diff options
author | Eric Dumazet <dada1@cosmosbay.com> | 2005-10-03 17:13:38 -0400 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2005-10-03 17:13:38 -0400 |
commit | 81c3d5470ecc70564eb9209946730fe2be93ad06 (patch) | |
tree | 1efa553c305a6453769dacfaf580bc6ccf146d82 /include/linux | |
parent | 399de50bbbb2501a6db43daaa8a2dafbc9bcfe0c (diff) |
[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 'include/linux')
-rw-r--r-- | include/linux/ipv6.h | 5 | ||||
-rw-r--r-- | include/linux/tc_ematch/tc_em_meta.h | 2 |
2 files changed, 4 insertions, 3 deletions
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index bb6f88e14061..e0b922785d98 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h | |||
@@ -372,8 +372,9 @@ static inline struct raw6_sock *raw6_sk(const struct sock *sk) | |||
372 | #define inet_v6_ipv6only(__sk) 0 | 372 | #define inet_v6_ipv6only(__sk) 0 |
373 | #endif /* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */ | 373 | #endif /* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */ |
374 | 374 | ||
375 | #define INET6_MATCH(__sk, __saddr, __daddr, __ports, __dif) \ | 375 | #define INET6_MATCH(__sk, __hash, __saddr, __daddr, __ports, __dif)\ |
376 | (((*((__u32 *)&(inet_sk(__sk)->dport))) == (__ports)) && \ | 376 | (((__sk)->sk_hash == (__hash)) && \ |
377 | ((*((__u32 *)&(inet_sk(__sk)->dport))) == (__ports)) && \ | ||
377 | ((__sk)->sk_family == AF_INET6) && \ | 378 | ((__sk)->sk_family == AF_INET6) && \ |
378 | ipv6_addr_equal(&inet6_sk(__sk)->daddr, (__saddr)) && \ | 379 | ipv6_addr_equal(&inet6_sk(__sk)->daddr, (__saddr)) && \ |
379 | ipv6_addr_equal(&inet6_sk(__sk)->rcv_saddr, (__daddr)) && \ | 380 | ipv6_addr_equal(&inet6_sk(__sk)->rcv_saddr, (__daddr)) && \ |
diff --git a/include/linux/tc_ematch/tc_em_meta.h b/include/linux/tc_ematch/tc_em_meta.h index 081b1ee8516e..e21937cf91d0 100644 --- a/include/linux/tc_ematch/tc_em_meta.h +++ b/include/linux/tc_ematch/tc_em_meta.h | |||
@@ -71,7 +71,7 @@ enum | |||
71 | TCF_META_ID_SK_SNDBUF, | 71 | TCF_META_ID_SK_SNDBUF, |
72 | TCF_META_ID_SK_ALLOCS, | 72 | TCF_META_ID_SK_ALLOCS, |
73 | TCF_META_ID_SK_ROUTE_CAPS, | 73 | TCF_META_ID_SK_ROUTE_CAPS, |
74 | TCF_META_ID_SK_HASHENT, | 74 | TCF_META_ID_SK_HASH, |
75 | TCF_META_ID_SK_LINGERTIME, | 75 | TCF_META_ID_SK_LINGERTIME, |
76 | TCF_META_ID_SK_ACK_BACKLOG, | 76 | TCF_META_ID_SK_ACK_BACKLOG, |
77 | TCF_META_ID_SK_MAX_ACK_BACKLOG, | 77 | TCF_META_ID_SK_MAX_ACK_BACKLOG, |