From: Shaohua Li <shli@fb.com>
To: <linux-kernel@vger.kernel.org>, <linux-block@vger.kernel.org>
Cc: <axboe@kernel.dk>, <tj@kernel.org>,
Vivek Goyal <vgoyal@redhat.com>, <jmoyer@redhat.com>,
<Kernel-team@fb.com>
Subject: [PATCH V7 07/18] blk-throttle: add downgrade logic
Date: Mon, 27 Mar 2017 10:51:35 -0700 [thread overview]
Message-ID: <d3a11011e8d35d416b534248b7211f51e879a9f9.1490634565.git.shli@fb.com> (raw)
In-Reply-To: <cover.1490634565.git.shli@fb.com>
When queue state machine is in LIMIT_MAX state, but a cgroup is below
its low limit for some time, the queue should be downgraded to lower
state as one cgroup's low limit isn't met.
Signed-off-by: Shaohua Li <shli@fb.com>
---
block/blk-throttle.c | 156 +++++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 156 insertions(+)
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index dd382d8..7878ec1 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -140,6 +140,13 @@ struct throtl_grp {
/* Number of bio's dispatched in current slice */
unsigned int io_disp[2];
+ unsigned long last_low_overflow_time[2];
+
+ uint64_t last_bytes_disp[2];
+ unsigned int last_io_disp[2];
+
+ unsigned long last_check_time;
+
/* When did we start a new slice */
unsigned long slice_start[2];
unsigned long slice_end[2];
@@ -159,6 +166,9 @@ struct throtl_data
struct work_struct dispatch_work;
unsigned int limit_index;
bool limit_valid[LIMIT_CNT];
+
+ unsigned long low_upgrade_time;
+ unsigned long low_downgrade_time;
};
static void throtl_pending_timer_fn(unsigned long arg);
@@ -898,6 +908,8 @@ static void throtl_charge_bio(struct throtl_grp *tg, struct bio *bio)
/* Charge the bio to the group */
tg->bytes_disp[rw] += bio->bi_iter.bi_size;
tg->io_disp[rw]++;
+ tg->last_bytes_disp[rw] += bio->bi_iter.bi_size;
+ tg->last_io_disp[rw]++;
/*
* BIO_THROTTLED is used to prevent the same bio to be throttled
@@ -1527,6 +1539,45 @@ static struct blkcg_policy blkcg_policy_throtl = {
.pd_free_fn = throtl_pd_free,
};
+static unsigned long __tg_last_low_overflow_time(struct throtl_grp *tg)
+{
+ unsigned long rtime = jiffies, wtime = jiffies;
+
+ if (tg->bps[READ][LIMIT_LOW] || tg->iops[READ][LIMIT_LOW])
+ rtime = tg->last_low_overflow_time[READ];
+ if (tg->bps[WRITE][LIMIT_LOW] || tg->iops[WRITE][LIMIT_LOW])
+ wtime = tg->last_low_overflow_time[WRITE];
+ return min(rtime, wtime);
+}
+
+/* tg should not be an intermediate node */
+static unsigned long tg_last_low_overflow_time(struct throtl_grp *tg)
+{
+ struct throtl_service_queue *parent_sq;
+ struct throtl_grp *parent = tg;
+ unsigned long ret = __tg_last_low_overflow_time(tg);
+
+ while (true) {
+ parent_sq = parent->service_queue.parent_sq;
+ parent = sq_to_tg(parent_sq);
+ if (!parent)
+ break;
+
+ /*
+ * The parent doesn't have low limit, it always reaches low
+ * limit. Its overflow time is useless for children
+ */
+ if (!parent->bps[READ][LIMIT_LOW] &&
+ !parent->iops[READ][LIMIT_LOW] &&
+ !parent->bps[WRITE][LIMIT_LOW] &&
+ !parent->iops[WRITE][LIMIT_LOW])
+ continue;
+ if (time_after(__tg_last_low_overflow_time(parent), ret))
+ ret = __tg_last_low_overflow_time(parent);
+ }
+ return ret;
+}
+
static bool throtl_tg_can_upgrade(struct throtl_grp *tg)
{
struct throtl_service_queue *sq = &tg->service_queue;
@@ -1570,6 +1621,9 @@ static bool throtl_can_upgrade(struct throtl_data *td,
if (td->limit_index != LIMIT_LOW)
