2005-08-09 19:59:20 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-08-09 20:09:30 -07:00
|
|
|
|
2005-08-09 20:07:13 -07:00
|
|
|
|
2008-10-07 11:41:57 -07:00
|
|
|
|
2005-08-09 20:09:06 -07:00
|
|
|
|
2005-08-09 20:00:51 -07:00
|
|
|
|
|
|
|
|
|
2005-08-09 20:09:06 -07:00
|
|
|
|
2005-08-09 20:00:51 -07:00
|
|
|
|
2005-08-09 19:59:20 -07:00
|
|
|
|
2005-08-09 20:08:09 -07:00
|
|
|
|
2007-11-10 21:18:39 -08:00
|
|
|
|
2005-08-09 19:59:20 -07:00
|
|
|
|
2005-08-09 20:10:42 -07:00
|
|
|
|
2005-12-27 02:43:12 -02:00
|
|
|
|
2005-08-09 20:07:13 -07:00
|
|
|
|
2008-10-07 11:41:57 -07:00
|
|
|
|
2005-08-09 20:08:28 -07:00
|
|
|
|
2008-06-16 17:14:11 -07:00
|
|
|
|
2005-08-09 20:07:13 -07:00
|
|
|
|
2005-08-09 20:08:09 -07:00
|
|
|
|
2005-08-09 20:09:46 -07:00
|
|
|
|
2005-08-09 20:08:09 -07:00
|
|
|
|
2005-08-09 20:00:51 -07:00
|
|
|
|
[NET]: change layout of ehash table
ehash table layout is currently this one :
First half of this table is used by sockets not in TIME_WAIT state
Second half of it is used by sockets in TIME_WAIT state.
This is non optimal because of for a given hash or socket, the two chain heads
are located in separate cache lines.
Moreover the locks of the second half are never used.
If instead of this halving, we use two list heads in inet_ehash_bucket instead
of only one, we probably can avoid one cache miss, and reduce ram usage,
particularly if sizeof(rwlock_t) is big (various CONFIG_DEBUG_SPINLOCK,
CONFIG_DEBUG_LOCK_ALLOC settings). So we still halves the table but we keep
together related chains to speedup lookups and socket state change.
In this patch I did not try to align struct inet_ehash_bucket, but a future
patch could try to make this structure have a convenient size (a power of two
or a multiple of L1_CACHE_SIZE).
I guess rwlock will just vanish as soon as RCU is plugged into ehash :) , so
maybe we dont need to scratch our heads to align the bucket...
Note : In case struct inet_ehash_bucket is not a power of two, we could
probably change alloc_large_system_hash() (in case it use __get_free_pages())
to free the unused space. It currently allocates a big zone, but the last
quarter of it could be freed. Again, this should be a temporary 'problem'.
Patch tested on ipv4 tcp only, but should be OK for IPV6 and DCCP.
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-02-08 14:16:46 -08:00
|
|
|
|
|
|
|
|
|
2005-08-09 20:00:51 -07:00
|
|
|
|
|
|
|
|
|
2008-11-16 19:40:17 -08:00
|
|
|
|
|
|
|
|
|
2005-10-04 15:55:51 -07:00
|
|
|
|
2005-08-09 20:00:51 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-11-12 00:54:20 -08:00
|
|
|
|
2008-01-31 05:05:50 -08:00
|
|
|
|
2008-11-12 00:54:20 -08:00
|
|
|
|
2005-08-09 20:00:51 -07:00
|
|
|
|
|
|
|
|
|
inet: Allowing more than 64k connections and heavily optimize bind(0) time.
With simple extension to the binding mechanism, which allows to bind more
than 64k sockets (or smaller amount, depending on sysctl parameters),
we have to traverse the whole bind hash table to find out empty bucket.
And while it is not a problem for example for 32k connections, bind()
completion time grows exponentially (since after each successful binding
we have to traverse one bucket more to find empty one) even if we start
each time from random offset inside the hash table.
So, when hash table is full, and we want to add another socket, we have
to traverse the whole table no matter what, so effectivelly this will be
the worst case performance and it will be constant.
Attached picture shows bind() time depending on number of already bound
sockets.
Green area corresponds to the usual binding to zero port process, which
turns on kernel port selection as described above. Red area is the bind
process, when number of reuse-bound sockets is not limited by 64k (or
sysctl parameters). The same exponential growth (hidden by the green
area) before number of ports reaches sysctl limit.
