diff options
| author |   David S. Miller <davem@davemloft.net> | 2019-11-03 17:18:04 -0800 |
|---|---|---|
| committer | David S. Miller <davem@davemloft.net> | 2019-11-03 17:18:04 -0800 |
| commit | c219a1662276668a7b93afdf00320f543c58bbcb (patch) | |
| tree | 87d133322f09ecf9fcc8feddc3fd9ef86e74273b /net/ipv4/icmp.c | |
| parent | Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next (diff) | |
| parent | net: openvswitch: simplify the ovs_dp_cmd_new (diff) | |
| download | linux-dev-c219a1662276668a7b93afdf00320f543c58bbcb.tar.xz linux-dev-c219a1662276668a7b93afdf00320f543c58bbcb.zip | |
Merge branch 'optimize-openvswitch-flow-looking-up'
Tonghao Zhang says:
====================
optimize openvswitch flow looking up
This series patch optimize openvswitch for performance or simplify
codes.
Patch 1, 2, 4: Port Pravin B Shelar patches to
linux upstream with little changes.
Patch 5, 6, 7: Optimize the flow looking up and
simplify the flow hash.
Patch 8, 9: are bugfix.
The performance test is on Intel Xeon E5-2630 v4.
The test topology is show as below:
+-----------------------------------+
| +---------------------------+ |
| | eth0 ovs-switch eth1 | | Host0
| +---------------------------+ |
+-----------------------------------+
^ |
| |
| |
| |
| v
+-----+----+ +----+-----+
| netperf | Host1 | netserver| Host2
+----------+ +----------+
We use netperf send the 64B packets, and insert 255+ flow-mask:
$ ovs-dpctl add-flow ovs-switch "in_port(1),eth(dst=00:01:00:00:00:00/ff:ff:ff:ff:ff:01),eth_type(0x0800),ipv4(frag=no)" 2
...
$ ovs-dpctl add-flow ovs-switch "in_port(1),eth(dst=00:ff:00:00:00:00/ff:ff:ff:ff:ff:ff),eth_type(0x0800),ipv4(frag=no)" 2
$
$ netperf -t UDP_STREAM -H 2.2.2.200 -l 40 -- -m 18
* Without series patch, throughput 8.28Mbps
* With series patch, throughput 46.05Mbps
v6:
some coding style fixes
v5:
rewrite patch 8, release flow-mask when freeing flow
v4:
access ma->count with READ_ONCE/WRITE_ONCE API. More information,
see patch 5 comments.
v3:
update ma point when realloc mask_array in patch 5
v2:
simplify codes. e.g. use kfree_rcu instead of call_rcu
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/ipv4/icmp.c')
0 files changed, 0 insertions, 0 deletions