009 - link

    I do agree though that the V Series branding is confusing and misleading, in light of the different controller. True to Intel tradition. Reply
  • The0ne - Tuesday, October 27, 2009 - link

    Seems not enough testing was done for them to have data corruption, again. These kind of issues shouldn't really surface if proper testing were carried out :/ Reply
  • mantis2000 - Tuesday, October 27, 2009 - link

    "Would I recommend waiting until next year to buy? This is one of the rare cases where I'd have to answer no."

    Given all of the serious reliability issues -- including today's latest Intel firmware debacle -- it's quite clear that SSD are not ready for prime time. Over and over again, we hear stories about disks not living up to their potential due to bad drivers or firmware, and there have been far too many cases of total failure with attendant catastrophic data loss.

    How can Anand recommend using a SSD on a primary machine?

    Wait at least a year for the bugs to be worked out if you value your data.
    Reply
  • Griswold - Wednesday, October 28, 2009 - link

    Bullshit. What reliability issues? What firmware debacle? The handful people with potentially bricked devices after the flash hardly qualify as a debacle. I would guess the success rate is over 90%. Flashing is always a risk, you know...

    Intel did the right thing by pulling the firmware, though. They'll look into it. But i wouldnt be surprised if it wasnt an error on their end - they spent lots of time making this firmware. Much, much more than the garbage the competition throws and its customers every week.
    Reply
  • drwho9437 - Wednesday, October 28, 2009 - link

    I find the statement that flashing is always a risk on a drive based on flash memory very ironic.

    I should think they could spare the space for a backup firmware if it is as you say.
    Reply
  • GullLars - Tuesday, October 27, 2009 - link

    I've heard this argument for years now, along with quite a few others that have died away. "SSDs are not ready for prime time". Wich SSDs, and for what usage are they not ready compared to HDDs?
    Unless you yourself upgrade the firmware of an SSD whitout first waiting and making sure the upgrade is safe, there is no risk by using SSDs that is not greater with HDDs. SSDs generaly are much more reliable and rugged, and when they near the end of their natural life, you will see the raw data failrate predictably increase until it hits the point where the ECC can't do the job anymore, before wich point you take backup and buy a new one.
    Anyone who keeps invaluable data on just one physical medium whitout backup would be a fool to think it is safe. Use the SSDs for OS + programs and have a RAID in a redundant mode with offsite backup for your valuable data.

    Anand is IMHO right to recommend buying an SSD now and not waiting because we have passed the point where the ratios between price, capacity, performance, and reliability make them far superior to harddisk for boot drives. I've had SSDs for over a year in my computer, and payed a hefty price for being an early adopter, but it was well worth it. The prices, specs, and reliable market today almost make me laugh out loud when people say "SSDs are not ready yet". Claiming "(many) people are not ready for SSDs yet" would be far more accurate.
    Reply
  • sotoa - Tuesday, October 27, 2009 - link

    The firmware was there this morning and now it's not available? Anyone else see this?
    Reply

Log in

Don't have an account? Sign up now