linux_dsm_epyc7002/drivers/net/ethernet/realtek
Eric Dumazet 2e71a6f808 net: gro: selective flush of packets
Current GRO can hold packets in gro_list for almost unlimited
time, in case napi->poll() handler consumes its budget over and over.

In this case, napi_complete()/napi_gro_flush() are not called.

Another problem is that gro_list is flushed in non friendly way :
We scan the list and complete packets in the reverse order.
(youngest packets first, oldest packets last)
This defeats priorities that sender could have cooked.

Since GRO currently only store TCP packets, we dont really notice the
bug because of retransmits, but this behavior can add unexpected
latencies, particularly on mice flows clamped by elephant flows.

This patch makes sure no packet can stay more than 1 ms in queue, and
only in stress situations.

It also complete packets in the right order to minimize latencies.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Jesse Gross <jesse@nicira.com>
Cc: Tom Herbert <therbert@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-10-08 14:51:51 -04:00
..
8139cp.c net: gro: selective flush of packets 2012-10-08 14:51:51 -04:00
8139too.c sections: fix section conflicts in drivers/net 2012-10-06 03:04:42 +09:00
atp.c Remove all #inclusions of asm/system.h 2012-03-28 18:30:03 +01:00
atp.h
Kconfig drivers/net: fix up stale paths from driver reorg 2012-01-30 12:54:40 -05:00
Makefile net/ethernet: sc92031 is not Realtek 2011-11-01 19:30:38 -04:00
r8169.c Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next 2012-10-02 13:38:27 -07:00