From: Andrzej Jakowski <andrzej.jakowski@linux.intel.com>
To: axboe@kernel.dk, song@kernel.org
Cc: linux-block@vger.kernel.org, linux-raid@vger.kernel.org,
Andrzej Jakowski <andrzej.jakowski@linux.intel.com>,
Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Subject: [PATCH v2 1/2] block: reintroduce polling on bio level
Date: Tue, 11 Feb 2020 12:17:28 -0700 [thread overview]
Message-ID: <20200211191729.4745-2-andrzej.jakowski@linux.intel.com> (raw)
In-Reply-To: <20200211191729.4745-1-andrzej.jakowski@linux.intel.com>
In current implementation it is possible to perform IO polling if
underlying device is block-mq device. It is not possible however to do
polled IO on stackable block devices like MD.
This patch does following:
- reintroduces polling on bio level that was removed some time ago.
Implementation for that has been pulled from commit
529262d56dbe ("block: remove ->poll_fn").
- modifies blk_poll() to introduce fastpath access for blk_mq_poll().
In other words bio_poll() calls poll_fn() for stackable block
devices supporting polling, otherwise it invokes blk_mq_poll()
directly.
We managed to collect performance data on RAID-0 volume built on top of
2xP4800X devices with polling on and off. Here are results for pvsync2:
Polling QD Latency IOPS
----------------------------------------------
off 1 12.20us 78400
on 1 8.80us 111000
Signed-off-by: Andrzej Jakowski <andrzej.jakowski@linux.intel.com>
Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
---
block/blk-core.c | 28 ++++++++++++++++++++++++++++
block/blk-mq.c | 23 ++---------------------
block/blk-mq.h | 2 ++
include/linux/blkdev.h | 2 ++
4 files changed, 34 insertions(+), 21 deletions(-)
diff --git a/block/blk-core.c b/block/blk-core.c
index 089e890ab208..48001538de92 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1201,6 +1201,34 @@ blk_qc_t submit_bio(struct bio *bio)
}
EXPORT_SYMBOL(submit_bio);
+/**
+ * blk_poll - poll for IO completions
+ * @q: the queue
+ * @cookie: cookie passed back at IO submission time
+ * @spin: whether to spin for completions
+ *
+ * Description:
+ * Poll for completions on the passed in queue. Returns number of
+ * completed entries found. If @spin is true, then blk_poll will continue
+ * looping until at least one completion is found, unless the task is
+ * otherwise marked running (or we need to reschedule).
+ */
+int blk_poll(struct request_queue *q, blk_qc_t cookie, bool spin)
+{
+ if (!test_bit(QUEUE_FLAG_POLL, &q->queue_flags) ||
+ !blk_qc_t_valid(cookie))
+ return 0;
+
+ if (current->plug)
+ blk_flush_plug_list(current->plug, false);
+
+ if (q->poll_fn)
+ return q->poll_fn(q, cookie, spin);
+
+ return blk_mq_poll(q, cookie, spin);
+}
+EXPORT_SYMBOL_GPL(blk_poll);
+
/**
* blk_cloned_rq_check_limits - Helper function to check a cloned request
* for new the queue limits
diff --git a/block/blk-mq.c b/block/blk-mq.c
index a12b1763508d..868aab100692 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -3509,30 +3509,11 @@ static bool blk_mq_poll_hybrid(struct request_queue *q,
return blk_mq_poll_hybrid_sleep(q, hctx, rq);
}
-/**
- * blk_poll - poll for IO completions
- * @q: the queue
- * @cookie: cookie passed back at IO submission time
- * @spin: whether to spin for completions
- *
- * Description:
- * Poll for completions on the passed in queue. Returns number of
- * completed entries found. If @spin is true, then blk_poll will continue
- * looping until at least one completion is found, unless the task is
- * otherwise marked running (or we need to reschedule).
- */
-int blk_poll(struct request_queue *q, blk_qc_t cookie, bool spin)
+int blk_mq_poll(struct request_queue *q, blk_qc_t cookie, bool spin)
{
struct blk_mq_hw_ctx *hctx;
long state;
- if (!blk_qc_t_valid(cookie) ||
- !test_bit(QUEUE_FLAG_POLL, &q->queue_flags))
- return 0;
-
- if (current->plug)
- blk_flush_plug_list(current->plug, false);
-
hctx = q->queue_hw_ctx[blk_qc_t_to_queue_num(cookie)];
/*
@@ -3573,7 +3554,7 @@ int blk_poll(struct request_queue *q, blk_qc_t cookie, bool spin)
__set_current_state(TASK_RUNNING);
return 0;
}
-EXPORT_SYMBOL_GPL(blk_poll);
+EXPORT_SYMBOL_GPL(blk_mq_poll);
unsigned int blk_mq_rq_cpu(struct request *rq)
{
diff --git a/block/blk-mq.h b/block/blk-mq.h
index eaaca8fc1c28..def2f85926b2 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -75,6 +75,8 @@ blk_status_t blk_mq_request_issue_directly(struct request *rq, bool last);
void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
struct list_head *list);
+int blk_mq_poll(struct request_queue *q, blk_qc_t cookie, bool spin);
+
/*
* CPU -> queue mappings
*/
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 053ea4b51988..ab703d655be0 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -288,6 +288,7 @@ static inline unsigned short req_get_ioprio(struct request *req)
struct blk_queue_ctx;
typedef blk_qc_t (make_request_fn) (struct request_queue *q, struct bio *bio);
+typedef int (poll_q_fn) (struct request_queue *q, blk_qc_t, bool spin);
struct bio_vec;
typedef int (dma_drain_needed_fn)(struct request *);
@@ -399,6 +400,7 @@ struct request_queue {
struct rq_qos *rq_qos;
make_request_fn *make_request_fn;
+ poll_q_fn *poll_fn;
dma_drain_needed_fn *dma_drain_needed;
const struct blk_mq_ops *mq_ops;
--
2.20.1
next prev parent reply other threads:[~2020-02-11 19:18 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-02-11 19:17 [PATCH v2 0/2] Enable polling on stackable devices Andrzej Jakowski
2020-02-11 19:17 ` Andrzej Jakowski [this message]
2020-02-11 19:17 ` [PATCH v2 2/2] md: enable io polling Andrzej Jakowski
2020-02-11 21:13 ` Keith Busch
2020-02-12 21:00 ` Andrzej Jakowski
2020-02-12 21:42 ` Keith Busch
2020-02-13 20:19 ` Andrzej Jakowski
2020-02-14 19:25 ` Keith Busch
2020-02-21 15:25 ` Andrzej Jakowski
2020-02-21 16:34 ` Keith Busch
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20200211191729.4745-2-andrzej.jakowski@linux.intel.com \
--to=andrzej.jakowski@linux.intel.com \
--cc=artur.paszkiewicz@intel.com \
--cc=axboe@kernel.dk \
--cc=linux-block@vger.kernel.org \
--cc=linux-raid@vger.kernel.org \
--cc=song@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).