Dave!
I ripped out the route hash just to test the slow path. Seems like your
patch was very good as we see the same performance w/o dst hash ~114 kpps.
So my test system drops from 450 kpps to 114 kpps when every incoming
interface carries 100% traffic which has 1 dst/pkt which is very unlikely
senario I would say. It is not that bad....
Conclusions:
* Your patch is good. (I played with some variants)
* We need to focus on slow path if we feel improving the 1 dst/pkt
scenario.
Input rate 2*190 kpps clone_skb=1
Iface MTU Met RX-OK RX-ERR RX-DRP RX-OVR TX-OK TX-ERR TX-DRP TX-OVR Flags
eth0 1500 0 3001546 9684614 9684614 6998518 53 0 0 0 BRU
eth1 1500 0 13 0 0 0 3001497 0 0 0 BRU
eth2 1500 0 3001114 9678333 9678333 6998889 3 0 0 0 BRU
eth3 1500 0 2 0 0 0 3001115 0 0 0 BRU
rt_cache_stat
00009146 00000000 005b97ed 00000000 00000000 00000000 00000000 00000000 00000004 00000006 00000000 005b107e 005b1071 00000006 00000000 00000000 00000001
--- net/ipv4/route.c.030610.2 2003-06-10 18:55:32.000000000 +0200
+++ net/ipv4/route.c 2003-06-10 19:09:23.000000000 +0200
@@ -722,44 +722,10 @@
static int rt_intern_hash(unsigned hash, struct rtable *rt, struct rtable **rp)
{
- struct rtable *rth, **rthp;
- unsigned long now = jiffies;
int attempts = !in_softirq();
restart:
- rthp = &rt_hash_table[hash].chain;
-
spin_lock_bh(&rt_hash_table[hash].lock);
- while ((rth = *rthp) != NULL) {
- if (compare_keys(&rth->fl, &rt->fl)) {
- /* Put it first */
- *rthp = rth->u.rt_next;
- /*
- * Since lookup is lockfree, the deletion
- * must be visible to another weakly ordered CPU before
- * the insertion at the start of the hash chain.
- */
- smp_wmb();
- rth->u.rt_next = rt_hash_table[hash].chain;
- /*
- * Since lookup is lockfree, the update writes
- * must be ordered for consistency on SMP.
- */
- smp_wmb();
- rt_hash_table[hash].chain = rth;
-
- rth->u.dst.__use++;
- dst_hold(&rth->u.dst);
- rth->u.dst.lastuse = now;
- spin_unlock_bh(&rt_hash_table[hash].lock);
-
- rt_drop(rt);
- *rp = rth;
- return 0;
- }
-
- rthp = &rth->u.rt_next;
- }
/* Try to bind route to arp only if it is output
route or unicast forwarding path.
@@ -916,10 +882,7 @@
static inline struct rtable *ip_rt_dst_alloc(unsigned int hash)
{
- if (atomic_read(&ipv4_dst_ops.entries) >
- ipv4_dst_ops.gc_thresh)
- __rt_hash_shrink(hash);
-
+ __rt_hash_shrink(hash);
return dst_alloc(&ipv4_dst_ops);
}
@@ -1801,37 +1764,6 @@
int ip_route_input(struct sk_buff *skb, u32 daddr, u32 saddr,
u8 tos, struct net_device *dev)
{
- struct rtable * rth;
- unsigned hash;
- int iif = dev->ifindex;
-
- tos &= IPTOS_RT_MASK;
- hash = rt_hash_code(daddr, saddr ^ (iif << 5), tos);
-
- prefetch(&rt_hash_table[hash].chain->fl);
-
- rcu_read_lock();
- for (rth = rt_hash_table[hash].chain; rth; rth = rth->u.rt_next) {
- smp_read_barrier_depends();
- if (rth->fl.fl4_dst == daddr &&
- rth->fl.fl4_src == saddr &&
- rth->fl.iif == iif &&
- rth->fl.oif == 0 &&
-#ifdef CONFIG_IP_ROUTE_FWMARK
- rth->fl.fl4_fwmark == skb->nfmark &&
-#endif
- rth->fl.fl4_tos == tos) {
- rth->u.dst.lastuse = jiffies;
- dst_hold(&rth->u.dst);
- rth->u.dst.__use++;
- RT_CACHE_STAT_INC(in_hit);
- rcu_read_unlock();
- skb->dst = (struct dst_entry*)rth;
- return 0;
- }
- RT_CACHE_STAT_INC(in_hlist_search);
- }
-
rcu_read_unlock();
/* Multicast recognition logic is moved from route cache to here.
Cheers.
--ro
-
: send the line "unsubscribe linux-net" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
