Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > linux.kernel > #1305401
| From | Florian Westphal <fw@strlen.de> |
|---|---|
| Newsgroups | linux.kernel |
| Subject | Re: [PATCH] netfilter: nf_conntrack: use safer way to lock all buckets |
| Date | 2016-01-10 02:10 +0100 |
| Message-ID | <qPcG5-5m2-1@gated-at.bofh.it> (permalink) |
| References | <qNpxL-3Lr-7@gated-at.bofh.it> |
| Organization | linux.* mail to news gateway |
Sasha Levin <sasha.levin@oracle.com> wrote: > When we need to lock all buckets in the connection hashtable we'd attempt to > lock 1024 spinlocks, which is way more preemption levels than supported by > the kernel. You're right. > Fix this by using a global lock and synchronize all buckets on it when we > need to lock them all. This is pretty heavyweight, but is only done when we > need to resize the hashtable, and that doesn't happen often enough (or at all). > diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c > index 3cb3cb8..3c008ce 100644 > --- a/net/netfilter/nf_conntrack_core.c > +++ b/net/netfilter/nf_conntrack_core.c > @@ -66,6 +66,32 @@ EXPORT_SYMBOL_GPL(nf_conntrack_locks); > __cacheline_aligned_in_smp DEFINE_SPINLOCK(nf_conntrack_expect_lock); > EXPORT_SYMBOL_GPL(nf_conntrack_expect_lock); > > +spinlock_t nf_conntrack_locks_all_lock; > +bool nf_conntrack_locks_all; Seems both of these can be static and __read_mostly too -- as you already note resizing virtually never happens. Otherwise: Reviewed-by: Florian Westphal <fw@strlen.de>
Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread
[PATCH] netfilter: nf_conntrack: use safer way to lock all buckets Sasha Levin <sasha.levin@oracle.com> - 2016-01-05 03:30 +0100
RE: [PATCH] netfilter: nf_conntrack: use safer way to lock all buckets David Laight <David.Laight@ACULAB.COM> - 2016-01-05 12:20 +0100
Re: [PATCH] netfilter: nf_conntrack: use safer way to lock all buckets Florian Westphal <fw@strlen.de> - 2016-01-10 02:10 +0100
Re: [PATCH] netfilter: nf_conntrack: use safer way to lock all buckets Pablo Neira Ayuso <pablo@netfilter.org> - 2016-01-13 18:00 +0100
Re: [PATCH] netfilter: nf_conntrack: use safer way to lock all buckets Sasha Levin <sasha.levin@oracle.com> - 2016-01-13 19:40 +0100
Re: [PATCH] netfilter: nf_conntrack: use safer way to lock all buckets Jesper Dangaard Brouer <brouer@redhat.com> - 2016-01-14 15:20 +0100
csiph-web