At this time bind hash table has exactly one reuse-enbaled socket in a
bucket, but it is possible that they have different addresses. Actually
kernel selects the first port to try randomly, so at the beginning bind
will take roughly constant time, but with time number of port to check
after random start will increase. And that will have exponential growth,
but because of above random selection, not every next port selection
will necessary take longer time than previous. So we have to consider
the area below in the graph (if you could zoom it, you could find, that
there are many different times placed there), so area can hide another.
Blue area corresponds to the port selection optimization.
This is rather simple design approach: hashtable now maintains (unprecise
and racely updated) number of currently bound sockets, and when number
of such sockets becomes greater than predefined value (I use maximum
port range defined by sysctls), we stop traversing the whole bind hash
table and just stop at first matching bucket after random start. Above
limit roughly corresponds to the case, when bind hash table is full and
we turned on mechanism of allowing to bind more reuse-enabled sockets,
so it does not change behaviour of other sockets.
Signed-off-by: Evgeniy Polyakov <zbr@ioremap.net>
Tested-by: Denys Fedoryschenko <denys@visp.net.lb>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-01-19 16:46:02 -08:00
|
|
|
|
2005-08-09 20:00:51 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-11-12 00:54:20 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-11-12 05:07:26 +00:00
|
|
|
|
|
|
|
|
|
2005-08-09 20:00:51 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-11-23 17:22:55 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-11-20 00:40:07 -08:00
|
|
|
|
|
|
|
|
|
2008-11-23 17:22:55 -08:00
|
|
|
|
2008-11-20 00:40:07 -08:00
|
|
|
|
|
|
|
|
|
2005-08-09 20:00:51 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
[NET]: change layout of ehash table
ehash table layout is currently this one :
First half of this table is used by sockets not in TIME_WAIT state
Second half of it is used by sockets in TIME_WAIT state.
This is non optimal because of for a given hash or socket, the two chain heads
are located in separate cache lines.
Moreover the locks of the second half are never used.
If instead of this halving, we use two list heads in inet_ehash_bucket instead
of only one, we probably can avoid one cache miss, and reduce ram usage,
particularly if sizeof(rwlock_t) is big (various CONFIG_DEBUG_SPINLOCK,
CONFIG_DEBUG_LOCK_ALLOC settings). So we still halves the table but we keep
together related chains to speedup lookups and socket state change.
In this patch I did not try to align struct inet_ehash_bucket, but a future
patch could try to make this structure have a convenient size (a power of two
or a multiple of L1_CACHE_SIZE).
I guess rwlock will just vanish as soon as RCU is plugged into ehash :) , so
maybe we dont need to scratch our heads to align the bucket...
Note : In case struct inet_ehash_bucket is not a power of two, we could
probably change alloc_large_system_hash() (in case it use __get_free_pages())
to free the unused space. It currently allocates a big zone, but the last
quarter of it could be freed. Again, this should be a temporary 'problem'.
Patch tested on ipv4 tcp only, but should be OK for IPV6 and DCCP.
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-02-08 14:16:46 -08:00
|
|
|
|
2005-08-09 20:00:51 -07:00
|
|
|
|
|
|
|
|
|
2008-11-20 20:39:09 -08:00
|
|
|
|
2009-10-09 00:16:19 +00:00
|
|
|
|
2007-11-07 02:40:20 -08:00
|
|
|
|
2005-08-09 20:00:51 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-10-09 01:59:42 -07:00
|
|
|
|
2009-02-01 12:31:33 -08:00
|
|
|
|
2005-08-09 20:00:51 -07:00
|
|
|
|
2008-11-20 00:40:07 -08:00
|
|
|
|
2005-08-09 20:00:51 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-11-20 00:40:07 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-08-09 20:00:51 -07:00
|
|
|
|
2008-11-20 00:40:07 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-02-01 12:31:33 -08:00
|
|
|
|
2005-08-09 20:00:51 -07:00
|
|
|
|
|
|
|
|
|
[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>
2005-10-03 14:13:38 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-10-09 00:16:19 +00:00
|
|
|
|
2005-08-09 19:59:20 -07:00
|
|
|
|
|
|
|
|
|
2008-11-20 20:39:09 -08:00
|
|
|
|
2007-11-07 02:40:20 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-01-27 17:45:10 -08:00
|
|
|
|
2007-11-07 02:40:20 -08:00
|
|
|
|
2008-11-20 20:39:09 -08:00
|
|
|
|
|
