diff options
| author |   Jens Axboe <axboe@kernel.dk> | 2021-03-08 11:40:23 -0700 |
|---|---|---|
| committer | Jens Axboe <axboe@kernel.dk> | 2021-08-23 13:44:55 -0600 |
| commit | 394918ebb889f99d89db6843bcc93279b2b745f9 (patch) | |
| tree | fdceeeefee346bd281fd73a52d8cb615fa0034c4 /fs/io_uring.c | |
| parent | block: clear BIO_PERCPU_CACHE flag if polling isn't supported (diff) | |
| download | linux-dev-394918ebb889f99d89db6843bcc93279b2b745f9.tar.xz linux-dev-394918ebb889f99d89db6843bcc93279b2b745f9.zip | |
io_uring: enable use of bio alloc cache
Mark polled IO as being safe for dipping into the bio allocation
cache, in case the targeted bio_set has it enabled.
This brings an IOPOLL gen2 Optane QD=128 workload from ~3.2M IOPS to
~3.5M IOPS.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Diffstat (limited to 'fs/io_uring.c')
| -rw-r--r-- | fs/io_uring.c | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/fs/io_uring.c b/fs/io_uring.c index 4f5a00707644..504aede8ca47 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -2737,7 +2737,7 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe) !kiocb->ki_filp->f_op->iopoll) return -EOPNOTSUPP; - kiocb->ki_flags |= IOCB_HIPRI; + kiocb->ki_flags |= IOCB_HIPRI | IOCB_ALLOC_CACHE; kiocb->ki_complete = io_complete_rw_iopoll; req->iopoll_completed = 0; } else { |