return false;
+ if (time_before(jiffies, td->low_downgrade_time + throtl_slice))
+ 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);
@@ -1593,6 +1647,7 @@ static void throtl_upgrade_state(struct throtl_data *td)
struct blkcg_gq *blkg;
td->limit_index = LIMIT_MAX;
+ td->low_upgrade_time = jiffies;
rcu_read_lock();
blkg_for_each_descendant_post(blkg, pos_css, td->queue->root_blkg) {
struct throtl_grp *tg = blkg_to_tg(blkg);
@@ -1608,6 +1663,99 @@ static void throtl_upgrade_state(struct throtl_data *td)
queue_work(kthrotld_workqueue, &td->dispatch_work);
}
+static void throtl_downgrade_state(struct throtl_data *td, int new)
+{
+ td->limit_index = new;
+ td->low_downgrade_time = jiffies;
+}
+
+static bool throtl_tg_can_downgrade(struct throtl_grp *tg)
+{
+ struct throtl_data *td = tg->td;
+ unsigned long now = jiffies;
+
+ /*
+ * If cgroup is below low limit, consider downgrade and throttle other
+ * cgroups
+ */
+ if (time_after_eq(now, td->low_upgrade_time + throtl_slice) &&
+ time_after_eq(now, tg_last_low_overflow_time(tg) + throtl_slice))
+ return true;
+ return false;
+}
+
+static bool throtl_hierarchy_can_downgrade(struct throtl_grp *tg)
+{
+ while (true) {
+ if (!throtl_tg_can_downgrade(tg))
+ return false;
+ tg = sq_to_tg(tg->service_queue.parent_sq);
+ if (!tg || !tg_to_blkg(tg)->parent)
+ break;
+ }
+ return true;
+}
+
+static void throtl_downgrade_check(struct throtl_grp *tg)
+{
+ uint64_t bps;
+ unsigned int iops;
+ unsigned long elapsed_time;
+ unsigned long now = jiffies;
+
+ if (tg->td->limit_index != LIMIT_MAX ||
+ !tg->td->limit_valid[LIMIT_LOW])
+ return;
+ if (!list_empty(&tg_to_blkg(tg)->blkcg->css.children))
+ return;
+ if (time_after(tg->last_check_time + throtl_slice, now))
+ return;
+
+ elapsed_time = now - tg->last_check_time;
+ tg->last_check_time = now;
+
+ if (time_before(now, tg_last_low_overflow_time(tg) + throtl_slice))
+ return;
+
+ if (tg->bps[READ][LIMIT_LOW]) {
+ bps = tg->last_bytes_disp[READ] * HZ;
+ do_div(bps, elapsed_time);
+ if (bps >= tg->bps[READ][LIMIT_LOW])
+ tg->last_low_overflow_time[READ] = now;
+ }
+
+ if (tg->bps[WRITE][LIMIT_LOW]) {
+ bps = tg->last_bytes_disp[WRITE] * HZ;
+ do_div(bps, elapsed_time);
+ if (bps >= tg->bps[WRITE][LIMIT_LOW])
+ tg->last_low_overflow_time[WRITE] = now;
+ }
+
+ if (tg->iops[READ][LIMIT_LOW]) {
+ iops = tg->last_io_disp[READ] * HZ / elapsed_time;
+ if (iops >= tg->iops[READ][LIMIT_LOW])
+ tg->last_low_overflow_time[READ] = now;
+ }
+
+ if (tg->iops[WRITE][LIMIT_LOW]) {
+ iops = tg->last_io_disp[WRITE] * HZ / elapsed_time;
+ if (iops >= tg->iops[WRITE][LIMIT_LOW])
+ tg->last_low_overflow_time[WRITE] = now;
+ }
+
+ /*
+ * If cgroup is below low limit, consider downgrade and throttle other
+ * cgroups
+ */
+ if (throtl_hierarchy_can_downgrade(tg))
+ throtl_downgrade_state(tg->td, LIMIT_LOW);
+
+ tg->last_bytes_disp[READ] = 0;
+ tg->last_bytes_disp[WRITE] = 0;
+ tg->last_io_disp[READ] = 0;
+ tg->last_io_disp[WRITE] = 0;
+}
+
bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg,
struct bio *bio)
{
@@ -1632,12 +1780,16 @@ bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg,
again:
while (true) {
+ if (tg->last_low_overflow_time[rw] == 0)
+ tg->last_low_overflow_time[rw] = jiffies;
+ throtl_downgrade_check(tg);
/* 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)) {
