From mboxrd@z Thu Jan 1 00:00:00 1970 From: Eric Dumazet Subject: Re: [PATCH] poll: Avoid extra wakeups in select/poll Date: Wed, 29 Apr 2009 14:29:39 +0200 Message-ID: <49F84833.5000908@cosmosbay.com> References: <49F3308B.1030507@cosmosbay.com> <20090426.020411.157511269.davem@davemloft.net> <49F43B8F.2050907@cosmosbay.com> <87ab60rh8t.fsf@basil.nowhere.org> <49F71B63.8010503@cosmosbay.com> <20090429091637.GA29874@elte.hu> <49F81FB9.50504@cosmosbay.com> <20090429102734.GC2373@elte.hu> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: linux kernel , Andi Kleen , David Miller , cl@linux.com, jesse.brandeburg@intel.com, netdev@vger.kernel.org, haoki@redhat.com, mchan@broadcom.com, davidel@xmailserver.org To: Ingo Molnar Return-path: In-Reply-To: <20090429102734.GC2373@elte.hu> Sender: linux-kernel-owner@vger.kernel.org List-Id: netdev.vger.kernel.org Ingo Molnar a =E9crit : > * Eric Dumazet wrote: >=20 >> Ingo Molnar a =E9crit : >>> * Eric Dumazet wrote: >>> >>>> @@ -418,8 +429,16 @@ int do_select(int n, fd_set_bits *fds, struct= timespec *end_time) >>>> if (file) { >>>> f_op =3D file->f_op; >>>> mask =3D DEFAULT_POLLMASK; >>>> - if (f_op && f_op->poll) >>>> + if (f_op && f_op->poll) { >>>> + if (wait) { >>>> + wait->key =3D POLLEX_SET; >>>> + if (in & bit) >>>> + wait->key |=3D POLLIN_SET; >>>> + if (out & bit) >>>> + wait->key |=3D POLLOUT_SET; >>>> + } >>>> mask =3D (*f_op->poll)(file, retval ? NULL : wait); >>>> + } >>>> fput_light(file, fput_needed); >>>> if ((mask & POLLIN_SET) && (in & bit)) { >>>> res_in |=3D bit; >>> Please factor this whole 'if (file)' branch out into a helper.=20 >>> Typical indentation levels go from 1 to 3 tabs - 4 should be avoide= d=20 >>> if possible and 5 is pretty excessive already. This goes to eight. >>> >> Thanks Ingo, >> >> Here is v3 of patch, with your Acked-by included :) >> >> This is IMHO clearer since helper immediatly follows POLLIN_SET / PO= LLOUT_SET / >> POLLEX_SET defines. >> >> [PATCH] poll: Avoid extra wakeups in select/poll >> >> After introduction of keyed wakeups Davide Libenzi did on epoll, we >> are able to avoid spurious wakeups in poll()/select() code too. >> >> For example, typical use of poll()/select() is to wait for incoming >> network frames on many sockets. But TX completion for UDP/TCP=20 >> frames call sock_wfree() which in turn schedules thread. >> >> When scheduled, thread does a full scan of all polled fds and >> can sleep again, because nothing is really available. If number >> of fds is large, this cause significant load. >> >> This patch makes select()/poll() aware of keyed wakeups and >> useless wakeups are avoided. This reduces number of context >> switches by about 50% on some setups, and work performed >> by sofirq handlers. >> >> Signed-off-by: Eric Dumazet >> Acked-by: David S. Miller >> Acked-by: Andi Kleen >> Acked-by: Ingo Molnar >=20 >> --- >> fs/select.c | 40 ++++++++++++++++++++++++++++++++++++---= - >> include/linux/poll.h | 3 +++ >> 2 files changed, 39 insertions(+), 4 deletions(-) >> >> diff --git a/fs/select.c b/fs/select.c >> index 0fe0e14..ba068ad 100644 >> --- a/fs/select.c >> +++ b/fs/select.c >> @@ -168,7 +168,7 @@ static struct poll_table_entry *poll_get_entry(s= truct poll_wqueues *p) >> return table->entry++; >> } >> =20 >> -static int pollwake(wait_queue_t *wait, unsigned mode, int sync, vo= id *key) >> +static int __pollwake(wait_queue_t *wait, unsigned mode, int sync, = void *key) >> { >> struct poll_wqueues *pwq =3D wait->private; >> DECLARE_WAITQUEUE(dummy_wait, pwq->polling_task); >> @@ -194,6 +194,16 @@ static int pollwake(wait_queue_t *wait, unsigne= d mode, int sync, void *key) >> return default_wake_function(&dummy_wait, mode, sync, key); >> } >> =20 >> +static int pollwake(wait_queue_t *wait, unsigned mode, int sync, vo= id *key) >> +{ >> + struct poll_table_entry *entry; >> + >> + entry =3D container_of(wait, struct poll_table_entry, wait); >> + if (key && !((unsigned long)key & entry->key)) >> + return 0; >> + return __pollwake(wait, mode, sync, key); >> +} >> + >> /* Add a new entry */ >> static void __pollwait(struct file *filp, wait_queue_head_t *wait_a= ddress, >> poll_table *p) >> @@ -205,6 +215,7 @@ static void __pollwait(struct file *filp, wait_q= ueue_head_t *wait_address, >> get_file(filp); >> entry->filp =3D filp; >> entry->wait_address =3D wait_address; >> + entry->key =3D p->key; >> init_waitqueue_func_entry(&entry->wait, pollwake); >> entry->wait.private =3D pwq; >> add_wait_queue(wait_address, &entry->wait); >> @@ -362,6 +373,18 @@ get_max: >> #define POLLOUT_SET (POLLWRBAND | POLLWRNORM | POLLOUT | POLLERR) >> #define POLLEX_SET (POLLPRI) >> =20 >> +static void wait_key_set(poll_table *wait, unsigned long in, >> + unsigned long out, unsigned long bit) >> +{ >> + if (wait) { >> + wait->key =3D POLLEX_SET; >> + if (in & bit) >> + wait->key |=3D POLLIN_SET; >> + if (out & bit) >> + wait->key |=3D POLLOUT_SET; >> + } >> +} >=20 > should be inline perhaps? Well, I thought current practice was not using inline for such trivial = functions, as gcc already inlines them anyway. Quoting Documentation/CodingStyle : Often people argue that adding inline to functions that are static an= d used only once is always a win since there is no space tradeoff. While thi= s is technically correct, gcc is capable of inlining these automatically w= ithout help, and the maintenance issue of removing the inline when a second = user appears outweighs the potential value of the hint that tells gcc to d= o something it would have done anyway. Anyway : [PATCH] poll: Avoid extra wakeups in select/poll After introduction of keyed wakeups Davide Libenzi did on epoll, we are able to avoid spurious wakeups in poll()/select() code too. =46or example, typical use of poll()/select() is to wait for incoming network frames on many sockets. But TX completion for UDP/TCP=20 frames call sock_wfree() which in turn schedules thread. When scheduled, thread does a full scan of all polled fds and can sleep again, because nothing is really available. If number of fds is large, this cause significant load. This patch makes select()/poll() aware of keyed wakeups and useless wakeups are avoided. This reduces number of context switches by about 50% on some setups, and work performed by sofirq handlers. Signed-off-by: Eric Dumazet Acked-by: David S. Miller Acked-by: Andi Kleen Acked-by: Ingo Molnar --- fs/select.c | 40 ++++++++++++++++++++++++++++++++++++---- include/linux/poll.h | 3 +++ 2 files changed, 39 insertions(+), 4 deletions(-) diff --git a/fs/select.c b/fs/select.c index 0fe0e14..ba068ad 100644 --- a/fs/select.c +++ b/fs/select.c @@ -168,7 +168,7 @@ static struct poll_table_entry *poll_get_entry(stru= ct poll_wqueues *p) return table->entry++; } =20 -static int pollwake(wait_queue_t *wait, unsigned mode, int sync, void = *key) +static int __pollwake(wait_queue_t *wait, unsigned mode, int sync, voi= d *key) { struct poll_wqueues *pwq =3D wait->private; DECLARE_WAITQUEUE(dummy_wait, pwq->polling_task); @@ -194,6 +194,16 @@ static int pollwake(wait_queue_t *wait, unsigned m= ode, int sync, void *key) return default_wake_function(&dummy_wait, mode, sync, key); } =20 +static int pollwake(wait_queue_t *wait, unsigned mode, int sync, void = *key) +{ + struct poll_table_entry *entry; + + entry =3D container_of(wait, struct poll_table_entry, wait); + if (key && !