All of lore.kernel.org
 help / color / mirror / Atom feed
From: Shaohua Li <shli@fb.com>
To: <linux-block@vger.kernel.org>, <linux-kernel@vger.kernel.org>
Cc: <axboe@fb.com>, <Kernel-team@fb.com>, <tj@kernel.org>,
	<jmoyer@redhat.com>, <vgoyal@redhat.com>
Subject: [PATCH v3 02/11] block-throttle: add .high interface
Date: Mon, 3 Oct 2016 14:20:21 -0700	[thread overview]
Message-ID: <d531e23e4d0a756884d7cfc18fb53fbda09c65af.1475529372.git.shli@fb.com> (raw)
In-Reply-To: <cover.1475529372.git.shli@fb.com>

Add high limit for cgroup and corresponding cgroup interface.

Signed-off-by: Shaohua Li <shli@fb.com>
---
 block/blk-throttle.c | 139 +++++++++++++++++++++++++++++++++++++++------------
 1 file changed, 107 insertions(+), 32 deletions(-)

diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 964b713..59d4b4c 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -84,8 +84,9 @@ enum tg_state_flags {
 #define rb_entry_tg(node)	rb_entry((node), struct throtl_grp, rb_node)
 
 enum {
-	LIMIT_MAX = 0,
-	LIMIT_CNT = 1,
+	LIMIT_HIGH = 0,
+	LIMIT_MAX = 1,
+	LIMIT_CNT = 2,
 };
 
 struct throtl_grp {
@@ -352,7 +353,7 @@ static struct blkg_policy_data *throtl_pd_alloc(gfp_t gfp, int node)
 
 	RB_CLEAR_NODE(&tg->rb_node);
 	for (rw = READ; rw <= WRITE; rw++) {
-		for (index = LIMIT_MAX; index < LIMIT_CNT; index++) {
+		for (index = LIMIT_HIGH; index < LIMIT_CNT; index++) {
 			tg->bps[rw][index] = -1;
 			tg->iops[rw][index] = -1;
 		}
@@ -414,6 +415,46 @@ static void throtl_pd_online(struct blkg_policy_data *pd)
 	tg_update_has_rules(pd_to_tg(pd));
 }
 
+static void blk_throtl_update_valid_limit(struct throtl_data *td)
+{
+	struct cgroup_subsys_state *pos_css;
+	struct blkcg_gq *blkg;
+	bool high_valid = false;
+
+	rcu_read_lock();
+	blkg_for_each_descendant_post(blkg, pos_css, td->queue->root_blkg) {
+		struct throtl_grp *tg = blkg_to_tg(blkg);
+
+		if (tg->bps[READ][LIMIT_HIGH] != -1 ||
+		    tg->bps[WRITE][LIMIT_HIGH] != -1 ||
+		    tg->iops[READ][LIMIT_HIGH] != -1 ||
+		    tg->iops[WRITE][LIMIT_HIGH] != -1)
+			high_valid = true;
+	}
+	rcu_read_unlock();
+
+	if (high_valid)
+		td->limit_valid[LIMIT_HIGH] = true;
+	else
+		td->limit_valid[LIMIT_HIGH] = false;
+}
+
+static void throtl_pd_offline(struct blkg_policy_data *pd)
+{
+	struct throtl_grp *tg = pd_to_tg(pd);
+
+	tg->bps[READ][LIMIT_HIGH] = -1;
+	tg->bps[WRITE][LIMIT_HIGH] = -1;
+	tg->iops[READ][LIMIT_HIGH] = -1;
+	tg->iops[WRITE][LIMIT_HIGH] = -1;
+
+	blk_throtl_update_valid_limit(tg->td);
+
+	if (tg->td->limit_index == LIMIT_HIGH &&
+	    !tg->td->limit_valid[LIMIT_HIGH])
+		tg->td->limit_index = LIMIT_MAX;
+}
+
 static void throtl_pd_free(struct blkg_policy_data *pd)
 {
 	struct throtl_grp *tg = pd_to_tg(pd);
@@ -1283,7 +1324,7 @@ static struct cftype throtl_legacy_files[] = {
 	{ }	/* terminate */
 };
 
