summaryrefslogtreecommitdiffstats
path: root/block/blk-sysfs.c
diff options
context:
space:
mode:
authorTejun Heo <tj@kernel.org>2012-06-26 15:05:44 -0700
committerJens Axboe <axboe@kernel.dk>2012-06-26 18:42:49 -0400
commita051661ca6d134c18599498b185b667859d4339b (patch)
tree9d840030874aed9b97a58051bf9568455126e8e8 /block/blk-sysfs.c
parent5b788ce3e2acac9bf109743b1281d77347cf2101 (diff)
downloadlinux-a051661ca6d134c18599498b185b667859d4339b.tar.gz
linux-a051661ca6d134c18599498b185b667859d4339b.tar.bz2
linux-a051661ca6d134c18599498b185b667859d4339b.zip
blkcg: implement per-blkg request allocation
Currently, request_queue has one request_list to allocate requests from regardless of blkcg of the IO being issued. When the unified request pool is used up, cfq proportional IO limits become meaningless - whoever grabs the next request being freed wins the race regardless of the configured weights. This can be easily demonstrated by creating a blkio cgroup w/ very low weight, put a program which can issue a lot of random direct IOs there and running a sequential IO from a different cgroup. As soon as the request pool is used up, the sequential IO bandwidth crashes. This patch implements per-blkg request_list. Each blkg has its own request_list and any IO allocates its request from the matching blkg making blkcgs completely isolated in terms of request allocation. * Root blkcg uses the request_list embedded in each request_queue, which was renamed to @q->root_rl from @q->rq. While making blkcg rl handling a bit harier, this enables avoiding most overhead for root blkcg. * Queue fullness is properly per request_list but bdi isn't blkcg aware yet, so congestion state currently just follows the root blkcg. As writeback isn't aware of blkcg yet, this works okay for async congestion but readahead may get the wrong signals. It's better than blkcg completely collapsing with shared request_list but needs to be improved with future changes. * After this change, each block cgroup gets a full request pool making resource consumption of each cgroup higher. This makes allowing non-root users to create cgroups less desirable; however, note that allowing non-root users to directly manage cgroups is already severely broken regardless of this patch - each block cgroup consumes kernel memory and skews IO weight (IO weights are not hierarchical). v2: queue-sysfs.txt updated and patch description udpated as suggested by Vivek. v3: blk_get_rl() wasn't checking error return from blkg_lookup_create() and may cause oops on lookup failure. Fix it by falling back to root_rl on blkg lookup failures. This problem was spotted by Rakesh Iyer <rni@google.com>. v4: Updated to accomodate 458f27a982 "block: Avoid missed wakeup in request waitqueue". blk_drain_queue() now wakes up waiters on all blkg->rl on the target queue. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Vivek Goyal <vgoyal@redhat.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
Diffstat (limited to 'block/blk-sysfs.c')
-rw-r--r--block/blk-sysfs.c32
1 files changed, 19 insertions, 13 deletions
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 234ce7c082fa..9628b291f960 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -40,7 +40,7 @@ static ssize_t queue_requests_show(struct request_queue *q, char *page)
static ssize_t
queue_requests_store(struct request_queue *q, const char *page, size_t count)
{
- struct request_list *rl = &q->rq;
+ struct request_list *rl;
unsigned long nr;
int ret;
@@ -55,6 +55,9 @@ queue_requests_store(struct request_queue *q, const char *page, size_t count)
q->nr_requests = nr;
blk_queue_congestion_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))
@@ -65,19 +68,22 @@ queue_requests_store(struct request_queue *q, const char *page, size_t count)
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_SYNC] >= q->nr_requests) {
- blk_set_rl_full(rl, BLK_RW_SYNC);
- } else {
- blk_clear_rl_full(rl, BLK_RW_SYNC);
- wake_up(&rl->wait[BLK_RW_SYNC]);
+ 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 {
+ blk_clear_rl_full(rl, BLK_RW_SYNC);
+ wake_up(&rl->wait[BLK_RW_SYNC]);
+ }
+
+ if (rl->count[BLK_RW_ASYNC] >= q->nr_requests) {
+ blk_set_rl_full(rl, BLK_RW_ASYNC);
+ } else {
+ blk_clear_rl_full(rl, BLK_RW_ASYNC);
+ wake_up(&rl->wait[BLK_RW_ASYNC]);
+ }
}
- if (rl->count[BLK_RW_ASYNC] >= q->nr_requests) {
- blk_set_rl_full(rl, BLK_RW_ASYNC);
- } else {
- blk_clear_rl_full(rl, BLK_RW_ASYNC);
- wake_up(&rl->wait[BLK_RW_ASYNC]);
- }
spin_unlock_irq(q->queue_lock);
return ret;
}
@@ -488,7 +494,7 @@ static void blk_release_queue(struct kobject *kobj)
elevator_exit(q->elevator);
}
- blk_exit_rl(&q->rq);
+ blk_exit_rl(&q->root_rl);
if (q->queue_tags)
__blk_queue_free_tags(q);