From: brookxu <brookxu.cn@gmail.com>
To: paolo.valente@linaro.org, axboe@kernel.dk, tj@kernel.org
Cc: linux-block@vger.kernel.org, cgroups@vger.kernel.org,
linux-kernel@vger.kernel.org
Subject: [PATCH v3 06/14] bfq: keep the minimun bandwidth for CLASS_BE
Date: Thu, 25 Mar 2021 14:57:50 +0800 [thread overview]
Message-ID: <bc39271c5f3835e4782c7ecd53fb205aa9cc97a0.1616649216.git.brookxu@tencent.com> (raw)
In-Reply-To: <cover.1616649216.git.brookxu@tencent.com>
In-Reply-To: <cover.1616649216.git.brookxu@tencent.com>
From: Chunguang Xu <brookxu@tencent.com>
CLASS_RT will preempt other classes, which may starve. At
present, CLASS_IDLE has alleviated the starvation problem
through the minimum bandwidth mechanism. Similarly, we
should do the same for CLASS_BE.
Signed-off-by: Chunguang Xu <brookxu@tencent.com>
---
block/bfq-iosched.c | 6 ++++--
block/bfq-iosched.h | 11 ++++++----
block/bfq-wf2q.c | 59 ++++++++++++++++++++++++++++++++++++++---------------
3 files changed, 53 insertions(+), 23 deletions(-)
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 8eaf0eb..ee8c457 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -6560,9 +6560,11 @@ static void bfq_init_root_group(struct bfq_group *root_group,
root_group->bfqd = bfqd;
#endif
root_group->rq_pos_tree = RB_ROOT;
- for (i = 0; i < BFQ_IOPRIO_CLASSES; i++)
+ for (i = 0; i < BFQ_IOPRIO_CLASSES; i++) {
root_group->sched_data.service_tree[i] = BFQ_SERVICE_TREE_INIT;
- root_group->sched_data.bfq_class_idle_last_service = jiffies;
+ root_group->sched_data.bfq_class_last_service[i] = jiffies;
+ }
+ root_group->sched_data.class_timeout_last_check = jiffies;
}
static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h
index 29a56b8..f9ed1da 100644
--- a/block/bfq-iosched.h
+++ b/block/bfq-iosched.h
@@ -13,7 +13,7 @@
#include "blk-cgroup-rwstat.h"
#define BFQ_IOPRIO_CLASSES 3
-#define BFQ_CL_IDLE_TIMEOUT (HZ/5)
+#define BFQ_CLASS_TIMEOUT (HZ/5)
#define BFQ_MIN_WEIGHT 1
#define BFQ_MAX_WEIGHT 1000
@@ -97,9 +97,12 @@ struct bfq_sched_data {
struct bfq_entity *next_in_service;
/* array of service trees, one per ioprio_class */
struct bfq_service_tree service_tree[BFQ_IOPRIO_CLASSES];
- /* last time CLASS_IDLE was served */
- unsigned long bfq_class_idle_last_service;
-
+ /* last time the class was served */
+ unsigned long bfq_class_last_service[BFQ_IOPRIO_CLASSES];
+ /* last time class timeout was checked */
+ unsigned long class_timeout_last_check;
+ /* next index to check class timeout */
+ unsigned int next_class_index;
};
/**
diff --git a/block/bfq-wf2q.c b/block/bfq-wf2q.c
index c91109e..1f8f3c5 100644
--- a/block/bfq-wf2q.c
+++ b/block/bfq-wf2q.c
@@ -1188,6 +1188,7 @@ bool __bfq_deactivate_entity(struct bfq_entity *entity, bool ins_into_idle_tree)
{
struct bfq_sched_data *sd = entity->sched_data;
struct bfq_service_tree *st;
+ int idx = bfq_class_idx(entity);
bool is_in_service;
if (!entity->on_st_or_in_serv) /*
@@ -1227,6 +1228,7 @@ bool __bfq_deactivate_entity(struct bfq_entity *entity, bool ins_into_idle_tree)
else
bfq_idle_insert(st, entity);
+ sd->bfq_class_last_service[idx] = jiffies;
return true;
}
@@ -1455,6 +1457,45 @@ static struct bfq_entity *bfq_first_active_entity(struct bfq_service_tree *st,
return entity;
}
+static int bfq_select_next_class(struct bfq_sched_data *sd)
+{
+ struct bfq_service_tree *st = sd->service_tree;
+ unsigned long last_check, last_serve;
+ int i, class_idx, next_class = 0;
+ bool found = false;
+
+ /*
+ * we needed to guarantee a minimum bandwidth for each class (if
+ * there is some active entity in this class). This should also
+ * mitigate priority-inversion problems in case a low priority
+ * task is holding file system resources.
+ */
+ last_check = sd->class_timeout_last_check;
+ if (time_is_after_jiffies(last_check + BFQ_CLASS_TIMEOUT))
+ return next_class;
+
+ sd->class_timeout_last_check = jiffies;
+ for (i = 0; i < BFQ_IOPRIO_CLASSES; i++) {
+ class_idx = (sd->next_class_index + i) % BFQ_IOPRIO_CLASSES;
+ last_serve = sd->bfq_class_last_service[class_idx];
+
+ if (time_is_after_jiffies(last_serve + BFQ_CLASS_TIMEOUT))
+ continue;
+
+ if (!RB_EMPTY_ROOT(&(st + class_idx)->active)) {
+ if (found)
+ continue;
+
+ next_class = class_idx++;
+ class_idx %= BFQ_IOPRIO_CLASSES;
+ sd->next_class_index = class_idx;
+ found = true;
+ }
+ sd->bfq_class_last_service[class_idx] = jiffies;
+ }
+ return next_class;
+}
+
/**
* bfq_lookup_next_entity - return the first eligible entity in @sd.
* @sd: the sched_data.
@@ -1468,24 +1509,8 @@ static struct bfq_entity *bfq_lookup_next_entity(struct bfq_sched_data *sd,
bool expiration)
{
struct bfq_service_tree *st = sd->service_tree;
- struct bfq_service_tree *idle_class_st = st + (BFQ_IOPRIO_CLASSES - 1);
struct bfq_entity *entity = NULL;
- int class_idx = 0;
-
- /*
- * Choose from idle class, if needed to guarantee a minimum
- * bandwidth to this class (and if there is some active entity
- * in idle class). This should also mitigate
- * priority-inversion problems in case a low priority task is
- * holding file system resources.
- */
- if (time_is_before_jiffies(sd->bfq_class_idle_last_service +
- BFQ_CL_IDLE_TIMEOUT)) {
- if (!RB_EMPTY_ROOT(&idle_class_st->active))
- class_idx = BFQ_IOPRIO_CLASSES - 1;
- /* About to be served if backlogged, or not yet backlogged */
- sd->bfq_class_idle_last_service = jiffies;
- }
+ int class_idx = bfq_select_next_class(sd);
/*
* Find the next entity to serve for the highest-priority
--
1.8.3.1
next prev parent reply other threads:[~2021-03-25 6:58 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-03-25 6:57 [PATCH v3 00/14] bfq: introduce bfq.ioprio for cgroup brookxu
2021-03-25 6:57 ` [PATCH v3 01/14] bfq: introduce bfq_entity_to_bfqg helper method brookxu
2021-03-25 6:57 ` [PATCH v3 02/14] bfq: convert the type of bfq_group.bfqd to bfq_data* brookxu
2021-03-25 6:57 ` [PATCH v3 03/14] bfq: introduce bfq.ioprio for cgroup brookxu
2021-03-25 6:57 ` [PATCH v3 04/14] bfq: introduce bfq_ioprio_class to get ioprio class brookxu
2021-03-25 6:57 ` [PATCH v3 05/14] bfq: limit the IO depth of CLASS_IDLE to 1 brookxu
2021-03-25 6:57 ` brookxu [this message]
2021-03-25 6:57 ` [PATCH v3 07/14] bfq: introduce better_fairness for container scene brookxu
2021-03-25 6:57 ` [PATCH v3 08/14] bfq: introduce prio_expire flag for bfq_queue brookxu
2021-03-25 6:57 ` [PATCH v3 09/14] bfq: expire in_serv_queue for prio_expire under better_fairness brookxu
2021-03-25 6:57 ` [PATCH v3 10/14] bfq: optimize IO injection " brookxu
2021-03-25 6:57 ` [PATCH v3 11/14] bfq: disable idle for prio_expire " brookxu
2021-03-25 6:57 ` [PATCH v3 12/14] bfq: disable merging between different groups " brookxu
2021-03-25 6:57 ` [PATCH v3 13/14] bfq: remove unnecessary initialization logic brookxu
2021-03-25 6:57 ` [PATCH v3 14/14] bfq: optimize the calculation of bfq_weight_to_ioprio() brookxu
2021-04-04 16:09 ` [PATCH v3 00/14] bfq: introduce bfq.ioprio for cgroup Tejun Heo
2021-04-06 7:31 ` brookxu
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=bc39271c5f3835e4782c7ecd53fb205aa9cc97a0.1616649216.git.brookxu@tencent.com \
--to=brookxu.cn@gmail.com \
--cc=axboe@kernel.dk \
--cc=cgroups@vger.kernel.org \
--cc=linux-block@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=paolo.valente@linaro.org \
--cc=tj@kernel.org \
/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).