From: Shaohua Li <shli@fb.com>
To: <linux-block@vger.kernel.org>, <linux-kernel@vger.kernel.org>
Cc: <kernel-team@fb.com>, <axboe@fb.com>, <tj@kernel.org>,
<vgoyal@redhat.com>
Subject: [PATCH V5 05/17] blk-throttle: add upgrade logic for LIMIT_LOW state
Date: Thu, 15 Dec 2016 12:32:56 -0800 [thread overview]
Message-ID: <75685643afd126cbccefe894ca56fd5dd83fe8cf.1481833017.git.shli@fb.com> (raw)
In-Reply-To: <cover.1481833017.git.shli@fb.com>
When queue is in LIMIT_LOW state and all cgroups with low limit cross
the bps/iops limitation, we will upgrade queue's state to
LIMIT_MAX
For a cgroup hierarchy, there are two cases. Children has lower low
limit than parent. Parent's low limit is meaningless. If children's
bps/iops cross low limit, we can upgrade queue state. The other case is
children has higher low limit than parent. Children's low limit is
meaningless. As long as parent's bps/iops cross low limit, we can
upgrade queue state.
Signed-off-by: Shaohua Li <shli@fb.com>
---
block/blk-throttle.c | 101 +++++++++++++++++++++++++++++++++++++++++++++++++--
1 file changed, 97 insertions(+), 4 deletions(-)
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index e55bd36..cfd74cfc 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -455,6 +455,7 @@ static void blk_throtl_update_valid_limit(struct throtl_data *td)
td->limit_valid[LIMIT_LOW] = false;
}
+static void throtl_upgrade_state(struct throtl_data *td);
static void throtl_pd_offline(struct blkg_policy_data *pd)
{
struct throtl_grp *tg = pd_to_tg(pd);
@@ -466,9 +467,8 @@ static void throtl_pd_offline(struct blkg_policy_data *pd)
blk_throtl_update_valid_limit(tg->td);
- if (tg->td->limit_index == LIMIT_LOW &&
- !tg->td->limit_valid[LIMIT_LOW])
- tg->td->limit_index = LIMIT_MAX;
+ if (!tg->td->limit_valid[tg->td->limit_index])
+ throtl_upgrade_state(tg->td);
}
static void throtl_pd_free(struct blkg_policy_data *pd)
@@ -1077,6 +1077,8 @@ static int throtl_select_dispatch(struct throtl_service_queue *parent_sq)
return nr_disp;
}
+static bool throtl_can_upgrade(struct throtl_data *td,
+ struct throtl_grp *this_tg);
/**
* throtl_pending_timer_fn - timer function for service_queue->pending_timer
* @arg: the throtl_service_queue being serviced
@@ -1103,6 +1105,9 @@ static void throtl_pending_timer_fn(unsigned long arg)
int ret;
spin_lock_irq(q->queue_lock);
+ if (throtl_can_upgrade(td, NULL))
+ throtl_upgrade_state(td);
+
again:
parent_sq = sq->parent_sq;
dispatched = false;
@@ -1506,6 +1511,88 @@ static struct blkcg_policy blkcg_policy_throtl = {
.pd_free_fn = throtl_pd_free,
};
+static bool throtl_tg_can_upgrade(struct throtl_grp *tg)
+{
+ struct throtl_service_queue *sq = &tg->service_queue;
+ bool read_limit, write_limit;
+
+ /*
+ * if cgroup reaches low/max limit (max >= low), it's ok to next
+ * limit
+ */
+ read_limit = tg->bps[READ][LIMIT_LOW] != U64_MAX ||
+ tg->iops[READ][LIMIT_LOW] != UINT_MAX;
+ write_limit = tg->bps[WRITE][LIMIT_LOW] != U64_MAX ||
+ tg->iops[WRITE][LIMIT_LOW] != UINT_MAX;
+ if (read_limit && sq->nr_queued[READ] &&
+ (!write_limit || sq->nr_queued[WRITE]))
+ return true;
+ if (write_limit && sq->nr_queued[WRITE] &&
+ (!read_limit || sq->nr_queued[READ]))
+ return true;
+ return false;
+}
+
+static bool throtl_hierarchy_can_upgrade(struct throtl_grp *tg)
+{
+ while (true) {
+ if (throtl_tg_can_upgrade(tg))
+ return true;
+ tg = sq_to_tg(tg->service_queue.parent_sq);
+ if (!tg || (cgroup_subsys_on_dfl(io_cgrp_subsys) &&
+ !tg_to_blkg(tg)->parent))
+ return false;
+ }
+ return false;
+}
+
+static bool throtl_can_upgrade(struct throtl_data *td,
+ struct throtl_grp *this_tg)
+{
+ struct cgroup_subsys_state *pos_css;
+ struct blkcg_gq *blkg;
+
+ if (td->limit_index != LIMIT_LOW)
+ return false;
+
+ rcu_read_lock();
+ blkg_for_each_descendant_post(blkg, pos_css, td->queue->root_blkg) {
+ struct throtl_grp *tg = blkg_to_tg(blkg);
+
+ if (tg == this_tg)
+ continue;
+ if (!list_empty(&tg_to_blkg(tg)->blkcg->css.children))
+ continue;
+ if (!throtl_hierarchy_can_upgrade(tg)) {
