The patch titled
Subject: fs/epoll: use faster rb_first_cached()
has been added to the -mm tree. Its filename is
fs-epoll-use-faster-rb_first_cached.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/fs-epoll-use-faster-rb_first_cached.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/fs-epoll-use-faster-rb_first_cached.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Davidlohr Bueso <dave@xxxxxxxxxxxx>
Subject: fs/epoll: use faster rb_first_cached()
... 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.
Link: http://lkml.kernel.org/r/20170719014603.19029-15-dave@xxxxxxxxxxxx
Signed-off-by: Davidlohr Bueso <dbueso@xxxxxxx>
Acked-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Cc: Jan Kara <jack@xxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
fs/eventpoll.c | 30 ++++++++++++++++--------------
1 file changed, 16 insertions(+), 14 deletions(-)
diff -puN fs/eventpoll.c~fs-epoll-use-faster-rb_first_cached fs/eventpoll.c
--- a/fs/eventpoll.c~fs-epoll-use-faster-rb_first_cached
+++ a/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 *e
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_fi
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 **p
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 eve
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
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
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 @@ error_remove_epi:
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
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;
_
Patches currently in -mm which might be from dave@xxxxxxxxxxxx are
rbtree-cache-leftmost-node-internally.patch
rbtree-optimize-root-check-during-rebalancing-loop.patch
rbtree-add-some-additional-comments-for-rebalancing-cases.patch
lib-rbtree_testc-make-input-module-parameters.patch
lib-rbtree_testc-add-inorder-traversal-test.patch
lib-rbtree_testc-support-rb_root_cached.patch
sched-fair-replace-cfs_rq-rb_leftmost.patch
sched-deadline-replace-earliest-dl-and-rq-leftmost-caching.patch
locking-rtmutex-replace-top-waiter-and-pi_waiters-leftmost-caching.patch
block-cfq-replace-cfq_rb_root-leftmost-caching.patch
lib-interval_tree-fast-overlap-detection.patch
lib-interval-tree-correct-comment-wrt-generic-flavor.patch
procfs-use-faster-rb_first_cached.patch
fs-epoll-use-faster-rb_first_cached.patch
mem-memcg-cache-rightmost-node.patch
block-cfq-cache-rightmost-rb_node.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
