Linux-Block Archive on lore.kernel.org
 help / color / Atom feed
From: Tejun Heo <tj@kernel.org>
To: Paolo Valente <paolo.valente@linaro.org>
Cc: "Michal Koutný" <mkoutny@suse.com>,
	"Johannes Weiner" <hannes@cmpxchg.org>,
	clm@fb.com, dennisz@fb.com, newella@fb.com,
	"Li Zefan" <lizefan@huawei.com>, "Jens Axboe" <axboe@kernel.dk>,
	"Josef Bacik" <josef@toxicpanda.com>,
	"Josef Bacik" <jbacik@fb.com>,
	kernel-team@fb.com, "Rik van Riel" <riel@surriel.com>,
	cgroups@vger.kernel.org, linux-block@vger.kernel.org,
	linux-kernel@vger.kernel.org
Subject: Re: [PATCH 08/10] blkcg: implement blk-iocost
Date: Wed, 11 Sep 2019 08:54:57 -0700
Message-ID: <20190911155457.GW2263813@devbig004.ftw2.facebook.com> (raw)
In-Reply-To: <20190911141630.GV2263813@devbig004.ftw2.facebook.com>

Hey,

On Wed, Sep 11, 2019 at 07:16:30AM -0700, Tejun Heo wrote:
> > >  I can implement
> > > the switching if so.
> > 
> > That would be perfect.
> 
> Whichever way it gets decided, this is easy enough.  I'll prep a
> patch.

Here's the patch.

* It disables iocost when bfq iosched is selected.  iocost is only
  re-enabled when bfq module is unloaded.  While it can easily be made
  to flip when there's no bfq queue left, I think minimizing the
  number of switches is likely is better.

* It looks like building bfq as module has been broken for some time
  and I added symbol exports to make it work.  They should be
  separated into a separate patch.

* It doesn't actually rename any of the bfq interface files.  It just
  gets rid of potential conflict from iocost.

Please feel free to use / modify the patch however you see fit.

Thanks.

---
diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
index 86a607cf19a1..decda96770f4 100644
--- a/block/bfq-cgroup.c
+++ b/block/bfq-cgroup.c
@@ -1194,7 +1194,9 @@ struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd, int node)
 }
 
 struct blkcg_policy blkcg_policy_bfq = {
+#ifndef CONFIG_BLK_CGROUP_IOCOST
 	.dfl_cftypes		= bfq_blkg_files,
+#endif
 	.legacy_cftypes		= bfq_blkcg_legacy_files,
 
 	.cpd_alloc_fn		= bfq_cpd_alloc,
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index b33be928d164..b4aaeef1fb87 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -6365,6 +6365,36 @@ static void bfq_init_root_group(struct bfq_group *root_group,
 	root_group->sched_data.bfq_class_idle_last_service = jiffies;
 }
 
+#if defined(CONFIG_BFQ_GROUP_IOSCHED) && defined(CONFIG_BLK_CGROUP_IOCOST)
+static bool bfq_enabled = false;
+
+static void bfq_enable(void)
+{
+	static DEFINE_MUTEX(bfq_enable_mutex);
+
+	mutex_lock(&bfq_enable_mutex);
+	if (!bfq_enabled) {
+		pr_info("bfq-iosched: Overriding iocost\n");
+		blkcg_policy_unregister(&blkcg_policy_iocost);
+		cgroup_add_dfl_cftypes(&io_cgrp_subsys, bfq_blkg_files);
+		bfq_enabled = true;
+	}
+	mutex_unlock(&bfq_enable_mutex);
+}
+
+static void __exit bfq_disable(void)
+{
+	if (bfq_enabled) {
+		pr_info("bfq-iosched: Restoring iocost\n");
+		cgroup_rm_cftypes(bfq_blkg_files);
+		blkcg_policy_register(&blkcg_policy_iocost);
+	}
+}
+#else
+static void bfq_enable(void) {}
+static void __exit bfq_disable(void) {}
+#endif
+
 static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
 {
 	struct bfq_data *bfqd;
@@ -6489,6 +6519,7 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
 	bfq_init_entity(&bfqd->oom_bfqq.entity, bfqd->root_group);
 
