[IPSEC] flow : Remove an unecessary ____cacheline_aligned

[IPSEC] flow : Remove an unecessary ____cacheline_aligned

[Eric Dumazet]

[-- Attachment #1: Type: text/plain, Size: 868 bytes --]

We use a percpu variable named flow_hash_info, which holds 12 bytes.

It is currently marked as ____cacheline_aligned, which makes linker
skip space to properly align this variable.

Before :
c065cc90 D per_cpu__softnet_data
c065cd00 d per_cpu__flow_tables
<Here, hole of 124 bytes>
c065cd80 d per_cpu__flow_hash_info
<Here, hole of 116 bytes>
c065ce00 d per_cpu__flow_flush_tasklets
c065ce14 d per_cpu__rt_cache_stat


This alignement is quite unproductive, and removing it reduces the
size of percpu data (by 240 bytes on my x86 machine), and improves
performance (flow_tables & flow_hash_info can share a single cache
line)

After patch :
c065cc04 D per_cpu__softnet_data
c065cc4c d per_cpu__flow_tables
c065cc50 d per_cpu__flow_hash_info
c065cc5c d per_cpu__flow_flush_tasklets
c065cc70 d per_cpu__rt_cache_stat

Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>


[-- Attachment #2: flow2.patch --]
[-- Type: text/plain, Size: 359 bytes --]

diff --git a/net/core/flow.c b/net/core/flow.c
index a618f89..2a735ba 100644
--- a/net/core/flow.c
+++ b/net/core/flow.c
@@ -52,7 +52,7 @@ struct flow_percpu_info {
 	int hash_rnd_recalc;
 	u32 hash_rnd;
 	int count;
-} ____cacheline_aligned;
+};
 static DEFINE_PER_CPU(struct flow_percpu_info, flow_hash_info) = { 0 };
 
 #define flow_hash_rnd_recalc(cpu) \

Re: [IPSEC] flow : Remove an unecessary ____cacheline_aligned

[David Miller]

From: Eric Dumazet <dada1@cosmosbay.com>
Date: Tue, 01 Jan 2008 16:33:33 +0100

> We use a percpu variable named flow_hash_info, which holds 12 bytes.
> 
> It is currently marked as ____cacheline_aligned, which makes linker
> skip space to properly align this variable.
> 
> Before :
> c065cc90 D per_cpu__softnet_data
> c065cd00 d per_cpu__flow_tables
> <Here, hole of 124 bytes>
> c065cd80 d per_cpu__flow_hash_info
> <Here, hole of 116 bytes>
> c065ce00 d per_cpu__flow_flush_tasklets
> c065ce14 d per_cpu__rt_cache_stat
> 
> 
> This alignement is quite unproductive, and removing it reduces the
> size of percpu data (by 240 bytes on my x86 machine), and improves
> performance (flow_tables & flow_hash_info can share a single cache
> line)
> 
> After patch :
> c065cc04 D per_cpu__softnet_data
> c065cc4c d per_cpu__flow_tables
> c065cc50 d per_cpu__flow_hash_info
> c065cc5c d per_cpu__flow_flush_tasklets
> c065cc70 d per_cpu__rt_cache_stat
> 
> Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>

Also applied, thanks a lot for these patches Eric.