From: Tejun Heo <tj@kernel.org>
To: axboe@kernel.dk
Cc: linux-kernel@vger.kernel.org, jack@suse.cz, hch@infradead.org,
hannes@cmpxchg.org, linux-fsdevel@vger.kernel.org,
vgoyal@redhat.com, lizefan@huawei.com, cgroups@vger.kernel.org,
linux-mm@kvack.org, mhocko@suse.cz, clm@fb.com,
fengguang.wu@intel.com, david@fromorbit.com,
Tejun Heo <tj@kernel.org>
Subject: [PATCH 10/45] writeback, blkcg: restructure blk_{set|clear}_queue_congested()
Date: Tue, 6 Jan 2015 16:25:47 -0500 [thread overview]
Message-ID: <1420579582-8516-11-git-send-email-tj@kernel.org> (raw)
In-Reply-To: <1420579582-8516-1-git-send-email-tj@kernel.org>
blk_{set|clear}_queue_congested() take @q and set or clear,
respectively, the congestion state of its bdi's root wb. Because bdi
used to be able to handle congestion state only on the root wb, the
callers of those functions tested whether the congestion is on the
root blkcg and skipped if not.
This is cumbersome and makes implementation of per cgroup
bdi_writeback congestion state propagation difficult. This patch
renames blk_{set|clear}_queue_congested() to
blk_{set|clear}_congested(), and makes them take request_list instead
of request_queue and test whether the specified request_list is the
root one before updating bdi_writeback congestion state. This makes
the tests in the callers unnecessary and simplifies them.
As there are no external users of these functions, the definitions are
moved from include/linux/blkdev.h to block/blk-core.c.
This patch doesn't introduce any noticeable behavior difference.
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Jan Kara <jack@suse.cz>
Cc: Vivek Goyal <vgoyal@redhat.com>
---
block/blk-core.c | 62 ++++++++++++++++++++++++++++++--------------------
include/linux/blkdev.h | 19 ----------------
2 files changed, 37 insertions(+), 44 deletions(-)
diff --git a/block/blk-core.c b/block/blk-core.c
index ff4d2f8..c9a7d6c 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -63,6 +63,28 @@ struct kmem_cache *blk_requestq_cachep;
*/
static struct workqueue_struct *kblockd_workqueue;
+static void blk_clear_congested(struct request_list *rl, int sync)
+{
+ if (rl != &rl->q->root_rl)
+ return;
+#ifdef CONFIG_CGROUP_WRITEBACK
+ clear_wb_congested(rl->blkg->wb, sync);
+#else
+ clear_wb_congested(&rl->q->backing_dev_info.wb, sync);
+#endif
+}
+
+static void blk_set_congested(struct request_list *rl, int sync)
+{
+ if (rl != &rl->q->root_rl)
+ return;
+#ifdef CONFIG_CGROUP_WRITEBACK
+ set_wb_congested(rl->blkg->wb, sync);
+#else
+ set_wb_congested(&rl->q->backing_dev_info.wb, sync);
+#endif
+}
+
void blk_queue_congestion_threshold(struct request_queue *q)
{
int nr;
@@ -828,13 +850,8 @@ static void __freed_request(struct request_list *rl, int sync)
{
struct request_queue *q = rl->q;
- /*
- * bdi isn't aware of blkcg yet. As all async IOs end up root
- * blkcg anyway, just use root blkcg state.
- */
- if (rl == &q->root_rl &&
- rl->count[sync] < queue_congestion_off_threshold(q))
- blk_clear_queue_congested(q, sync);
+ if (rl->count[sync] < queue_congestion_off_threshold(q))
+ blk_clear_congested(rl, sync);
if (rl->count[sync] + 1 <= q->nr_requests) {
if (waitqueue_active(&rl->wait[sync]))
@@ -867,25 +884,25 @@ static void freed_request(struct request_list *rl, unsigned int flags)
int blk_update_nr_requests(struct request_queue *q, unsigned int nr)
{
struct request_list *rl;
+ int on_thresh, off_thresh;
spin_lock_irq(q->queue_lock);
q->nr_requests = nr;
blk_queue_congestion_threshold(q);
+ on_thresh = queue_congestion_on_threshold(q);
+ off_thresh = queue_congestion_off_threshold(q);
- /* congestion isn't cgroup aware and follows root blkcg for now */
- rl = &q->root_rl;
-
- if (rl->count[BLK_RW_SYNC] >= queue_congestion_on_threshold(q))
- blk_set_queue_congested(q, BLK_RW_SYNC);
- else if (rl->count[BLK_RW_SYNC] < queue_congestion_off_threshold(q))
- blk_clear_queue_congested(q, BLK_RW_SYNC);
+ blk_queue_for_each_rl(rl, q) {
+ if (rl->count[BLK_RW_SYNC] >= on_thresh)
+ blk_set_congested(rl, BLK_RW_SYNC);
+ else if (rl->count[BLK_RW_SYNC] < off_thresh)
+ blk_clear_congested(rl, BLK_RW_SYNC);
- if (rl->count[BLK_RW_ASYNC] >= queue_congestion_on_threshold(q))
- blk_set_queue_congested(q, BLK_RW_ASYNC);
- else if (rl->count[BLK_RW_ASYNC] < queue_congestion_off_threshold(q))
- blk_clear_queue_congested(q, BLK_RW_ASYNC);
+ if (rl->count[BLK_RW_ASYNC] >= on_thresh)
+ blk_set_congested(rl, BLK_RW_ASYNC);
+ else if (rl->count[BLK_RW_ASYNC] < off_thresh)
+ blk_clear_congested(rl, BLK_RW_ASYNC);
- blk_queue_for_each_rl(rl, q) {
if (rl->count[BLK_RW_SYNC] >= q->nr_requests) {
blk_set_rl_full(rl, BLK_RW_SYNC);
} else {
@@ -995,12 +1012,7 @@ static struct request *__get_request(struct request_list *rl, int rw_flags,
}
}
}
- /*
- * bdi isn't aware of blkcg yet. As all async IOs end up
- * root blkcg anyway, just use root blkcg state.
