Comments on: Enabling and Testing SSD TRIM Support Under Linux http://techgage.com/article/enabling_and_testing_ssd_trim_support_under_linux/ PC enthusiasts one-stop resource for high-quality reviews, articles and current technology news. Thu, 30 Jul 2015 21:03:00 +0000 hourly 1 By: kris maussen http://techgage.com/article/enabling_and_testing_ssd_trim_support_under_linux/#comment-10032 Wed, 17 Jun 2015 22:43:00 +0000 http://beta.techgage.com/article/enabling_and_testing_ssd_trim_support_under_linux/#comment-10032 When I try this test out, then it seems I’ve an issue with PIO … is there maybe an exploination to understand the problem, or to fix it.

hdparm -fibmap ./testfile ->

./testfile:
attempting to set PIO mode to 0
HDIO_SET_PIO_MODE failed: Inappropriate ioctl for device
HDIO_DRIVE_CMD(identify) failed: Inappropriate ioctl for device
HDIO_GET_MULTCOUNT failed: Inappropriate ioctl for device
BLKRAGET failed: Inappropriate ioctl for device
HDIO_GET_IDENTITY failed: Inappropriate ioctl for device
HDIO_GET_BUSSTATE failed: Inappropriate ioctl for device
BLKFLSBUF failed: Inappropriate ioctl for device

sudo hdparm -I /dev/sda2 ->


Capabilities:
LBA, IORDY(can be disabled)
Queue depth: 32
Standby timer values: spec’d by Standard, no device specific minimum
R/W multiple sector transfer: Max = 16 Current = 16
DMA: mdma0 mdma1 mdma2 udma0 udma1 udma2 udma3 udma4 udma5 *udma6
Cycle time: min=120ns recommended=120ns
PIO: pio0 pio1 pio2 pio3 pio4
Cycle time: no flow control=120ns IORDY flow control=120ns
….

]]>
By: Zachary Sonicfast http://techgage.com/article/enabling_and_testing_ssd_trim_support_under_linux/#comment-1142 Sun, 24 Mar 2013 21:07:00 +0000 http://beta.techgage.com/article/enabling_and_testing_ssd_trim_support_under_linux/#comment-1142 Why not just have discard already built into Linux? That way no manual manipulation would be needed.

It would be nice to have a point and click method to run trim (discard) manually without all the typing. Right click on a drive and left click on trim sorta thing.

I have discard put into my fstab but the system seems to be getting really slow on startup.

]]>
By: codeboy http://techgage.com/article/enabling_and_testing_ssd_trim_support_under_linux/#comment-473 Tue, 01 Jan 2013 07:03:00 +0000 http://beta.techgage.com/article/enabling_and_testing_ssd_trim_support_under_linux/#comment-473 If it used to have valid testfile data before you deleted it, and after you delete the file it shows either all 00 or all FF then trim is working. The difference is due to different technologies, NOR flash vs NAND flash.

NOR flash must write all data to 00 before it can be erased (to FF)

NAND flash does not need to do this, and can quickly erase to FF.

Finally, both technologies require any block to be in the erased state before it can be rewritten with data.

The drive that shows all 00 is probably using NOR flash and wrote all 00 but did not erase it yet. That might come later, when the controller’s garbage collector erases the blocks.

The drive that shows all FF is probably using NAND flash and quickly erased the block and marked it free to use.

In both cases, it would appear to me that TRIM is working as intended.

For some flash technologies, an empty cell is a 0 bit. For other flash technologies, and empty cell is a 1 bit. Thus an empty flash block would be filled with 1’s and would show up as FF after trim.

]]>
By: Rob Williams http://techgage.com/article/enabling_and_testing_ssd_trim_support_under_linux/#comment-454 Thu, 27 Dec 2012 22:36:00 +0000 http://beta.techgage.com/article/enabling_and_testing_ssd_trim_support_under_linux/#comment-454 Those should be 0s, so no, I don’t think so. The fact that the characters are all the same leads me to believe it’s just bunk data (as if the drive was purposely filled).

You may wish to look at the fstrim tool instead:

http://manpages.ubuntu.com/manpages/oneiric/en/man8/fstrim.8.html

I’ve heard that it’s recommended over the “discard” option mentioned in this article, but I haven’t had a chance to give it a good test. The idea would be to set up a scrip that would run once per day to clean all deleted blocks.

