linux-block.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Jens Axboe <axboe@kernel.dk>
To: linux-block@vger.kernel.org, linux-xfs@vger.kernel.org
Cc: dchinner@redhat.com, hch@lst.de, Jens Axboe <axboe@kernel.dk>
Subject: [PATCH 4/4] blk-wbt: throttle discards like background writes
Date: Mon,  7 May 2018 10:13:35 -0600	[thread overview]
Message-ID: <1525709615-14395-5-git-send-email-axboe@kernel.dk> (raw)
In-Reply-To: <1525709615-14395-1-git-send-email-axboe@kernel.dk>

Throttle discards like we would any background write. Discards should
be background activity, so if they are impacting foreground IO, then
we will throttle them down.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-stat.h |  6 +++---
 block/blk-wbt.c  | 43 ++++++++++++++++++++++++++-----------------
 block/blk-wbt.h  |  4 +++-
 3 files changed, 32 insertions(+), 21 deletions(-)

diff --git a/block/blk-stat.h b/block/blk-stat.h
index 2dd36347252a..c22049a8125e 100644
--- a/block/blk-stat.h
+++ b/block/blk-stat.h
@@ -10,11 +10,11 @@
 
 /*
  * from upper:
- * 3 bits: reserved for other usage
+ * 4 bits: reserved for other usage
  * 12 bits: size
- * 49 bits: time
+ * 48 bits: time
  */
-#define BLK_STAT_RES_BITS	3
+#define BLK_STAT_RES_BITS	4
 #define BLK_STAT_SIZE_BITS	12
 #define BLK_STAT_RES_SHIFT	(64 - BLK_STAT_RES_BITS)
 #define BLK_STAT_SIZE_SHIFT	(BLK_STAT_RES_SHIFT - BLK_STAT_SIZE_BITS)
diff --git a/block/blk-wbt.c b/block/blk-wbt.c
index 25d202345965..a7a724580033 100644
--- a/block/blk-wbt.c
+++ b/block/blk-wbt.c
@@ -106,6 +106,8 @@ static inline struct rq_wait *get_rq_wait(struct rq_wb *rwb,
 {
 	if (wb_acct & WBT_KSWAPD)
 		return &rwb->rq_wait[WBT_RWQ_KSWAPD];
+	else if (wb_acct & WBT_DISCARD)
+		return &rwb->rq_wait[WBT_RWQ_DISCARD];
 
 	return &rwb->rq_wait[WBT_RWQ_BG];
 }
@@ -143,10 +145,13 @@ void __wbt_done(struct rq_wb *rwb, enum wbt_flags wb_acct)
 	}
 
 	/*
-	 * If the device does write back caching, drop further down
-	 * before we wake people up.
+	 * For discards, our limit is always the background. For writes, if
+	 * the device does write back caching, drop further down before we
+	 * wake people up.
 	 */
-	if (rwb->wc && !wb_recent_wait(rwb))
+	if (wb_acct & WBT_DISCARD)
+		limit = rwb->wb_background;
+	else if (rwb->wc && !wb_recent_wait(rwb))
 		limit = 0;
 	else
 		limit = rwb->wb_normal;
@@ -483,6 +488,9 @@ static inline unsigned int get_limit(struct rq_wb *rwb, unsigned long rw)
 {
 	unsigned int limit;
 
+	if ((rw & REQ_OP_MASK) == REQ_OP_DISCARD)
+		return rwb->wb_background;
+
 	/*
 	 * At this point we know it's a buffered write. If this is
 	 * kswapd trying to free memory, or REQ_SYNC is set, then
@@ -564,21 +572,20 @@ static void __wbt_wait(struct rq_wb *rwb, enum wbt_flags wb_acct,
 
 static inline bool wbt_should_throttle(struct rq_wb *rwb, struct bio *bio)
 {
-	const int op = bio_op(bio);
-
-	/*
-	 * If not a WRITE, do nothing
-	 */
-	if (op != REQ_OP_WRITE)
-		return false;
-
-	/*
-	 * Don't throttle WRITE_ODIRECT
-	 */
-	if ((bio->bi_opf & (REQ_SYNC | REQ_IDLE)) == (REQ_SYNC | REQ_IDLE))
+	switch (bio_op(bio)) {
+	case REQ_OP_WRITE:
+		/*
+		 * Don't throttle WRITE_ODIRECT
+		 */
+		if ((bio->bi_opf & (REQ_SYNC | REQ_IDLE)) ==
+		    (REQ_SYNC | REQ_IDLE))
+			return false;
+		/* fallthrough */
+	case REQ_OP_DISCARD:
+		return true;
+	default:
 		return false;
-
-	return true;
+	}
 }
 
 /*
@@ -605,6 +612,8 @@ enum wbt_flags wbt_wait(struct rq_wb *rwb, struct bio *bio, spinlock_t *lock)
 
 	if (current_is_kswapd())
 		ret |= WBT_KSWAPD;
+	if (bio_op(bio) == REQ_OP_DISCARD)
+		ret |= WBT_DISCARD;
 
 	__wbt_wait(rwb, ret, bio->bi_opf, lock);
 
diff --git a/block/blk-wbt.h b/block/blk-wbt.h
index 8038b4a0d4ef..d6a125e49db5 100644
--- a/block/blk-wbt.h
+++ b/block/blk-wbt.h
@@ -14,13 +14,15 @@ enum wbt_flags {
 	WBT_TRACKED		= 1,	/* write, tracked for throttling */
 	WBT_READ		= 2,	/* read */
 	WBT_KSWAPD		= 4,	/* write, from kswapd */
+	WBT_DISCARD		= 8,	/* discard */
 
-	WBT_NR_BITS		= 3,	/* number of bits */
+	WBT_NR_BITS		= 4,	/* number of bits */
 };
 
 enum {
 	WBT_RWQ_BG		= 0,
 	WBT_RWQ_KSWAPD,
+	WBT_RWQ_DISCARD,
 	WBT_NUM_RWQ,
 };
 
-- 
2.7.4

  parent reply	other threads:[~2018-05-07 16:13 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-05-07 16:13 [PATCHSET v2 0/4] Add throttling for discards Jens Axboe
2018-05-07 16:13 ` [PATCH 1/4] block: break discard submissions into the user defined size Jens Axboe
2018-05-07 23:56   ` Darrick J. Wong
2018-05-08 20:43   ` Omar Sandoval
2018-05-08 20:57     ` Jens Axboe
2018-05-07 16:13 ` [PATCH 2/4] blk-wbt: account any writing command as a write Jens Axboe
2018-05-07 23:58   ` Darrick J. Wong
2018-05-08 20:44   ` Omar Sandoval
2018-05-07 16:13 ` [PATCH 3/4] blk-wbt: pass in enum wbt_flags to get_rq_wait() Jens Axboe
2018-05-08  0:07   ` Darrick J. Wong
2018-05-08 20:46   ` Omar Sandoval
2018-05-07 16:13 ` Jens Axboe [this message]
2018-05-08  0:13   ` [PATCH 4/4] blk-wbt: throttle discards like background writes Darrick J. Wong
2018-05-08 20:48   ` Omar Sandoval

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=1525709615-14395-5-git-send-email-axboe@kernel.dk \
    --to=axboe@kernel.dk \
    --cc=dchinner@redhat.com \
    --cc=hch@lst.de \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-xfs@vger.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).