openvswitch: use percpu flow stats
Instead of using flow stats per NUMA node, use it per CPU. When using
megaflows, the stats lock can be a bottleneck in scalability.
On a E5-2690 12-core system, usual throughput went from ~4Mpps to
~15Mpps when forwarding between two 40GbE ports with a single flow
configured on the datapath.
This has been tested on a system with possible CPUs 0-7,16-23. After
module removal, there were no corruption on the slab cache.
Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@redhat.com>
Cc: pravin shelar <pshelar@ovn.org>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c
index 957a3c3..ea7a807 100644
--- a/net/openvswitch/flow_table.c
+++ b/net/openvswitch/flow_table.c
@@ -32,6 +32,7 @@
#include <linux/module.h>
#include <linux/in.h>
#include <linux/rcupdate.h>
+#include <linux/cpumask.h>
#include <linux/if_arp.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
@@ -79,17 +80,12 @@
{
struct sw_flow *flow;
struct flow_stats *stats;
- int node;
- flow = kmem_cache_alloc(flow_cache, GFP_KERNEL);
+ flow = kmem_cache_zalloc(flow_cache, GFP_KERNEL);
if (!flow)
return ERR_PTR(-ENOMEM);
- flow->sf_acts = NULL;
- flow->mask = NULL;
- flow->id.unmasked_key = NULL;
- flow->id.ufid_len = 0;
- flow->stats_last_writer = NUMA_NO_NODE;
+ flow->stats_last_writer = -1;
/* Initialize the default stat node. */
stats = kmem_cache_alloc_node(flow_stats_cache,
@@ -102,10 +98,6 @@
RCU_INIT_POINTER(flow->stats[0], stats);
- for_each_node(node)
- if (node != 0)
- RCU_INIT_POINTER(flow->stats[node], NULL);
-
return flow;
err:
kmem_cache_free(flow_cache, flow);
@@ -142,17 +134,17 @@
static void flow_free(struct sw_flow *flow)
{
- int node;
+ int cpu;
if (ovs_identifier_is_key(&flow->id))
kfree(flow->id.unmasked_key);
if (flow->sf_acts)
ovs_nla_free_flow_actions((struct sw_flow_actions __force *)flow->sf_acts);
- /* We open code this to make sure node 0 is always considered */
- for (node = 0; node < MAX_NUMNODES; node = next_node(node, node_possible_map))
- if (node != 0 && flow->stats[node])
+ /* We open code this to make sure cpu 0 is always considered */
+ for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, cpu_possible_mask))
+ if (flow->stats[cpu])
kmem_cache_free(flow_stats_cache,
- (struct flow_stats __force *)flow->stats[node]);
+ (struct flow_stats __force *)flow->stats[cpu]);
kmem_cache_free(flow_cache, flow);
}
@@ -757,7 +749,7 @@
BUILD_BUG_ON(sizeof(struct sw_flow_key) % sizeof(long));
flow_cache = kmem_cache_create("sw_flow", sizeof(struct sw_flow)
- + (nr_node_ids
+ + (nr_cpu_ids
* sizeof(struct flow_stats *)),
0, 0, NULL);
if (flow_cache == NULL)