Re: Heads up

On Thu, 14 Apr 2016, Warner Losh wrote:

> 
> On Thu, Apr 14, 2016 at 9:56 PM, Warren Block <wblock_at_wonkity.com> wrote:
>       On Thu, 14 Apr 2016, Warner Losh wrote:
>
>             The CAM I/O scheduler has been committed to current. This work is described
>             in https://people.freebsd.org/~imp/bsdcan2015/iosched-v3.pdf though the
>             default scheduler doesn't change the default (old) behavior.
>
>             One possible issue, however, is that it also enables NCQ Trims on ada SSDs.
>             There are a few rogue drives that claim support for this feature, but
>             actually implement data corrupt instead of queued trims. The list of known
>             rogues is believed to be complete, but some caution is in order.
> 
>  
>       Is the list of drives queryable?  Is there an easy way to tell if the currently-connected drives are on the list?
> 
> 
> /usr/src/sys/cam/ata/ata_da.c has the list.
> 
> dmesg will tell you if it detected a bad one since it prints the drive's quirks.
> But that's no big deal, because the bad one work just fine if you never issue
> a NCQ TRIM. This small group of drives were early adapters of this technology
> 
> Here's the full list of known rogues:
> 
> Crucial/Micron M500 (all firmware prior to MU07)
> Micron M510 MU01 firmware (newer firmware is good)
> Crucial/Micron M550 MU01 firmware (newer firmware is good)
> Crucial MX100 MU01 firmware (newer firmware is good)
> FCCT M500 all firmware
> Samsung 830 all firmware
> Samsung 840 all firmware
> Samsung 850 all firmware
> 
> All of these are at least 18 months old (if not older). There's some confusing in Linux lists on
> the full impact of the Samsung drives (there was a bug in the Linux implementation (that can't
> be present in the FreeBSD implementation) that may have been the root cause for the Samsung
> black listing). Out of an abundance of caution, I've kept them in the list. Also, it's my belief that
> the Crucial/Micron models with MU01 firmware were mostly corrected after early samples
> since most of the channel drives I've helped people debug had MU02 firmware. Also, a quick
> google search shows the MU02 firmware for each of these models has been available for
> at least a year.

After updating a Dell E7240, booting showed a bunch of FPDMA errors and 
then panicked after about 30 seconds.

The SSD is a Samsung PM851 mSATA drive with firmware EXT4AD0Q.  I 
believe this is the OEM version of the Samsung 840 Evo.  According to 
the Dell support page, the machine shipped on January 22, 2015.  So 
while the drive might not have been manufactured in a while, Dell was 
still using them that recently.  Note that this is a used machine, I 
have only had it a week.

After booting with mfsBSD, a quick fsck, and setting 
kern.cam.ada.0.quirks=0x2 in /boot/loader.conf, it came up without 
errors and appears to be working normally.