[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <yq1v9mi4o31.fsf@oracle.com>
Date: Wed, 01 Apr 2020 22:29:38 -0400
From: "Martin K. Petersen" <martin.petersen@...cle.com>
To: Konstantin Khlebnikov <khlebnikov@...dex-team.ru>
Cc: Chaitanya Kulkarni <chaitanya.kulkarni@....com>, hch@....de,
martin.petersen@...cle.com, darrick.wong@...cle.com,
axboe@...nel.dk, tytso@....edu, adilger.kernel@...ger.ca,
ming.lei@...hat.com, jthumshirn@...e.de, minwoo.im.dev@...il.com,
damien.lemoal@....com, andrea.parri@...rulasolutions.com,
hare@...e.com, tj@...nel.org, hannes@...xchg.org,
ajay.joshi@....com, bvanassche@....org, arnd@...db.de,
houtao1@...wei.com, asml.silence@...il.com,
linux-block@...r.kernel.org, linux-ext4@...r.kernel.org
Subject: Re: [PATCH 0/4] block: Add support for REQ_OP_ASSIGN_RANGE
Konstantin,
>> The corresponding exported primitive is called
>> blkdev_issue_assign_range().
>
> What exact semantics of that?
REQ_OP_ALLOCATE will be used to compel a device to allocate a block
range. What a given block contains after successful allocation is
undefined (depends on the device implementation).
For block allocation with deterministic zeroing, one must keep using
REQ_OP_WRITE_ZEROES with the NOUNMAP flag set.
--
Martin K. Petersen Oracle Linux Engineering
Powered by blists - more mailing lists