connlimit currently suffers from spinlock contention, example for
4-core system with rps enabled:
+ 20.84% ksoftirqd/2 [kernel.kallsyms] [k] _raw_spin_lock_bh
+ 20.76% ksoftirqd/1 [kernel.kallsyms] [k] _raw_spin_lock_bh
+ 20.42% ksoftirqd/0 [kernel.kallsyms] [k] _raw_spin_lock_bh
+ 6.07% ksoftirqd/2 [nf_conntrack] [k] ____nf_conntrack_find
+ 6.07% ksoftirqd/1 [nf_conntrack] [k] ____nf_conntrack_find
+ 5.97% ksoftirqd/0 [nf_conntrack] [k] ____nf_conntrack_find
+ 2.47% ksoftirqd/2 [nf_conntrack] [k] hash_conntrack_raw
+ 2.45% ksoftirqd/0 [nf_conntrack] [k] hash_conntrack_raw
+ 2.44% ksoftirqd/1 [nf_conntrack] [k] hash_conntrack_raw
May allow parallel lookup/insert/delete if the entry is hashed to
another slot. With patch:
+ 20.95% ksoftirqd/0 [nf_conntrack] [k] ____nf_conntrack_find
+ 20.50% ksoftirqd/1 [nf_conntrack] [k] ____nf_conntrack_find
+ 20.27% ksoftirqd/2 [nf_conntrack] [k] ____nf_conntrack_find
+ 5.76% ksoftirqd/1 [nf_conntrack] [k] hash_conntrack_raw
+ 5.39% ksoftirqd/2 [nf_conntrack] [k] hash_conntrack_raw
+ 5.35% ksoftirqd/0 [nf_conntrack] [k] hash_conntrack_raw
+ 2.00% ksoftirqd/1 [kernel.kallsyms] [k] __rcu_read_unlock
Improved rx processing rate from ~35kpps to ~50 kpps.
Reviewed-by: Jesper Dangaard Brouer <brouer@xxxxxxxxxx>
Signed-off-by: Florian Westphal <fw@xxxxxxxxx>
---
net/netfilter/xt_connlimit.c | 25 +++++++++++++++++--------
1 file changed, 17 insertions(+), 8 deletions(-)
diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c
index a8eaabb..892566f 100644
--- a/net/netfilter/xt_connlimit.c
+++ b/net/netfilter/xt_connlimit.c
@@ -31,6 +31,9 @@
#include <net/netfilter/nf_conntrack_tuple.h>
#include <net/netfilter/nf_conntrack_zones.h>
+#define CONNLIMIT_SLOTS 256 /* power-of-two */
+#define CONNLIMIT_LOCK_SLOTS 32 /* power-of-two */
+
/* we will save the tuples of all connections we care about */
struct xt_connlimit_conn {
struct hlist_node node;
@@ -39,8 +42,8 @@ struct xt_connlimit_conn {
};
struct xt_connlimit_data {
- struct hlist_head iphash[256];
- spinlock_t lock;
+ struct hlist_head iphash[CONNLIMIT_SLOTS];
+ spinlock_t locks[CONNLIMIT_LOCK_SLOTS];
};
static u_int32_t connlimit_rnd __read_mostly;
@@ -48,7 +51,8 @@ static struct kmem_cache *connlimit_conn_cachep __read_mostly;
static inline unsigned int connlimit_iphash(__be32 addr)
{
- return jhash_1word((__force __u32)addr, connlimit_rnd) & 0xFF;
+ return jhash_1word((__force __u32)addr,
+ connlimit_rnd) % CONNLIMIT_SLOTS;
}
static inline unsigned int
@@ -61,7 +65,8 @@ connlimit_iphash6(const union nf_inet_addr *addr,
for (i = 0; i < ARRAY_SIZE(addr->ip6); ++i)
res.ip6[i] = addr->ip6[i] & mask->ip6[i];
- return jhash2((u32 *)res.ip6, ARRAY_SIZE(res.ip6), connlimit_rnd) & 0xFF;
+ return jhash2((u32 *)res.ip6, ARRAY_SIZE(res.ip6),
+ connlimit_rnd) % CONNLIMIT_SLOTS;
}
static inline bool already_closed(const struct nf_conn *conn)
@@ -183,7 +188,7 @@ static int count_them(struct net *net,
hhead = &data->iphash[hash];
- spin_lock_bh(&data->lock);
+ spin_lock_bh(&data->locks[hash % CONNLIMIT_LOCK_SLOTS]);
count = count_hlist(net, hhead, tuple, addr, mask, family, &addit);
if (addit) {
if (add_hlist(hhead, tuple, addr))
@@ -191,7 +196,7 @@ static int count_them(struct net *net,
else
count = -ENOMEM;
}
- spin_unlock_bh(&data->lock);
+ spin_unlock_bh(&data->locks[hash % CONNLIMIT_LOCK_SLOTS]);
return count;
}
@@ -227,7 +232,6 @@ connlimit_mt(const struct sk_buff *skb, struct xt_action_param *par)
connections = count_them(net, info->data, tuple_ptr, &addr,
&info->mask, par->family);
-
if (connections < 0)
/* kmalloc failed, drop it entirely */
goto hotdrop;
@@ -268,7 +272,9 @@ static int connlimit_mt_check(const struct xt_mtchk_param *par)
return -ENOMEM;
}
- spin_lock_init(&info->data->lock);
+ for (i = 0; i < ARRAY_SIZE(info->data->locks); ++i)
+ spin_lock_init(&info->data->locks[i]);
+
for (i = 0; i < ARRAY_SIZE(info->data->iphash); ++i)
INIT_HLIST_HEAD(&info->data->iphash[i]);
@@ -309,6 +315,9 @@ static struct xt_match connlimit_mt_reg __read_mostly = {
static int __init connlimit_mt_init(void)
{
int ret;
+
+ BUILD_BUG_ON(CONNLIMIT_LOCK_SLOTS > CONNLIMIT_SLOTS);
+
connlimit_conn_cachep = kmem_cache_create("xt_connlimit_conn",
sizeof(struct xt_connlimit_conn),
0, 0, NULL);
--
1.8.1.5
--
To unsubscribe from this list: send the line "unsubscribe netfilter-devel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
