From: Chengming Zhou <[email protected]>
Add batched mq_ops.queue_rqs() support in null_blk for testing. The
implementation is much easy since null_blk doesn't have commit_rqs().
We simply handle each request one by one, if errors are encountered,
leave them in the passed in list and return back.
There is about 3.6% improvement in IOPS of fio/t/io_uring on null_blk
with hw_queue_depth=256 on my test VM, from 1.09M to 1.13M.
Signed-off-by: Chengming Zhou <[email protected]>
---
drivers/block/null_blk/main.c | 20 ++++++++++++++++++++
1 file changed, 20 insertions(+)
diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c
index 968090935eb2..79d6cd3c3d41 100644
--- a/drivers/block/null_blk/main.c
+++ b/drivers/block/null_blk/main.c
@@ -1750,6 +1750,25 @@ static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx,
return null_handle_cmd(cmd, sector, nr_sectors, req_op(rq));
}
+static void null_queue_rqs(struct request **rqlist)
+{
+ struct request *requeue_list = NULL;
+ struct request **requeue_lastp = &requeue_list;
+ struct blk_mq_queue_data bd = { };
+ blk_status_t ret;
+
+ do {
+ struct request *rq = rq_list_pop(rqlist);
+
+ bd.rq = rq;
+ ret = null_queue_rq(rq->mq_hctx, &bd);
+ if (ret != BLK_STS_OK)
+ rq_list_add_tail(&requeue_lastp, rq);
+ } while (!rq_list_empty(*rqlist));
+
+ *rqlist = requeue_list;
+}
+
static void cleanup_queue(struct nullb_queue *nq)
{
bitmap_free(nq->tag_map);
@@ -1802,6 +1821,7 @@ static int null_init_hctx(struct blk_mq_hw_ctx *hctx, void *driver_data,
static const struct blk_mq_ops null_mq_ops = {
.queue_rq = null_queue_rq,
+ .queue_rqs = null_queue_rqs,
.complete = null_complete_rq,
.timeout = null_timeout_rq,
.poll = null_poll,
--
2.40.1
On Wed, Sep 13, 2023 at 03:16:16PM +0000, [email protected] wrote:
> From: Chengming Zhou <[email protected]>
>
> Add batched mq_ops.queue_rqs() support in null_blk for testing. The
> implementation is much easy since null_blk doesn't have commit_rqs().
>
> We simply handle each request one by one, if errors are encountered,
> leave them in the passed in list and return back.
>
> There is about 3.6% improvement in IOPS of fio/t/io_uring on null_blk
> with hw_queue_depth=256 on my test VM, from 1.09M to 1.13M.
I guess you pass 'shared_tags' to null_blk for the verification?
>
> Signed-off-by: Chengming Zhou <[email protected]>
> ---
> drivers/block/null_blk/main.c | 20 ++++++++++++++++++++
> 1 file changed, 20 insertions(+)
>
> diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c
> index 968090935eb2..79d6cd3c3d41 100644
> --- a/drivers/block/null_blk/main.c
> +++ b/drivers/block/null_blk/main.c
> @@ -1750,6 +1750,25 @@ static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx,
> return null_handle_cmd(cmd, sector, nr_sectors, req_op(rq));
> }
>
> +static void null_queue_rqs(struct request **rqlist)
> +{
> + struct request *requeue_list = NULL;
> + struct request **requeue_lastp = &requeue_list;
> + struct blk_mq_queue_data bd = { };
> + blk_status_t ret;
> +
> + do {
> + struct request *rq = rq_list_pop(rqlist);
> +
> + bd.rq = rq;
> + ret = null_queue_rq(rq->mq_hctx, &bd);
> + if (ret != BLK_STS_OK)
> + rq_list_add_tail(&requeue_lastp, rq);
> + } while (!rq_list_empty(*rqlist));
> +
> + *rqlist = requeue_list;
> +}
> +
null_blk may not be one perfect example for showing queue_rqs()
which is usually for handling request in batch, but for test or
demo purpose, it is fine:
Reviewed-by: Ming Lei <[email protected]>
Thanks
Ming
On 2023/9/22 16:54, Ming Lei wrote:
> On Wed, Sep 13, 2023 at 03:16:16PM +0000, [email protected] wrote:
>> From: Chengming Zhou <[email protected]>
>>
>> Add batched mq_ops.queue_rqs() support in null_blk for testing. The
>> implementation is much easy since null_blk doesn't have commit_rqs().
>>
>> We simply handle each request one by one, if errors are encountered,
>> leave them in the passed in list and return back.
>>
>> There is about 3.6% improvement in IOPS of fio/t/io_uring on null_blk
>> with hw_queue_depth=256 on my test VM, from 1.09M to 1.13M.
>
> I guess you pass 'shared_tags' to null_blk for the verification?
IIRC it should be "modprobe null_blk hw_queue_depth=256 nr_devices=2 shared_tags=1".
>
>>
>> Signed-off-by: Chengming Zhou <[email protected]>
>> ---
>> drivers/block/null_blk/main.c | 20 ++++++++++++++++++++
>> 1 file changed, 20 insertions(+)
>>
>> diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c
>> index 968090935eb2..79d6cd3c3d41 100644
>> --- a/drivers/block/null_blk/main.c
>> +++ b/drivers/block/null_blk/main.c
>> @@ -1750,6 +1750,25 @@ static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx,
>> return null_handle_cmd(cmd, sector, nr_sectors, req_op(rq));
>> }
>>
>> +static void null_queue_rqs(struct request **rqlist)
>> +{
>> + struct request *requeue_list = NULL;
>> + struct request **requeue_lastp = &requeue_list;
>> + struct blk_mq_queue_data bd = { };
>> + blk_status_t ret;
>> +
>> + do {
>> + struct request *rq = rq_list_pop(rqlist);
>> +
>> + bd.rq = rq;
>> + ret = null_queue_rq(rq->mq_hctx, &bd);
>> + if (ret != BLK_STS_OK)
>> + rq_list_add_tail(&requeue_lastp, rq);
>> + } while (!rq_list_empty(*rqlist));
>> +
>> + *rqlist = requeue_list;
>> +}
>> +
>
> null_blk may not be one perfect example for showing queue_rqs()
> which is usually for handling request in batch, but for test or
> demo purpose, it is fine:
>
> Reviewed-by: Ming Lei <[email protected]>
>
Yes, some other "real" drivers should be better choice that we can
handle more things in batch to improve performance. Maybe ublk driver
can benefit from this too.
Thanks!