+ rcu_read_unlock();
+ return false;
+ }
+ }
+ rcu_read_unlock();
+ return true;
+}
+
+static void throtl_upgrade_state(struct throtl_data *td)
+{
+ struct cgroup_subsys_state *pos_css;
+ struct blkcg_gq *blkg;
+
+ td->limit_index = LIMIT_MAX;
+ rcu_read_lock();
+ blkg_for_each_descendant_post(blkg, pos_css, td->queue->root_blkg) {
+ struct throtl_grp *tg = blkg_to_tg(blkg);
+ struct throtl_service_queue *sq = &tg->service_queue;
+
+ tg->disptime = jiffies - 1;
+ throtl_select_dispatch(sq);
+ throtl_schedule_next_dispatch(sq, false);
+ }
+ rcu_read_unlock();
+ throtl_select_dispatch(&td->service_queue);
+ throtl_schedule_next_dispatch(&td->service_queue, false);
+ queue_work(kthrotld_workqueue, &td->dispatch_work);
+}
+
bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg,
struct bio *bio)
{
@@ -1528,14 +1615,20 @@ bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg,
sq = &tg->service_queue;
+again:
while (true) {
/* throtl is FIFO - if bios are already queued, should queue */
if (sq->nr_queued[rw])
break;
/* if above limits, break to queue */
- if (!tg_may_dispatch(tg, bio, NULL))
+ if (!tg_may_dispatch(tg, bio, NULL)) {
+ if (throtl_can_upgrade(tg->td, tg)) {
+ throtl_upgrade_state(tg->td);
+ goto again;
+ }
break;
+ }
/* within limits, let's charge and dispatch directly */
throtl_charge_bio(tg, bio);
--
2.9.3
next prev parent reply other threads:[~2016-12-15 20:38 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-12-15 20:32 [PATCH V5 00/17] blk-throttle: add .low limit Shaohua Li
2016-12-15 20:32 ` [PATCH V5 01/17] blk-throttle: use U64_MAX/UINT_MAX to replace -1 Shaohua Li
2016-12-15 20:32 ` [PATCH V5 02/17] blk-throttle: prepare support multiple limits Shaohua Li
2016-12-15 20:32 ` [PATCH V5 03/17] blk-throttle: add .low interface Shaohua Li
2017-01-09 16:35 ` Tejun Heo
2016-12-15 20:32 ` [PATCH V5 04/17] blk-throttle: configure bps/iops limit for cgroup in low limit Shaohua Li
2017-01-09 17:35 ` Tejun Heo
2016-12-15 20:32 ` Shaohua Li [this message]
2017-01-09 18:40 ` [PATCH V5 05/17] blk-throttle: add upgrade logic for LIMIT_LOW state Tejun Heo
2017-01-09 19:46 ` Tejun Heo
2016-12-15 20:32 ` [PATCH V5 06/17] blk-throttle: add downgrade logic Shaohua Li
2016-12-15 20:32 ` [PATCH V5 07/17] blk-throttle: make sure expire time isn't too big Shaohua Li
2017-01-09 19:54 ` Tejun Heo
2016-12-15 20:32 ` [PATCH V5 08/17] blk-throttle: make throtl_slice tunable Shaohua Li
2017-01-09 20:08 ` Tejun Heo
2016-12-15 20:33 ` [PATCH V5 09/17] blk-throttle: detect completed idle cgroup Shaohua Li
2017-01-09 20:13 ` Tejun Heo
2016-12-15 20:33 ` [PATCH V5 10/17] blk-throttle: make bandwidth change smooth Shaohua Li
2017-01-09 20:28 ` Tejun Heo
2016-12-15 20:33 ` [PATCH V5 11/17] blk-throttle: add a simple idle detection Shaohua Li
2017-01-09 20:56 ` Tejun Heo
2016-12-15 20:33 ` [PATCH V5 12/17] blk-throttle: add interface to configure idle time threshold Shaohua Li
2017-01-09 20:58 ` Tejun Heo
2016-12-15 20:33 ` [PATCH V5 13/17] blk-throttle: ignore idle cgroup limit Shaohua Li
2017-01-09 21:01 ` Tejun Heo
2016-12-15 20:33 ` [PATCH V5 14/17] blk-throttle: add interface for per-cgroup target latency Shaohua Li
2017-01-09 21:14 ` Tejun Heo
2016-12-15 20:33 ` [PATCH V5 15/17] block: track request size in blk_issue_stat Shaohua Li
2016-12-16 2:01 ` kbuild test robot
2017-01-09 21:17 ` Tejun Heo
2016-12-15 20:33 ` [PATCH V5 16/17] blk-throttle: add a mechanism to estimate IO latency Shaohua Li
2017-01-09 21:39 ` Tejun Heo
2016-12-15 20:33 ` [PATCH V5 17/17] blk-throttle: add latency target support Shaohua Li
2017-01-09 21:46 ` [PATCH V5 00/17] blk-throttle: add .low limit Tejun Heo
2017-01-09 22:27 ` Shaohua Li
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=75685643afd126cbccefe894ca56fd5dd83fe8cf.1481833017.git.shli@fb.com \
--to=shli@fb.com \
--cc=axboe@fb.com \
--cc=kernel-team@fb.com \
--cc=linux-block@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=tj@kernel.org \
--cc=vgoyal@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).