kernel_optimize_test/net/openvswitch/flow_table.h
Eelco Chaudron eac87c413b net: openvswitch: reorder masks array based on usage
This patch reorders the masks array every 4 seconds based on their
usage count. This greatly reduces the masks per packet hit, and
hence the overall performance. Especially in the OVS/OVN case for
OpenShift.

Here are some results from the OVS/OVN OpenShift test, which use
8 pods, each pod having 512 uperf connections, each connection
sends a 64-byte request and gets a 1024-byte response (TCP).
All uperf clients are on 1 worker node while all uperf servers are
on the other worker node.

Kernel without this patch     :  7.71 Gbps
Kernel with this patch applied: 14.52 Gbps

We also run some tests to verify the rebalance activity does not
lower the flow insertion rate, which does not.

Signed-off-by: Eelco Chaudron <echaudro@redhat.com>
Tested-by: Andrew Theurer <atheurer@redhat.com>
Reviewed-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-07-17 10:36:50 -07:00

101 lines
2.6 KiB
C

/* SPDX-License-Identifier: GPL-2.0-only */
/*
* Copyright (c) 2007-2013 Nicira, Inc.
*/
#ifndef FLOW_TABLE_H
#define FLOW_TABLE_H 1
#include <linux/kernel.h>
#include <linux/netlink.h>
#include <linux/openvswitch.h>
#include <linux/spinlock.h>
#include <linux/types.h>
#include <linux/rcupdate.h>
#include <linux/if_ether.h>
#include <linux/in6.h>
#include <linux/jiffies.h>
#include <linux/time.h>
#include <net/inet_ecn.h>
#include <net/ip_tunnels.h>
#include "flow.h"
struct mask_cache_entry {
u32 skb_hash;
u32 mask_index;
};
struct mask_count {
int index;
u64 counter;
};
struct mask_array {
struct rcu_head rcu;
int count, max;
u64 __percpu *masks_usage_cntr;
u64 *masks_usage_zero_cntr;
struct u64_stats_sync syncp;
struct sw_flow_mask __rcu *masks[];
};
struct table_instance {
struct hlist_head *buckets;
unsigned int n_buckets;
struct rcu_head rcu;
int node_ver;
u32 hash_seed;
bool keep_flows;
};
struct flow_table {
struct table_instance __rcu *ti;
struct table_instance __rcu *ufid_ti;
struct mask_cache_entry __percpu *mask_cache;
struct mask_array __rcu *mask_array;
unsigned long last_rehash;
unsigned int count;
unsigned int ufid_count;
};
extern struct kmem_cache *flow_stats_cache;
int ovs_flow_init(void);
void ovs_flow_exit(void);
struct sw_flow *ovs_flow_alloc(void);
void ovs_flow_free(struct sw_flow *, bool deferred);
int ovs_flow_tbl_init(struct flow_table *);
int ovs_flow_tbl_count(const struct flow_table *table);
void ovs_flow_tbl_destroy(struct flow_table *table);
int ovs_flow_tbl_flush(struct flow_table *flow_table);
int ovs_flow_tbl_insert(struct flow_table *table, struct sw_flow *flow,
const struct sw_flow_mask *mask);
void ovs_flow_tbl_remove(struct flow_table *table, struct sw_flow *flow);
int ovs_flow_tbl_num_masks(const struct flow_table *table);
struct sw_flow *ovs_flow_tbl_dump_next(struct table_instance *table,
u32 *bucket, u32 *idx);
struct sw_flow *ovs_flow_tbl_lookup_stats(struct flow_table *,
const struct sw_flow_key *,
u32 skb_hash,
u32 *n_mask_hit);
struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *,
const struct sw_flow_key *);
struct sw_flow *ovs_flow_tbl_lookup_exact(struct flow_table *tbl,
const struct sw_flow_match *match);
struct sw_flow *ovs_flow_tbl_lookup_ufid(struct flow_table *,
const struct sw_flow_id *);
bool ovs_flow_cmp(const struct sw_flow *, const struct sw_flow_match *);
void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src,
bool full, const struct sw_flow_mask *mask);
void ovs_flow_masks_rebalance(struct flow_table *table);
#endif /* flow_table.h */