xfs
[Top] [All Lists]

Re: [PATCH, RFC] xfs: batched discard support

To: Ric Wheeler <rwheeler@xxxxxxxxxx>
Subject: Re: [PATCH, RFC] xfs: batched discard support
From: Douglas Gilbert <dgilbert@xxxxxxxxxxxx>
Date: Thu, 20 Aug 2009 10:58:45 -0400
Cc: Mark Lord <liml@xxxxxx>, Ingo Molnar <mingo@xxxxxxx>, Christoph Hellwig <hch@xxxxxxxxxxxxx>, Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>, Paul Mackerras <paulus@xxxxxxxxx>, Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>, xfs@xxxxxxxxxxx, linux-fsdevel@xxxxxxxxxxxxxxx, linux-scsi@xxxxxxxxxxxxxxx, linux-kernel@xxxxxxxxxxxxxxx, jens.axboe@xxxxxxxxxx, IDE/ATA development list <linux-ide@xxxxxxxxxxxxxxx>, Neil Brown <neilb@xxxxxxx>
In-reply-to: <4A8D5442.1000302@xxxxxxxxxx>
References: <20090816004705.GA7347@xxxxxxxxxxxxx> <20090819203916.GA25296@xxxxxxx> <4A8CA956.2060406@xxxxxx> <4A8D5442.1000302@xxxxxxxxxx>
Reply-to: dgilbert@xxxxxxxxxxxx
User-agent: Thunderbird 2.0.0.22 (X11/20090608)
Ric Wheeler wrote:
On 08/19/2009 09:39 PM, Mark Lord wrote:
[resending, after fixing the Cc: list; somebody trimmed it earlier]

Jamie Lokier wrote:
..
I don't remember - does TRIM guarantee the blocks read zeros afterwards?
..

No, it doesn't.

A drive can optionally support "deterministic TRIM", whereby it will return consistent data for any given trimmed sector afterwards, but that doesn't mean zeros.

-ml

Note that returning consistent data is critical for devices that are used in a RAID group since you will need each RAID block that is used to compute the parity to continue to return the same data until you overwrite it with new data :-)

If we have a device that does not support this (or is misconfigured not to do this), we should not use those devices in an MD group & do discard against it...

A closer reading of d2015r2-ATAATAPI_Command_Set_-_2_ACS-2.pdf
section 7.10.3.2 (latest ACS-2 draft from www.t13.org) shows
that there are 3 possible variants for data read from a logical
block that has been trimmed (or "unmapped"):
   a) indeterminate
   b) determinate
   c) determinate, return all zeroes

In the case of b) the same data is returned for each
subsequent read. And that data must not be something
that has previously be written to some other LBA!

In the case of SCSI (sbc3r19.pdf) case b) is not
supported (very sensibly IMO).


Another difference I noticed between SCSI and ATA
drafts is with the SECURITY ERASE UNIT command which
is somewhat similar to the SCSI FORMAT UNIT command
(which includes a security erase option). The ATA
draft says that all blocks are determinate ("mapped"
in the SCSI state model) after a SECURITY ERASE UNIT.
The SCSI draft says that all logical blocks may be
unmapped after FORMAT UNIT.

Doug Gilbert

<Prev in Thread] Current Thread [Next in Thread>