From: Pablo Neira Ayuso <pablo@netfilter.org>
To: netfilter-devel@vger.kernel.org
Cc: davem@davemloft.net, netdev@vger.kernel.org, kuba@kernel.org,
pabeni@redhat.com, edumazet@google.com, horms@kernel.org,
fw@strlen.de, ja@ssi.bg
Subject: [PATCH net 03/13] ipvs: add totalconns for dest
Date: Mon, 10 Aug 2026 21:06:11 +0200 [thread overview]
Message-ID: <20260810190621.894119-4-pablo@netfilter.org> (raw)
In-Reply-To: <20260810190621.894119-1-pablo@netfilter.org>
From: Julian Anastasov <ja@ssi.bg>
Replace the inactconns dest counter with totalconns, now
inactconns can be obtained from totalconns - activeconns.
This reduces the atomic inc/dec ops for TCP/SCTP from
6 to 4 if the connection is established and then closed.
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Cc: stable@vger.kernel.org
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Yizhou Zhao <zhaoyz24@mails.tsinghua.edu.cn>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
include/net/ip_vs.h | 17 ++++++++++++-----
net/netfilter/ipvs/ip_vs_conn.c | 24 +++++++-----------------
net/netfilter/ipvs/ip_vs_ctl.c | 10 +++++-----
net/netfilter/ipvs/ip_vs_lc.c | 4 ++--
net/netfilter/ipvs/ip_vs_proto_sctp.c | 2 --
net/netfilter/ipvs/ip_vs_proto_tcp.c | 2 --
net/netfilter/ipvs/ip_vs_sync.c | 7 ++-----
7 files changed, 28 insertions(+), 38 deletions(-)
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index d2813eb795be..11f430646db8 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -987,7 +987,7 @@ struct ip_vs_dest {
/* connection counters and thresholds */
atomic_t activeconns; /* active connections */
- atomic_t inactconns; /* inactive connections */
+ atomic_t totalconns; /* total connections */
atomic_t persistconns; /* persistent connections */
__u32 u_threshold; /* upper threshold */
__u32 l_threshold; /* lower threshold */
@@ -2220,14 +2220,21 @@ void ip_vs_unregister_hooks(struct netns_ipvs *ipvs, unsigned int af);
static inline int
ip_vs_dest_conn_overhead(struct ip_vs_dest *dest)
{
- /* We think the overhead of processing active connections is 256
+ /* We think the overhead of processing active connections is 257
* times higher than that of inactive connections in average. (This
- * 256 times might not be accurate, we will change it later) We
+ * 257 times might not be accurate, we will change it later) We
* use the following formula to estimate the overhead now:
- * dest->activeconns*256 + dest->inactconns
+ * dest->activeconns*256 + dest->totalconns
*/
return (atomic_read(&dest->activeconns) << 8) +
- atomic_read(&dest->inactconns);
+ atomic_read(&dest->totalconns);
+}
+
+static inline int
+ip_vs_dest_inactconns(const struct ip_vs_dest *dest)
+{
+ return max(atomic_read(&dest->totalconns) -
+ atomic_read(&dest->activeconns), 0);
}
#ifdef CONFIG_IP_VS_PROTO_TCP
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 36c5cba03f5b..4d0a6f718ced 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -1081,12 +1081,6 @@ static inline void ip_vs_bind_xmit_v6(struct ip_vs_conn *cp)
#endif
-static inline int ip_vs_dest_totalconns(struct ip_vs_dest *dest)
-{
- return atomic_read(&dest->activeconns)
- + atomic_read(&dest->inactconns);
-}
-
/*
* Bind a connection entry with a virtual service destination
* Called just after a new connection entry is created.
@@ -1153,8 +1147,7 @@ ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest)
*/
if (!(flags & IP_VS_CONN_F_INACTIVE))
atomic_inc(&dest->activeconns);
- else
- atomic_inc(&dest->inactconns);
+ atomic_inc(&dest->totalconns);
} else {
/* It is a persistent connection/template, so increase
the persistent connection counter */
@@ -1162,7 +1155,7 @@ ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest)
}
if (dest->u_threshold != 0 &&
- ip_vs_dest_totalconns(dest) >= dest->u_threshold)
+ atomic_read(&dest->totalconns) >= dest->u_threshold)
dest->flags |= IP_VS_DEST_F_OVERLOAD;
}
@@ -1244,13 +1237,10 @@ static inline void ip_vs_unbind_dest(struct ip_vs_conn *cp)
/* Update the connection counters */
if (!(cp->flags & IP_VS_CONN_F_TEMPLATE)) {
- /* It is a normal connection, so decrease the inactconns
- or activeconns counter */
- if (cp->flags & IP_VS_CONN_F_INACTIVE) {
- atomic_dec(&dest->inactconns);
- } else {
+ /* It is a normal connection, so decrease the counters */
+ if (!(cp->flags & IP_VS_CONN_F_INACTIVE))
atomic_dec(&dest->activeconns);
- }
+ atomic_dec(&dest->totalconns);
} else {
/* It is a persistent connection/template, so decrease
the persistent connection counter */
@@ -1258,10 +1248,10 @@ static inline void ip_vs_unbind_dest(struct ip_vs_conn *cp)
}
if (dest->l_threshold != 0) {
- if (ip_vs_dest_totalconns(dest) < dest->l_threshold)
+ if (atomic_read(&dest->totalconns) < dest->l_threshold)
dest->flags &= ~IP_VS_DEST_F_OVERLOAD;
} else if (dest->u_threshold != 0) {
- if (ip_vs_dest_totalconns(dest) * 4 < dest->u_threshold * 3)
+ if (atomic_read(&dest->totalconns) * 4 < dest->u_threshold * 3)
dest->flags &= ~IP_VS_DEST_F_OVERLOAD;
} else {
if (dest->flags & IP_VS_DEST_F_OVERLOAD)
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index bcf40b8c41cf..45f534427d23 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -1445,7 +1445,7 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
dest->port = udest->port;
atomic_set(&dest->activeconns, 0);
- atomic_set(&dest->inactconns, 0);
+ atomic_set(&dest->totalconns, 0);
atomic_set(&dest->persistconns, 0);
refcount_set(&dest->refcnt, 1);
@@ -3031,7 +3031,7 @@ static int ip_vs_info_seq_show(struct seq_file *seq, void *v)
ip_vs_fwd_name(atomic_read(&dest->conn_flags)),
atomic_read(&dest->weight),
atomic_read(&dest->activeconns),
- atomic_read(&dest->inactconns));
+ ip_vs_dest_inactconns(dest));
else
#endif
seq_printf(seq,
@@ -3042,7 +3042,7 @@ static int ip_vs_info_seq_show(struct seq_file *seq, void *v)
ip_vs_fwd_name(atomic_read(&dest->conn_flags)),
atomic_read(&dest->weight),
atomic_read(&dest->activeconns),
- atomic_read(&dest->inactconns));
+ ip_vs_dest_inactconns(dest));
}
}
@@ -3670,7 +3670,7 @@ __ip_vs_get_dest_entries(struct netns_ipvs *ipvs, const struct ip_vs_get_dests *
entry.u_threshold = dest->u_threshold;
entry.l_threshold = dest->l_threshold;
entry.activeconns = atomic_read(&dest->activeconns);
- entry.inactconns = atomic_read(&dest->inactconns);
+ entry.inactconns = ip_vs_dest_inactconns(dest);
entry.persistconns = atomic_read(&dest->persistconns);
ip_vs_copy_stats(&kstats, &dest->stats);
ip_vs_export_stats_user(&entry.stats, &kstats);
@@ -4282,7 +4282,7 @@ static int ip_vs_genl_fill_dest(struct sk_buff *skb, struct ip_vs_dest *dest)
nla_put_u32(skb, IPVS_DEST_ATTR_ACTIVE_CONNS,
atomic_read(&dest->activeconns)) ||
nla_put_u32(skb, IPVS_DEST_ATTR_INACT_CONNS,
- atomic_read(&dest->inactconns)) ||
+ ip_vs_dest_inactconns(dest)) ||
nla_put_u32(skb, IPVS_DEST_ATTR_PERSIST_CONNS,
atomic_read(&dest->persistconns)) ||
nla_put_u16(skb, IPVS_DEST_ATTR_ADDR_FAMILY, dest->af))
diff --git a/net/netfilter/ipvs/ip_vs_lc.c b/net/netfilter/ipvs/ip_vs_lc.c
index 38cc38c5d8bb..18b976a7c4d2 100644
--- a/net/netfilter/ipvs/ip_vs_lc.c
+++ b/net/netfilter/ipvs/ip_vs_lc.c
@@ -30,7 +30,7 @@ ip_vs_lc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
/*
* Simply select the server with the least number of
- * (activeconns<<5) + inactconns
+ * (activeconns*256) + totalconns
* Except whose weight is equal to zero.