]]>
By: Tiago Ventura Mendes http://techgage.com/article/enabling_and_testing_ssd_trim_support_under_linux/#comment-453 Thu, 27 Dec 2012 22:34:00 +0000 http://beta.techgage.com/article/enabling_and_testing_ssd_trim_support_under_linux/#comment-453 Good evening.

I got “f” instead of “0”

IS it enabled?

Thank you.

]]>
By: Tiago Ventura Mendes http://techgage.com/article/enabling_and_testing_ssd_trim_support_under_linux/#comment-452 Thu, 27 Dec 2012 22:31:00 +0000 http://beta.techgage.com/article/enabling_and_testing_ssd_trim_support_under_linux/#comment-452 Good evening.

I got this instead:

reading sector 119807832: succeeded

ffff ffff ffff ffff ffff ffff ffff ffff

ffff ffff ffff ffff ffff ffff ffff ffff

ffff ffff ffff ffff ffff ffff ffff ffff

ffff ffff ffff ffff ffff ffff ffff ffff

ffff ffff ffff ffff ffff ffff ffff ffff

ffff ffff ffff ffff ffff ffff ffff ffff

ffff ffff ffff ffff ffff ffff ffff ffff

ffff ffff ffff ffff ffff ffff ffff ffff

ffff ffff ffff ffff ffff ffff ffff ffff

ffff ffff ffff ffff ffff ffff ffff ffff

ffff ffff ffff ffff ffff ffff ffff ffff

ffff ffff ffff ffff ffff ffff ffff ffff

ffff ffff ffff ffff ffff ffff ffff ffff

ffff ffff ffff ffff ffff ffff ffff ffff

ffff ffff ffff ffff ffff ffff ffff ffff

ffff ffff ffff ffff ffff ffff ffff ffff

ffff ffff ffff ffff ffff ffff ffff ffff

ffff ffff ffff ffff ffff ffff ffff ffff

ffff ffff ffff ffff ffff ffff ffff ffff

ffff ffff ffff ffff ffff ffff ffff ffff

ffff ffff ffff ffff ffff ffff ffff ffff

ffff ffff ffff ffff ffff ffff ffff ffff

ffff ffff ffff ffff ffff ffff ffff ffff

ffff ffff ffff ffff ffff ffff ffff ffff

ffff ffff ffff ffff ffff ffff ffff ffff

ffff ffff ffff ffff ffff ffff ffff ffff

ffff ffff ffff ffff ffff ffff ffff ffff

ffff ffff ffff ffff ffff ffff ffff ffff

ffff ffff ffff ffff ffff ffff ffff ffff

ffff ffff ffff ffff ffff ffff ffff ffff

ffff ffff ffff ffff ffff ffff ffff ffff

ffff ffff ffff ffff ffff ffff ffff ffff

IS it enabled?

Thank you.

]]>
By: Julio BĂȘtta http://techgage.com/article/enabling_and_testing_ssd_trim_support_under_linux/#comment-166 Tue, 20 Nov 2012 21:46:00 +0000 http://beta.techgage.com/article/enabling_and_testing_ssd_trim_support_under_linux/#comment-166 thanks!!!

]]>
By: matuog http://techgage.com/article/enabling_and_testing_ssd_trim_support_under_linux/#comment-100 Tue, 13 Nov 2012 00:32:00 +0000 http://beta.techgage.com/article/enabling_and_testing_ssd_trim_support_under_linux/#comment-100 a very nice article! thank you!

]]>
By: Rob Williams http://techgage.com/article/enabling_and_testing_ssd_trim_support_under_linux/#comment-93 Mon, 12 Nov 2012 18:58:00 +0000 http://beta.techgage.com/article/enabling_and_testing_ssd_trim_support_under_linux/#comment-93 I’m glad the article proved useful!

]]>
By: fsk141 http://techgage.com/article/enabling_and_testing_ssd_trim_support_under_linux/#comment-92 Mon, 12 Nov 2012 18:30:00 +0000 http://beta.techgage.com/article/enabling_and_testing_ssd_trim_support_under_linux/#comment-92 Thanks for this, been planning on setting up trim support with JFS on the new 3.7 kernel. Now I’ll know how to easily test that it’s working.

Appreciate it!

]]>