ipv4: speedup inet_dump_ifaddr() (eec4df98) · Commits · 戴 / test

Stephen Hemminger a écrit : > On Thu, 12 Nov 2009 15:11:36 +0100 > Eric Dumazet <eric.dumazet@gmail.com> wrote: > >> When handling large number of netdevices, inet_dump_ifaddr() >> is very slow because it has O(N^2) complexity. >> >> Instead of scanning one single list, we can use the NETDEV_HASHENTRIES >> sub lists of the dev_index hash table, and RCU lookups. >> >> Signed-off-by:

Eric Dumazet <eric.dumazet@gmail.com> > > You might be able to make RCU critical section smaller by moving > it into loop. > Indeed. But we dump at most one skb (<= 8192 bytes ?), so rcu_read_lock holding time is small, unless we meet many netdevices without addresses. I wonder if its really common... Thanks [PATCH net-next-2.6] ipv4: speedup inet_dump_ifaddr() When handling large number of netdevices, inet_dump_ifaddr() is very slow because it has O(N2) complexity. Instead of scanning one single list, we can use the NETDEV_HASHENTRIES sub lists of the dev_index hash table, and RCU lookups. Signed-off-by:

Eric Dumazet <eric.dumazet@gmail.com> Acked-by:

Stephen Hemminger <shemminger@vyatta.com> Signed-off-by:

David S. Miller <davem@davemloft.net>

net/ipv4/devinet.c

+38 −23

Original line number	Diff line number	Diff line
		@@ -1174,20 +1174,29 @@ nla_put_failure:
		static int inet_dump_ifaddr(struct sk_buff skb, struct netlink_callback cb)
		{
		struct net *net = sock_net(skb->sk);
		int idx, ip_idx;
		int h, s_h;
		int idx, s_idx;
		int ip_idx, s_ip_idx;
		struct net_device *dev;
		struct in_device *in_dev;
		struct in_ifaddr *ifa;
		int s_ip_idx, s_idx = cb->args[0];
		struct hlist_head *head;
		struct hlist_node *node;

		s_ip_idx = ip_idx = cb->args[1];
		s_h = cb->args[0];
		s_idx = idx = cb->args[1];
		s_ip_idx = ip_idx = cb->args[2];

		for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
		idx = 0;
		for_each_netdev(net, dev) {
		head = &net->dev_index_head[h];
		rcu_read_lock();
		hlist_for_each_entry_rcu(dev, node, head, index_hlist) {
		if (idx < s_idx)
		goto cont;
		if (idx > s_idx)
		s_ip_idx = 0;
		in_dev = __in_dev_get_rtnl(dev);
		in_dev = __in_dev_get_rcu(dev);
		if (!in_dev)
		goto cont;

		@@ -1195,18 +1204,24 @@ static int inet_dump_ifaddr(struct sk_buff skb, struct netlink_callback cb)
		ifa = ifa->ifa_next, ip_idx++) {
		if (ip_idx < s_ip_idx)
		continue;
		if (inet_fill_ifaddr(skb, ifa, NETLINK_CB(cb->skb).pid,
		if (inet_fill_ifaddr(skb, ifa,
		NETLINK_CB(cb->skb).pid,
		cb->nlh->nlmsg_seq,
		RTM_NEWADDR, NLM_F_MULTI) <= 0)
		RTM_NEWADDR, NLM_F_MULTI) <= 0) {
		rcu_read_unlock();
		goto done;
		}
		}
		cont:
		idx++;
		}
		rcu_read_unlock();
		}

		done:
		cb->args[0] = idx;
		cb->args[1] = ip_idx;
		cb->args[0] = h;
		cb->args[1] = idx;
		cb->args[2] = ip_idx;

		return skb->len;
		}

Admin message