+ tg->last_low_overflow_time[rw] = jiffies;
if (throtl_can_upgrade(tg->td, tg)) {
throtl_upgrade_state(tg->td);
goto again;
@@ -1681,6 +1833,8 @@ bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg,
tg->io_disp[rw], tg_iops_limit(tg, rw),
sq->nr_queued[READ], sq->nr_queued[WRITE]);
+ tg->last_low_overflow_time[rw] = jiffies;
+
bio_associate_current(bio);
tg->td->nr_queued[rw]++;
throtl_add_bio_tg(bio, qn, tg);
@@ -1791,6 +1945,8 @@ int blk_throtl_init(struct request_queue *q)
td->limit_valid[LIMIT_MAX] = true;
td->limit_index = LIMIT_MAX;
+ td->low_upgrade_time = jiffies;
+ td->low_downgrade_time = jiffies;
/* activate policy */
ret = blkcg_activate_policy(q, &blkcg_policy_throtl);
if (ret)
--
2.9.3
next prev parent reply other threads:[~2017-03-27 17:51 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-03-27 17:51 [PATCH V7 00/18] blk-throttle: add .low limit Shaohua Li
2017-03-27 17:51 ` [PATCH V7 01/18] blk-throttle: use U64_MAX/UINT_MAX to replace -1 Shaohua Li
2017-03-27 17:51 ` [PATCH V7 02/18] blk-throttle: prepare support multiple limits Shaohua Li
2017-03-27 17:51 ` [PATCH V7 03/18] blk-throttle: add configure option for new .low interface Shaohua Li
2017-03-27 17:51 ` [PATCH V7 04/18] blk-throttle: add " Shaohua Li
2017-03-27 17:51 ` [PATCH V7 05/18] blk-throttle: configure bps/iops limit for cgroup in low limit Shaohua Li
2017-03-27 17:51 ` [PATCH V7 06/18] blk-throttle: add upgrade logic for LIMIT_LOW state Shaohua Li
2017-03-27 17:51 ` Shaohua Li [this message]
2017-03-27 17:51 ` [PATCH V7 08/18] blk-throttle: make sure expire time isn't too big Shaohua Li
2017-03-27 17:51 ` [PATCH V7 09/18] blk-throttle: make throtl_slice tunable Shaohua Li
2017-03-27 17:51 ` [PATCH V7 10/18] blk-throttle: choose a small throtl_slice for SSD Shaohua Li
2017-03-27 17:51 ` [PATCH V7 11/18] blk-throttle: detect completed idle cgroup Shaohua Li
2017-03-27 17:51 ` [PATCH V7 12/18] blk-throttle: make bandwidth change smooth Shaohua Li
2017-03-27 17:51 ` [PATCH V7 13/18] blk-throttle: add a simple idle detection Shaohua Li
2017-03-27 17:51 ` [PATCH V7 14/18] blk-throttle: add interface to configure idle time threshold Shaohua Li
2017-03-27 17:51 ` [PATCH V7 15/18] blk-throttle: ignore idle cgroup limit Shaohua Li
2017-03-27 17:51 ` [PATCH V7 16/18] blk-throttle: add interface for per-cgroup target latency Shaohua Li
2017-03-27 17:51 ` [PATCH V7 17/18] blk-throttle: add a mechanism to estimate IO latency Shaohua Li
2017-03-27 17:51 ` [PATCH V7 18/18] blk-throttle: add latency target support Shaohua Li
2017-03-27 18:15 ` [PATCH V7 00/18] blk-throttle: add .low limit Jens Axboe
2017-03-27 19:00 ` Shaohua Li
2017-03-27 19:11 ` Jens Axboe
2017-03-27 22:19 ` [PATCH 0/3] blk-throttle: add .low limit fix Shaohua Li
2017-03-27 22:19 ` [PATCH 1/3] block: track request size in blk_issue_stat Shaohua Li
2017-03-27 22:19 ` [PATCH 2/3] blk-throttle: add a mechanism to estimate IO latency Shaohua Li
2017-03-27 22:19 ` [PATCH 3/3] blk-throttle: add latency target support Shaohua Li
2017-03-28 15:58 ` [PATCH 0/3] blk-throttle: add .low limit fix Jens Axboe
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=d3a11011e8d35d416b534248b7211f51e879a9f9.1490634565.git.shli@fb.com \
--to=shli@fb.com \
--cc=Kernel-team@fb.com \
--cc=axboe@kernel.dk \
--cc=jmoyer@redhat.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.