Skip site navigation (1)Skip section navigation (2)
Date:      Sat, 21 Jan 2017 03:22:33 +0000
From:      bugzilla-noreply@freebsd.org
To:        freebsd-bugs@FreeBSD.org
Subject:   [Bug 211852] Unsafe shutdowns on Intel 750 SSD
Message-ID:  <bug-211852-8-sagxbA21Av@https.bugs.freebsd.org/bugzilla/>
In-Reply-To: <bug-211852-8@https.bugs.freebsd.org/bugzilla/>
References:  <bug-211852-8@https.bugs.freebsd.org/bugzilla/>

next in thread | previous in thread | raw e-mail | index | archive | help
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=3D211852

Ravi Pokala <rpokala@panasas.com> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
                 CC|                            |jimharris@FreeBSD.org

--- Comment #3 from Ravi Pokala <rpokala@panasas.com> ---
As it happens, I also have an Intel 750; dumping it's identify info:

----------------------------------------------------------------
[threepio:dev/base/head] rpokala% sudo nvmecontrol identify -x nvme0
000: 80868086 51435643 32323435 304a3030 41303034 20204e47 45544e49 5353204=
c=20
020: 44455044 3034574d 20344730 20202020 20202020 20202020 20202020 2020202=
0=20
040: 31564538 31373130 5cd2e400 00000500 00000000 00000000 00000000 0000000=
0=20
060: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 0000000=
0=20
080: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 0000000=
0=20
0a0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 0000000=
0=20
0c0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 0000000=
0=20
0e0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 0000000=
0=20
100: 03030006 003f0202 00000000 00000000 00000000 00000000 00000000 0000000=
0=20
120: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 0000000=
0=20
140: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 0000000=
0=20
160: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 0000000=
0=20
180: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 0000000=
0=20
1a0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 0000000=
0=20
1c0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 0000000=
0=20
1e0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 0000000=
0=20
200: 00004466 00000001 00000006 00000007 00000000 00000000 00000000 0000000=
0=20
220: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 0000000=
0=20
240: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 0000000=
0=20
260: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 0000000=
0=20
280: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 0000000=
0=20
2a0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 0000000=
0=20
----------------------------------------------------------------

RTD3E is in bytes 91:88, which are offsets 0x58-0x5B in hex, which are zero=
ed
out. So, even if the code was updated to look at and honor RTD3E, it wouldn=
't
help in this case. :-(

Perhaps we should make the SHN wait time configurable? Default to 5 seconds,
overridden by RTD3E if present, overridden by per-device sysctl if set?

--=20
You are receiving this mail because:
You are the assignee for the bug.=



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?bug-211852-8-sagxbA21Av>