* [PATCH] net: Always allocate at least 16 skb frags regardless of page size
@ 2011-03-28 0:57 Anton Blanchard
2011-03-29 5:27 ` David Miller
0 siblings, 1 reply; 2+ messages in thread
From: Anton Blanchard @ 2011-03-28 0:57 UTC (permalink / raw)
To: davem, eric.dumazet, herbert; +Cc: netdev
When analysing performance of the cxgb3 on a ppc64 box I noticed that
we weren't doing much GRO merging. It turns out we are limited by the
number of SKB frags:
#define MAX_SKB_FRAGS (65536/PAGE_SIZE + 2)
With a 4kB page size we have 18 frags, but with a 64kB page size we
only have 3 frags.
I ran a single stream TCP bandwidth test to compare the performance of
different values of MAX_SKB_FRAGS on the receiver:
MAX_SKB_FRAGS Mbps
3 7080
8 7931 (+12%)
16 8335 (+17%)
32 8349 (+17%)
Performance continues to increase up to 16 frags then levels off so
the patch below puts a lower bound of 16 on MAX_SKB_FRAGS.
Signed-off-by: Anton Blanchard <anton@samba.org>
---
Index: powerpc.git/include/linux/skbuff.h
===================================================================
--- powerpc.git.orig/include/linux/skbuff.h 2011-03-28 09:41:25.392124844 +1100
+++ powerpc.git/include/linux/skbuff.h 2011-03-28 10:18:58.253050000 +1100
@@ -122,8 +122,14 @@ struct sk_buff_head {
struct sk_buff;
-/* To allow 64K frame to be packed as single skb without frag_list */
+/* To allow 64K frame to be packed as single skb without frag_list. Since
+ * GRO uses frags we allocate at least 16 regardless of page size.
+ */
+#if (65536/PAGE_SIZE + 2) < 16
+#define MAX_SKB_FRAGS 16
+#else
#define MAX_SKB_FRAGS (65536/PAGE_SIZE + 2)
+#endif
typedef struct skb_frag_struct skb_frag_t;
^ permalink raw reply [flat|nested] 2+ messages in thread* Re: [PATCH] net: Always allocate at least 16 skb frags regardless of page size
2011-03-28 0:57 [PATCH] net: Always allocate at least 16 skb frags regardless of page size Anton Blanchard
@ 2011-03-29 5:27 ` David Miller
0 siblings, 0 replies; 2+ messages in thread
From: David Miller @ 2011-03-29 5:27 UTC (permalink / raw)
To: anton; +Cc: eric.dumazet, herbert, netdev
From: Anton Blanchard <anton@samba.org>
Date: Mon, 28 Mar 2011 11:57:26 +1100
>
> When analysing performance of the cxgb3 on a ppc64 box I noticed that
> we weren't doing much GRO merging. It turns out we are limited by the
> number of SKB frags:
>
> #define MAX_SKB_FRAGS (65536/PAGE_SIZE + 2)
>
> With a 4kB page size we have 18 frags, but with a 64kB page size we
> only have 3 frags.
>
> I ran a single stream TCP bandwidth test to compare the performance of
> different values of MAX_SKB_FRAGS on the receiver:
>
> MAX_SKB_FRAGS Mbps
> 3 7080
> 8 7931 (+12%)
> 16 8335 (+17%)
> 32 8349 (+17%)
>
> Performance continues to increase up to 16 frags then levels off so
> the patch below puts a lower bound of 16 on MAX_SKB_FRAGS.
>
> Signed-off-by: Anton Blanchard <anton@samba.org>
Thanks for investigating this and fixing the problem.
Applied.
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2011-03-29 5:27 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2011-03-28 0:57 [PATCH] net: Always allocate at least 16 skb frags regardless of page size Anton Blanchard
2011-03-29 5:27 ` David Miller
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).