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>
static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb)
{
struct net *net = sock_net(skb->sk);
static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb)
{
struct net *net = sock_net(skb->sk);
+ 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;
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];
- idx = 0;
- for_each_netdev(net, dev) {
- if (idx < s_idx)
- goto cont;
- if (idx > s_idx)
- s_ip_idx = 0;
- in_dev = __in_dev_get_rtnl(dev);
- if (!in_dev)
- goto cont;
+ s_h = cb->args[0];
+ s_idx = idx = cb->args[1];
+ s_ip_idx = ip_idx = cb->args[2];
- for (ifa = in_dev->ifa_list, ip_idx = 0; ifa;
- ifa = ifa->ifa_next, ip_idx++) {
- if (ip_idx < s_ip_idx)
- continue;
- if (inet_fill_ifaddr(skb, ifa, NETLINK_CB(cb->skb).pid,
+ for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
+ idx = 0;
+ 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_rcu(dev);
+ if (!in_dev)
+ goto cont;
+
+ for (ifa = in_dev->ifa_list, ip_idx = 0; ifa;
+ ifa = ifa->ifa_next, ip_idx++) {
+ if (ip_idx < s_ip_idx)
+ continue;
+ if (inet_fill_ifaddr(skb, ifa,
+ NETLINK_CB(cb->skb).pid,
- RTM_NEWADDR, NLM_F_MULTI) <= 0)
- goto done;
- }
+ RTM_NEWADDR, NLM_F_MULTI) <= 0) {
+ rcu_read_unlock();
+ goto done;
+ }
+ }
+ idx++;
+ }
+ rcu_read_unlock();
- cb->args[0] = idx;
- cb->args[1] = ip_idx;
+ cb->args[0] = h;
+ cb->args[1] = idx;
+ cb->args[2] = ip_idx;