[<prev] [next>] [day] [month] [year] [list]
Message-ID: <472F5968.5030607@cosmosbay.com>
Date: Mon, 05 Nov 2007 18:56:56 +0100
From: Eric Dumazet <dada1@...mosbay.com>
To: "David S. Miller" <davem@...emloft.net>
Cc: netdev@...r.kernel.org
Subject: [PATCH 1/4] NET : defines an 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 <dada1@...mosbay.com>
include/net/sock.h | 63 ++++++++++++++++++++++++++++++++++++++-----
net/core/sock.c | 48 ++++++++++++++++++++++++++++++++
net/ipv4/proc.c | 19 ++----------
net/ipv6/proc.c | 19 ++----------
4 files changed, 112 insertions(+), 37 deletions(-)
View attachment "prot_inuse_infra.patch" of type "text/plain" (7187 bytes)
Powered by blists - more mailing lists