summaryrefslogtreecommitdiffstats
path: root/fs/ocfs2/heartbeat.c
blob: c4c36171240d0555d5db10d0edb341c2a52627c9 (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
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
/* -*- mode: c; c-basic-offset: 8; -*-
 * vim: noexpandtab sw=8 ts=8 sts=0:
 *
 * heartbeat.c
 *
 * Register ourselves with the heartbaet service, keep our node maps
 * up to date, and fire off recovery when needed.
 *
 * Copyright (C) 2002, 2004 Oracle.  All rights reserved.
 *
 * 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.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * General Public License for more details.
 *
 * You should have received a copy of the GNU General Public
 * License along with this program; if not, write to the
 * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
 * Boston, MA 021110-1307, USA.
 */

#include <linux/fs.h>
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/highmem.h>
#include <linux/kmod.h>

#include <cluster/heartbeat.h>
#include <cluster/nodemanager.h>

#include <dlm/dlmapi.h>

#define MLOG_MASK_PREFIX ML_SUPER
#include <cluster/masklog.h>

#include "ocfs2.h"

#include "alloc.h"
#include "heartbeat.h"
#include "inode.h"
#include "journal.h"
#include "vote.h"

#include "buffer_head_io.h"

#define OCFS2_HB_NODE_DOWN_PRI     (0x0000002)
#define OCFS2_HB_NODE_UP_PRI	   OCFS2_HB_NODE_DOWN_PRI

static inline void __ocfs2_node_map_set_bit(struct ocfs2_node_map *map,
					    int bit);
static inline void __ocfs2_node_map_clear_bit(struct ocfs2_node_map *map,
					      int bit);
static inline int __ocfs2_node_map_is_empty(struct ocfs2_node_map *map);
static void __ocfs2_node_map_dup(struct ocfs2_node_map *target,
				 struct ocfs2_node_map *from);
static void __ocfs2_node_map_set(struct ocfs2_node_map *target,
				 struct ocfs2_node_map *from);

void ocfs2_init_node_maps(struct ocfs2_super *osb)
{
	spin_lock_init(&osb->node_map_lock);
	ocfs2_node_map_init(&osb->mounted_map);
	ocfs2_node_map_init(&osb->recovery_map);
	ocfs2_node_map_init(&osb->umount_map);
	ocfs2_node_map_init(&osb->osb_recovering_orphan_dirs);
}

static void ocfs2_do_node_down(int node_num,
			       struct ocfs2_super *osb)
{
	BUG_ON(osb->node_num == node_num);

	mlog(0, "ocfs2: node down event for %d\n", node_num);

	if (!osb->dlm) {
		/*
		 * No DLM means we're not even ready to participate yet.
		 * We check the slots after the DLM comes up, so we will
		 * notice the node death then.  We can safely ignore it
		 * here.
		 */
		return;
	}

	if (ocfs2_node_map_test_bit(osb, &osb->umount_map, node_num)) {
		/* If a node is in the umount map, then we've been
		 * expecting him to go down and we know ahead of time
		 * that recovery is not necessary. */
		ocfs2_node_map_clear_bit(osb, &osb->umount_map, node_num);
		return;
	}

	ocfs2_recovery_thread(osb, node_num);

	ocfs2_remove_node_from_vote_queues(osb, node_num);
}

static void ocfs2_hb_node_down_cb(struct o2nm_node *node,
				  int node_num,
				  void *data)
{
	ocfs2_do_node_down(node_num, (struct ocfs2_super *) data);
}

/* Called from the dlm when it's about to evict a node. We may also
 * get a heartbeat callback later. */
static void ocfs2_dlm_eviction_cb(int node_num,
				  void *data)
{
	struct ocfs2_super *osb = (struct ocfs2_super *) data;
	struct super_block *sb = osb->sb;

	mlog(ML_NOTICE, "device (%u,%u): dlm has evicted node %d\n",
	     MAJOR(sb->s_dev), MINOR(sb->s_dev), node_num);

	ocfs2_do_node_down(node_num, osb);
}

static void ocfs2_hb_node_up_cb(struct o2nm_node *node,
				int node_num,
				void *data)
{
	struct ocfs2_super *osb = data;

