[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-Id: <20190919092413.11141-1-r@hev.cc>
Date: Thu, 19 Sep 2019 17:24:13 +0800
From: hev <r@....cc>
To: linux-fsdevel@...r.kernel.org
Cc: Heiher <r@....cc>, Al Viro <viro@...IV.linux.org.uk>,
Andrew Morton <akpm@...ux-foundation.org>,
Davide Libenzi <davidel@...ilserver.org>,
Davidlohr Bueso <dave@...olabs.net>,
Dominik Brodowski <linux@...inikbrodowski.net>,
Eric Wong <e@...24.org>, Jason Baron <jbaron@...mai.com>,
Linus Torvalds <torvalds@...ux-foundation.org>,
Roman Penyaev <rpenyaev@...e.de>,
Sridhar Samudrala <sridhar.samudrala@...el.com>,
linux-kernel@...r.kernel.org
Subject: [PATCH RESEND v2] fs/epoll: Remove unnecessary wakeups of nested epoll that in ET mode
From: Heiher <r@....cc>
Take the case where we have:
t0
| (ew)
e0
| (et)
e1
| (lt)
s0
t0: thread 0
e0: epoll fd 0
e1: epoll fd 1
s0: socket fd 0
ew: epoll_wait
et: edge-trigger
lt: level-trigger
When s0 fires an event, e1 catches the event, and then e0 catches an event from
e1. After this, There is a thread t0 do epoll_wait() many times on e0, it should
only get one event in total, because e1 is a dded to e0 in edge-triggered mode.
This patch only allows the wakeup(&ep->poll_wait) in ep_scan_ready_list under
two conditions:
1. depth == 0.
2. There have event is added to ep->ovflist during processing.
Test code:
#include <unistd.h>
#include <sys/epoll.h>
#include <sys/socket.h>
int main(int argc, char *argv[])
{
int sfd[2];
int efd[2];
struct epoll_event e;
if (socketpair(AF_UNIX, SOCK_STREAM, 0, sfd) < 0)
goto out;
efd[0] = epoll_create(1);
if (efd[0] < 0)
goto out;
efd[1] = epoll_create(1);
if (efd[1] < 0)
goto out;
e.events = EPOLLIN;
if (epoll_ctl(efd[1], EPOLL_CTL_ADD, sfd[0], &e) < 0)
goto out;
e.events = EPOLLIN | EPOLLET;
if (epoll_ctl(efd[0], EPOLL_CTL_ADD, efd[1], &e) < 0)
goto out;
if (write(sfd[1], "w", 1) != 1)
goto out;
if (epoll_wait(efd[0], &e, 1, 0) != 1)
goto out;
if (epoll_wait(efd[0], &e, 1, 0) != 0)
goto out;
close(efd[0]);
close(efd[1]);
close(sfd[0]);
close(sfd[1]);
return 0;
out:
return -1;
}
More tests:
https://github.com/heiher/epoll-wakeup
Cc: Al Viro <viro@...IV.linux.org.uk>
Cc: Andrew Morton <akpm@...ux-foundation.org>
Cc: Davide Libenzi <davidel@...ilserver.org>
Cc: Davidlohr Bueso <dave@...olabs.net>
Cc: Dominik Brodowski <linux@...inikbrodowski.net>
Cc: Eric Wong <e@...24.org>
Cc: Jason Baron <jbaron@...mai.com>
Cc: Linus Torvalds <torvalds@...ux-foundation.org>
Cc: Roman Penyaev <rpenyaev@...e.de>
Cc: Sridhar Samudrala <sridhar.samudrala@...el.com>
Cc: linux-kernel@...r.kernel.org
Cc: linux-fsdevel@...r.kernel.org
Signed-off-by: hev <r@....cc>
---
fs/eventpoll.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index c4159bcc05d9..fa71468dbd51 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -685,6 +685,9 @@ static __poll_t ep_scan_ready_list(struct eventpoll *ep,
if (!ep_locked)
mutex_lock_nested(&ep->mtx, depth);
+ if (!depth || list_empty_careful(&ep->rdllist))
+ pwake++;
+
/*
* Steal the ready list, and re-init the original one to the
* empty list. Also, set ep->ovflist to NULL so that events
@@ -755,7 +758,7 @@ static __poll_t ep_scan_ready_list(struct eventpoll *ep,
mutex_unlock(&ep->mtx);
/* We have to call this outside the lock */
- if (pwake)
+ if (pwake == 2)
ep_poll_safewake(&ep->poll_wait);
return res;
--
2.23.0
Powered by blists - more mailing lists