| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <1454364778-25179-18-git-send-email-paolo.valente@linaro.org>
Date: Mon, 1 Feb 2016 23:12:53 +0100
From: Paolo Valente <paolo.valente@...aro.org>
To: Jens Axboe <axboe@...nel.dk>, Tejun Heo <tj@...nel.org>
Cc: Fabio Checconi <fchecconi@...il.com>,
Arianna Avanzini <avanzini.arianna@...il.com>,
linux-block@...r.kernel.org, linux-kernel@...r.kernel.org,
ulf.hansson@...aro.org, linus.walleij@...aro.org,
broonie@...nel.org, Paolo Valente <paolo.valente@...aro.org>
Subject: [PATCH RFC 17/22] block, bfq: reduce latency during request-pool saturation
This patch introduces an heuristic that reduces latency when the
I/O-request pool is saturated. This goal is achieved by disabling
device idling, for non-weight-raised queues, when there are weight-
raised queues with pending or in-flight requests. In fact, as
explained in more detail in the comment on the function
bfq_bfqq_must_not_expire(), this reduces the rate at which processes
associated with non-weight-raised queues grab requests from the pool,
thereby increasing the probability that processes associated with
weight-raised queues get a request immediately (or at least soon) when
they need one.
Signed-off-by: Paolo Valente <paolo.valente@...aro.org>
Signed-off-by: Arianna Avanzini <avanzini.arianna@...il.com>
---
block/bfq.h | 2 ++
block/cfq-iosched.c | 53 +++++++++++++++++++++++++++++++++++++++++++++++++++--
2 files changed, 53 insertions(+), 2 deletions(-)
diff --git a/block/bfq.h b/block/bfq.h
index 68969ba..2960e5d 100644
--- a/block/bfq.h
+++ b/block/bfq.h
@@ -299,6 +299,7 @@ enum bfq_device_speed {
* @root_group: root bfq_group for the device.
* @busy_queues: number of bfq_queues containing requests (including the
* queue in service, even if it is idling).
+ * @wr_busy_queues: number of weight-raised busy @bfq_queues.
* @queued: number of queued requests.
* @rq_in_driver: number of requests dispatched and waiting for completion.
* @sync_flight: number of sync requests in the driver.
@@ -368,6 +369,7 @@ struct bfq_data {
struct bfq_group *root_group;
int busy_queues;
+ int wr_busy_queues;
int queued;
int rq_in_driver;
int sync_flight;
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 40feb47..0539df4 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -1228,6 +1228,9 @@ static void bfq_del_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq,
bfqd->busy_queues--;
+ if (bfqq->wr_coeff > 1)
+ bfqd->wr_busy_queues--;
+
#ifdef CONFIG_CFQ_GROUP_IOSCHED
bfqg_stats_update_dequeue(bfqq_group(bfqq));
#endif
@@ -1246,6 +1249,9 @@ static void bfq_add_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq)
bfq_mark_bfqq_busy(bfqq);
bfqd->busy_queues++;
+
+ if (bfqq->wr_coeff > 1)
+ bfqd->wr_busy_queues++;
}
#if defined(CONFIG_CFQ_GROUP_IOSCHED) && defined(CONFIG_DEBUG_BLK_CGROUP)
@@ -2722,6 +2728,7 @@ add_bfqq_busy:
bfqq->wr_coeff = bfqd->bfq_wr_coeff;
bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
+ bfqd->wr_busy_queues++;
entity->prio_changed = 1;
bfq_log_bfqq(bfqd, bfqq,
"non-idle wrais starting at %lu, rais_max_time %u",
@@ -2889,6 +2896,8 @@ static void bfq_merged_requests(struct request_queue *q, struct request *rq,
/* Must be called with bfqq != NULL */
static void bfq_bfqq_end_wr(struct bfq_queue *bfqq)
{
+ if (bfq_bfqq_busy(bfqq))
+ bfqq->bfqd->wr_busy_queues--;
bfqq->wr_coeff = 1;
bfqq->wr_cur_max_time = 0;
/* Trigger a weight change on the next activation of the queue */
@@ -3677,7 +3686,8 @@ static bool bfq_may_expire_for_budg_timeout(struct bfq_queue *bfqq)
static bool bfq_bfqq_may_idle(struct bfq_queue *bfqq)
{
struct bfq_data *bfqd = bfqq->bfqd;
- bool idling_boosts_thr, asymmetric_scenario;
+ bool idling_boosts_thr, idling_boosts_thr_without_issues,
+ asymmetric_scenario;
/*
* The next variable takes into account the cases where idling
@@ -3697,6 +3707,44 @@ static bool bfq_bfqq_may_idle(struct bfq_queue *bfqq)
idling_boosts_thr = !bfqd->hw_tag || bfq_bfqq_IO_bound(bfqq);
/*
+ * The value of the next variable,
+ * idling_boosts_thr_without_issues, is equal to that of
+ * idling_boosts_thr, unless a special case holds. In this
+ * special case, described below, idling may cause problems to
+ * weight-raised queues.
+ *
+ * When the request pool is saturated (e.g., in the presence
+ * of write hogs), if the processes associated with
+ * non-weight-raised queues ask for requests at a lower rate,
+ * then processes associated with weight-raised queues have a
+ * higher probability to get a request from the pool
+ * immediately (or at least soon) when they need one. Thus
+ * they have a higher probability to actually get a fraction
+ * of the device throughput proportional to their high
+ * weight. This is especially true with NCQ-capable drives,
+ * which enqueue several requests in advance, and further
+ * reorder internally-queued requests.
+ *
+ * For this reason, we force to false the value of
+ * idling_boosts_thr_without_issues if there are weight-raised
+ * busy queues. In this case, and if bfqq is not weight-raised,
+ * this guarantees that the device is not idled for bfqq (if,
+ * instead, bfqq is weight-raised, then idling will be
+ * guaranteed by another variable, see below). Combined with
+ * the timestamping rules of BFQ (see [1] for details), this
+ * behavior causes bfqq, and hence any sync non-weight-raised
+ * queue, to get a lower number of requests served, and thus
+ * to ask for a lower number of requests from the request
+ * pool, before the busy weight-raised queues get served
+ * again. This often mitigates starvation problems in the
+ * presence of heavy write workloads and NCQ, thereby
+ * guaranteeing a higher application and system responsiveness
+ * in these hostile scenarios.
+ */
+ idling_boosts_thr_without_issues = idling_boosts_thr &&
+ bfqd->wr_busy_queues == 0;
+
+ /*
* There is then a case where idling must be performed not for
* throughput concerns, but to preserve service guarantees. To
* introduce it, we can note that allowing the drive to
@@ -3770,7 +3818,7 @@ static bool bfq_bfqq_may_idle(struct bfq_queue *bfqq)
* is necessary to preserve service guarantees.
*/
return bfq_bfqq_sync(bfqq) &&
- (idling_boosts_thr || asymmetric_scenario);
+ (idling_boosts_thr_without_issues || asymmetric_scenario);
}
/*
@@ -4975,6 +5023,7 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
* high-definition compressed
* video.
*/
+ bfqd->wr_busy_queues = 0;
/*
* Begin by assuming, optimistically, that the device peak rate is
--
1.9.1
Powered by blists - more mailing lists