Re: Treat REQ_FUA and REQ_PREFLUSH as synchronous

2017-05-02 Thread Jan Kara
On Tue 02-05-17 08:18:15, Christoph Hellwig wrote: > On Tue, May 02, 2017 at 05:15:58PM +0200, Jan Kara wrote: > > in generic_make_request_checks()? Or just set it unconditionally in that > > function if we see REQ_FUA | REQ_PREFLUSH set? > > Just add REQ_FUA and REQ_PREFLUSH to the test in

Re: Treat REQ_FUA and REQ_PREFLUSH as synchronous

2017-05-02 Thread Jan Kara
On Tue 02-05-17 08:49:14, Jens Axboe wrote: > On 05/02/2017 08:45 AM, Christoph Hellwig wrote: > > On Tue, May 02, 2017 at 12:21:23PM +0200, Jan Kara wrote: > >> it makes sense to treat REQ_FUA and REQ_PREFLUSH ops as synchronous in > >> op_is_sync() since callers cannot rely on this anyway...

Re: Treat REQ_FUA and REQ_PREFLUSH as synchronous

2017-05-02 Thread Christoph Hellwig
On Tue, May 02, 2017 at 12:21:23PM +0200, Jan Kara wrote: > it makes sense to treat REQ_FUA and REQ_PREFLUSH ops as synchronous in > op_is_sync() since callers cannot rely on this anyway... Thoughts? I'm fine with treating them as sync.

Treat REQ_FUA and REQ_PREFLUSH as synchronous

2017-05-02 Thread Jan Kara
Hello, Commit b685d3d65ac7 "block: treat REQ_FUA and REQ_PREFLUSH as synchronous" made requests with REQ_FUA and REQ_PREFLUSH to be treated as synchronous and dropped REQ_SYNC from definitions of WRITE_FUA and friends. This however introduced a bunch of bugs to filesystems (I know

[PATCH 07/16] block: treat REQ_FUA and REQ_PREFLUSH as synchronous

2016-11-01 Thread Christoph Hellwig
Instead of requiring everyone to specify the REQ_SYNC flag aѕ well. Signed-off-by: Christoph Hellwig --- include/linux/blk_types.h | 8 +++- include/linux/fs.h| 6 +++--- 2 files changed, 10 insertions(+), 4 deletions(-) diff --git a/include/linux/blk_types.h