[PATCH] ipv4: Cache local output routes

[PATCH] ipv4: Cache local output routes

[Yan, Zheng]

Commit caacf05e5ad1abf causes big drop of UDP loop back performance.
The cause of the regression is that we do not cache the local output
routes. Each time we send a datagram from unconnected UDP socket,
the kernel allocates a dst_entry and adds it to the rt_uncached_list.
It creates lock contention on the rt_uncached_lock.

Reported-by: Alex Shi <alex.shi@intel.com>
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
---
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index e4ba974..fd9ecb5 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2028,7 +2028,6 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4)
 		}
 		dev_out = net->loopback_dev;
 		fl4->flowi4_oif = dev_out->ifindex;
-		res.fi = NULL;
 		flags |= RTCF_LOCAL;
 		goto make_route;
 	}

Re: [PATCH] ipv4: Cache local output routes

[David Miller]

From: "Yan, Zheng" <zheng.z.yan@intel.com>
Date: Mon, 13 Aug 2012 14:09:59 +0800

> Commit caacf05e5ad1abf causes big drop of UDP loop back performance.
> The cause of the regression is that we do not cache the local output
> routes. Each time we send a datagram from unconnected UDP socket,
> the kernel allocates a dst_entry and adds it to the rt_uncached_list.
> It creates lock contention on the rt_uncached_lock.
> 
> Reported-by: Alex Shi <alex.shi@intel.com>
> Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>

I was pretty sure not using 'fi' was necessary for semantic
reasons here, but I can't find any such requirement, so I've
applied this, thanks.