lkml.org 
[lkml]   [2016]   [Feb]   [22]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH V2 12/13] blk-throttle: restore shrinked cgroup share
Date
If a cgroup share gets shrinked but the cgroup hits its limit, the
shrink isn't optimal, we restore its original share.

Signed-off-by: Shaohua Li <shli@fb.com>
---
block/blk-throttle.c | 13 ++++++++++++-
1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 2271c7e..7db7d8e 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -2229,6 +2229,7 @@ bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg,

sq = &tg->service_queue;

+again:
tg_check_new_weight(tg);
detect_inactive_cg(tg);
while (true) {
@@ -2238,8 +2239,18 @@ bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg,
tg_update_perf(tg);

/* if above limits, break to queue */
- if (!tg_may_dispatch(tg, bio, NULL))
+ if (!tg_may_dispatch(tg, bio, NULL)) {
+ /*
+ * If the cg hits limit but its share is shrinked, the
+ * shrink isn't optimal
+ */
+ if (sq->acting_weight < sq->weight) {
+ /* pretend we are changing weight */
+ sq->new_weight = sq->weight;
+ goto again;
+ }
break;
+ }

/* within limits, let's charge and dispatch directly */
throtl_charge_bio(tg, bio);
--
2.6.5
\
 
 \ /
  Last update: 2016-02-22 23:21    [W:0.239 / U:0.072 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site