|
|
|
|
2007-11-07 02:40:20 -08:00
|
|
|
|
|
|
|
|
|
2008-11-20 20:39:09 -08:00
|
|
|
|
2007-11-07 02:40:20 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-11-20 20:39:09 -08:00
|
|
|
|
2007-11-07 02:40:20 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-11-20 20:39:09 -08:00
|
|
|
|
2007-11-07 02:40:20 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-11-26 20:23:31 +08:00
|
|
|
|
2007-11-07 02:40:20 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-08-09 20:00:51 -07:00
|
|
|
|
2006-12-06 20:33:20 -08:00
|
|
|
|
2008-01-31 05:05:50 -08:00
|
|
|
|
2005-08-09 20:00:51 -07:00
|
|
|
|
|
|
|
|
|
2006-12-06 20:33:20 -08:00
|
|
|
|
2005-08-09 20:00:51 -07:00
|
|
|
|
|
|
|
|
|
2008-06-16 17:12:49 -07:00
|
|
|
|
|
|
|
|
|
2005-08-09 20:00:51 -07:00
|
|
|
|
2008-06-16 17:14:11 -07:00
|
|
|
|
2005-08-09 20:00:51 -07:00
|
|
|
|
|
|
|
|
|
2005-08-09 20:07:13 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-08-09 20:00:51 -07:00
|
|
|
|
2008-06-16 17:13:08 -07:00
|
|
|
|
2005-08-09 20:00:51 -07:00
|
|
|
|
2008-06-16 17:14:11 -07:00
|
|
|
|
2005-08-09 20:00:51 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-10-15 06:30:45 +00:00
|
|
|
|
2005-08-09 20:00:51 -07:00
|
|
|
|
|
|
|
|
|
2005-08-09 20:07:13 -07:00
|
|
|
|
2008-04-17 23:18:15 -07:00
|
|
|
|
2005-08-09 20:07:13 -07:00
|
|
|
|
[SOCK] proto: Add hashinfo member to struct proto
This way we can remove TCP and DCCP specific versions of
sk->sk_prot->get_port: both v4 and v6 use inet_csk_get_port
sk->sk_prot->hash: inet_hash is directly used, only v6 need
a specific version to deal with mapped sockets
sk->sk_prot->unhash: both v4 and v6 use inet_hash directly
struct inet_connection_sock_af_ops also gets a new member, bind_conflict, so
that inet_csk_get_port can find the per family routine.
Now only the lookup routines receive as a parameter a struct inet_hashtable.
With this we further reuse code, reducing the difference among INET transport
protocols.
Eventually work has to be done on UDP and SCTP to make them share this
infrastructure and get as a bonus inet_diag interfaces so that iproute can be
used with these protocols.
net-2.6/net/ipv4/inet_hashtables.c:
struct proto | +8
struct inet_connection_sock_af_ops | +8
2 structs changed
__inet_hash_nolisten | +18
__inet_hash | -210
inet_put_port | +8
inet_bind_bucket_create | +1
__inet_hash_connect | -8
5 functions changed, 27 bytes added, 218 bytes removed, diff: -191
net-2.6/net/core/sock.c:
proto_seq_show | +3
1 function changed, 3 bytes added, diff: +3
net-2.6/net/ipv4/inet_connection_sock.c:
inet_csk_get_port | +15
1 function changed, 15 bytes added, diff: +15
net-2.6/net/ipv4/tcp.c:
tcp_set_state | -7
1 function changed, 7 bytes removed, diff: -7
net-2.6/net/ipv4/tcp_ipv4.c:
tcp_v4_get_port | -31
tcp_v4_hash | -48
tcp_v4_destroy_sock | -7
tcp_v4_syn_recv_sock | -2
tcp_unhash | -179
5 functions changed, 267 bytes removed, diff: -267
net-2.6/net/ipv6/inet6_hashtables.c:
__inet6_hash | +8
1 function changed, 8 bytes added, diff: +8
net-2.6/net/ipv4/inet_hashtables.c:
inet_unhash | +190
inet_hash | +242
2 functions changed, 432 bytes added, diff: +432
vmlinux:
16 functions changed, 485 bytes added, 492 bytes removed, diff: -7
/home/acme/git/net-2.6/net/ipv6/tcp_ipv6.c:
tcp_v6_get_port | -31
tcp_v6_hash | -7
tcp_v6_syn_recv_sock | -9
3 functions changed, 47 bytes removed, diff: -47
/home/acme/git/net-2.6/net/dccp/proto.c:
dccp_destroy_sock | -7
dccp_unhash | -179
dccp_hash | -49
dccp_set_state | -7
dccp_done | +1
5 functions changed, 1 bytes added, 242 bytes removed, diff: -241
/home/acme/git/net-2.6/net/dccp/ipv4.c:
dccp_v4_get_port | -31
dccp_v4_request_recv_sock | -2
2 functions changed, 33 bytes removed, diff: -33
/home/acme/git/net-2.6/net/dccp/ipv6.c:
dccp_v6_get_port | -31
dccp_v6_hash | -7
dccp_v6_request_recv_sock | +5
3 functions changed, 5 bytes added, 38 bytes removed, diff: -33
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-02-03 04:06:04 -08:00
|
|
|
|
2005-08-09 20:07:13 -07:00
|
|
|
|
2008-11-20 00:40:07 -08:00
|
|
|
|
2005-08-09 20:08:09 -07:00
|
|
|
|
2009-12-04 03:46:54 +00:00
|
|
|
|
[SOCK] proto: Add hashinfo member to struct proto
This way we can remove TCP and DCCP specific versions of
sk->sk_prot->get_port: both v4 and v6 use inet_csk_get_port
sk->sk_prot->hash: inet_hash is directly used, only v6 need
a specific version to deal with mapped sockets
sk->sk_prot->unhash: both v4 and v6 use inet_hash directly
struct inet_connection_sock_af_ops also gets a new member, bind_conflict, so
that inet_csk_get_port can find the per family routine.