- */
- if (rl == &q->root_rl)
- blk_set_queue_congested(q, is_sync);
+ blk_set_congested(rl, is_sync);
}
/*
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index fc980a6..b8964a7 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -819,25 +819,6 @@ extern int sg_scsi_ioctl(struct request_queue *, struct gendisk *, fmode_t,
extern void blk_queue_bio(struct request_queue *q, struct bio *bio);
-/*
- * A queue has just exitted congestion. Note this in the global counter of
- * congested queues, and wake up anyone who was waiting for requests to be
- * put back.
- */
-static inline void blk_clear_queue_congested(struct request_queue *q, int sync)
-{
- clear_bdi_congested(&q->backing_dev_info, sync);
-}
-
-/*
- * A queue has just entered congestion. Flag that in the queue's VM-visible
- * state flags and increment the global gounter of congested queues.
- */
-static inline void blk_set_queue_congested(struct request_queue *q, int sync)
-{
- set_bdi_congested(&q->backing_dev_info, sync);
-}
-
extern void blk_start_queue(struct request_queue *q);
extern void blk_stop_queue(struct request_queue *q);
extern void blk_sync_queue(struct request_queue *q);
--
2.1.0
next prev parent reply other threads:[~2015-01-06 21:25 UTC|newest]
Thread overview: 54+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-01-06 21:25 [PATCHSET RFC block/for-next] writeback: cgroup writeback support Tejun Heo
2015-01-06 21:25 ` [PATCH 01/45] writeback: add struct dirty_context Tejun Heo
2015-01-06 21:25 ` [PATCH 02/45] writeback: add {CONFIG|BDI_CAP|FS}_CGROUP_WRITEBACK Tejun Heo
2015-01-06 21:25 ` [PATCH 03/45] memcg: encode page_cgflags in the lower bits of page->mem_cgroup Tejun Heo
2015-01-06 21:25 ` [PATCH 04/45] memcg, writeback: implement memcg_blkcg_ptr Tejun Heo
2015-01-06 21:25 ` [PATCH 05/45] writeback: make backing_dev_info host cgroup-specific bdi_writebacks Tejun Heo
2015-01-06 21:25 ` [PATCH 06/45] writeback, blkcg: associate each blkcg_gq with the corresponding bdi_writeback Tejun Heo
2015-01-06 21:25 ` [PATCH 07/45] writeback: attribute stats to the matching per-cgroup bdi_writeback Tejun Heo
2015-01-06 21:25 ` [PATCH 08/45] writeback: let balance_dirty_pages() work on the matching cgroup bdi_writeback Tejun Heo
2015-01-06 21:25 ` [PATCH 09/45] writeback: make congestion functions per bdi_writeback Tejun Heo
2015-01-06 21:25 ` Tejun Heo [this message]
2015-01-06 21:25 ` [PATCH 11/45] writeback, blkcg: propagate non-root blkcg congestion state Tejun Heo
2015-01-06 21:25 ` [PATCH 12/45] writeback: implement and use mapping_congested() Tejun Heo
2015-01-06 21:25 ` [PATCH 13/45] writeback: implement WB_has_dirty_io wb_state flag Tejun Heo
2015-01-06 21:25 ` [PATCH 14/45] writeback: implement backing_dev_info->tot_write_bandwidth Tejun Heo
2015-01-06 21:25 ` [PATCH 15/45] writeback: make bdi_has_dirty_io() take multiple bdi_writeback's into account Tejun Heo
2015-01-06 21:25 ` [PATCH 16/45] writeback: don't issue wb_writeback_work if clean Tejun Heo
2015-01-06 21:25 ` [PATCH 17/45] writeback: make bdi->min/max_ratio handling cgroup writeback aware Tejun Heo
2015-01-06 21:25 ` [PATCH 18/45] writeback: implement bdi_for_each_wb() Tejun Heo
2015-01-06 21:25 ` [PATCH 19/45] writeback: remove bdi_start_writeback() Tejun Heo
2015-01-06 21:25 ` [PATCH 20/45] writeback: make laptop_mode_timer_fn() handle multiple bdi_writeback's Tejun Heo
2015-01-06 21:25 ` [PATCH 22/45] writeback: make bdi_start_background_writeback() take bdi_writeback instead of backing_dev_info Tejun Heo
2015-01-06 21:26 ` [PATCH 23/45] writeback: make wakeup_flusher_threads() handle multiple bdi_writeback's Tejun Heo
2015-01-06 21:26 ` [PATCH 24/45] writeback: add wb_writeback_work->auto_free Tejun Heo
2015-01-06 21:26 ` [PATCH 25/45] writeback: implement bdi_wait_for_completion() Tejun Heo
2015-01-06 21:26 ` [PATCH 26/45] writeback: implement wb_wait_for_single_work() Tejun Heo
2015-01-06 21:26 ` [PATCH 27/45] writeback: restructure try_writeback_inodes_sb[_nr]() Tejun Heo
2015-01-06 21:26 ` [PATCH 28/45] writeback: make writeback initiation functions handle multiple bdi_writeback's Tejun Heo
2015-01-06 21:26 ` [PATCH 29/45] writeback: move i_wb_list emptiness test into inode_wb_list_del() from its caller Tejun Heo
2015-01-06 21:26 ` [PATCH 30/45] vfs, writeback: introduce struct inode_wb_link Tejun Heo
2015-01-06 21:26 ` [PATCH 31/45] vfs, writeback: add inode_wb_link->data point to the associated bdi_writeback Tejun Heo
2015-01-06 21:26 ` [PATCH 32/45] vfs, writeback: move inode->dirtied_when into inode->i_wb_link Tejun Heo
2015-01-06 21:26 ` [PATCH 33/45] writeback: minor reorganization of fs/fs-writeback.c Tejun Heo
2015-01-06 21:26 ` [PATCH 34/45] vfs, writeback: implement support for multiple inode_wb_link's Tejun Heo
2015-01-06 21:26 ` [PATCH 35/45] vfs, writeback: implement inode->i_nr_syncs Tejun Heo
2015-01-06 21:26 ` [PATCH 36/45] writeback: dirty inodes against their matching cgroup bdi_writeback's Tejun Heo
2015-01-06 21:26 ` [PATCH 37/45] writeback: make writeback_control carry the inode_wb_link being served Tejun Heo
2015-01-06 21:26 ` [PATCH 38/45] writeback: make cyclic writeback cursor cgroup writeback aware Tejun Heo
2015-01-06 21:26 ` [PATCH 39/45] writeback: make DIRTY_PAGES tracking " Tejun Heo
2015-01-06 21:26 ` [PATCH 40/45] writeback: make write_cache_pages() " Tejun Heo
2015-01-06 21:26 ` [PATCH 41/45] writeback: make __writeback_single_inode() " Tejun Heo
2015-01-06 21:26 ` [PATCH 42/45] writeback: make __filemap_fdatawrite_range() croup " Tejun Heo
2015-01-06 21:26 ` [PATCH 43/45] buffer, writeback: make __block_write_full_page() honor cgroup writeback Tejun Heo
[not found] ` <1420579582-8516-1-git-send-email-tj-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>
2015-01-06 21:25 ` [PATCH 21/45] writeback: make writeback_in_progress() take bdi_writeback instead of backing_dev_info Tejun Heo
2015-01-06 21:26 ` [PATCH 44/45] mpage: make __mpage_writepage() honor cgroup writeback Tejun Heo
2015-01-06 21:26 ` [PATCH 45/45] ext2: enable cgroup writeback support Tejun Heo
2015-01-06 21:44 ` [PATCHSET RFC block/for-next] writeback: " Tejun Heo
2015-01-07 23:45 ` Dave Chinner
2015-01-09 21:23 ` Tejun Heo
2015-01-10 0:38 ` Dave Chinner
2015-01-10 15:56 ` Tejun Heo
2015-01-10 16:05 ` Tejun Heo
2015-01-08 9:30 ` Jan Kara
2015-01-09 21:36 ` Tejun Heo
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=1420579582-8516-11-git-send-email-tj@kernel.org \
--to=tj@kernel.org \
--cc=axboe@kernel.dk \
--cc=cgroups@vger.kernel.org \
--cc=clm@fb.com \
--cc=david@fromorbit.com \
--cc=fengguang.wu@intel.com \
--cc=hannes@cmpxchg.org \
--cc=hch@infradead.org \
--cc=jack@suse.cz \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=lizefan@huawei.com \
--cc=mhocko@suse.cz \
--cc=vgoyal@redhat.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).