Commit db2bf247 authored by David S. Miller's avatar David S. Miller

Merge branch 'lvs-next-2.6' of git://git.kernel.org/pub/scm/linux/kernel/git/horms/lvs-2.6

Conflicts:

	net/netfilter/Kconfig
parents 02015180 a5e8546a
...@@ -630,5 +630,3 @@ config TCP_MD5SIG ...@@ -630,5 +630,3 @@ config TCP_MD5SIG
If unsure, say N. If unsure, say N.
source "net/ipv4/ipvs/Kconfig"
...@@ -33,7 +33,6 @@ obj-$(CONFIG_INET_XFRM_MODE_TRANSPORT) += xfrm4_mode_transport.o ...@@ -33,7 +33,6 @@ obj-$(CONFIG_INET_XFRM_MODE_TRANSPORT) += xfrm4_mode_transport.o
obj-$(CONFIG_INET_XFRM_MODE_TUNNEL) += xfrm4_mode_tunnel.o obj-$(CONFIG_INET_XFRM_MODE_TUNNEL) += xfrm4_mode_tunnel.o
obj-$(CONFIG_IP_PNP) += ipconfig.o obj-$(CONFIG_IP_PNP) += ipconfig.o
obj-$(CONFIG_NETFILTER) += netfilter.o netfilter/ obj-$(CONFIG_NETFILTER) += netfilter.o netfilter/
obj-$(CONFIG_IP_VS) += ipvs/
obj-$(CONFIG_INET_DIAG) += inet_diag.o obj-$(CONFIG_INET_DIAG) += inet_diag.o
obj-$(CONFIG_INET_TCP_DIAG) += tcp_diag.o obj-$(CONFIG_INET_TCP_DIAG) += tcp_diag.o
obj-$(CONFIG_NET_TCPPROBE) += tcp_probe.o obj-$(CONFIG_NET_TCPPROBE) += tcp_probe.o
......
...@@ -858,3 +858,5 @@ config NETFILTER_XT_MATCH_U32 ...@@ -858,3 +858,5 @@ config NETFILTER_XT_MATCH_U32
endif # NETFILTER_XTABLES endif # NETFILTER_XTABLES
endmenu endmenu
source "net/netfilter/ipvs/Kconfig"
...@@ -89,3 +89,6 @@ obj-$(CONFIG_NETFILTER_XT_MATCH_STRING) += xt_string.o ...@@ -89,3 +89,6 @@ obj-$(CONFIG_NETFILTER_XT_MATCH_STRING) += xt_string.o
obj-$(CONFIG_NETFILTER_XT_MATCH_TCPMSS) += xt_tcpmss.o obj-$(CONFIG_NETFILTER_XT_MATCH_TCPMSS) += xt_tcpmss.o
obj-$(CONFIG_NETFILTER_XT_MATCH_TIME) += xt_time.o obj-$(CONFIG_NETFILTER_XT_MATCH_TIME) += xt_time.o
obj-$(CONFIG_NETFILTER_XT_MATCH_U32) += xt_u32.o obj-$(CONFIG_NETFILTER_XT_MATCH_U32) += xt_u32.o
# IPVS
obj-$(CONFIG_IP_VS) += ipvs/
...@@ -1330,7 +1330,9 @@ ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u) ...@@ -1330,7 +1330,9 @@ ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u)
out_unlock: out_unlock:
write_unlock_bh(&__ip_vs_svc_lock); write_unlock_bh(&__ip_vs_svc_lock);
#ifdef CONFIG_IP_VS_IPV6
out: out:
#endif
if (old_sched) if (old_sched)
ip_vs_scheduler_put(old_sched); ip_vs_scheduler_put(old_sched);
......
/*
* IPVS: Destination Hashing scheduling module
*
* Authors: Wensong Zhang <wensong@gnuchina.org>
*
* Inspired by the consistent hashing scheduler patch from
* Thomas Proell <proellt@gmx.de>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*
* Changes:
*
*/
/*
* The dh algorithm is to select server by the hash key of destination IP
* address. The pseudo code is as follows:
*
* n <- servernode[dest_ip];
* if (n is dead) OR
* (n is overloaded) OR (n.weight <= 0) then
* return NULL;
*
* return n;
*
* Notes that servernode is a 256-bucket hash table that maps the hash
* index derived from packet destination IP address to the current server
* array. If the dh scheduler is used in cache cluster, it is good to
* combine it with cache_bypass feature. When the statically assigned
* server is dead or overloaded, the load balancer can bypass the cache
* server and send requests to the original server directly.
*
*/
#include <linux/ip.h>
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/skbuff.h>
#include <net/ip_vs.h>
/*
* IPVS DH bucket
*/
struct ip_vs_dh_bucket {
struct ip_vs_dest *dest; /* real server (cache) */
};
/*
* for IPVS DH entry hash table
*/
#ifndef CONFIG_IP_VS_DH_TAB_BITS
#define CONFIG_IP_VS_DH_TAB_BITS 8
#endif
#define IP_VS_DH_TAB_BITS CONFIG_IP_VS_DH_TAB_BITS
#define IP_VS_DH_TAB_SIZE (1 << IP_VS_DH_TAB_BITS)
#define IP_VS_DH_TAB_MASK (IP_VS_DH_TAB_SIZE - 1)
/*
* Returns hash value for IPVS DH entry
*/
static inline unsigned ip_vs_dh_hashkey(__be32 addr)
{
return (ntohl(addr)*2654435761UL) & IP_VS_DH_TAB_MASK;
}
/*
* Get ip_vs_dest associated with supplied parameters.
*/
static inline struct ip_vs_dest *
ip_vs_dh_get(struct ip_vs_dh_bucket *tbl, __be32 addr)
{
return (tbl[ip_vs_dh_hashkey(addr)]).dest;
}
/*
* Assign all the hash buckets of the specified table with the service.
*/
static int
ip_vs_dh_assign(struct ip_vs_dh_bucket *tbl, struct ip_vs_service *svc)
{
int i;
struct ip_vs_dh_bucket *b;
struct list_head *p;
struct ip_vs_dest *dest;
b = tbl;
p = &svc->destinations;
for (i=0; i<IP_VS_DH_TAB_SIZE; i++) {
if (list_empty(p)) {
b->dest = NULL;
} else {
if (p == &svc->destinations)
p = p->next;
dest = list_entry(p, struct ip_vs_dest, n_list);
atomic_inc(&dest->refcnt);
b->dest = dest;
p = p->next;
}
b++;
}
return 0;
}
/*
* Flush all the hash buckets of the specified table.
*/
static void ip_vs_dh_flush(struct ip_vs_dh_bucket *tbl)
{
int i;
struct ip_vs_dh_bucket *b;
b = tbl;
for (i=0; i<IP_VS_DH_TAB_SIZE; i++) {
if (b->dest) {
atomic_dec(&b->dest->refcnt);
b->dest = NULL;
}
b++;
}
}
static int ip_vs_dh_init_svc(struct ip_vs_service *svc)
{
struct ip_vs_dh_bucket *tbl;
/* allocate the DH table for this service */
tbl = kmalloc(sizeof(struct ip_vs_dh_bucket)*IP_VS_DH_TAB_SIZE,
GFP_ATOMIC);
if (tbl == NULL) {
IP_VS_ERR("ip_vs_dh_init_svc(): no memory\n");
return -ENOMEM;
}
svc->sched_data = tbl;
IP_VS_DBG(6, "DH hash table (memory=%Zdbytes) allocated for "
"current service\n",
sizeof(struct ip_vs_dh_bucket)*IP_VS_DH_TAB_SIZE);
/* assign the hash buckets with the updated service */
ip_vs_dh_assign(tbl, svc);
return 0;
}
static int ip_vs_dh_done_svc(struct ip_vs_service *svc)
{
struct ip_vs_dh_bucket *tbl = svc->sched_data;
/* got to clean up hash buckets here */
ip_vs_dh_flush(tbl);
/* release the table itself */
kfree(svc->sched_data);
IP_VS_DBG(6, "DH hash table (memory=%Zdbytes) released\n",
sizeof(struct ip_vs_dh_bucket)*IP_VS_DH_TAB_SIZE);
return 0;
}
static int ip_vs_dh_update_svc(struct ip_vs_service *svc)
{
struct ip_vs_dh_bucket *tbl = svc->sched_data;
/* got to clean up hash buckets here */
ip_vs_dh_flush(tbl);
/* assign the hash buckets with the updated service */
ip_vs_dh_assign(tbl, svc);
return 0;
}
/*
* If the dest flags is set with IP_VS_DEST_F_OVERLOAD,
* consider that the server is overloaded here.
*/
static inline int is_overloaded(struct ip_vs_dest *dest)
{
return dest->flags & IP_VS_DEST_F_OVERLOAD;
}
/*
* Destination hashing scheduling
*/
static struct ip_vs_dest *
ip_vs_dh_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
{
struct ip_vs_dest *dest;
struct ip_vs_dh_bucket *tbl;
struct iphdr *iph = ip_hdr(skb);
IP_VS_DBG(6, "ip_vs_dh_schedule(): Scheduling...\n");
tbl = (struct ip_vs_dh_bucket *)svc->sched_data;
dest = ip_vs_dh_get(tbl, iph->daddr);
if (!dest
|| !(dest->flags & IP_VS_DEST_F_AVAILABLE)
|| atomic_read(&dest->weight) <= 0
|| is_overloaded(dest)) {
return NULL;
}
IP_VS_DBG(6, "DH: destination IP address %u.%u.%u.%u "
"--> server %u.%u.%u.%u:%d\n",
NIPQUAD(iph->daddr),
NIPQUAD(dest->addr.ip),
ntohs(dest->port));
return dest;
}
/*
* IPVS DH Scheduler structure
*/
static struct ip_vs_scheduler ip_vs_dh_scheduler =
{
.name = "dh",
.refcnt = ATOMIC_INIT(0),
.module = THIS_MODULE,
.n_list = LIST_HEAD_INIT(ip_vs_dh_scheduler.n_list),
#ifdef CONFIG_IP_VS_IPV6
.supports_ipv6 = 0,
#endif
.init_service = ip_vs_dh_init_svc,
.done_service = ip_vs_dh_done_svc,
.update_service = ip_vs_dh_update_svc,
.schedule = ip_vs_dh_schedule,
};
static int __init ip_vs_dh_init(void)
{
return register_ip_vs_scheduler(&ip_vs_dh_scheduler);
}
static void __exit ip_vs_dh_cleanup(void)
{
unregister_ip_vs_scheduler(&ip_vs_dh_scheduler);
}
module_init(ip_vs_dh_init);
module_exit(ip_vs_dh_cleanup);
MODULE_LICENSE("GPL");
...@@ -30,6 +30,7 @@ ...@@ -30,6 +30,7 @@
#include <linux/err.h> #include <linux/err.h>
#include <linux/kthread.h> #include <linux/kthread.h>
#include <linux/wait.h> #include <linux/wait.h>
#include <linux/kernel.h>
#include <net/ip.h> #include <net/ip.h>
#include <net/sock.h> #include <net/sock.h>
...@@ -99,6 +100,7 @@ struct ip_vs_sync_thread_data { ...@@ -99,6 +100,7 @@ struct ip_vs_sync_thread_data {
*/ */
#define SYNC_MESG_HEADER_LEN 4 #define SYNC_MESG_HEADER_LEN 4
#define MAX_CONNS_PER_SYNCBUFF 255 /* nr_conns in ip_vs_sync_mesg is 8 bit */
struct ip_vs_sync_mesg { struct ip_vs_sync_mesg {
__u8 nr_conns; __u8 nr_conns;
...@@ -516,8 +518,8 @@ static int set_sync_mesg_maxlen(int sync_state) ...@@ -516,8 +518,8 @@ static int set_sync_mesg_maxlen(int sync_state)
num = (dev->mtu - sizeof(struct iphdr) - num = (dev->mtu - sizeof(struct iphdr) -
sizeof(struct udphdr) - sizeof(struct udphdr) -
SYNC_MESG_HEADER_LEN - 20) / SIMPLE_CONN_SIZE; SYNC_MESG_HEADER_LEN - 20) / SIMPLE_CONN_SIZE;
sync_send_mesg_maxlen = sync_send_mesg_maxlen = SYNC_MESG_HEADER_LEN +
SYNC_MESG_HEADER_LEN + SIMPLE_CONN_SIZE * num; SIMPLE_CONN_SIZE * min(num, MAX_CONNS_PER_SYNCBUFF);
IP_VS_DBG(7, "setting the maximum length of sync sending " IP_VS_DBG(7, "setting the maximum length of sync sending "
"message %d.\n", sync_send_mesg_maxlen); "message %d.\n", sync_send_mesg_maxlen);
} else if (sync_state == IP_VS_STATE_BACKUP) { } else if (sync_state == IP_VS_STATE_BACKUP) {
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment