Re: [PATCH] block: correctly fallback for zeroout
From: "Martin K. Petersen" <martin.petersen@oracle.com>
Date: 2016-06-03 02:56:20
Also in:
lkml
Possibly related (same subject, not in this thread)
- 2016-06-03 · Re: [PATCH] block: correctly fallback for zeroout · "Martin K. Petersen" <martin.petersen@oracle.com>
- 2016-06-03 · Re: [PATCH] block: correctly fallback for zeroout · "Martin K. Petersen" <martin.petersen@oracle.com>
- 2016-06-02 · Re: [PATCH] block: correctly fallback for zeroout · "Martin K. Petersen" <martin.petersen@oracle.com>
- 2016-06-02 · Re: [PATCH] block: correctly fallback for zeroout · Shaohua Li <hidden>
- 2016-05-29 · Re: [PATCH] block: correctly fallback for zeroout · Christoph Hellwig <hch@infradead.org>
quoted
quoted
quoted
quoted
"Sitsofe" == Sitsofe Wheeler [off-list ref] writes:
Sitsofe> The original SCSI WRITE SAME has overloaded semantics - not Sitsofe> only does it mean "write this data multiple times" but it can Sitsofe> also be used to mean "discard this range" too. If the kernel's Sitsofe> command was modelled on the SCSI original perhaps this Sitsofe> conflation clouded things? REQ_WRITE_SAME in the context of the kernel explicitly means "write payload to this block range". A REQ_DISCARD command may be serviced using WRITE SAME(16) with the UNMAP bit set in the SCSI disk driver but that's entirely orthogonal. -- Martin K. Petersen Oracle Linux Engineering