 	wbt_disable_default(q);
+	bfq_enable();
 	return 0;
 
 out_free:
@@ -6806,6 +6837,7 @@ static void __exit bfq_exit(void)
 	blkcg_policy_unregister(&blkcg_policy_bfq);
 #endif
 	bfq_slab_kill();
+	bfq_disable();
 }
 
 module_init(bfq_init);
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 0e2619c1a422..b6f20be0fc78 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -900,6 +900,7 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 	}
 	return ret;
 }
+EXPORT_SYMBOL_GPL(blkg_conf_prep);
 
 /**
  * blkg_conf_finish - finish up per-blkg config update
@@ -915,6 +916,7 @@ void blkg_conf_finish(struct blkg_conf_ctx *ctx)
 	rcu_read_unlock();
 	put_disk_and_module(ctx->disk);
 }
+EXPORT_SYMBOL_GPL(blkg_conf_finish);
 
 static int blkcg_print_stat(struct seq_file *sf, void *v)
 {
diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index 3b39deb8b9f8..1ef5b443c09a 100644
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -605,8 +605,6 @@ static u32 vrate_adj_pct[] =
 	  2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
 	  4, 4, 4, 4, 4, 4, 4, 4, 8, 8, 8, 8, 8, 8, 8, 8, 16 };
 
-static struct blkcg_policy blkcg_policy_iocost;
-
 /* accessors and helpers */
 static struct ioc *rqos_to_ioc(struct rq_qos *rqos)
 {
@@ -2434,7 +2432,7 @@ static struct cftype ioc_files[] = {
 	{}
 };
 
-static struct blkcg_policy blkcg_policy_iocost = {
+struct blkcg_policy blkcg_policy_iocost = {
 	.dfl_cftypes	= ioc_files,
 	.cpd_alloc_fn	= ioc_cpd_alloc,
 	.cpd_free_fn	= ioc_cpd_free,
@@ -2442,6 +2440,7 @@ static struct blkcg_policy blkcg_policy_iocost = {
 	.pd_init_fn	= ioc_pd_init,
 	.pd_free_fn	= ioc_pd_free,
 };
+EXPORT_SYMBOL_GPL(blkcg_policy_iocost);
 
 static int __init ioc_init(void)
 {
diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index bed9e43f9426..5669e3cfa1bc 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -815,6 +815,11 @@ static inline void blkcg_clear_delay(struct blkcg_gq *blkg)
 void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta);
 void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay);
 void blkcg_maybe_throttle_current(void);
+
+#ifdef CONFIG_BLK_CGROUP_IOCOST
+extern struct blkcg_policy blkcg_policy_iocost;
+#endif
+
 #else	/* CONFIG_BLK_CGROUP */
 
 struct blkcg {
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 753afbca549f..ced23229f359 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -4059,6 +4059,7 @@ int cgroup_rm_cftypes(struct cftype *cfts)
 	mutex_unlock(&cgroup_mutex);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(cgroup_rm_cftypes);
 
 /**
  * cgroup_add_cftypes - add an array of cftypes to a subsystem
@@ -4115,6 +4116,7 @@ int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
 		cft->flags |= __CFTYPE_ONLY_ON_DFL;
 	return cgroup_add_cftypes(ss, cfts);
 }
+EXPORT_SYMBOL_GPL(cgroup_add_dfl_cftypes);
 
 /**
  * cgroup_add_legacy_cftypes - add an array of cftypes for legacy hierarchies

  reply index

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-08-28 22:05 [PATCHSET v3 block/for-linus] IO cost model based work-conserving porportional controller Tejun Heo
2019-08-28 22:05 ` [PATCH 01/10] blkcg: pass @q and @blkcg into blkcg_pol_alloc_pd_fn() Tejun Heo
2019-08-28 22:05 ` [PATCH 02/10] blkcg: make ->cpd_init_fn() optional Tejun Heo
2019-08-28 22:05 ` [PATCH 03/10] blkcg: separate blkcg_conf_get_disk() out of blkg_conf_prep() Tejun Heo
2019-08-28 22:05 ` [PATCH 04/10] block/rq_qos: add rq_qos_merge() Tejun Heo
2019-08-28 22:05 ` [PATCH 05/10] block/rq_qos: implement rq_qos_ops->queue_depth_changed() Tejun Heo
2019-08-28 22:05 ` [PATCH 06/10] blkcg: s/RQ_QOS_CGROUP/RQ_QOS_LATENCY/ Tejun Heo
2019-08-28 22:05 ` [PATCH 07/10] blk-mq: add optional request->alloc_time_ns Tejun Heo
2019-08-28 22:05 ` [PATCH 08/10] blkcg: implement blk-iocost Tejun Heo
2019-08-29 15:53   ` [PATCH] blkcg: fix missing free on error path of blk_iocost_init() Tejun Heo
2019-09-10 12:55   ` [PATCH 08/10] blkcg: implement blk-iocost Michal Koutný
2019-09-10 16:08     ` Tejun Heo
2019-09-11  8:18       ` Paolo Valente
2019-09-11 14:16         ` Tejun Heo
2019-09-11 15:54           ` Tejun Heo [this message]
2019-09-11 16:44           ` Paolo Valente
2019-10-03 14:51       ` Michal Koutný
2019-10-03 16:45         ` Tejun Heo
2019-10-09 15:36           ` Michal Koutný
2019-10-14 15:36             ` Tejun Heo
2019-11-01 16:15               ` Michal Koutný
2019-11-01 16:56                 ` Paolo Valente
2019-08-28 22:05 ` [PATCH 09/10] blkcg: add tools/cgroup/iocost_monitor.py Tejun Heo
2019-08-28 22:06 ` [PATCH 10/10] blkcg: add tools/cgroup/iocost_coef_gen.py Tejun Heo
2019-08-29  3:29 ` [PATCHSET v3 block/for-linus] IO cost model based work-conserving porportional controller Jens Axboe
     [not found] ` <20190829082248.6464-1-hdanton@sina.com>
2019-08-29 15:43   ` [PATCH 07/10] blk-mq: add optional request->alloc_time_ns Tejun Heo
     [not found] ` <20190829133928.16192-1-hdanton@sina.com>
2019-08-29 15:46   ` [PATCH 08/10] blkcg: implement blk-iocost Tejun Heo
2019-08-29 15:54 ` [PATCHSET v3 block/for-linus] IO cost model based work-conserving porportional controller Paolo Valente
2019-08-29 15:56   ` Tejun Heo
  -- strict thread matches above, loose matches on Subject: below --
2019-07-10 20:51 [PATCHSET v2 " Tejun Heo
2019-07-10 20:51 ` [PATCH 08/10] blkcg: implement blk-iocost Tejun Heo

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=20190911155457.GW2263813@devbig004.ftw2.facebook.com \
    --to=tj@kernel.org \
    --cc=axboe@kernel.dk \
    --cc=cgroups@vger.kernel.org \
    --cc=clm@fb.com \
    --cc=dennisz@fb.com \
    --cc=hannes@cmpxchg.org \
    --cc=jbacik@fb.com \
    --cc=josef@toxicpanda.com \
    --cc=kernel-team@fb.com \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=lizefan@huawei.com \
    --cc=mkoutny@suse.com \
    --cc=newella@fb.com \
    --cc=paolo.valente@linaro.org \
    --cc=riel@surriel.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

Linux-Block Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-block/0 linux-block/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-block linux-block/ https://lore.kernel.org/linux-block \
		linux-block@vger.kernel.org
	public-inbox-index linux-block

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-block


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git