	BUG_ON(osb->node_num == node_num);

	mlog(0, "node up event for %d\n", node_num);
	ocfs2_node_map_clear_bit(osb, &osb->umount_map, node_num);
}

void ocfs2_setup_hb_callbacks(struct ocfs2_super *osb)
{
	o2hb_setup_callback(&osb->osb_hb_down, O2HB_NODE_DOWN_CB,
			    ocfs2_hb_node_down_cb, osb,
			    OCFS2_HB_NODE_DOWN_PRI);

	o2hb_setup_callback(&osb->osb_hb_up, O2HB_NODE_UP_CB,
			    ocfs2_hb_node_up_cb, osb, OCFS2_HB_NODE_UP_PRI);

	/* Not exactly a heartbeat callback, but leads to essentially
	 * the same path so we set it up here. */
	dlm_setup_eviction_cb(&osb->osb_eviction_cb,
			      ocfs2_dlm_eviction_cb,
			      osb);
}

/* Most functions here are just stubs for now... */
int ocfs2_register_hb_callbacks(struct ocfs2_super *osb)
{
	int status;

	if (ocfs2_mount_local(osb))
		return 0;

	status = o2hb_register_callback(osb->uuid_str, &osb->osb_hb_down);
	if (status < 0) {
		mlog_errno(status);
		goto bail;
	}

	status = o2hb_register_callback(osb->uuid_str, &osb->osb_hb_up);
	if (status < 0) {
		mlog_errno(status);
		o2hb_unregister_callback(osb->uuid_str, &osb->osb_hb_down);
	}

bail:
	return status;
}

void ocfs2_clear_hb_callbacks(struct ocfs2_super *osb)
{
	if (ocfs2_mount_local(osb))
		return;

	o2hb_unregister_callback(osb->uuid_str, &osb->osb_hb_down);
	o2hb_unregister_callback(osb->uuid_str, &osb->osb_hb_up);
}

void ocfs2_stop_heartbeat(struct ocfs2_super *osb)
{
	int ret;
	char *argv[5], *envp[3];

	if (ocfs2_mount_local(osb))
		return;

	if (!osb->uuid_str) {
		/* This can happen if we don't get far enough in mount... */
		mlog(0, "No UUID with which to stop heartbeat!\n\n");
		return;
	}

	argv[0] = (char *)o2nm_get_hb_ctl_path();
	argv[1] = "-K";
	argv[2] = "-u";
	argv[3] = osb->uuid_str;
	argv[4] = NULL;

	mlog(0, "Run: %s %s %s %s\n", argv[0], argv[1], argv[2], argv[3]);

	/* minimal command environment taken from cpu_run_sbin_hotplug */
	envp[0] = "HOME=/";
	envp[1] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin";
	envp[2] = NULL;

	ret = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_PROC);
	if (ret < 0)
		mlog_errno(ret);
}

/* special case -1 for now
 * TODO: should *really* make sure the calling func never passes -1!!  */
void ocfs2_node_map_init(struct ocfs2_node_map *map)
{
	map->num_nodes = OCFS2_NODE_MAP_MAX_NODES;
	memset(map->map, 0, BITS_TO_LONGS(OCFS2_NODE_MAP_MAX_NODES) *
	       sizeof(unsigned long));
}

static inline void __ocfs2_node_map_set_bit(struct ocfs2_node_map *map,
					    int bit)
{
	set_bit(bit, map->map);
}

void ocfs2_node_map_set_bit(struct ocfs2_super *osb,
			    struct ocfs2_node_map *map,
			    int bit)
{
	if (bit==-1)
		return;
	BUG_ON(bit >= map->num_nodes);
	spin_lock(&osb->node_map_lock);
	__ocfs2_node_map_set_bit(map, bit);
	spin_unlock(&osb->node_map_lock);
}

static inline void __ocfs2_node_map_clear_bit(struct ocfs2_node_map *map,
					      int bit)
{
	clear_bit(bit, map->map);
}

