Thread (18 messages) read the whole thread 18 messages, 4 authors, 2011-06-30

Re: [RFC PATCH 0/3] block: Fix fsync slowness with CFQ cgroups

From: Konstantin Khlebnikov <hidden>
Date: 2011-06-28 11:00:39
Also in: linux-fsdevel, lkml

Vivek Goyal wrote:
This patch series seems to be working for me. I did testing for ext4 only.
This series is based on for-3.1/core branch of Jen's block tree.
Konstantin, can you please give it a try and see if it fixes your
issue.
It works for me too, for ext3 and ext4, on top 3.0-rc5, after these trivial fixes:
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -1511,7 +1519,7 @@ static void cfq_add_rq_rb(struct request *rq)
          * if that happens, put the alias on the dispatch list
          */
         while ((__alias = elv_rb_add(&cfqq->sort_list, rq)) != NULL)
-               cfq_dispatch_insert(cfqd->queue, __alias);
+               cfq_dispatch_insert(cfqd->queue, __alias, false);

         if (!cfq_cfqq_on_rr(cfqq))
                 cfq_add_cfqq_rr(cfqd, cfqq);
@@ -3797,12 +3797,11 @@ cfq_set_depends_on_task(struct request_queue *q, struct task_struct *tsk)
          */
         rcu_read_lock();
         if (task_blkio_cgroup(current) == task_blkio_cgroup(tsk))
-               return;
-       rcu_read_unlock();
+               goto out_unlock_rcu;

         cic = cfq_cic_lookup(cfqd, current->io_context);
         if (!cic)
-               return;
+               goto out_unlock_rcu;

         task_lock(tsk);
         spin_lock_irq(q->queue_lock);
@@ -3847,6 +3846,8 @@ cfq_set_depends_on_task(struct request_queue *q, struct task_struct *tsk)
  out_unlock:
         spin_unlock_irq(q->queue_lock);
         task_unlock(tsk);
+out_unlock_rcu:
+       rcu_read_unlock();
  }
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help