[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <491C27F0.8000507@cosmosbay.com>
Date: Thu, 13 Nov 2008 14:13:20 +0100
From: Eric Dumazet <dada1@...mosbay.com>
To: David Miller <davem@...emloft.net>
CC: "Paul E. McKenney" <paulmck@...ux.vnet.ibm.com>,
Corey Minyard <minyard@....org>,
Stephen Hemminger <shemminger@...tta.com>,
benny+usenet@...rsen.dk,
Linux Netdev List <netdev@...r.kernel.org>,
Christoph Lameter <cl@...ux-foundation.org>,
Peter Zijlstra <a.p.zijlstra@...llo.nl>,
Evgeniy Polyakov <zbr@...emap.net>,
Christian Bell <christian@...i.com>
Subject: [PATCH 0/3] net: RCU lookups for UDP, DCCP and TCP protocol
Hi all
Here is a serie of three patches (based on net-next-2.6), to continue work
with RCU on UDP/TCP/DCCP stacks
Many thanks for all usefull reviews and comments, especially from Paul and Corey.
1) Introduce hlist_nulls variant of hlist
hlist uses NULL value to finish a chain.
hlist_nulls variant use the low order bit set to 1 to signal an end marker.
This allows to store many different end markers, so that some RCU lockless
algos (used in TCP/UDP stack for example) can save some memory barriers in
fast paths.
2) Use hlist_nulls in UDP RCU code
This is a straightforward patch, using hlist_nulls infrastructure.
RCU-ification already done on UDP two weeks ago, so hlist_nulls
permits us to avoid some memory barriers, both at lookup time
and delete time. Patch is large because it adds new macros to
include/net/sock.h. These macros will be used by TCP & DCCP too.
3) Convert TCP & DCCP hash tables to use RCU & hlist_nulls
RCU was added to UDP lookups, using a fast infrastructure :
- sockets kmem_cache use SLAB_DESTROY_BY_RCU and dont pay the
price of call_rcu() at freeing time.
- hlist_nulls permits to use few memory barriers.
This patch uses same infrastructure for TCP/DCCP established
and timewait sockets.
Thanks to SLAB_DESTROY_BY_RCU, no slowdown for applications
using short lived TCP connections. A followup patch, converting
rwlocks to spinlocks will even speedup this case.
__inet_lookup_established() is pretty fast now we dont have to
dirty a contended cache line (read_lock/read_unlock)
Only established and timewait hashtable are converted to RCU
(bind table and listen table are still using traditional locking)
Signed-off-by: Eric Dumazet <dada1@...mosbay.com>
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists