[GIT PULL nf-next-2.6] IPVS

[GIT PULL nf-next-2.6] IPVS

[Simon Horman]

Hi Patrick,

please consider pulling
git://git.kernel.org/pub/scm/linux/kernel/git/horms/lvs-test-2.6.git master
go get the following changes by Changli.

      ipvs: use hlist instead of list
      ipvs: use enum to instead of magic numbers
      ipvs: unify the formula to estimate the overhead of processing connections

 include/net/ip_vs.h              |   16 +++++++++++-
 net/netfilter/ipvs/ip_vs_conn.c  |   52 +++++++++++++++++++++----------------
 net/netfilter/ipvs/ip_vs_lblc.c  |   13 ++-------
 net/netfilter/ipvs/ip_vs_lblcr.c |   25 +++++-------------
 net/netfilter/ipvs/ip_vs_lc.c    |   18 +------------
 net/netfilter/ipvs/ip_vs_wlc.c   |   20 +-------------
 net/netfilter/ipvs/ip_vs_xmit.c  |   41 +++++++++++++++++++----------
 7 files changed, 84 insertions(+), 101 deletions(-)

[PATCH 1/3] ipvs: use hlist instead of list

[Simon Horman]

From: Changli Gao <xiaosuo@gmail.com>

Signed-off-by: Changli Gao <xiaosuo@gmail.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h             |    2 +-
 net/netfilter/ipvs/ip_vs_conn.c |   52 +++++++++++++++++++++-----------------
 2 files changed, 30 insertions(+), 24 deletions(-)

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 9399549..17b01b2 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -494,7 +494,7 @@ struct ip_vs_conn_param {
  *	IP_VS structure allocated for each dynamically scheduled connection
  */
 struct ip_vs_conn {
-	struct list_head        c_list;         /* hashed list heads */
+	struct hlist_node	c_list;         /* hashed list heads */
 #ifdef CONFIG_NET_NS
 	struct net              *net;           /* Name space */
 #endif
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 83233fe..9c2a517 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -59,7 +59,7 @@ static int ip_vs_conn_tab_mask __read_mostly;
 /*
  *  Connection hash table: for input and output packets lookups of IPVS
  */
-static struct list_head *ip_vs_conn_tab __read_mostly;
+static struct hlist_head *ip_vs_conn_tab __read_mostly;
 
 /*  SLAB cache for IPVS connections */
 static struct kmem_cache *ip_vs_conn_cachep __read_mostly;
@@ -201,7 +201,7 @@ static inline int ip_vs_conn_hash(struct ip_vs_conn *cp)
 	spin_lock(&cp->lock);
 
 	if (!(cp->flags & IP_VS_CONN_F_HASHED)) {
-		list_add(&cp->c_list, &ip_vs_conn_tab[hash]);
+		hlist_add_head(&cp->c_list, &ip_vs_conn_tab[hash]);
 		cp->flags |= IP_VS_CONN_F_HASHED;
 		atomic_inc(&cp->refcnt);
 		ret = 1;
@@ -234,7 +234,7 @@ static inline int ip_vs_conn_unhash(struct ip_vs_conn *cp)
 	spin_lock(&cp->lock);
 
 	if (cp->flags & IP_VS_CONN_F_HASHED) {
-		list_del(&cp->c_list);
+		hlist_del(&cp->c_list);
 		cp->flags &= ~IP_VS_CONN_F_HASHED;
 		atomic_dec(&cp->refcnt);
 		ret = 1;
@@ -259,12 +259,13 @@ __ip_vs_conn_in_get(const struct ip_vs_conn_param *p)
 {
 	unsigned hash;
 	struct ip_vs_conn *cp;
+	struct hlist_node *n;
 
 	hash = ip_vs_conn_hashkey_param(p, false);
 
 	ct_read_lock(hash);
 
-	list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) {
+	hlist_for_each_entry(cp, n, &ip_vs_conn_tab[hash], c_list) {
 		if (cp->af == p->af &&
 		    p->cport == cp->cport && p->vport == cp->vport &&
 		    ip_vs_addr_equal(p->af, p->caddr, &cp->caddr) &&
@@ -345,12 +346,13 @@ struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p)
 {
 	unsigned hash;
 	struct ip_vs_conn *cp;
+	struct hlist_node *n;
 
 	hash = ip_vs_conn_hashkey_param(p, false);
 
 	ct_read_lock(hash);
 
-	list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) {
+	hlist_for_each_entry(cp, n, &ip_vs_conn_tab[hash], c_list) {
 		if (!ip_vs_conn_net_eq(cp, p->net))
 			continue;
 		if (p->pe_data && p->pe->ct_match) {
@@ -394,6 +396,7 @@ struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p)
 {
 	unsigned hash;
 	struct ip_vs_conn *cp, *ret=NULL;
+	struct hlist_node *n;
 
 	/*
 	 *	Check for "full" addressed entries
@@ -402,7 +405,7 @@ struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p)
 
 	ct_read_lock(hash);
 
-	list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) {
+	hlist_for_each_entry(cp, n, &ip_vs_conn_tab[hash], c_list) {
 		if (cp->af == p->af &&
 		    p->vport == cp->cport && p->cport == cp->dport &&
 		    ip_vs_addr_equal(p->af, p->vaddr, &cp->caddr) &&
@@ -818,7 +821,7 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p,
 		return NULL;
 	}
 
-	INIT_LIST_HEAD(&cp->c_list);
+	INIT_HLIST_NODE(&cp->c_list);
 	setup_timer(&cp->timer, ip_vs_conn_expire, (unsigned long)cp);
 	ip_vs_conn_net_set(cp, p->net);
 	cp->af		   = p->af;
@@ -894,8 +897,8 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p,
  */
 #ifdef CONFIG_PROC_FS
 struct ip_vs_iter_state {
-	struct seq_net_private p;
-	struct list_head *l;
+	struct seq_net_private	p;
+	struct hlist_head	*l;
 };
 
 static void *ip_vs_conn_array(struct seq_file *seq, loff_t pos)
@@ -903,13 +906,14 @@ static void *ip_vs_conn_array(struct seq_file *seq, loff_t pos)
 	int idx;
 	struct ip_vs_conn *cp;
 	struct ip_vs_iter_state *iter = seq->private;
+	struct hlist_node *n;
 
 	for (idx = 0; idx < ip_vs_conn_tab_size; idx++) {
 		ct_read_lock_bh(idx);
-		list_for_each_entry(cp, &ip_vs_conn_tab[idx], c_list) {
+		hlist_for_each_entry(cp, n, &ip_vs_conn_tab[idx], c_list) {
 			if (pos-- == 0) {
 				iter->l = &ip_vs_conn_tab[idx];
-			return cp;
+				return cp;
 			}
 		}
 		ct_read_unlock_bh(idx);
@@ -930,7 +934,8 @@ static void *ip_vs_conn_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
 	struct ip_vs_conn *cp = v;
 	struct ip_vs_iter_state *iter = seq->private;
-	struct list_head *e, *l = iter->l;
+	struct hlist_node *e;
+	struct hlist_head *l = iter->l;
 	int idx;
 
 	++*pos;
@@ -938,15 +943,15 @@ static void *ip_vs_conn_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 		return ip_vs_conn_array(seq, 0);
 
 	/* more on same hash chain? */
-	if ((e = cp->c_list.next) != l)
-		return list_entry(e, struct ip_vs_conn, c_list);
+	if ((e = cp->c_list.next))
+		return hlist_entry(e, struct ip_vs_conn, c_list);
 
 	idx = l - ip_vs_conn_tab;
 	ct_read_unlock_bh(idx);
 
 	while (++idx < ip_vs_conn_tab_size) {
 		ct_read_lock_bh(idx);
-		list_for_each_entry(cp, &ip_vs_conn_tab[idx], c_list) {
+		hlist_for_each_entry(cp, e, &ip_vs_conn_tab[idx], c_list) {
 			iter->l = &ip_vs_conn_tab[idx];
 			return cp;
 		}
@@ -959,7 +964,7 @@ static void *ip_vs_conn_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 static void ip_vs_conn_seq_stop(struct seq_file *seq, void *v)
 {
 	struct ip_vs_iter_state *iter = seq->private;
-	struct list_head *l = iter->l;
+	struct hlist_head *l = iter->l;
 
 	if (l)
 		ct_read_unlock_bh(l - ip_vs_conn_tab);
@@ -1148,13 +1153,14 @@ void ip_vs_random_dropentry(struct net *net)
 	 */
 	for (idx = 0; idx < (ip_vs_conn_tab_size>>5); idx++) {
 		unsigned hash = net_random() & ip_vs_conn_tab_mask;
+		struct hlist_node *n;
 
 		/*
 		 *  Lock is actually needed in this loop.
 		 */
 		ct_write_lock_bh(hash);
 
-		list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) {
+		hlist_for_each_entry(cp, n, &ip_vs_conn_tab[hash], c_list) {
 			if (cp->flags & IP_VS_CONN_F_TEMPLATE)
 				/* connection template */
 				continue;
@@ -1202,12 +1208,14 @@ static void ip_vs_conn_flush(struct net *net)
 
 flush_again:
 	for (idx = 0; idx < ip_vs_conn_tab_size; idx++) {
+		struct hlist_node *n;
+
 		/*
 		 *  Lock is actually needed in this loop.
 		 */
 		ct_write_lock_bh(idx);
 
-		list_for_each_entry(cp, &ip_vs_conn_tab[idx], c_list) {
+		hlist_for_each_entry(cp, n, &ip_vs_conn_tab[idx], c_list) {
 			if (!ip_vs_conn_net_eq(cp, net))
 				continue;
 			IP_VS_DBG(4, "del connection\n");
@@ -1265,8 +1273,7 @@ int __init ip_vs_conn_init(void)
 	/*
 	 * Allocate the connection hash table and initialize its list heads
 	 */
-	ip_vs_conn_tab = vmalloc(ip_vs_conn_tab_size *
-				 sizeof(struct list_head));
+	ip_vs_conn_tab = vmalloc(ip_vs_conn_tab_size * sizeof(*ip_vs_conn_tab));
 	if (!ip_vs_conn_tab)
 		return -ENOMEM;
 
@@ -1286,9 +1293,8 @@ int __init ip_vs_conn_init(void)
 	IP_VS_DBG(0, "Each connection entry needs %Zd bytes at least\n",
 		  sizeof(struct ip_vs_conn));
 
-	for (idx = 0; idx < ip_vs_conn_tab_size; idx++) {
-		INIT_LIST_HEAD(&ip_vs_conn_tab[idx]);
-	}
+	for (idx = 0; idx < ip_vs_conn_tab_size; idx++)
+		INIT_HLIST_HEAD(&ip_vs_conn_tab[idx]);
 
 	for (idx = 0; idx < CT_LOCKARRAY_SIZE; idx++)  {
 		rwlock_init(&__ip_vs_conntbl_lock_array[idx].l);
-- 
1.7.2.3

[PATCH 2/3] ipvs: use enum to instead of magic numbers

[Simon Horman]

From: Changli Gao <xiaosuo@gmail.com>

Signed-off-by: Changli Gao <xiaosuo@gmail.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/ip_vs_xmit.c |   41 +++++++++++++++++++++++++-------------
 1 files changed, 27 insertions(+), 14 deletions(-)

diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 1f2a4e3..a48239a 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -43,6 +43,13 @@
 
 #include <net/ip_vs.h>
 
+enum {
+	IP_VS_RT_MODE_LOCAL	= 1, /* Allow local dest */
+	IP_VS_RT_MODE_NON_LOCAL	= 2, /* Allow non-local dest */
+	IP_VS_RT_MODE_RDR	= 4, /* Allow redirect from remote daddr to
+				      * local
+				      */
+};
 
 /*
  *      Destination cache to speed up outgoing route lookup
@@ -77,11 +84,7 @@ __ip_vs_dst_check(struct ip_vs_dest *dest, u32 rtos)
 	return dst;
 }
 
-/*
- * Get route to destination or remote server
- * rt_mode: flags, &1=Allow local dest, &2=Allow non-local dest,
- *	    &4=Allow redirect from remote daddr to local
- */
+/* Get route to destination or remote server */
 static struct rtable *
 __ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest,
 		   __be32 daddr, u32 rtos, int rt_mode)
@@ -126,15 +129,16 @@ __ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest,
 	}
 
 	local = rt->rt_flags & RTCF_LOCAL;
-	if (!((local ? 1 : 2) & rt_mode)) {
+	if (!((local ? IP_VS_RT_MODE_LOCAL : IP_VS_RT_MODE_NON_LOCAL) &
+	      rt_mode)) {
 		IP_VS_DBG_RL("Stopping traffic to %s address, dest: %pI4\n",
 			     (rt->rt_flags & RTCF_LOCAL) ?
 			     "local":"non-local", &rt->rt_dst);
 		ip_rt_put(rt);
 		return NULL;
 	}
-	if (local && !(rt_mode & 4) && !((ort = skb_rtable(skb)) &&
-					 ort->rt_flags & RTCF_LOCAL)) {
+	if (local && !(rt_mode & IP_VS_RT_MODE_RDR) &&
+	    !((ort = skb_rtable(skb)) && ort->rt_flags & RTCF_LOCAL)) {
 		IP_VS_DBG_RL("Redirect from non-local address %pI4 to local "
 			     "requires NAT method, dest: %pI4\n",
 			     &ip_hdr(skb)->daddr, &rt->rt_dst);
@@ -383,8 +387,8 @@ ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 
 	EnterFunction(10);
 
-	if (!(rt = __ip_vs_get_out_rt(skb, NULL, iph->daddr,
-				      RT_TOS(iph->tos), 2)))
+	if (!(rt = __ip_vs_get_out_rt(skb, NULL, iph->daddr, RT_TOS(iph->tos),
+				      IP_VS_RT_MODE_NON_LOCAL)))
 		goto tx_error_icmp;
 
 	/* MTU checking */
@@ -512,7 +516,10 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	}
 
 	if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip,
-				      RT_TOS(iph->tos), 1|2|4)))
+				      RT_TOS(iph->tos),
+				      IP_VS_RT_MODE_LOCAL |
+					IP_VS_RT_MODE_NON_LOCAL |
+					IP_VS_RT_MODE_RDR)))
 		goto tx_error_icmp;
 	local = rt->rt_flags & RTCF_LOCAL;
 	/*
@@ -755,7 +762,8 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	EnterFunction(10);
 
 	if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip,
-				      RT_TOS(tos), 1|2)))
+				      RT_TOS(tos), IP_VS_RT_MODE_LOCAL |
+						   IP_VS_RT_MODE_NON_LOCAL)))
 		goto tx_error_icmp;
 	if (rt->rt_flags & RTCF_LOCAL) {
 		ip_rt_put(rt);
@@ -984,7 +992,9 @@ ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	EnterFunction(10);
 
 	if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip,
-				      RT_TOS(iph->tos), 1|2)))
+				      RT_TOS(iph->tos),
+				      IP_VS_RT_MODE_LOCAL |
+					IP_VS_RT_MODE_NON_LOCAL)))
 		goto tx_error_icmp;
 	if (rt->rt_flags & RTCF_LOCAL) {
 		ip_rt_put(rt);
@@ -1128,7 +1138,10 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	 */
 
 	if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip,
-				      RT_TOS(ip_hdr(skb)->tos), 1|2|4)))
+				      RT_TOS(ip_hdr(skb)->tos),
+				      IP_VS_RT_MODE_LOCAL |
+					IP_VS_RT_MODE_NON_LOCAL |
+					IP_VS_RT_MODE_RDR)))
 		goto tx_error_icmp;
 	local = rt->rt_flags & RTCF_LOCAL;
 
-- 
1.7.2.3

[PATCH 3/3] ipvs: unify the formula to estimate the overhead of processing connections

[Simon Horman]

From: Changli Gao <xiaosuo@gmail.com>

lc and wlc use the same formula, but lblc and lblcr use another one. There
is no reason for using two different formulas for the lc variants.

The formula used by lc is used by all the lc variants in this patch.

Signed-off-by: Changli Gao <xiaosuo@gmail.com>
Acked-by: Wensong Zhang <wensong@linux-vs.org>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 include/net/ip_vs.h              |   14 ++++++++++++++
 net/netfilter/ipvs/ip_vs_lblc.c  |   13 +++----------
 net/netfilter/ipvs/ip_vs_lblcr.c |   25 +++++++------------------
 net/netfilter/ipvs/ip_vs_lc.c    |   18 +-----------------
 net/netfilter/ipvs/ip_vs_wlc.c   |   20 ++------------------
 5 files changed, 27 insertions(+), 63 deletions(-)

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 17b01b2..e74da41e 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -1243,6 +1243,20 @@ static inline void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp)
 /* CONFIG_IP_VS_NFCT */
 #endif
 
+static inline unsigned int
+ip_vs_dest_conn_overhead(struct ip_vs_dest *dest)
+{
+	/*
+	 * We think the overhead of processing active connections is 256
+	 * times higher than that of inactive connections in average. (This
+	 * 256 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
+	 */
+	return (atomic_read(&dest->activeconns) << 8) +
+		atomic_read(&dest->inactconns);
+}
+
 #endif /* __KERNEL__ */
 
 #endif	/* _NET_IP_VS_H */
diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c
index 4a9c8cd..6bf7a80 100644
--- a/net/netfilter/ipvs/ip_vs_lblc.c
+++ b/net/netfilter/ipvs/ip_vs_lblc.c
@@ -389,12 +389,7 @@ __ip_vs_lblc_schedule(struct ip_vs_service *svc)
 	int loh, doh;
 
 	/*
-	 * We think the overhead of processing active connections is fifty
-	 * times higher than that of inactive connections in average. (This
-	 * fifty times might not be accurate, we will change it later.) We
-	 * use the following formula to estimate the overhead:
-	 *                dest->activeconns*50 + dest->inactconns
-	 * and the load:
+	 * We use the following formula to estimate the load:
 	 *                (dest overhead) / dest->weight
 	 *
 	 * Remember -- no floats in kernel mode!!!
@@ -410,8 +405,7 @@ __ip_vs_lblc_schedule(struct ip_vs_service *svc)
 			continue;
 		if (atomic_read(&dest->weight) > 0) {
 			least = dest;
-			loh = atomic_read(&least->activeconns) * 50
-				+ atomic_read(&least->inactconns);
+			loh = ip_vs_dest_conn_overhead(least);
 			goto nextstage;
 		}
 	}
@@ -425,8 +419,7 @@ __ip_vs_lblc_schedule(struct ip_vs_service *svc)
 		if (dest->flags & IP_VS_DEST_F_OVERLOAD)
 			continue;
 
-		doh = atomic_read(&dest->activeconns) * 50
-			+ atomic_read(&dest->inactconns);
+		doh = ip_vs_dest_conn_overhead(dest);
 		if (loh * atomic_read(&dest->weight) >
 		    doh * atomic_read(&least->weight)) {
 			least = dest;
diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c
index bd329b1..0063176 100644
--- a/net/netfilter/ipvs/ip_vs_lblcr.c
+++ b/net/netfilter/ipvs/ip_vs_lblcr.c
@@ -178,8 +178,7 @@ static inline struct ip_vs_dest *ip_vs_dest_set_min(struct ip_vs_dest_set *set)
 
 		if ((atomic_read(&least->weight) > 0)
 		    && (least->flags & IP_VS_DEST_F_AVAILABLE)) {
-			loh = atomic_read(&least->activeconns) * 50
-				+ atomic_read(&least->inactconns);
+			loh = ip_vs_dest_conn_overhead(least);
 			goto nextstage;
 		}
 	}
@@ -192,8 +191,7 @@ static inline struct ip_vs_dest *ip_vs_dest_set_min(struct ip_vs_dest_set *set)
 		if (dest->flags & IP_VS_DEST_F_OVERLOAD)
 			continue;
 
-		doh = atomic_read(&dest->activeconns) * 50
-			+ atomic_read(&dest->inactconns);
+		doh = ip_vs_dest_conn_overhead(dest);
 		if ((loh * atomic_read(&dest->weight) >
 		     doh * atomic_read(&least->weight))
 		    && (dest->flags & IP_VS_DEST_F_AVAILABLE)) {
@@ -228,8 +226,7 @@ static inline struct ip_vs_dest *ip_vs_dest_set_max(struct ip_vs_dest_set *set)
 	list_for_each_entry(e, &set->list, list) {
 		most = e->dest;
 		if (atomic_read(&most->weight) > 0) {
-			moh = atomic_read(&most->activeconns) * 50
-				+ atomic_read(&most->inactconns);
+			moh = ip_vs_dest_conn_overhead(most);
 			goto nextstage;
 		}
 	}
@@ -239,8 +236,7 @@ static inline struct ip_vs_dest *ip_vs_dest_set_max(struct ip_vs_dest_set *set)
   nextstage:
 	list_for_each_entry(e, &set->list, list) {
 		dest = e->dest;
-		doh = atomic_read(&dest->activeconns) * 50
-			+ atomic_read(&dest->inactconns);
+		doh = ip_vs_dest_conn_overhead(dest);
 		/* moh/mw < doh/dw ==> moh*dw < doh*mw, where mw,dw>0 */
 		if ((moh * atomic_read(&dest->weight) <
 		     doh * atomic_read(&most->weight))
@@ -563,12 +559,7 @@ __ip_vs_lblcr_schedule(struct ip_vs_service *svc)
 	int loh, doh;
 
 	/*
-	 * We think the overhead of processing active connections is fifty
-	 * times higher than that of inactive connections in average. (This
-	 * fifty times might not be accurate, we will change it later.) We
-	 * use the following formula to estimate the overhead:
-	 *                dest->activeconns*50 + dest->inactconns
-	 * and the load:
+	 * We use the following formula to estimate the load:
 	 *                (dest overhead) / dest->weight
 	 *
 	 * Remember -- no floats in kernel mode!!!
@@ -585,8 +576,7 @@ __ip_vs_lblcr_schedule(struct ip_vs_service *svc)
 
 		if (atomic_read(&dest->weight) > 0) {
 			least = dest;
-			loh = atomic_read(&least->activeconns) * 50
-				+ atomic_read(&least->inactconns);
+			loh = ip_vs_dest_conn_overhead(least);
 			goto nextstage;
 		}
 	}
@@ -600,8 +590,7 @@ __ip_vs_lblcr_schedule(struct ip_vs_service *svc)
 		if (dest->flags & IP_VS_DEST_F_OVERLOAD)
 			continue;
 
-		doh = atomic_read(&dest->activeconns) * 50
-			+ atomic_read(&dest->inactconns);
+		doh = ip_vs_dest_conn_overhead(dest);
 		if (loh * atomic_read(&dest->weight) >
 		    doh * atomic_read(&least->weight)) {
 			least = dest;
diff --git a/net/netfilter/ipvs/ip_vs_lc.c b/net/netfilter/ipvs/ip_vs_lc.c
index 6063800..f391819 100644
--- a/net/netfilter/ipvs/ip_vs_lc.c
+++ b/net/netfilter/ipvs/ip_vs_lc.c
@@ -22,22 +22,6 @@
 
 #include <net/ip_vs.h>
 
-
-static inline unsigned int
-ip_vs_lc_dest_overhead(struct ip_vs_dest *dest)
-{
-	/*
-	 * We think the overhead of processing active connections is 256
-	 * times higher than that of inactive connections in average. (This
-	 * 256 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
-	 */
-	return (atomic_read(&dest->activeconns) << 8) +
-		atomic_read(&dest->inactconns);
-}
-
-
 /*
  *	Least Connection scheduling
  */
@@ -62,7 +46,7 @@ ip_vs_lc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
 		if ((dest->flags & IP_VS_DEST_F_OVERLOAD) ||
 		    atomic_read(&dest->weight) == 0)
 			continue;
-		doh = ip_vs_lc_dest_overhead(dest);
+		doh = ip_vs_dest_conn_overhead(dest);
 		if (!least || doh < loh) {
 			least = dest;
 			loh = doh;
diff --git a/net/netfilter/ipvs/ip_vs_wlc.c b/net/netfilter/ipvs/ip_vs_wlc.c
index fdf0f58..bc1bfc4 100644
--- a/net/netfilter/ipvs/ip_vs_wlc.c
+++ b/net/netfilter/ipvs/ip_vs_wlc.c
@@ -27,22 +27,6 @@
 
 #include <net/ip_vs.h>
 
-
-static inline unsigned int
-ip_vs_wlc_dest_overhead(struct ip_vs_dest *dest)
-{
-	/*
-	 * We think the overhead of processing active connections is 256
-	 * times higher than that of inactive connections in average. (This
-	 * 256 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
-	 */
-	return (atomic_read(&dest->activeconns) << 8) +
-		atomic_read(&dest->inactconns);
-}
-
-
 /*
  *	Weighted Least Connection scheduling
  */
@@ -71,7 +55,7 @@ ip_vs_wlc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
 		if (!(dest->flags & IP_VS_DEST_F_OVERLOAD) &&
 		    atomic_read(&dest->weight) > 0) {
 			least = dest;
-			loh = ip_vs_wlc_dest_overhead(least);
+			loh = ip_vs_dest_conn_overhead(least);
 			goto nextstage;
 		}
 	}
@@ -85,7 +69,7 @@ ip_vs_wlc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
 	list_for_each_entry_continue(dest, &svc->destinations, n_list) {
 		if (dest->flags & IP_VS_DEST_F_OVERLOAD)
 			continue;
-		doh = ip_vs_wlc_dest_overhead(dest);
+		doh = ip_vs_dest_conn_overhead(dest);
 		if (loh * atomic_read(&dest->weight) >
 		    doh * atomic_read(&least->weight)) {
 			least = dest;
-- 
1.7.2.3

Re: [GIT PULL nf-next-2.6] IPVS

[Patrick McHardy]

On 25.02.2011 03:43, Simon Horman wrote:
> Hi Patrick,
> 
> please consider pulling
> git://git.kernel.org/pub/scm/linux/kernel/git/horms/lvs-test-2.6.git master
> go get the following changes by Changli.
> 
>       ipvs: use hlist instead of list
>       ipvs: use enum to instead of magic numbers
>       ipvs: unify the formula to estimate the overhead of processing connections

Pulled, thanks Simon.