summaryrefslogtreecommitdiffstats
path: root/net/atm/common.c
diff options
context:
space:
mode:
authorEric Dumazet <dada1@cosmosbay.com>2005-10-03 14:13:38 -0700
committerDavid S. Miller <davem@davemloft.net>2005-10-03 14:13:38 -0700
commit81c3d5470ecc70564eb9209946730fe2be93ad06 (patch)
tree1efa553c305a6453769dacfaf580bc6ccf146d82 /net/atm/common.c
parent399de50bbbb2501a6db43daaa8a2dafbc9bcfe0c (diff)
downloadlinux-81c3d5470ecc70564eb9209946730fe2be93ad06.tar.gz
linux-81c3d5470ecc70564eb9209946730fe2be93ad06.tar.bz2
linux-81c3d5470ecc70564eb9209946730fe2be93ad06.zip
[INET]: speedup inet (tcp/dccp) lookups
Arnaldo and I agreed it could be applied now, because I have other pending patches depending on this one (Thank you Arnaldo) (The other important patch moves skc_refcnt in a separate cache line, so that the SMP/NUMA performance doesnt suffer from cache line ping pongs) 1) First some performance data : -------------------------------- tcp_v4_rcv() wastes a *lot* of time in __inet_lookup_established() The most time critical code is : sk_for_each(sk, node, &head->chain) { if (INET_MATCH(sk, acookie, saddr, daddr, ports, dif)) goto hit; /* You sunk my battleship! */ } The sk_for_each() does use prefetch() hints but only the begining of "struct sock" is prefetched. As INET_MATCH first comparison uses inet_sk(__sk)->daddr, wich is far away from the begining of "struct sock", it has to bring into CPU cache cold cache line. Each iteration has to use at least 2 cache lines. This can be problematic if some chains are very long. 2) The goal ----------- The idea I had is to change things so that INET_MATCH() may return FALSE in 99% of cases only using the data already in the CPU cache, using one cache line per iteration. 3) Description of the patch --------------------------- Adds a new 'unsigned int skc_hash' field in 'struct sock_common', filling a 32 bits hole on 64 bits platform. struct sock_common { unsigned short skc_family; volatile unsigned char skc_state; unsigned char skc_reuse; int skc_bound_dev_if; struct hlist_node skc_node; struct hlist_node skc_bind_node; atomic_t skc_refcnt; + unsigned int skc_hash; struct proto *skc_prot; }; Store in this 32 bits field the full hash, not masked by (ehash_size - 1) Using this full hash as the first comparison done in INET_MATCH permits us immediatly skip the element without touching a second cache line in case of a miss. Suppress the sk_hashent/tw_hashent fields since skc_hash (aliased to sk_hash and tw_hash) already contains the slot number if we mask with (ehash_size - 1) File include/net/inet_hashtables.h 64 bits platforms : #define INET_MATCH(__sk, __hash, __cookie, __saddr, __daddr, __ports, __dif)\ (((__sk)->sk_hash == (__hash)) ((*((__u64 *)&(inet_sk(__sk)->daddr)))== (__cookie)) && \ ((*((__u32 *)&(inet_sk(__sk)->dport))) == (__ports)) && \ (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif)))) 32bits platforms: #define TCP_IPV4_MATCH(__sk, __hash, __cookie, __saddr, __daddr, __ports, __dif)\ (((__sk)->sk_hash == (__hash)) && \ (inet_sk(__sk)->daddr == (__saddr)) && \ (inet_sk(__sk)->rcv_saddr == (__daddr)) && \ (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif)))) - Adds a prefetch(head->chain.first) in __inet_lookup_established()/__tcp_v4_check_established() and __inet6_lookup_established()/__tcp_v6_check_established() and __dccp_v4_check_established() to bring into cache the first element of the list, before the {read|write}_lock(&head->lock); Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Acked-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/atm/common.c')
-rw-r--r--net/atm/common.c2
1 files changed, 1 insertions, 1 deletions
diff --git a/net/atm/common.c b/net/atm/common.c
index 801a5813ec60..63feea49fb13 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -46,7 +46,7 @@ static void __vcc_insert_socket(struct sock *sk)
struct atm_vcc *vcc = atm_sk(sk);
struct hlist_head *head = &vcc_hash[vcc->vci &
(VCC_HTABLE_SIZE - 1)];
- sk->sk_hashent = vcc->vci & (VCC_HTABLE_SIZE - 1);
+ sk->sk_hash = vcc->vci & (VCC_HTABLE_SIZE - 1);
sk_add_node(sk, head);
}