* If the weight is equal to zero, it means that the server is
* quiesced, the existing connections to the server still get
@@ -56,7 +56,7 @@ ip_vs_lc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
IP_VS_DBG_ADDR(least->af, &least->addr),
ntohs(least->port),
atomic_read(&least->activeconns),
- atomic_read(&least->inactconns));
+ ip_vs_dest_inactconns(least));
return least;
}
diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c
index c80567c73469..fb8af6b15a39 100644
--- a/net/netfilter/ipvs/ip_vs_proto_sctp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c
@@ -446,12 +446,10 @@ set_sctp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp,
if (!(cp->flags & IP_VS_CONN_F_INACTIVE) &&
(next_state != IP_VS_SCTP_S_ESTABLISHED)) {
atomic_dec(&dest->activeconns);
- atomic_inc(&dest->inactconns);
cp->flags |= IP_VS_CONN_F_INACTIVE;
} else if ((cp->flags & IP_VS_CONN_F_INACTIVE) &&
(next_state == IP_VS_SCTP_S_ESTABLISHED)) {
atomic_inc(&dest->activeconns);
- atomic_dec(&dest->inactconns);
cp->flags &= ~IP_VS_CONN_F_INACTIVE;
}
}
diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c
index 99a286fdc90c..fec0e8b47b71 100644
--- a/net/netfilter/ipvs/ip_vs_proto_tcp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c
@@ -526,12 +526,10 @@ set_tcp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp,
if (!(cp->flags & IP_VS_CONN_F_INACTIVE) &&
!tcp_state_active(new_state)) {
atomic_dec(&dest->activeconns);
- atomic_inc(&dest->inactconns);
cp->flags |= IP_VS_CONN_F_INACTIVE;
} else if ((cp->flags & IP_VS_CONN_F_INACTIVE) &&
tcp_state_active(new_state)) {
atomic_inc(&dest->activeconns);
- atomic_dec(&dest->inactconns);
cp->flags &= ~IP_VS_CONN_F_INACTIVE;
}
}
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 93038abbf5e0..ea5fdd4f4ce7 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -878,13 +878,10 @@ static void ip_vs_proc_conn(struct netns_ipvs *ipvs, struct ip_vs_conn_param *pa
spin_lock_bh(&cp->lock);
if ((cp->flags ^ flags) & IP_VS_CONN_F_INACTIVE &&
!(flags & IP_VS_CONN_F_TEMPLATE) && dest) {
- if (flags & IP_VS_CONN_F_INACTIVE) {
+ if (flags & IP_VS_CONN_F_INACTIVE)
atomic_dec(&dest->activeconns);
- atomic_inc(&dest->inactconns);
- } else {
+ else
atomic_inc(&dest->activeconns);
- atomic_dec(&dest->inactconns);
- }
}
flags &= IP_VS_CONN_F_BACKUP_UPD_MASK;
flags |= cp->flags & ~IP_VS_CONN_F_BACKUP_UPD_MASK;
--
2.47.3
next prev parent reply other threads:[~2026-08-10 19:06 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-08-10 19:06 [PATCH net 00/13] Netfilter/IPVS fixes for net Pablo Neira Ayuso
2026-08-10 19:06 ` [PATCH net 01/13] netfilter: ipset: fix refcount race between list:set GC and swap Pablo Neira Ayuso
2026-08-10 19:06 ` [PATCH net 02/13] netfilter: bridge: release template ct on non-IP path Pablo Neira Ayuso
2026-08-10 19:06 ` Pablo Neira Ayuso [this message]
2026-08-10 19:06 ` [PATCH net 04/13] ipvs: properly update the overload flag on dest edit Pablo Neira Ayuso
2026-08-10 19:06 ` [PATCH net 05/13] ipvs: separate destination availability state Pablo Neira Ayuso
2026-08-10 19:06 ` [PATCH net 06/13] netfilter: nf_conntrack: defer invalid log until after unlock Pablo Neira Ayuso
2026-08-10 19:06 ` [PATCH net 07/13] netfilter: nfnetlink_log: wait for rcu grace period before freeing pernet state Pablo Neira Ayuso
2026-08-10 19:06 ` [PATCH net 08/13] ipvs: clear IPv4 options after rebasing tunnel ICMP errors Pablo Neira Ayuso
2026-08-10 19:06 ` [PATCH net 09/13] ipvs: revalidate ihl to prevent out-of-bounds access Pablo Neira Ayuso
2026-08-10 19:06 ` [PATCH net 10/13] netfilter: nf_tables_offload: suppress WARN_ON_ONCE for ENOMEM in abort path Pablo Neira Ayuso
2026-08-10 19:06 ` [PATCH net 11/13] netfilter: flowtable: publish GC-visible tuple last Pablo Neira Ayuso
2026-08-10 19:06 ` [PATCH net 12/13] netfilter: ipset: fix list type element drift bug Pablo Neira Ayuso
2026-08-10 19:06 ` [PATCH net 13/13] netfilter: ipset: let destroy callbacks adjust ext mem size Pablo Neira Ayuso
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20260810190621.894119-4-pablo@netfilter.org \
--to=pablo@netfilter.org \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=fw@strlen.de \
--cc=horms@kernel.org \
--cc=ja@ssi.bg \
--cc=kuba@kernel.org \
--cc=netdev@vger.kernel.org \
--cc=netfilter-devel@vger.kernel.org \
--cc=pabeni@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox