forked from Minki/linux
567e4b7973
Receive Flow Steering is a nice solution but suffers from hash collisions when a mix of connected and unconnected traffic is received on the host, when flow hash table is populated. Also, clearing flow in inet_release() makes RFS not very good for short lived flows, as many packets can follow close(). (FIN , ACK packets, ...) This patch extends the information stored into global hash table to not only include cpu number, but upper part of the hash value. I use a 32bit value, and dynamically split it in two parts. For host with less than 64 possible cpus, this gives 6 bits for the cpu number, and 26 (32-6) bits for the upper part of the hash. Since hash bucket selection use low order bits of the hash, we have a full hash match, if /proc/sys/net/core/rps_sock_flow_entries is big enough. If the hash found in flow table does not match, we fallback to RPS (if it is enabled for the rxqueue). This means that a packet for an non connected flow can avoid the IPI through a unrelated/victim CPU. This also means we no longer have to clear the table at socket close time, and this helps short lived flows performance. Signed-off-by: Eric Dumazet <edumazet@google.com> Acked-by: Tom Herbert <therbert@google.com> Signed-off-by: David S. Miller <davem@davemloft.net> |
||
---|---|---|
.. | ||
appletalk | ||
arcnet | ||
bonding | ||
caif | ||
can | ||
cris | ||
dsa | ||
ethernet | ||
fddi | ||
hamradio | ||
hippi | ||
hyperv | ||
ieee802154 | ||
ipvlan | ||
irda | ||
phy | ||
plip | ||
ppp | ||
slip | ||
team | ||
usb | ||
vmxnet3 | ||
wan | ||
wimax | ||
wireless | ||
xen-netback | ||
dummy.c | ||
eql.c | ||
ifb.c | ||
Kconfig | ||
LICENSE.SRC | ||
loopback.c | ||
macvlan.c | ||
macvtap.c | ||
Makefile | ||
mdio.c | ||
mii.c | ||
netconsole.c | ||
nlmon.c | ||
ntb_netdev.c | ||
rionet.c | ||
sb1000.c | ||
Space.c | ||
sungem_phy.c | ||
tun.c | ||
veth.c | ||
virtio_net.c | ||
vxlan.c | ||
xen-netfront.c |