| Message ID | 1456160876-14560-7-git-send-email-hch@lst.de (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
Hi, Christoph, Christoph Hellwig <hch@lst.de> writes: > Now that applications need to explicitly ask for polling we can enable it > by default in blk-mq drivers. I don't think this is a good idea. I'd just enable it in nvme and the micron driver for now. Cheers, Jeff > > Signed-off-by: Christoph Hellwig <hch@lst.de> > --- > include/linux/blkdev.h | 3 ++- > 1 file changed, 2 insertions(+), 1 deletion(-) > > diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h > index 4571ef1..458f6ef 100644 > --- a/include/linux/blkdev.h > +++ b/include/linux/blkdev.h > @@ -499,7 +499,8 @@ struct request_queue { > > #define QUEUE_FLAG_MQ_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ > (1 << QUEUE_FLAG_STACKABLE) | \ > - (1 << QUEUE_FLAG_SAME_COMP)) > + (1 << QUEUE_FLAG_SAME_COMP) | \ > + (1 << QUEUE_FLAG_POLL)) > > static inline void queue_lockdep_assert_held(struct request_queue *q) > { -- To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
On Fri, Feb 26, 2016 at 03:44:30PM -0500, Jeff Moyer wrote: > Hi, Christoph, > > Christoph Hellwig <hch@lst.de> writes: > > > Now that applications need to explicitly ask for polling we can enable it > > by default in blk-mq drivers. > > I don't think this is a good idea. I'd just enable it in nvme and the > micron driver for now. I think my wording was a bit unclear - the flag to enable polling is enabled everywhere. You still need to implement the poll blk_mq operation, which currently only NVMe implements. -- To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Christoph Hellwig <hch@lst.de> writes: > On Fri, Feb 26, 2016 at 03:44:30PM -0500, Jeff Moyer wrote: >> Hi, Christoph, >> >> Christoph Hellwig <hch@lst.de> writes: >> >> > Now that applications need to explicitly ask for polling we can enable it >> > by default in blk-mq drivers. >> >> I don't think this is a good idea. I'd just enable it in nvme and the >> micron driver for now. > > I think my wording was a bit unclear - the flag to enable polling is > enabled everywhere. You still need to implement the poll blk_mq operation, > which currently only NVMe implements. Oh, duh. Yeah, this is fine, then. Reviewed-by: Jeff Moyer <jmoyer@redhat.com> -- To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 4571ef1..458f6ef 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -499,7 +499,8 @@ struct request_queue { #define QUEUE_FLAG_MQ_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_STACKABLE) | \ - (1 << QUEUE_FLAG_SAME_COMP)) + (1 << QUEUE_FLAG_SAME_COMP) | \ + (1 << QUEUE_FLAG_POLL)) static inline void queue_lockdep_assert_held(struct request_queue *q) {
Now that applications need to explicitly ask for polling we can enable it by default in blk-mq drivers. Signed-off-by: Christoph Hellwig <hch@lst.de> --- include/linux/blkdev.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)