diff options
authorTejun Heo2012-09-20 16:08:52 -0500
committerJens Axboe2012-09-21 08:32:57 -0500
commit749fefe6778e98dfefe3b8bb72a93875196ec554 (patch)
tree7e3b2f2fb6e7bec5579a58e9f0c33fb614e69d80 /block/blk-sysfs.c
parent66ba32dc167202c3cf8c86806581a9393ec7f488 (diff)
block: lift the initial queue bypass mode on blk_register_queue() instead of blk_init_allocated_queue()
b82d4b197c ("blkcg: make request_queue bypassing on allocation") made request_queues bypassed on allocation to avoid switching on and off bypass mode on a queue being initialized. Some drivers allocate and then destroy a lot of queues without fully initializing them and incurring bypass latency overhead on each of them could add upto significant overhead. Unfortunately, blk_init_allocated_queue() is never used by queues of bio-based drivers, which means that all bio-based driver queues are in bypass mode even after initialization and registration complete successfully. Due to the limited way request_queues are used by bio drivers, this problem is hidden pretty well but it shows up when blk-throttle is used in combination with a bio-based driver. Trying to configure (echoing to cgroupfs file) blk-throttle for a bio-based driver hangs indefinitely in blkg_conf_prep() waiting for bypass mode to end. This patch moves the initial blk_queue_bypass_end() call from blk_init_allocated_queue() to blk_register_queue() which is called for any userland-visible queues regardless of its type. I believe this is correct because I don't think there is any block driver which needs or wants working elevator and blk-cgroup on a queue which isn't visible to userland. If there are such users, we need a different solution. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Joseph Glanville <joseph.glanville@orionvm.com.au> Cc: stable@vger.kernel.org Acked-by: Vivek Goyal <vgoyal@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
Diffstat (limited to 'block/blk-sysfs.c')
1 files changed, 6 insertions, 0 deletions
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 247dbfd4262..ce620460882 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -561,6 +561,12 @@ int blk_register_queue(struct gendisk *disk)
561 if (WARN_ON(!q)) 561 if (WARN_ON(!q))
562 return -ENXIO; 562 return -ENXIO;
563 563
564 /*
565 * Initialization must be complete by now. Finish the initial
566 * bypass from queue allocation.
567 */
568 blk_queue_bypass_end(q);
564 ret = blk_trace_init_sysfs(dev); 570 ret = blk_trace_init_sysfs(dev);
565 if (ret) 571 if (ret)
566 return ret; 572 return ret;