M500 on Linux with fstrim or discard under heavy load could cause data loss

Memory Leak Geek

M500 on Linux with fstrim or discard under heavy load could cause data loss

Hello,

 

according to the following Ubuntu bug the M500 has a bug which can cause data loss under heavy load when using the discard option or the fstrim command. For me it sounds like this is a bug which could be fixed with an firmware upgrade by Crucial. Are the Crucial engineers already aware and working on this?

 

P.S.: I really hope that I don't get an crapy answer like "We don't support Linux, use Windows." because I payed a lot of money for my CT960M500SSD1 and this is definitly a faulty implementation on the hardware side. Until now I have a high opinion of Crucial.

 

Yours sincerly

Jusic

7 Replies
JEDEC Jedi

Re: M500 on Linux with fstrim or discard under heavy load could cause data loss

You can work around it using an appropriate Linux kernel version until it is fixed: http://forum.crucial.com/t5/Solid-State-Drives-SSD/M500-M5x0-QUEUED-TRIM-data-corruption-alert-mostl...

_______________________________________
How do I know what memory to buy?
Shop for your region: US | UK | EU | France | Global
I think my memory is bad. What do I do now?
FAQs and Top Forum Solutions
We want your feedback! Post in the Suggestion Box
Did a user help you? Say thanks by giving Kudos!
Still need help? Contact Customer Service
Want to be a Super User?
Memory Leak Geek

Re: M500 on Linux with fstrim or discard under heavy load could cause data loss

Interessing thread, thanks. But the posts says it only affects the M500 up to MU04, so it is already fixed in MU05 isn't it? Is this somehow confirmed by Crucial?

JEDEC Jedi

Re: M500 on Linux with fstrim or discard under heavy load could cause data loss

I don't know.  There isn't an MU04 for starters... Smiley Very Happy

_______________________________________
How do I know what memory to buy?
Shop for your region: US | UK | EU | France | Global
I think my memory is bad. What do I do now?
FAQs and Top Forum Solutions
We want your feedback! Post in the Suggestion Box
Did a user help you? Say thanks by giving Kudos!
Still need help? Contact Customer Service
Want to be a Super User?
JEDEC Jedi

Re: M500 on Linux with fstrim or discard under heavy load could cause data loss

Following the comments on linux-ide.vger.kernel.org I would assume they have confirmed that M500 MU05 firmware is not affected. But I believe we didn't see anything official from Crucial here on this forum.

______________________________________

FAQs and Top Forum Solutions
Did a user help you? Say thanks by giving Kudos!
How do I know what memory to buy?
Still need help? Contact Crucial Customer Service
Remember to regularly backup your important data!

Tracer Lite

Re: M500 on Linux with fstrim or discard under heavy load could cause data loss


targetbsp wrote:

I don't know.  There isn't an MU04 for starters... Smiley Very Happy


It would not surprise me if there was an MU04 which was never released, perhaps for this exact reason.

In any case, it's all covered in the linked messages. Upgrade the kernel and/or SSD firmware.

 

http://comments.gmane.org/gmane.linux.ide/56084

http://www.spinics.net/lists/linux-ide/msg48361.html

 

JEDEC Jedi

Re: M500 on Linux with fstrim or discard under heavy load could cause data loss

[ Edited ]

I think that they just exclude firmware revisions this way that if they know that particular one resolves the issue they blacklist all possibly older revisions ("MU0[1-4]*") without verifying which of them were in fact released. But who knows Smiley Happy

______________________________________

FAQs and Top Forum Solutions
Did a user help you? Say thanks by giving Kudos!
How do I know what memory to buy?
Still need help? Contact Crucial Customer Service
Remember to regularly backup your important data!

hmh
Binary Boss

Re: M500 on Linux with fstrim or discard under heavy load could cause data loss


bogdan wrote:

I think that they just exclude firmware revisions this way that if they know that particular one resolves the issue they blacklist all possibly older revisions ("MU0[1-4]*") without verifying which of them were in fact released. But who knows Smiley Happy


That's correct.  We blacklist everything older than the first known-good version as the general rule.  Exceptions exist, of course, but this wasn't one.