From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jarek Poplawski Subject: Re: [PATCH] netfilter: use per-CPU recursive lock {XIV} Date: Fri, 24 Apr 2009 22:43:17 +0200 Message-ID: <49F22465.80305@gmail.com> References: <20090418094001.GA2369@ioremap.net> <20090418141455.GA7082@linux.vnet.ibm.com> <20090420103414.1b4c490f@nehalam> <49ECBE0A.7010303@cosmosbay.com> <18924.59347.375292.102385@cargo.ozlabs.ibm.com> <20090420215827.GK6822@linux.vnet.ibm.com> <18924.64032.103954.171918@cargo.ozlabs.ibm.com> <20090420160121.268a8226@nehalam> <20090421111541.228e977a@nehalam> <20090421193924.GA24404@elte.hu> <20090421143927.52d7d89d@nehalam> <20090423210938.1501507b@nehalam> <49F146FF.5050200@cosmosbay.com> <20090424091839.6e13ebec@nehalam> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: Eric Dumazet , Linus Torvalds , Ingo Molnar , Paul Mackerras , paulmck@linux.vnet.ibm.com, Evgeniy Polyakov , David Miller , kaber@trash.net, jeff.chua.linux@gmail.com, laijs@cn.fujitsu.com, jengelh@medozas.de, r000n@r000n.net, linux-kernel@vger.kernel.org, netfilter-devel@vger.kernel.org, netdev@vger.kernel.org, benh@kernel.crashing.org, mathieu.desnoyers@polymtl.ca To: Stephen Hemminger Return-path: Received: from mail-fx0-f158.google.com ([209.85.220.158]:60482 "EHLO mail-fx0-f158.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753180AbZDXUoO (ORCPT ); Fri, 24 Apr 2009 16:44:14 -0400 In-Reply-To: <20090424091839.6e13ebec@nehalam> Sender: netdev-owner@vger.kernel.org List-ID: Stephen Hemminger wrote, On 04/24/2009 06:18 PM: > On Fri, 24 Apr 2009 06:58:39 +0200 > Eric Dumazet wrote: >=20 >> Stephen Hemminger a =C3=A9crit : >>> In days of old in 2.6.29, netfilter did locketh using a=20 >>> lock of the reader kind when doing its table business, and do >>> a writer when with pen in hand like a overworked accountant >>> did replace the tables. This sucketh and caused the single >>> lock to fly back and forth like a poor errant boy. >>> >>> But then netfilter was blessed with RCU and the performance >>> was divine, but alas there were those that suffered for >>> trying to replace their many rules one at a time. >>> >>> So now RCU must be vanquished from the scene, and better >>> chastity belts be placed upon this valuable asset most dear. >>> The locks that were but one are now replaced by one per suitor. >>> >>> The repair was made after much discussion involving >>> Eric the wise, and Linus the foul. With flowers springing >>> up amid the thorns some peace has finally prevailed and >>> all is soothed. This patch and purple prose was penned by >>> in honor of "Talk like Shakespeare" day. >>> >>> Signed-off-by: Stephen Hemminger >> >> Philip Davis of the university=E2=80=99s School of English said : >> >> "Shakespeare surprises the brain and catches it off guard in >> a manner that produces a sudden burst of activity - a sense=20 >> of drama created out of the simplest of things." >> >> http://www.physorg.com/news85664210.html >> >>> --- >>> What hath changed over the last two setting suns: >>> * more words, mostly correct... >>> >>> * no need to locketh for writeh on current cpu tis=20 >>> always so >>> >>> * the locking of all cpu's on replace is always done as >>> part of the get_counters cycle, so the sychronize swip >>> in replace tables is gone with only a comment remaing >>> >>> include/linux/netfilter/x_tables.h | 55 ++++++++++++++-- >>> net/ipv4/netfilter/arp_tables.c | 125 ++++++++++--------------= ------------ >>> net/ipv4/netfilter/ip_tables.c | 126 ++++++++++--------------= ------------- >>> net/ipv6/netfilter/ip6_tables.c | 123 ++++++++++--------------= ------------ >>> net/netfilter/x_tables.c | 55 ++++++++-------- >>> 5 files changed, 188 insertions(+), 296 deletions(-) >>> >> >>> =20 >>> static int __init xt_init(void) >>> { >>> - int i, rv; >>> + unsigned int i; >>> + int rv; >>> + static struct lock_class_key xt_lock_key[NR_CPUS]; >> Could we avoid this [NR_CPUS] thing ? >> >>> + >>> + for_each_possible_cpu(i) { >>> + rwlock_t *lock =3D &per_cpu(xt_info_locks, i); >>> + >>> + rwlock_init(lock); >>> + lockdep_set_class(lock, xt_lock_key+i); >>> + } >> >> Did you tried : >> >> static DECLARE_PER_CPU(struct lock_class_key, xt_locks_key); >> >=20 > The lock keys are really only used by lock dep, and I thought per cpu > space was more scarce on some arch. >=20 Maybe I'm wrong but after this change: "- only acquire one cpu write lock at a time" lockdep_set_class() might be unnecessary. Alas I'm not able to test it. Jarek P.