Hi,
This is another result from my likely profiling tool ([EMAIL PROTECTED] just
sent the patch of the profiling tool to linux-kernel mailing list, which is
similar to what I use).
On my system (not very busy, normal development machine within a VMWare workstation), I
see a 6/5 miss/hit ratio for the following "likely".
I am not sure what would happen for a busy system though (on which performance
actually matters), but I am just reporting what I find and hope it might help.
Signed-off-by: Hua Zhong <[EMAIL PROTECTED]>
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 18d7fad..9f44359 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -337,7 +337,7 @@ static inline int ip_rcv_finish(struct s
* Initialise the virtual path cache for the packet. It describes
* how the packet travels inside Linux networking.
*/
- if (likely(skb->dst == NULL)) {
+ if (skb->dst) {
int err = ip_route_input(skb, iph->daddr, iph->saddr, iph->tos,
skb->dev);
if (unlikely(err)) {
-
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
