| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <alpine.DEB.1.10.0812011711280.27086@alien.or.mcafeemobile.com>
Date: Mon, 1 Dec 2008 17:27:23 -0800 (PST)
From: Davide Libenzi <davidel@...ilserver.org>
To: Mathieu Desnoyers <compudj@...stal.dyndns.org>
cc: KOSAKI Motohiro <kosaki.motohiro@...fujitsu.com>,
Ingo Molnar <mingo@...e.hu>, ltt-dev@...ts.casi.polymtl.ca,
Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
William Lee Irwin III <wli@...omorphy.com>
Subject: Re: [ltt-dev] [PATCH] Poll : introduce poll_wait_exclusive() new
function
On Fri, 28 Nov 2008, Mathieu Desnoyers wrote:
> Nope, sorry, I don't own any machine with such huge amount of CPUs,
> therefore I can't afford to test that scalability level.
OK, but maybe before trying to push a performance-based patch, some
pseudo-real numbers should be given ;)
> You say that "You've got at least the spinlock protecting the queue
> where these threads are focusing", you assume we stay limited to the
> current implementation inability to scale correctly. We could think of a
> scheme with :
>
> - Per cpu waiters. Waiters are added to their own CPU waiting list.
> - Per cpu wakeups, where the wakeup will try to wake up a waiter on the
> local CPU first.
>
> If there happens to be no waiters for a local CPU wakeup, the wakeup
> would then be broadcasted to other CPUs, which involves proper locking
> which I think could be done pretty efficiently so we don't hurt the "add
> waiter" fastpath.
>
> By doing this, we could end up not even taking a global spinlock in the
> add waiter/wakeup fastpaths. So then we would have fixed both the
> thundering herd problem _and_ the global spinlock issue altogether.
>
> Any thought ?
That looks fine, but before waving the Thundering Herd flag some
performance numbers should be given IMO, considerng also that this is a
rather particular use of the poll subsystem.
Eventually, isn't something like the patch below better than adding custom
case names to poll_wait() ALA poll_wait_LONGNAMESFOLLOW()?
That way you can pass your own queueing function:
poll_wait_qfunc(file, head, pt, add_wait_queue_exclusive);
- Davide
---
fs/eventpoll.c | 7 +++++--
fs/select.c | 28 +++++++++++++---------------
include/linux/poll.h | 18 +++++++++++++++---
3 files changed, 33 insertions(+), 20 deletions(-)
Index: linux-2.6.mod/fs/select.c
===================================================================
--- linux-2.6.mod.orig/fs/select.c 2008-12-01 16:27:15.000000000 -0800
+++ linux-2.6.mod/fs/select.c 2008-12-01 16:47:53.000000000 -0800
@@ -103,19 +103,6 @@
* as all select/poll functions have to call it to add an entry to the
* poll table.
*/
-static void __pollwait(struct file *filp, wait_queue_head_t *wait_address,
- poll_table *p);
-
-void poll_initwait(struct poll_wqueues *pwq)
-{
- init_poll_funcptr(&pwq->pt, __pollwait);
- pwq->error = 0;
- pwq->table = NULL;
- pwq->inline_index = 0;
-}
-
-EXPORT_SYMBOL(poll_initwait);
-
static void free_poll_entry(struct poll_table_entry *entry)
{
remove_wait_queue(entry->wait_address, &entry->wait);
@@ -173,7 +160,8 @@
/* Add a new entry */
static void __pollwait(struct file *filp, wait_queue_head_t *wait_address,
- poll_table *p)
+ poll_table *p, void (*qfunc)(wait_queue_head_t *,
+ wait_queue_t *))
{
struct poll_table_entry *entry = poll_get_entry(p);
if (!entry)
@@ -182,9 +170,19 @@
entry->filp = filp;
entry->wait_address = wait_address;
init_waitqueue_entry(&entry->wait, current);
- add_wait_queue(wait_address, &entry->wait);
+ (*qfunc)(wait_address, &entry->wait);
}
+void poll_initwait(struct poll_wqueues *pwq)
+{
+ init_poll_funcptr(&pwq->pt, __pollwait);
+ pwq->error = 0;
+ pwq->table = NULL;
+ pwq->inline_index = 0;
+}
+
+EXPORT_SYMBOL(poll_initwait);
+
/**
* poll_select_set_timeout - helper function to setup the timeout value
* @to: pointer to timespec variable for the final timeout
Index: linux-2.6.mod/include/linux/poll.h
===================================================================
--- linux-2.6.mod.orig/include/linux/poll.h 2008-12-01 16:27:15.000000000 -0800
+++ linux-2.6.mod/include/linux/poll.h 2008-12-01 16:55:11.000000000 -0800
@@ -28,16 +28,28 @@
/*
* structures and helpers for f_op->poll implementations
*/
-typedef void (*poll_queue_proc)(struct file *, wait_queue_head_t *, struct poll_table_struct *);
+typedef void (*poll_queue_proc)(struct file *, wait_queue_head_t *,
+ struct poll_table_struct *,
+ void (*)(wait_queue_head_t *, wait_queue_t *));
typedef struct poll_table_struct {
poll_queue_proc qproc;
} poll_table;
-static inline void poll_wait(struct file * filp, wait_queue_head_t * wait_address, poll_table *p)
+static inline void poll_wait_qfunc(struct file *filp,
+ wait_queue_head_t *wait_address,
+ poll_table *p,
+ void (*qfunc)(wait_queue_head_t *,
+ wait_queue_t *))
{
if (p && wait_address)
- p->qproc(filp, wait_address, p);
+ p->qproc(filp, wait_address, p, qfunc);
+}
+
+static inline void poll_wait(struct file *filp, wait_queue_head_t *wait_address,
+ poll_table *p)
+{
+ poll_wait_qfunc(filp, wait_address, p, add_wait_queue);
}
static inline void init_poll_funcptr(poll_table *pt, poll_queue_proc qproc)
Index: linux-2.6.mod/fs/eventpoll.c
===================================================================
--- linux-2.6.mod.orig/fs/eventpoll.c 2008-12-01 16:27:15.000000000 -0800
+++ linux-2.6.mod/fs/eventpoll.c 2008-12-01 16:39:02.000000000 -0800
@@ -655,7 +655,10 @@
* target file wakeup lists.
*/
static void ep_ptable_queue_proc(struct file *file, wait_queue_head_t *whead,
- poll_table *pt)
+ poll_table *pt,
+ void (*qfunc)(wait_queue_head_t *,
+ wait_queue_t *))
+
{
struct epitem *epi = ep_item_from_epqueue(pt);
struct eppoll_entry *pwq;
@@ -664,7 +667,7 @@
init_waitqueue_func_entry(&pwq->wait, ep_poll_callback);
pwq->whead = whead;
pwq->base = epi;
- add_wait_queue(whead, &pwq->wait);
+ (*qfunc)(whead, &pwq->wait);
list_add_tail(&pwq->llink, &epi->pwqlist);
epi->nwait++;
} else {
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists