Re: [PATCH V2 for-4.21 2/2] blk-mq: alloc q->queue_ctx as normal array

On Sat, Nov 17, 2018 at 10:34:18AM +0800, Ming Lei wrote: > On Fri, Nov 16, 2018 at 06:06:23AM -0800, Greg Kroah-Hartman wrote: > > On Fri, Nov 16, 2018 at 07:23:11PM +0800, Ming Lei wrote: > > > Now q->queue_ctx is just one read-mostly table for query the > > > 'blk_mq_ctx' instance from one cpu

Re: [PATCH 6/6] mmc: stop abusing the request queue_lock pointer

On 16 November 2018 at 09:10, Christoph Hellwig wrote: > Replace the lock in mmc_blk_data that is only used through a pointer > in struct mmc_queue and to protect fields in that structure with > an actual lock in struct mmc_queue. > > Suggested-by: Ulf Hansson > Signed-off-by: Christoph Hellwig

[RFC] block: add io timeout to sysfs

Give a interface to adjust io timeout by device. Signed-off-by: Weiping Zhang --- block/blk-sysfs.c | 27 +++ 1 file changed, 27 insertions(+) diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 80eef48fddc8..0cabfb935e71 100644 --- a/block/blk-sysfs.c +++

[PATCH 2/5] aio: fix failure to put the file pointer

If the ioprio capability check fails, we return without putting the file pointer. Fixes: d9a08a9e616b ("fs: Add aio iopriority support") Signed-off-by: Jens Axboe --- fs/aio.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/aio.c b/fs/aio.c index b36691268b6c..3d9bc81cf500 100644 ---

[PATCHSET 0/5] Support for polled aio

Up until now, IO polling has been exclusively available through preadv2 and pwrite2, both fully synchronous interfaces. This works fine for completely synchronous use cases, but that's about it. If QD=1 wasn't enough read the performance goals, the only alternative was to increase the thread

[PATCH 3/5] aio: add iocb->ki_blk_qc field

Add the field and have the blockdev direct_IO() helpers set it. This is in preparation for being able to poll for iocb completion. Signed-off-by: Jens Axboe --- fs/block_dev.c | 2 ++ include/linux/fs.h | 1 + 2 files changed, 3 insertions(+) diff --git a/fs/block_dev.c b/fs/block_dev.c

[PATCH 1/5] aio: use assigned completion handler

We know this is a read/write request, but in preparation for having different kinds of those, ensure that we call the assigned handler instead of assuming it's aio_complete_rq(). Signed-off-by: Jens Axboe --- fs/aio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/aio.c

[PATCH 4/5] aio: support for IO polling

Add polled variants of PREAD/PREADV and PWRITE/PWRITEV. These act like their non-polled counterparts, except we expect to poll for completion of them. The polling happens at io_getevent() time, and works just like non-polled IO. Polled IO doesn't support the user mapped completion ring. Events

[PATCH 5/5] aio: add support for file based polled IO

Needs further work, but this should work fine on normal setups with a file system on a pollable block device. Signed-off-by: Jens Axboe --- fs/aio.c | 2 ++ fs/direct-io.c | 4 +++- fs/iomap.c | 7 +-- 3 files changed, 10 insertions(+), 3 deletions(-) diff --git a/fs/aio.c

[PATCH 6/7] block: make blk_poll() take a parameter on whether to spin or not

blk_poll() has always kept spinning until it found an IO. This is fine for SYNC polling, since we need to find one request we have pending, but in preparation for ASYNC polling it can be beneficial to just check if we have any entries available or not. Existing callers are converted to pass in

[PATCH 3/7] nvme-fc: remove unused poll implementation

This relies on the fc taget ops setting ->poll_queue, which nobody does. Otherwise it just checks if something has completed, which isn't very useful. Signed-off-by: Jens Axboe --- drivers/nvme/host/fc.c | 33 - 1 file changed, 33 deletions(-) diff --git

[PATCH 7/7] blk-mq: ensure mq_ops ->poll() is entered at least once

Right now we immediately bail if need_resched() is true, but we need to do at least one loop in case we have entries waiting. So just invert the need_resched() check, putting it at the bottom of the loop. Signed-off-by: Jens Axboe --- block/blk-mq.c | 4 ++-- 1 file changed, 2 insertions(+), 2

[PATCH 1/7] block: avoid ordered task state change for polled IO

For the core poll helper, the task state setting don't need to imply any atomics, as it's the current task itself that is being modified and we're not going to sleep. For IRQ driven, the wakeup path have the necessary barriers to not need us using the heavy handed version of the task state

[PATCH 2/7] block: have ->poll_fn() return number of entries polled

We currently only really support sync poll, ie poll with 1 IO in flight. This prepares us for supporting async poll. Note that the returned value isn't necessarily 100% accurate. If poll races with IRQ completion, we assume that the fact that the task is now runnable means we found at least one

[PATCH 5/7] blk-mq: remove 'tag' parameter from mq_ops->poll()

We always pass in -1 now and none of the callers use the tag value, remove the parameter. Signed-off-by: Jens Axboe --- block/blk-mq.c | 2 +- drivers/nvme/host/pci.c | 8 drivers/nvme/host/rdma.c | 2 +- include/linux/blk-mq.h | 2 +- 4 files changed, 7 insertions(+), 7

[PATCH 4/7] blk-mq: when polling for IO, look for any completion

If we want to support async IO polling, then we have to allow finding completions that aren't just for the one we are looking for. Always pass in -1 to the mq_ops->poll() helper, and have that return how many events were found in this poll loop. Signed-off-by: Jens Axboe --- block/blk-mq.c

[PATCHSET v4] Various block optimizations

Some of these are optimizations, the latter part is prep work for supporting polling with aio. Patches against my for-4.21/block branch. These patches can also be found in my mq-perf branch. Some of them are prep patches for the aio poll work, which can be found in my aio-poll branch. These will