| Message ID | d5c7dbf6f10efa44271dcb36a178f9566fe76c19.1607263384.git.asml.silence@gmail.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | [v3] blk-mq: skip hybrid polling if iopoll doesn't spin | expand |
On 12/6/20 7:04 AM, Pavel Begunkov wrote: > If blk_poll() is not going to spin (i.e. @spin=false), it also must not > sleep in hybrid polling, otherwise it might be pretty suprising for > users trying to do a quick check and expecting no-wait behaviour. Applied, thanks.
diff --git a/block/blk-mq.c b/block/blk-mq.c index e9799fed98c7..8d81fe0d8fbc 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -3865,9 +3865,10 @@ int blk_poll(struct request_queue *q, blk_qc_t cookie, bool spin) * the state. Like for the other success return cases, the * caller is responsible for checking if the IO completed. If * the IO isn't complete, we'll get called again and will go - * straight to the busy poll loop. + * straight to the busy poll loop. If specified not to spin, + * we also should not sleep. */ - if (blk_mq_poll_hybrid(q, hctx, cookie)) + if (spin && blk_mq_poll_hybrid(q, hctx, cookie)) return 1; hctx->poll_considered++;
If blk_poll() is not going to spin (i.e. @spin=false), it also must not sleep in hybrid polling, otherwise it might be pretty suprising for users trying to do a quick check and expecting no-wait behaviour. Signed-off-by: Pavel Begunkov <asml.silence@gmail.com> --- v2: inverse invalid spin check v3: add comments, reword and resend block/blk-mq.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)