Now only the lookup routines receive as a parameter a struct inet_hashtable.
With this we further reuse code, reducing the difference among INET transport
protocols.
Eventually work has to be done on UDP and SCTP to make them share this
infrastructure and get as a bonus inet_diag interfaces so that iproute can be
used with these protocols.
net-2.6/net/ipv4/inet_hashtables.c:
struct proto | +8
struct inet_connection_sock_af_ops | +8
2 structs changed
__inet_hash_nolisten | +18
__inet_hash | -210
inet_put_port | +8
inet_bind_bucket_create | +1
__inet_hash_connect | -8
5 functions changed, 27 bytes added, 218 bytes removed, diff: -191
net-2.6/net/core/sock.c:
proto_seq_show | +3
1 function changed, 3 bytes added, diff: +3
net-2.6/net/ipv4/inet_connection_sock.c:
inet_csk_get_port | +15
1 function changed, 15 bytes added, diff: +15
net-2.6/net/ipv4/tcp.c:
tcp_set_state | -7
1 function changed, 7 bytes removed, diff: -7
net-2.6/net/ipv4/tcp_ipv4.c:
tcp_v4_get_port | -31
tcp_v4_hash | -48
tcp_v4_destroy_sock | -7
tcp_v4_syn_recv_sock | -2
tcp_unhash | -179
5 functions changed, 267 bytes removed, diff: -267
net-2.6/net/ipv6/inet6_hashtables.c:
__inet6_hash | +8
1 function changed, 8 bytes added, diff: +8
net-2.6/net/ipv4/inet_hashtables.c:
inet_unhash | +190
inet_hash | +242
2 functions changed, 432 bytes added, diff: +432
vmlinux:
16 functions changed, 485 bytes added, 492 bytes removed, diff: -7
/home/acme/git/net-2.6/net/ipv6/tcp_ipv6.c:
tcp_v6_get_port | -31
tcp_v6_hash | -7
tcp_v6_syn_recv_sock | -9
3 functions changed, 47 bytes removed, diff: -47
/home/acme/git/net-2.6/net/dccp/proto.c:
dccp_destroy_sock | -7
dccp_unhash | -179
dccp_hash | -49
dccp_set_state | -7
dccp_done | +1
5 functions changed, 1 bytes added, 242 bytes removed, diff: -241
/home/acme/git/net-2.6/net/dccp/ipv4.c:
dccp_v4_get_port | -31
dccp_v4_request_recv_sock | -2
2 functions changed, 33 bytes removed, diff: -33
/home/acme/git/net-2.6/net/dccp/ipv6.c:
dccp_v6_get_port | -31
dccp_v6_hash | -7
dccp_v6_request_recv_sock | +5
3 functions changed, 5 bytes added, 38 bytes removed, diff: -33
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-02-03 04:06:04 -08:00
|
|
|
|
|
|
|
|
|
2005-08-09 20:09:06 -07:00
|
|
|
|
2008-01-31 05:06:40 -08:00
|
|
|
|
|
|
|
|
|
2006-09-27 18:43:33 -07:00
|
|
|
|
2006-08-09 15:47:12 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-01-31 05:06:40 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2006-08-09 15:47:12 -07:00
|
|
|
|
2008-01-31 05:06:40 -08:00
|
|
|
|
2006-08-09 15:47:12 -07:00
|
|
|
|
2005-08-09 20:09:30 -07:00
|
|
|
|
|
|
|
|
|
2006-09-27 18:43:07 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-08-09 20:09:30 -07:00
|
|
|
|
|
|
|
|
|
2006-09-27 18:43:07 -07:00
|
|
|
|
2005-08-09 20:09:30 -07:00
|
|
|
|
|
|
|
|
|
2006-09-27 18:43:07 -07:00
|
|
|
|
2005-08-09 20:09:30 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2006-09-27 18:43:07 -07:00
|
|
|
|
2005-08-09 20:09:30 -07:00
|
|
|
|
|
|
|
|
|
2006-09-27 18:43:07 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-08-09 20:09:30 -07:00
|
|
|
|
|
|
|
|
|
2006-09-27 18:43:07 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-08-09 20:09:30 -07:00
|
|
|
|
2008-01-31 05:06:40 -08:00
|
|
|
|
2008-11-21 15:49:19 -08:00
|
|
|
|
2009-10-15 06:30:45 +00:00
|
|
|
|
|
|
|
|
|
2005-08-09 20:09:30 -07:00
|
|
|
|
2008-01-31 05:06:40 -08:00
|
|
|
|
2008-11-21 15:49:19 -08:00
|
|
|
|
2006-09-27 18:43:07 -07:00
|
|
|
|
|
|
|
|
|
2005-08-09 20:09:30 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-01-31 05:06:40 -08:00
|
|
|
|
2008-11-21 15:49:19 -08:00
|
|
|
|
2009-10-15 06:30:45 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-08-09 20:09:30 -07:00
|
|
|
|
2008-01-31 05:06:40 -08:00
|
|
|
|
2008-11-21 15:49:19 -08:00
|
|
|
|
[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>
2005-10-03 14:13:38 -07:00
|
|
|
|
2005-08-09 20:09:30 -07:00
|
|
|
|
2006-09-27 18:43:07 -07:00
|
|
|
|
2005-08-09 20:09:30 -07:00
|
|
|
|
|
|
|
|
|
2005-08-09 20:09:46 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-01-31 05:06:40 -08:00
|
|
|
|
|
|
|
|
|
2007-12-20 15:32:17 -08:00
|
|
|
|
|
|
|
|
|
2005-08-09 20:09:46 -07:00
|
|
|
|
2006-08-09 15:47:12 -07:00
|
|
|
|
2008-01-31 05:06:40 -08:00
|
|
|
|
2006-09-27 18:43:33 -07:00
|
|
|
|
|
|
|
|
|
2006-08-09 15:47:12 -07:00
|
|
|
|
|
|
|
|
|
2008-01-31 05:06:40 -08:00
|
|
|
|
2006-08-09 15:47:12 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-01-31 05:06:40 -08:00
|
|
|
|
|
|
|
|
|
2006-09-27 18:43:33 -07:00
|
|
|
|
|
|
|
|
|
2005-08-09 20:09:46 -07:00
|
|
|
|
|
|
|
|
|
2006-08-09 15:47:12 -07:00
|
|
|
|
2008-01-31 05:06:40 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-08-09 20:09:46 -07:00
|
|
|
|
|
|
|
|
|
2008-01-31 05:06:40 -08:00
|
|
|
|
|
|
|
|
|
2006-09-27 18:43:33 -07:00
|
|
|
|
|
|
|
|
|
2005-08-09 20:09:46 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-01-31 05:06:40 -08:00
|
|
|
|
2005-08-09 20:09:46 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-12-13 23:25:31 -08:00
|
|
|
|
2008-10-07 11:41:57 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-10-07 12:41:01 -07:00
|
|
|
|
2008-10-07 11:41:57 -07:00
|
|
|
|
|
|
|
|
|
2008-10-07 12:41:01 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-06-02 05:19:30 +00:00
|
|
|
|
2008-10-07 12:41:01 -07:00
|
|
|
|
|
|
|
|
|
2008-10-07 11:41:57 -07:00
|
|
|
|
|
|
|
|
|
2008-01-31 05:04:45 -08:00
|
|
|
|
2009-12-04 03:46:54 +00:00
|
|
|
|
|
|
|
|
|
2008-01-31 05:04:45 -08:00
|
|
|
|
|
|
|
|
|
2009-12-04 03:46:54 +00:00
|
|
|
|
|
|
|
|
|
2005-12-13 23:25:31 -08:00
|
|
|
|
|
|
|
|
|
2005-08-09 19:59:20 -07:00
|
|
|
|