void ocfs2_node_map_clear_bit(struct ocfs2_super *osb,
			      struct ocfs2_node_map *map,
			      int bit)
{
	if (bit==-1)
		return;
	BUG_ON(bit >= map->num_nodes);
	spin_lock(&osb->node_map_lock);
	__ocfs2_node_map_clear_bit(map, bit);
	spin_unlock(&osb->node_map_lock);
}

int ocfs2_node_map_test_bit(struct ocfs2_super *osb,
			    struct ocfs2_node_map *map,
			    int bit)
{
	int ret;
	if (bit >= map->num_nodes) {
		mlog(ML_ERROR, "bit=%d map->num_nodes=%d\n", bit, map->num_nodes);
		BUG();
	}
	spin_lock(&osb->node_map_lock);
	ret = test_bit(bit, map->map);
	spin_unlock(&osb->node_map_lock);
	return ret;
}

static inline int __ocfs2_node_map_is_empty(struct ocfs2_node_map *map)
{
	int bit;
	bit = find_next_bit(map->map, map->num_nodes, 0);
	if (bit < map->num_nodes)
		return 0;
	return 1;
}

int ocfs2_node_map_is_empty(struct ocfs2_super *osb,
			    struct ocfs2_node_map *map)
{
	int ret;
	BUG_ON(map->num_nodes == 0);
	spin_lock(&osb->node_map_lock);
	ret = __ocfs2_node_map_is_empty(map);
	spin_unlock(&osb->node_map_lock);
	return ret;
}

static void __ocfs2_node_map_dup(struct ocfs2_node_map *target,
				 struct ocfs2_node_map *from)
{
	BUG_ON(from->num_nodes == 0);
	ocfs2_node_map_init(target);
	__ocfs2_node_map_set(target, from);
}

/* returns 1 if bit is the only bit set in target, 0 otherwise */
int ocfs2_node_map_is_only(struct ocfs2_super *osb,
			   struct ocfs2_node_map *target,
			   int bit)
{
	struct ocfs2_node_map temp;
	int ret;

	spin_lock(&osb->node_map_lock);
	__ocfs2_node_map_dup(&temp, target);
	__ocfs2_node_map_clear_bit(&temp, bit);
	ret = __ocfs2_node_map_is_empty(&temp);
	spin_unlock(&osb->node_map_lock);

	return ret;
}

static void __ocfs2_node_map_set(struct ocfs2_node_map *target,
				 struct ocfs2_node_map *from)
{
	int num_longs, i;

	BUG_ON(target->num_nodes != from->num_nodes);
	BUG_ON(target->num_nodes == 0);

	num_longs = BITS_TO_LONGS(target->num_nodes);
	for (i = 0; i < num_longs; i++)
		target->map[i] = from->map[i];
}

/* Returns whether the recovery bit was actually set - it may not be
 * if a node is still marked as needing recovery */
int ocfs2_recovery_map_set(struct ocfs2_super *osb,
			   int num)
{
	int set = 0;

	spin_lock(&osb->node_map_lock);

	__ocfs2_node_map_clear_bit(&osb->mounted_map, num);

	if (!test_bit(num, osb->recovery_map.map)) {
	    __ocfs2_node_map_set_bit(&osb->recovery_map, num);
	    set = 1;
	}

	spin_unlock(&osb->node_map_lock);

	return set;
}

void ocfs2_recovery_map_clear(struct ocfs2_super *osb,
			      int num)
{
	ocfs2_node_map_clear_bit(osb, &osb->recovery_map, num);
}

int ocfs2_node_map_iterate(struct ocfs2_super *osb,
			   struct ocfs2_node_map *map,
			   int idx)
{
	int i = idx;

	idx = O2NM_INVALID_NODE_NUM;
	spin_lock(&osb->node_map_lock);
	if ((i != O2NM_INVALID_NODE_NUM) &&
	    (i >= 0) &&
	    (i < map->num_nodes)) {
		while(i < map->num_nodes) {
			if (test_bit(i, map->map)) {
				idx = i;
				break;
			}
			i++;
		}
	}
	spin_unlock(&osb->node_map_lock);
	return idx;
}