linux-kernel - [PATCH] io-controller: Preempt a non-rt queue if a rt ioq is present in ancestor or sibling groups

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

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <4A3F3648.7080007@cn.fujitsu.com>
Date:	Mon, 22 Jun 2009 15:44:08 +0800
From:	Gui Jianfeng <guijianfeng@...fujitsu.com>
To:	Vivek Goyal <vgoyal@...hat.com>
CC:	linux-kernel@...r.kernel.org,
	containers@...ts.linux-foundation.org, dm-devel@...hat.com,
	jens.axboe@...cle.com, nauman@...gle.com, dpshah@...gle.com,
	lizf@...fujitsu.com, mikew@...gle.com, fchecconi@...il.com,
	paolo.valente@...more.it, ryov@...inux.co.jp,
	fernando@....ntt.co.jp, s-uchida@...jp.nec.com, taka@...inux.co.jp,
	jmoyer@...hat.com, dhaval@...ux.vnet.ibm.com,
	balbir@...ux.vnet.ibm.com, righi.andrea@...il.com,
	m-ikeda@...jp.nec.com, jbaron@...hat.com, agk@...hat.com,
	snitzer@...hat.com, akpm@...ux-foundation.org, peterz@...radead.org
Subject: [PATCH] io-controller: Preempt a non-rt queue if a rt ioq is present
 in ancestor or sibling groups

Preempt the ongoing non-rt ioq if there are rt ioqs waiting for dispatching
in ancestor or sibling groups. It will give other group's rt ioq an chance 
to dispatch ASAP.

Signed-off-by: Gui Jianfeng <guijianfeng@...fujitsu.com>
---
 block/elevator-fq.c |   44 +++++++++++++++++++++++++++++++++++++++-----
 block/elevator-fq.h |    1 +
 2 files changed, 40 insertions(+), 5 deletions(-)

diff --git a/block/elevator-fq.c b/block/elevator-fq.c
index 2ad40eb..80526fd 100644
--- a/block/elevator-fq.c
+++ b/block/elevator-fq.c
@@ -3245,8 +3245,16 @@ void elv_add_ioq_busy(struct elv_fq_data *efqd, struct io_queue *ioq)
 	elv_mark_ioq_busy(ioq);
 	efqd->busy_queues++;
 	if (elv_ioq_class_rt(ioq)) {
+		struct io_entity *entity;
 		struct io_group *iog = ioq_to_io_group(ioq);
+
 		iog->busy_rt_queues++;
+		entity = iog->entity.parent;
+
+		for_each_entity(entity) {
+			iog = io_entity_to_iog(entity);
+			iog->sub_busy_rt_queues++;
+		}
 	}
 
 #ifdef CONFIG_DEBUG_GROUP_IOSCHED
@@ -3290,9 +3298,18 @@ void elv_del_ioq_busy(struct elevator_queue *e, struct io_queue *ioq,
 	elv_clear_ioq_busy(ioq);
 	BUG_ON(efqd->busy_queues == 0);
 	efqd->busy_queues--;
+
 	if (elv_ioq_class_rt(ioq)) {
+		struct io_entity *entity;
 		struct io_group *iog = ioq_to_io_group(ioq);
+
 		iog->busy_rt_queues--;
+		entity = iog->entity.parent;
+
+		for_each_entity(entity) {
+			iog = io_entity_to_iog(entity);
+			iog->sub_busy_rt_queues--;
+		}
 	}
 
 	elv_deactivate_ioq(efqd, ioq, requeue);
@@ -3735,12 +3752,32 @@ int elv_iosched_expire_ioq(struct request_queue *q, int slice_expired,
 	return ret;
 }
 
+static int check_rt_queue(struct io_queue *ioq)
+{
+	struct io_group *iog;
+	struct io_entity *entity;
+
+	iog = ioq_to_io_group(ioq);
+
+	if (iog->busy_rt_queues)
+		return 1;
+
+	entity = iog->entity.parent;
+
+	for_each_entity(entity) {
+		iog = io_entity_to_iog(entity);
+		if (iog->sub_busy_rt_queues)
+			return 1;
+	}
+
+	return 0;
+}
+
 /* Common layer function to select the next queue to dispatch from */
 void *elv_fq_select_ioq(struct request_queue *q, int force)
 {
 	struct elv_fq_data *efqd = &q->elevator->efqd;
 	struct io_queue *new_ioq = NULL, *ioq = elv_active_ioq(q->elevator);
-	struct io_group *iog;
 	int slice_expired = 1;
 
 	if (!elv_nr_busy_ioq(q->elevator))
@@ -3811,12 +3848,9 @@ void *elv_fq_select_ioq(struct request_queue *q, int force)
 	/*
 	 * If we have a RT cfqq waiting, then we pre-empt the current non-rt
 	 * cfqq.
-	 *
-	 * TODO: This does not seem right across the io groups. Fix it.
 	 */
-	iog = ioq_to_io_group(ioq);
 
-	if (!elv_ioq_class_rt(ioq) && iog->busy_rt_queues) {
+	if (!elv_ioq_class_rt(ioq) && check_rt_queue(ioq)) {
 		/*
 		 * We simulate this as cfqq timed out so that it gets to bank
 		 * the remaining of its time slice.
diff --git a/block/elevator-fq.h b/block/elevator-fq.h
index b3193f8..be6c1af 100644
--- a/block/elevator-fq.h
+++ b/block/elevator-fq.h
@@ -248,6 +248,7 @@ struct io_group {
 	 * non-RT cfqq in service when this value is non-zero.
 	 */
 	unsigned int busy_rt_queues;
+	unsigned int sub_busy_rt_queues;
 
 	int deleting;
 	unsigned short iocg_id;
-- 
1.5.4.rc3


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/