summaryrefslogtreecommitdiffstats
path: root/net/ipv4/ipvs/ip_vs_dh.c
blob: f3bc320dce93a66e5902f4032d2ee05cf2a1f41f (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
/*
 * IPVS:        Destination Hashing scheduling module
 *
 * Version:     $Id: ip_vs_dh.c,v 1.5 2002/09/15 08:14:08 wensong Exp $
 *
 * 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/module.h>
#include <linux/kernel.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(__u32 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, __u32 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 = skb->nh.iph;

	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),
		  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,
	.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)
{
	INIT_LIST_HEAD(&ip_vs_dh_scheduler.n_list);
	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");
OpenPOWER on IntegriCloud