From: Jens Axboe <jens.axboe@oracle.com>
To: linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org
Cc: chris.mason@oracle.com, david@fromorbit.com, hch@infradead.org,
akpm@linux-foundation.org, jack@suse.cz,
yanmin_zhang@linux.intel.com, Jens Axboe <jens.axboe@oracle.com>
Subject: [PATCH 08/13] block: change the tag sync vs async restriction logic
Date: Mon, 25 May 2009 09:30:58 +0200 [thread overview]
Message-ID: <1243236668-3398-16-git-send-email-jens.axboe@oracle.com> (raw)
In-Reply-To: <1243236668-3398-1-git-send-email-jens.axboe@oracle.com>
Make them fully share the tag space, but disallow async requests using
the last any two slots.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
block/blk-barrier.c | 2 +-
block/blk-tag.c | 15 +++++++++------
block/elevator.c | 10 +++++-----
include/linux/blkdev.h | 7 ++++++-
4 files changed, 21 insertions(+), 13 deletions(-)
diff --git a/block/blk-barrier.c b/block/blk-barrier.c
index 20b4111..3716ba5 100644
--- a/block/blk-barrier.c
+++ b/block/blk-barrier.c
@@ -221,7 +221,7 @@ static inline bool start_ordered(struct request_queue *q, struct request **rqp)
} else
skip |= QUEUE_ORDSEQ_PREFLUSH;
- if ((q->ordered & QUEUE_ORDERED_BY_DRAIN) && q->in_flight)
+ if ((q->ordered & QUEUE_ORDERED_BY_DRAIN) && queue_in_flight(q))
rq = NULL;
else
skip |= QUEUE_ORDSEQ_DRAIN;
diff --git a/block/blk-tag.c b/block/blk-tag.c
index 3c518e3..e9a7501 100644
--- a/block/blk-tag.c
+++ b/block/blk-tag.c
@@ -336,7 +336,7 @@ EXPORT_SYMBOL(blk_queue_end_tag);
int blk_queue_start_tag(struct request_queue *q, struct request *rq)
{
struct blk_queue_tag *bqt = q->queue_tags;
- unsigned max_depth, offset;
+ unsigned max_depth;
int tag;
if (unlikely((rq->cmd_flags & REQ_QUEUED))) {
@@ -355,13 +355,16 @@ int blk_queue_start_tag(struct request_queue *q, struct request *rq)
* to starve sync IO on behalf of flooding async IO.
*/
max_depth = bqt->max_depth;
- if (rq_is_sync(rq))
- offset = 0;
- else
- offset = max_depth >> 2;
+ if (!rq_is_sync(rq) && max_depth > 1) {
+ max_depth -= 2;
+ if (!max_depth)
+ max_depth = 1;
+ if (q->in_flight[0] > max_depth)
+ return 1;
+ }
do {
- tag = find_next_zero_bit(bqt->tag_map, max_depth, offset);
+ tag = find_first_zero_bit(bqt->tag_map, max_depth);
if (tag >= max_depth)
return 1;
diff --git a/block/elevator.c b/block/elevator.c
index c7143fb..6261b24 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -555,7 +555,7 @@ void elv_requeue_request(struct request_queue *q, struct request *rq)
* in_flight count again
*/
if (blk_account_rq(rq)) {
- q->in_flight--;
+ q->in_flight[rq_is_sync(rq)]--;
if (blk_sorted_rq(rq))
elv_deactivate_rq(q, rq);
}
@@ -697,7 +697,7 @@ void elv_insert(struct request_queue *q, struct request *rq, int where)
if (unplug_it && blk_queue_plugged(q)) {
int nrq = q->rq.count[BLK_RW_SYNC] + q->rq.count[BLK_RW_ASYNC]
- - q->in_flight;
+ - queue_in_flight(q);
if (nrq >= q->unplug_thresh)
__generic_unplug_device(q);
@@ -861,7 +861,7 @@ void elv_dequeue_request(struct request_queue *q, struct request *rq)
* the driver side.
*/
if (blk_account_rq(rq))
- q->in_flight++;
+ q->in_flight[rq_is_sync(rq)]++;
}
int elv_queue_empty(struct request_queue *q)
@@ -934,7 +934,7 @@ void elv_completed_request(struct request_queue *q, struct request *rq)
* request is released from the driver, io must be done
*/
if (blk_account_rq(rq)) {
- q->in_flight--;
+ q->in_flight[rq_is_sync(rq)]--;
if (blk_sorted_rq(rq) && q->elv_ops.elevator_completed_req_fn)
elv_call_completed_req_fn(q, rq);
}
@@ -949,7 +949,7 @@ void elv_completed_request(struct request_queue *q, struct request *rq)
if (!list_empty(&q->queue_head))
next = list_entry_rq(q->queue_head.next);
- if (!q->in_flight &&
+ if (!queue_in_flight(q) &&
blk_ordered_cur_seq(q) == QUEUE_ORDSEQ_DRAIN &&
(!next || blk_ordered_req_seq(next) > QUEUE_ORDSEQ_DRAIN)) {
blk_ordered_complete_seq(q, QUEUE_ORDSEQ_DRAIN, 0);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 4d6db9f..ca322da 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -416,7 +416,7 @@ struct request_queue
struct list_head tag_busy_list;
unsigned int nr_sorted;
- unsigned int in_flight;
+ unsigned int in_flight[2];
unsigned int rq_timeout;
struct timer_list timeout;
@@ -528,6 +528,11 @@ static inline void queue_flag_clear_unlocked(unsigned int flag,
__clear_bit(flag, &q->queue_flags);
}
+static inline int queue_in_flight(struct request_queue *q)
+{
+ return q->in_flight[0] + q->in_flight[1];
+}
+
static inline void queue_flag_clear(unsigned int flag, struct request_queue *q)
{
WARN_ON_ONCE(!queue_is_locked(q));
--
1.6.3.rc0.1.gf800
next prev parent reply other threads:[~2009-05-25 7:31 UTC|newest]
Thread overview: 59+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-05-25 7:30 [PATCH 0/12] Per-bdi writeback flusher threads #5 Jens Axboe
2009-05-25 7:30 ` [PATCH 01/13] libata: get rid of ATA_MAX_QUEUE loop in ata_qc_complete_multiple() Jens Axboe
2009-05-25 7:30 ` [PATCH 01/12] ntfs: remove old debug check for dirty data in ntfs_put_super() Jens Axboe
2009-05-25 7:30 ` [PATCH 02/13] block: add static rq allocation cache Jens Axboe
2009-05-25 7:30 ` [PATCH 02/12] btrfs: properly register fs backing device Jens Axboe
2009-05-25 7:30 ` [PATCH 03/13] scsi: unify allocation of scsi command and sense buffer Jens Axboe
2009-05-25 7:41 ` Christoph Hellwig
2009-05-25 7:46 ` Jens Axboe
2009-05-25 7:50 ` Christoph Hellwig
2009-05-25 7:54 ` Jens Axboe
2009-05-25 10:33 ` Boaz Harrosh
2009-05-25 10:42 ` Christoph Hellwig
2009-05-25 10:49 ` Jens Axboe
2009-05-26 4:36 ` FUJITA Tomonori
2009-05-26 5:08 ` FUJITA Tomonori
2009-05-25 8:15 ` Pekka Enberg
2009-05-25 11:32 ` Nick Piggin
2009-05-25 9:28 ` Boaz Harrosh
2009-05-26 1:45 ` Roland Dreier
2009-05-26 4:36 ` FUJITA Tomonori
2009-05-26 6:29 ` Jens Axboe
2009-05-26 7:25 ` FUJITA Tomonori
2009-05-26 7:32 ` Jens Axboe
2009-05-26 7:38 ` FUJITA Tomonori
2009-05-26 14:47 ` James Bottomley
2009-05-26 15:13 ` Matthew Wilcox
2009-05-26 15:31 ` FUJITA Tomonori
2009-05-26 16:05 ` Boaz Harrosh
2009-05-27 1:36 ` FUJITA Tomonori
2009-05-27 7:54 ` Boaz Harrosh
2009-05-27 8:26 ` FUJITA Tomonori
2009-05-27 9:11 ` Boaz Harrosh
2009-05-26 16:12 ` Boaz Harrosh
2009-05-26 16:28 ` Boaz Harrosh
2009-05-26 7:56 ` FUJITA Tomonori
2009-05-26 5:23 ` FUJITA Tomonori
2009-05-25 7:30 ` [PATCH 03/12] writeback: move dirty inodes from super_block to backing_dev_info Jens Axboe
2009-05-25 7:30 ` [PATCH 04/13] scsi: get rid of lock in __scsi_put_command() Jens Axboe
2009-05-25 7:30 ` [PATCH 04/12] writeback: switch to per-bdi threads for flushing data Jens Axboe
2009-05-25 7:30 ` [PATCH 05/13] aio: mostly crap Jens Axboe
2009-05-25 9:09 ` Jan Kara
2009-05-25 7:30 ` [PATCH 05/12] writeback: get rid of pdflush completely Jens Axboe
2009-05-25 7:30 ` [PATCH 06/13] block: move elevator ops into the queue Jens Axboe
2009-05-25 7:30 ` [PATCH 06/12] writeback: separate the flushing state/task from the bdi Jens Axboe
2009-05-25 7:30 ` [PATCH 07/13] block: avoid indirect calls to enter cfq io scheduler Jens Axboe
2009-05-26 9:02 ` Nikanth K
2009-05-25 7:30 ` [PATCH 07/12] writeback: support > 1 flusher thread per bdi Jens Axboe
2009-05-25 7:30 ` Jens Axboe [this message]
2009-05-25 7:30 ` [PATCH 08/12] writeback: include default_backing_dev_info in writeback Jens Axboe
2009-05-25 7:31 ` [PATCH 09/13] libata: switch to using block layer tagging support Jens Axboe
2009-05-25 7:31 ` [PATCH 09/12] writeback: allow sleepy exit of default writeback task Jens Axboe
2009-05-25 7:31 ` [PATCH 10/13] block: add function for waiting for a specific free tag Jens Axboe
2009-05-25 7:31 ` [PATCH 10/12] writeback: add some debug inode list counters to bdi stats Jens Axboe
2009-05-25 7:31 ` [PATCH 11/13] block: disallow merging of read-ahead bits into normal request Jens Axboe
2009-05-25 7:31 ` [PATCH 11/12] writeback: add name to backing_dev_info Jens Axboe
2009-05-25 7:31 ` [PATCH 12/13] block: first cut at implementing a NAPI approach for block devices Jens Axboe
2009-05-25 7:31 ` [PATCH 12/12] writeback: check for registered bdi in flusher add and inode dirty Jens Axboe
2009-05-25 7:31 ` [PATCH 13/13] block: unlocked completion test patch Jens Axboe
2009-05-25 7:33 ` [PATCH 0/12] Per-bdi writeback flusher threads #5 Jens Axboe
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=1243236668-3398-16-git-send-email-jens.axboe@oracle.com \
--to=jens.axboe@oracle.com \
--cc=akpm@linux-foundation.org \
--cc=chris.mason@oracle.com \
--cc=david@fromorbit.com \
--cc=hch@infradead.org \
--cc=jack@suse.cz \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=yanmin_zhang@linux.intel.com \
/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).