From 230140cffa7feae90ad50bf259db1fa07674f3a7 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 7 Nov 2007 02:40:20 -0800 Subject: [INET]: Remove per bucket rwlock in tcp/dccp ehash table. As done two years ago on IP route cache table (commit 22c047ccbc68fa8f3fa57f0e8f906479a062c426) , we can avoid using one lock per hash bucket for the huge TCP/DCCP hash tables. On a typical x86_64 platform, this saves about 2MB or 4MB of ram, for litle performance differences. (we hit a different cache line for the rwlock, but then the bucket cache line have a better sharing factor among cpus, since we dirty it less often). For netstat or ss commands that want a full scan of hash table, we perform fewer memory accesses. Using a 'small' table of hashed rwlocks should be more than enough to provide correct SMP concurrency between different buckets, without using too much memory. Sizing of this table depends on num_possible_cpus() and various CONFIG settings. This patch provides some locking abstraction that may ease a future work using a different model for TCP/DCCP table. Signed-off-by: Eric Dumazet Acked-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- net/ipv4/inet_diag.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'net/ipv4/inet_diag.c') diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index dc429b6b0ba6..b0170732b5e9 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -747,13 +747,14 @@ skip_listen_ht: for (i = s_i; i < hashinfo->ehash_size; i++) { struct inet_ehash_bucket *head = &hashinfo->ehash[i]; + rwlock_t *lock = inet_ehash_lockp(hashinfo, i); struct sock *sk; struct hlist_node *node; if (i > s_i) s_num = 0; - read_lock_bh(&head->lock); + read_lock_bh(lock); num = 0; sk_for_each(sk, node, &head->chain) { struct inet_sock *inet = inet_sk(sk); @@ -769,7 +770,7 @@ skip_listen_ht: r->id.idiag_dport) goto next_normal; if (inet_csk_diag_dump(sk, skb, cb) < 0) { - read_unlock_bh(&head->lock); + read_unlock_bh(lock); goto done; } next_normal: @@ -791,14 +792,14 @@ next_normal: r->id.idiag_dport) goto next_dying; if (inet_twsk_diag_dump(tw, skb, cb) < 0) { - read_unlock_bh(&head->lock); + read_unlock_bh(lock); goto done; } next_dying: ++num; } } - read_unlock_bh(&head->lock); + read_unlock_bh(lock); } done: -- cgit v1.2.3