-static u64 tg_prfill_max(struct seq_file *sf, struct blkg_policy_data *pd,
+static u64 tg_prfill_limit(struct seq_file *sf, struct blkg_policy_data *pd,
 			 int off)
 {
 	struct throtl_grp *tg = pd_to_tg(pd);
@@ -1292,36 +1333,32 @@ static u64 tg_prfill_max(struct seq_file *sf, struct blkg_policy_data *pd,
 
 	if (!dname)
 		return 0;
-	if (tg->bps[READ][LIMIT_MAX] == -1 && tg->bps[WRITE][LIMIT_MAX] == -1 &&
-	    tg->iops[READ][LIMIT_MAX] == -1 && tg->iops[WRITE][LIMIT_MAX] == -1)
+	if (tg->bps[READ][off] == -1 && tg->bps[WRITE][off] == -1 &&
+	    tg->iops[READ][off] == -1 && tg->iops[WRITE][off] == -1)
 		return 0;
 
-	if (tg->bps[READ][LIMIT_MAX] != -1)
-		snprintf(bufs[0], sizeof(bufs[0]), "%llu",
-			tg->bps[READ][LIMIT_MAX]);
-	if (tg->bps[WRITE][LIMIT_MAX] != -1)
-		snprintf(bufs[1], sizeof(bufs[1]), "%llu",
-			tg->bps[WRITE][LIMIT_MAX]);
-	if (tg->iops[READ][LIMIT_MAX] != -1)
-		snprintf(bufs[2], sizeof(bufs[2]), "%u",
-			tg->iops[READ][LIMIT_MAX]);
-	if (tg->iops[WRITE][LIMIT_MAX] != -1)
-		snprintf(bufs[3], sizeof(bufs[3]), "%u",
-			tg->iops[WRITE][LIMIT_MAX]);
+	if (tg->bps[READ][off] != -1)
+		snprintf(bufs[0], sizeof(bufs[0]), "%llu", tg->bps[READ][off]);
+	if (tg->bps[WRITE][off] != -1)
+		snprintf(bufs[1], sizeof(bufs[1]), "%llu", tg->bps[WRITE][off]);
+	if (tg->iops[READ][off] != -1)
+		snprintf(bufs[2], sizeof(bufs[2]), "%u", tg->iops[READ][off]);
+	if (tg->iops[WRITE][off] != -1)
+		snprintf(bufs[3], sizeof(bufs[3]), "%u", tg->iops[WRITE][off]);
 
 	seq_printf(sf, "%s rbps=%s wbps=%s riops=%s wiops=%s\n",
 		   dname, bufs[0], bufs[1], bufs[2], bufs[3]);
 	return 0;
 }
 
-static int tg_print_max(struct seq_file *sf, void *v)
+static int tg_print_limit(struct seq_file *sf, void *v)
 {
-	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), tg_prfill_max,
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), tg_prfill_limit,
 			  &blkcg_policy_throtl, seq_cft(sf)->private, false);
 	return 0;
 }
 
-static ssize_t tg_set_max(struct kernfs_open_file *of,
+static ssize_t tg_set_limit(struct kernfs_open_file *of,
 			  char *buf, size_t nbytes, loff_t off)
 {
 	struct blkcg *blkcg = css_to_blkcg(of_css(of));
@@ -1329,6 +1366,7 @@ static ssize_t tg_set_max(struct kernfs_open_file *of,
 	struct throtl_grp *tg;
 	u64 v[4];
 	int ret;
+	int index = of_cft(of)->private;
 
 	ret = blkg_conf_prep(blkcg, &blkcg_policy_throtl, buf, &ctx);
 	if (ret)
@@ -1336,10 +1374,10 @@ static ssize_t tg_set_max(struct kernfs_open_file *of,
 
 	tg = blkg_to_tg(ctx.blkg);
 
-	v[0] = tg->bps[READ][LIMIT_MAX];
-	v[1] = tg->bps[WRITE][LIMIT_MAX];
-	v[2] = tg->iops[READ][LIMIT_MAX];
-	v[3] = tg->iops[WRITE][LIMIT_MAX];
+	v[0] = tg->bps[READ][index];
+	v[1] = tg->bps[WRITE][index];
+	v[2] = tg->iops[READ][index];
+	v[3] = tg->iops[WRITE][index];
 
 	while (true) {
 		char tok[27];	/* wiops=18446744073709551616 */
@@ -1376,11 +1414,37 @@ static ssize_t tg_set_max(struct kernfs_open_file *of,
 			goto out_finish;
 	}
 
-	tg->bps[READ][LIMIT_MAX] = v[0];
-	tg->bps[WRITE][LIMIT_MAX] = v[1];
-	tg->iops[READ][LIMIT_MAX] = v[2];
-	tg->iops[WRITE][LIMIT_MAX] = v[3];
-
+	if (index == LIMIT_MAX) {
+		if ((v[0] < tg->bps[READ][LIMIT_HIGH] &&
+		       tg->bps[READ][LIMIT_HIGH] != -1) ||
+		    (v[1] < tg->bps[WRITE][LIMIT_HIGH] &&
+		       tg->bps[WRITE][LIMIT_HIGH] != -1) ||
+		    (v[2] < tg->iops[READ][LIMIT_HIGH] &&
+		       tg->iops[READ][LIMIT_HIGH] != -1) ||
+		    (v[3] < tg->iops[WRITE][LIMIT_HIGH] &&
+		       tg->iops[WRITE][LIMIT_HIGH] != -1)) {
+			ret = -EINVAL;
+			goto out_finish;
+		}
+	} else if (index == LIMIT_HIGH) {
+		if ((v[0] > tg->bps[READ][LIMIT_MAX] && v[0] != -1) ||
+		    (v[1] > tg->bps[WRITE][LIMIT_MAX] && v[1] != -1) ||
+		    (v[2] > tg->iops[READ][LIMIT_MAX] && v[2] != -1) ||
+		    (v[3] > tg->iops[WRITE][LIMIT_MAX] && v[3] != -1)) {
+			ret = -EINVAL;
+			goto out_finish;
+		}
+	}
+	tg->bps[READ][index] = v[0];
+	tg->bps[WRITE][index] = v[1];
+	tg->iops[READ][index] = v[2];
+	tg->iops[WRITE][index] = v[3];
+
+	if (index == LIMIT_HIGH) {
+		blk_throtl_update_valid_limit(tg->td);
+		if (tg->td->limit_valid[LIMIT_HIGH])
+			tg->td->limit_index = LIMIT_HIGH;
+	}
 	tg_conf_updated(tg);
 	ret = 0;
 out_finish:
@@ -1390,10 +1454,18 @@ static ssize_t tg_set_max(struct kernfs_open_file *of,
 
 static struct cftype throtl_files[] = {
 	{
+		.name = "high",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.seq_show = tg_print_limit,
+		.write = tg_set_limit,
+		.private = LIMIT_HIGH,
+	},
+	{
 		.name = "max",
 		.flags = CFTYPE_NOT_ON_ROOT,
-		.seq_show = tg_print_max,
-		.write = tg_set_max,
+		.seq_show = tg_print_limit,
+		.write = tg_set_limit,
+		.private = LIMIT_MAX,
 	},
 	{ }	/* terminate */
 };
@@ -1412,6 +1484,7 @@ static struct blkcg_policy blkcg_policy_throtl = {
 	.pd_alloc_fn		= throtl_pd_alloc,
 	.pd_init_fn		= throtl_pd_init,
 	.pd_online_fn		= throtl_pd_online,
+	.pd_offline_fn		= throtl_pd_offline,
 	.pd_free_fn		= throtl_pd_free,
 };
 
@@ -1589,7 +1662,9 @@ int blk_throtl_init(struct request_queue *q)
 	q->td = td;
 	td->queue = q;
 
+	td->limit_valid[LIMIT_HIGH] = false;
 	td->limit_valid[LIMIT_MAX] = true;
+	td->limit_index = LIMIT_MAX;
 	/* activate policy */
 	ret = blkcg_activate_policy(q, &blkcg_policy_throtl);
 	if (ret)
-- 
2.9.3


  parent reply	other threads:[~2016-10-03 21:21 UTC|newest]

Thread overview: 65+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-10-03 21:20 [PATCH V3 00/11] block-throttle: add .high limit Shaohua Li
2016-10-03 21:20 ` [PATCH v3 01/11] block-throttle: prepare support multiple limits Shaohua Li
2016-10-03 21:20 ` Shaohua Li [this message]
2016-10-03 21:20 ` [PATCH v3 03/11] block-throttle: configure bps/iops limit for cgroup in high limit Shaohua Li
2016-10-03 21:20 ` [PATCH v3 04/11] block-throttle: add upgrade logic for LIMIT_HIGH state Shaohua Li
2016-10-03 21:20 ` [PATCH v3 05/11] block-throttle: add downgrade logic Shaohua Li
2016-10-03 21:20 ` [PATCH v3 06/11] blk-throttle: make sure expire time isn't too big Shaohua Li
2016-10-03 21:20 ` [PATCH v3 07/11] blk-throttle: make throtl_slice tunable Shaohua Li
2016-10-03 21:20 ` [PATCH v3 08/11] blk-throttle: detect completed idle cgroup Shaohua Li
2016-10-03 21:20 ` [PATCH v3 09/11] block-throttle: make bandwidth change smooth Shaohua Li
2016-10-03 21:20 ` [PATCH v3 10/11] block-throttle: add a simple idle detection Shaohua Li
2016-10-03 21:20 ` [PATCH v3 11/11] blk-throttle: ignore idle cgroup limit Shaohua Li
2016-10-04 13:28 ` [PATCH V3 00/11] block-throttle: add .high limit Vivek Goyal
2016-10-04 15:56   ` Tejun Heo
2016-10-04 16:22     ` Paolo Valente
2016-10-04 16:27       ` Tejun Heo
2016-10-04 17:01         ` Paolo Valente
2016-10-04 17:28           ` Shaohua Li
2016-10-04 17:43             ` Paolo Valente
2016-10-04 18:28               ` Shaohua Li
2016-10-04 19:49                 ` Paolo Valente
2016-10-04 18:54               ` Tejun Heo
2016-10-04 19:02                 ` Paolo Valente
2016-10-04 19:14                   ` Tejun Heo
2016-10-04 19:29                     ` Paolo Valente
2016-10-04 20:27                       ` Tejun Heo
2016-10-05 12:37                         ` Paolo Valente
2016-10-05 13:12                           ` Vivek Goyal
2016-10-05 14:04                             ` Paolo Valente
2016-10-05 14:49                           ` Tejun Heo
2016-10-05 18:30                             ` Shaohua Li
2016-10-05 19:08                               ` Shaohua Li
2016-10-05 19:57                                 ` Paolo Valente
2016-10-05 20:36                                   ` Shaohua Li
2016-10-06  7:22                                     ` Paolo Valente
2016-10-05 19:47                               ` Paolo Valente
2016-10-05 20:07                                 ` Paolo Valente
2016-10-05 20:46                                 ` Shaohua Li
2016-10-06  7:58                                   ` Paolo Valente
2016-10-06 13:15                                     ` Paolo Valente
2016-10-06 17:49                                       ` Vivek Goyal
2016-10-06 18:01                                         ` Paolo Valente
2016-10-06 18:32                                           ` Vivek Goyal
2016-10-06 20:51                                             ` Paolo Valente
2016-10-06 19:44                                         ` Mark Brown
2016-10-06 19:57                                     ` Shaohua Li
2016-10-06 22:24                                       ` Paolo Valente
     [not found]                         ` <CACsaVZ+AqSXHTRdpdrQQp6PuynEPeB-5YOyweWsenjvuKsD12w@mail.gmail.com>
2016-10-09  1:15                           ` Fwd: " Kyle Sanderson
2016-10-14 16:40                             ` Tejun Heo
2016-10-14 17:13                               ` Paolo Valente
2016-10-14 18:35                                 ` Tejun Heo
2016-10-16 19:02                                   ` Paolo Valente
2016-10-18  5:15                                     ` Kyle Sanderson
2016-10-06  8:04                     ` Linus Walleij
2016-10-06 11:03                       ` Mark Brown
2016-10-06 11:57                         ` Austin S. Hemmelgarn
2016-10-06 12:50                           ` Paolo Valente
2016-10-06 13:52                             ` Austin S. Hemmelgarn
2016-10-06 15:05                               ` Paolo Valente
2016-10-06 15:10                                 ` Austin S. Hemmelgarn
2016-10-08 10:46                       ` Heinz Diehl
2016-10-04 18:12     ` Vivek Goyal
2016-10-04 18:50       ` Tejun Heo
2016-10-04 18:56         ` Paolo Valente
2016-10-04 17:08   ` Shaohua Li

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=d531e23e4d0a756884d7cfc18fb53fbda09c65af.1475529372.git.shli@fb.com \
    --to=shli@fb.com \
    --cc=Kernel-team@fb.com \
    --cc=axboe@fb.com \
    --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.