From 286ab3d46058840d68e5d7d52e316c1f7e98c59f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 5 Nov 2007 23:38:39 -0800 Subject: [NET]: Define infrastructure to keep 'inuse' changes in an efficent SMP/NUMA way. "struct proto" currently uses an array stats[NR_CPUS] to track change on 'inuse' sockets per protocol. If NR_CPUS is big, this means we use a big memory area for this. Moreover, all this memory area is located on a single node on NUMA machines, increasing memory pressure on the boot node. In this patch, I tried to : - Keep a fast !CONFIG_SMP implementation - Keep a fast CONFIG_SMP implementation for often used protocols (tcp,udp,raw,...) - Introduce a NUMA efficient implementation Some helper macros are defined in include/net/sock.h These macros take into account CONFIG_SMP If a "struct proto" is declared without using DEFINE_PROTO_INUSE / REF_PROTO_INUSE macros, it will automatically use a default implementation, using a dynamically allocated percpu zone. This default implementation will be NUMA efficient, but might use 32/64 bytes per possible cpu because of current alloc_percpu() implementation. However it still should be better than previous implementation based on stats[NR_CPUS] field. When a "struct proto" is changed to use the new macros, we use a single static "int" percpu variable, lowering the memory and cpu costs, still preserving NUMA efficiency. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/proc.c | 19 ++++--------------- 1 file changed, 4 insertions(+), 15 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index ffdccc0972e..ce34b281803 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -46,17 +46,6 @@ #include #include -static int fold_prot_inuse(struct proto *proto) -{ - int res = 0; - int cpu; - - for_each_possible_cpu(cpu) - res += proto->stats[cpu].inuse; - - return res; -} - /* * Report socket allocation statistics [mea@utu.fi] */ @@ -64,12 +53,12 @@ static int sockstat_seq_show(struct seq_file *seq, void *v) { socket_seq_show(seq); seq_printf(seq, "TCP: inuse %d orphan %d tw %d alloc %d mem %d\n", - fold_prot_inuse(&tcp_prot), atomic_read(&tcp_orphan_count), + sock_prot_inuse(&tcp_prot), atomic_read(&tcp_orphan_count), tcp_death_row.tw_count, atomic_read(&tcp_sockets_allocated), atomic_read(&tcp_memory_allocated)); - seq_printf(seq, "UDP: inuse %d\n", fold_prot_inuse(&udp_prot)); - seq_printf(seq, "UDPLITE: inuse %d\n", fold_prot_inuse(&udplite_prot)); - seq_printf(seq, "RAW: inuse %d\n", fold_prot_inuse(&raw_prot)); + seq_printf(seq, "UDP: inuse %d\n", sock_prot_inuse(&udp_prot)); + seq_printf(seq, "UDPLITE: inuse %d\n", sock_prot_inuse(&udplite_prot)); + seq_printf(seq, "RAW: inuse %d\n", sock_prot_inuse(&raw_prot)); seq_printf(seq, "FRAG: inuse %d memory %d\n", ip_frag_nqueues(), ip_frag_mem()); return 0; -- cgit v1.2.3