[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Fri, 10 Oct 2014 16:23:09 +0200
From: Jan Kara <jack@...e.cz>
To: linux-fsdevel@...r.kernel.org
Cc: linux-ext4@...r.kernel.org, Dave Chinner <david@...morbit.com>,
xfs@....sgi.com, cluster-devel@...hat.com,
Steven Whitehouse <swhiteho@...hat.com>,
Mark Fasheh <mfasheh@...e.com>,
Joel Becker <jlbec@...lplan.org>, ocfs2-devel@....oracle.com,
reiserfs-devel@...r.kernel.org, Jeff Mahoney <jeffm@...e.de>,
Dave Kleikamp <shaggy@...nel.org>,
jfs-discussion@...ts.sourceforge.net, tytso@....edu,
viro@...iv.linux.org.uk, Tao Ma <boyu.mt@...bao.com>,
Christoph Hellwig <hch@...radead.org>,
Roland Dreier <roland@...estorage.com>,
Dan Williams <dan.j.williams@...el.com>,
Jens Axboe <jaxboe@...ionio.com>
Subject: [PATCH] block: Make rq_affinity = 1 work as expected
From: Tao Ma <boyu.mt@...bao.com>
Commit 5757a6d76c introduced a new rq_affinity = 2 so as to make
the request completed in the __make_request cpu. But it makes the
old rq_affinity = 1 not work any more. The root cause is that
if the 'cpu' and 'req->cpu' is in the same group and cpu != req->cpu,
ccpu will be the same as group_cpu, so the completion will be
excuted in the 'cpu' not 'group_cpu'.
This patch fix problem by simpling removing group_cpu and the codes
are more explicit now. If ccpu == cpu, we complete in cpu, otherwise
we raise_blk_irq to ccpu.
Cc: Christoph Hellwig <hch@...radead.org>
Cc: Roland Dreier <roland@...estorage.com>
Cc: Dan Williams <dan.j.williams@...el.com>
Cc: Jens Axboe <jaxboe@...ionio.com>
Signed-off-by: Tao Ma <boyu.mt@...bao.com>
Reviewed-by: Shaohua Li <shaohua.li@...el.com>
Signed-off-by: Jens Axboe <jaxboe@...ionio.com>
---
block/blk-softirq.c | 8 +++-----
1 file changed, 3 insertions(+), 5 deletions(-)
diff --git a/block/blk-softirq.c b/block/blk-softirq.c
index 475fab809a80..487addc85bb5 100644
--- a/block/blk-softirq.c
+++ b/block/blk-softirq.c
@@ -103,7 +103,7 @@ static struct notifier_block __cpuinitdata blk_cpu_notifier = {
void __blk_complete_request(struct request *req)
{
- int ccpu, cpu, group_cpu = NR_CPUS;
+ int ccpu, cpu;
struct request_queue *q = req->q;
unsigned long flags;
@@ -117,14 +117,12 @@ void __blk_complete_request(struct request *req)
*/
if (test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags) && req->cpu != -1) {
ccpu = req->cpu;
- if (!test_bit(QUEUE_FLAG_SAME_FORCE, &q->queue_flags)) {
+ if (!test_bit(QUEUE_FLAG_SAME_FORCE, &q->queue_flags))
ccpu = blk_cpu_to_group(ccpu);
- group_cpu = blk_cpu_to_group(cpu);
- }
} else
ccpu = cpu;
- if (ccpu == cpu || ccpu == group_cpu) {
+ if (ccpu == cpu) {
struct list_head *list;
do_local:
list = &__get_cpu_var(blk_cpu_done);
--
1.8.1.4
--
To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists