LKML Archive on lore.kernel.org
 help / Atom feed
From: Davidlohr Bueso <dave@stgolabs.net>
To: akpm@linux-foundation.org
Cc: mingo@kernel.org, peterz@infradead.org, jack@suse.cz,
	torvalds@linux-foundation.org, kirill.shutemov@linux.intel.com,
	hch@infradead.org, ldufour@linux.vnet.ibm.com, mhocko@suse.com,
	mgorman@techsingularity.net, dave@stgolabs.net,
	linux-kernel@vger.kernel.org, Davidlohr Bueso <dbueso@suse.de>
Subject: [PATCH 14/17] fs/epoll: use faster rb_first_cached()
Date: Tue, 18 Jul 2017 18:46:00 -0700
Message-ID: <20170719014603.19029-15-dave@stgolabs.net> (raw)
In-Reply-To: <20170719014603.19029-1-dave@stgolabs.net>

... such that we can avoid the tree walks to get the
node with the smallest key. Semantically the same,
as the previously used rb_first(), but O(1). The
main overhead is the extra footprint for the cached
rb_node pointer, which should not matter for epoll.

Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
---
 fs/eventpoll.c | 30 ++++++++++++++++--------------
 1 file changed, 16 insertions(+), 14 deletions(-)

diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index e767e4389cb1..c56e842bc9cc 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -205,7 +205,7 @@ struct eventpoll {
 	struct list_head rdllist;
 
 	/* RB tree root used to store monitored fd structs */
-	struct rb_root rbr;
+	struct rb_root_cached rbr;
 
 	/*
 	 * This is a single linked list that chains all the "struct epitem" that
@@ -791,7 +791,7 @@ static int ep_remove(struct eventpoll *ep, struct epitem *epi)
 	list_del_rcu(&epi->fllink);
 	spin_unlock(&file->f_lock);
 
-	rb_erase(&epi->rbn, &ep->rbr);
+	rb_erase_cached(&epi->rbn, &ep->rbr);
 
 	spin_lock_irqsave(&ep->lock, flags);
 	if (ep_is_linked(&epi->rdllink))
@@ -835,7 +835,7 @@ static void ep_free(struct eventpoll *ep)
 	/*
 	 * Walks through the whole tree by unregistering poll callbacks.
 	 */
-	for (rbp = rb_first(&ep->rbr); rbp; rbp = rb_next(rbp)) {
+	for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) {
 		epi = rb_entry(rbp, struct epitem, rbn);
 
 		ep_unregister_pollwait(ep, epi);
@@ -851,7 +851,7 @@ static void ep_free(struct eventpoll *ep)
 	 * a lockdep warning.
 	 */
 	mutex_lock(&ep->mtx);
-	while ((rbp = rb_first(&ep->rbr)) != NULL) {
+	while ((rbp = rb_first_cached(&ep->rbr)) != NULL) {
 		epi = rb_entry(rbp, struct epitem, rbn);
 		ep_remove(ep, epi);
 		cond_resched();
@@ -958,7 +958,7 @@ static void ep_show_fdinfo(struct seq_file *m, struct file *f)
 	struct rb_node *rbp;
 
 	mutex_lock(&ep->mtx);
-	for (rbp = rb_first(&ep->rbr); rbp; rbp = rb_next(rbp)) {
+	for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) {
 		struct epitem *epi = rb_entry(rbp, struct epitem, rbn);
 		struct inode *inode = file_inode(epi->ffd.file);
 
@@ -1035,7 +1035,7 @@ static int ep_alloc(struct eventpoll **pep)
 	init_waitqueue_head(&ep->wq);
 	init_waitqueue_head(&ep->poll_wait);
 	INIT_LIST_HEAD(&ep->rdllist);
-	ep->rbr = RB_ROOT;
+	ep->rbr = RB_ROOT_CACHED;
 	ep->ovflist = EP_UNACTIVE_PTR;
 	ep->user = user;
 
@@ -1061,7 +1061,7 @@ static struct epitem *ep_find(struct eventpoll *ep, struct file *file, int fd)
 	struct epoll_filefd ffd;
 
 	ep_set_ffd(&ffd, file, fd);
-	for (rbp = ep->rbr.rb_node; rbp; ) {
+	for (rbp = ep->rbr.rb_root.rb_node; rbp; ) {
 		epi = rb_entry(rbp, struct epitem, rbn);
 		kcmp = ep_cmp_ffd(&ffd, &epi->ffd);
 		if (kcmp > 0)
@@ -1083,7 +1083,7 @@ static struct epitem *ep_find_tfd(struct eventpoll *ep, int tfd, unsigned long t
 	struct rb_node *rbp;
 	struct epitem *epi;
 
-	for (rbp = rb_first(&ep->rbr); rbp; rbp = rb_next(rbp)) {
+	for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) {
 		epi = rb_entry(rbp, struct epitem, rbn);
 		if (epi->ffd.fd == tfd) {
 			if (toff == 0)
@@ -1263,20 +1263,22 @@ static void ep_ptable_queue_proc(struct file *file, wait_queue_head_t *whead,
 static void ep_rbtree_insert(struct eventpoll *ep, struct epitem *epi)
 {
 	int kcmp;
-	struct rb_node **p = &ep->rbr.rb_node, *parent = NULL;
+	struct rb_node **p = &ep->rbr.rb_root.rb_node, *parent = NULL;
 	struct epitem *epic;
+	bool leftmost = true;
 
 	while (*p) {
 		parent = *p;
 		epic = rb_entry(parent, struct epitem, rbn);
 		kcmp = ep_cmp_ffd(&epi->ffd, &epic->ffd);
-		if (kcmp > 0)
+		if (kcmp > 0) {
 			p = &parent->rb_right;
-		else
+			leftmost = false;
+		} else
 			p = &parent->rb_left;
 	}
 	rb_link_node(&epi->rbn, parent, p);
-	rb_insert_color(&epi->rbn, &ep->rbr);
+	rb_insert_color_cached(&epi->rbn, &ep->rbr, leftmost);
 }
 
 
@@ -1520,7 +1522,7 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
 	list_del_rcu(&epi->fllink);
 	spin_unlock(&tfile->f_lock);
 
-	rb_erase(&epi->rbn, &ep->rbr);
+	rb_erase_cached(&epi->rbn, &ep->rbr);
 
 error_unregister:
 	ep_unregister_pollwait(ep, epi);
@@ -1868,7 +1870,7 @@ static int ep_loop_check_proc(void *priv, void *cookie, int call_nests)
 	mutex_lock_nested(&ep->mtx, call_nests + 1);
 	ep->visited = 1;
 	list_add(&ep->visited_list_link, &visited_list);
-	for (rbp = rb_first(&ep->rbr); rbp; rbp = rb_next(rbp)) {
+	for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) {
 		epi = rb_entry(rbp, struct epitem, rbn);
 		if (unlikely(is_file_epoll(epi->ffd.file))) {
 			ep_tovisit = epi->ffd.file->private_data;
-- 
2.12.0

  parent reply index

Thread overview: 27+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-07-19  1:45 [PATCH -next v4 00/17] rbtree: cache leftmost node internally Davidlohr Bueso
2017-07-19  1:45 ` [PATCH 01/17] " Davidlohr Bueso
2017-07-19  1:45 ` [PATCH 02/17] rbtree: optimize root-check during rebalancing loop Davidlohr Bueso
2017-07-19  1:45 ` [PATCH 03/17] rbtree: add some additional comments for rebalancing cases Davidlohr Bueso
2017-07-19  1:45 ` [PATCH 04/17] lib/rbtree_test.c: make input module parameters Davidlohr Bueso
2017-07-19  1:45 ` [PATCH 05/17] lib/rbtree_test.c: add (inorder) traversal test Davidlohr Bueso
2017-07-19  1:45 ` [PATCH 06/17] lib/rbtree_test.c: support rb_root_cached Davidlohr Bueso
2017-07-19  1:45 ` [PATCH 07/17] sched/fair: replace cfs_rq->rb_leftmost Davidlohr Bueso
2017-07-19  1:45 ` [PATCH 08/17] sched/deadline: replace earliest dl and rq leftmost caching Davidlohr Bueso
2017-07-19  1:45 ` [PATCH 09/17] locking/rtmutex: replace top-waiter and pi_waiters " Davidlohr Bueso
2017-07-19  1:45 ` [PATCH 10/17] block/cfq: replace cfq_rb_root " Davidlohr Bueso
2017-07-19  7:46   ` Jan Kara
2017-07-19  1:45 ` [PATCH 11/17] lib/interval_tree: fast overlap detection Davidlohr Bueso
2017-07-22 17:52   ` Doug Ledford
2017-08-01 17:16   ` Michael S. Tsirkin
2017-07-19  1:45 ` [PATCH 12/17] lib/interval-tree: correct comment wrt generic flavor Davidlohr Bueso
2017-07-19  1:45 ` [PATCH 13/17] procfs: use faster rb_first_cached() Davidlohr Bueso
2017-07-19  1:46 ` Davidlohr Bueso [this message]
2017-07-19  1:46 ` [PATCH 15/17] fs/ext4: use cached rbtrees Davidlohr Bueso
2017-07-19  7:40   ` Jan Kara
2017-07-19 22:50     ` Davidlohr Bueso
2017-07-19  1:46 ` [PATCH 16/17] mem/memcg: cache rightmost node Davidlohr Bueso
2017-07-19  7:50   ` Michal Hocko
2017-07-26 21:09     ` Andrew Morton
2017-07-27  7:06       ` Michal Hocko
2017-07-19  1:46 ` [PATCH 17/17] block/cfq: cache rightmost rb_node Davidlohr Bueso
2017-07-19  7:59   ` Jan Kara

Reply instructions:

You may reply publically 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=20170719014603.19029-15-dave@stgolabs.net \
    --to=dave@stgolabs.net \
    --cc=akpm@linux-foundation.org \
    --cc=dbueso@suse.de \
    --cc=hch@infradead.org \
    --cc=jack@suse.cz \
    --cc=kirill.shutemov@linux.intel.com \
    --cc=ldufour@linux.vnet.ibm.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mgorman@techsingularity.net \
    --cc=mhocko@suse.com \
    --cc=mingo@kernel.org \
    --cc=peterz@infradead.org \
    --cc=torvalds@linux-foundation.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

LKML Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/lkml/0 lkml/git/0.git
	git clone --mirror https://lore.kernel.org/lkml/1 lkml/git/1.git
	git clone --mirror https://lore.kernel.org/lkml/2 lkml/git/2.git
	git clone --mirror https://lore.kernel.org/lkml/3 lkml/git/3.git
	git clone --mirror https://lore.kernel.org/lkml/4 lkml/git/4.git
	git clone --mirror https://lore.kernel.org/lkml/5 lkml/git/5.git
	git clone --mirror https://lore.kernel.org/lkml/6 lkml/git/6.git

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


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


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