Files
linux/include/net
Eric Dumazet c377411f24 net: sk_add_backlog() take rmem_alloc into account
Current socket backlog limit is not enough to really stop DDOS attacks,
because user thread spend many time to process a full backlog each
round, and user might crazy spin on socket lock.

We should add backlog size and receive_queue size (aka rmem_alloc) to
pace writers, and let user run without being slow down too much.

Introduce a sk_rcvqueues_full() helper, to avoid taking socket lock in
stress situations.

Under huge stress from a multiqueue/RPS enabled NIC, a single flow udp
receiver can now process ~200.000 pps (instead of ~100 pps before the
patch) on a 8 core machine.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-27 15:13:20 -07:00
..
2010-04-13 14:49:34 -07:00
2010-01-07 00:24:55 -08:00
2010-03-21 18:34:16 -07:00
…
2009-11-04 05:06:25 -08:00
2009-09-01 17:40:57 -07:00
2009-11-04 05:06:25 -08:00
2009-03-21 19:06:54 -07:00
…
2009-09-01 17:40:31 -07:00
2010-04-13 01:41:33 -07:00
…
…
2009-11-04 05:06:25 -08:00
2009-11-04 05:06:25 -08:00
2009-11-13 20:46:58 -08:00
2010-04-13 01:41:33 -07:00
2010-04-15 23:36:37 -07:00
2009-11-04 05:06:25 -08:00
2010-04-23 23:35:29 -07:00
…
…
…
…
2009-12-26 20:46:28 -08:00
…
2010-03-12 15:52:40 -08:00
2009-01-06 11:38:15 -07:00
…
…
2009-11-20 15:35:04 -08:00
2010-04-01 18:38:48 -07:00
2009-03-21 19:06:50 -07:00
2010-04-13 14:49:34 -07:00
2009-11-04 05:06:25 -08:00
2009-07-26 19:11:14 -07:00
2010-04-01 18:38:48 -07:00
2009-11-04 05:06:25 -08:00
…
2010-04-22 16:00:00 -07:00
…
2009-11-10 20:54:38 -08:00
2009-10-07 16:39:43 -04:00