((unsigned long)key & entry->key)) + return 0; + return __pollwake(wait, mode, sync, key); +} + /* Add a new entry */ static void __pollwait(struct file *filp, wait_queue_head_t *wait_addr= ess, poll_table *p) @@ -205,6 +215,7 @@ static void __pollwait(struct file *filp, wait_queu= e_head_t *wait_address, get_file(filp); entry->filp =3D filp; entry->wait_address =3D wait_address; + entry->key =3D p->key; init_waitqueue_func_entry(&entry->wait, pollwake); entry->wait.private =3D pwq; add_wait_queue(wait_address, &entry->wait); @@ -362,6 +373,18 @@ get_max: #define POLLOUT_SET (POLLWRBAND | POLLWRNORM | POLLOUT | POLLERR) #define POLLEX_SET (POLLPRI) =20 +static inline void wait_key_set(poll_table *wait, unsigned long in, + unsigned long out, unsigned long bit) +{ + if (wait) { + wait->key =3D POLLEX_SET; + if (in & bit) + wait->key |=3D POLLIN_SET; + if (out & bit) + wait->key |=3D POLLOUT_SET; + } +} + int do_select(int n, fd_set_bits *fds, struct timespec *end_time) { ktime_t expire, *to =3D NULL; @@ -418,20 +441,25 @@ int do_select(int n, fd_set_bits *fds, struct tim= espec *end_time) if (file) { f_op =3D file->f_op; mask =3D DEFAULT_POLLMASK; - if (f_op && f_op->poll) - mask =3D (*f_op->poll)(file, retval ? NULL : wait); + if (f_op && f_op->poll) { + wait_key_set(wait, in, out, bit); + mask =3D (*f_op->poll)(file, wait); + } fput_light(file, fput_needed); if ((mask & POLLIN_SET) && (in & bit)) { res_in |=3D bit; retval++; + wait =3D NULL; } if ((mask & POLLOUT_SET) && (out & bit)) { res_out |=3D bit; retval++; + wait =3D NULL; } if ((mask & POLLEX_SET) && (ex & bit)) { res_ex |=3D bit; retval++; + wait =3D NULL; } } } @@ -685,8 +713,12 @@ static inline unsigned int do_pollfd(struct pollfd= *pollfd, poll_table *pwait) mask =3D POLLNVAL; if (file !=3D NULL) { mask =3D DEFAULT_POLLMASK; - if (file->f_op && file->f_op->poll) + if (file->f_op && file->f_op->poll) { + if (pwait) + pwait->key =3D pollfd->events | + POLLERR | POLLHUP; mask =3D file->f_op->poll(file, pwait); + } /* Mask out unneeded events. */ mask &=3D pollfd->events | POLLERR | POLLHUP; fput_light(file, fput_needed); diff --git a/include/linux/poll.h b/include/linux/poll.h index 8c24ef8..3327389 100644 --- a/include/linux/poll.h +++ b/include/linux/poll.h @@ -32,6 +32,7 @@ typedef void (*poll_queue_proc)(struct file *, wait_q= ueue_head_t *, struct poll_ =20 typedef struct poll_table_struct { poll_queue_proc qproc; + unsigned long key; } poll_table; =20 static inline void poll_wait(struct file * filp, wait_queue_head_t * w= ait_address, poll_table *p) @@ -43,10 +44,12 @@ static inline void poll_wait(struct file * filp, wa= it_queue_head_t * wait_addres static inline void init_poll_funcptr(poll_table *pt, poll_queue_proc q= proc) { pt->qproc =3D qproc; + pt->key =3D ~0UL; /* all events enabled */ } =20 struct poll_table_entry { struct file *filp; + unsigned long key; wait_queue_t wait; wait_queue_head_t *wait_address; };