| Mark Fasheh | ccd979b | 2005-12-15 14:31:24 -0800 | [diff] [blame] | 1 | /* -*- mode: c; c-basic-offset: 8; -*- | 
 | 2 |  * vim: noexpandtab sw=8 ts=8 sts=0: | 
 | 3 |  * | 
 | 4 |  * heartbeat.c | 
 | 5 |  * | 
 | 6 |  * Register ourselves with the heartbaet service, keep our node maps | 
 | 7 |  * up to date, and fire off recovery when needed. | 
 | 8 |  * | 
 | 9 |  * Copyright (C) 2002, 2004 Oracle.  All rights reserved. | 
 | 10 |  * | 
 | 11 |  * This program is free software; you can redistribute it and/or | 
 | 12 |  * modify it under the terms of the GNU General Public | 
 | 13 |  * License as published by the Free Software Foundation; either | 
 | 14 |  * version 2 of the License, or (at your option) any later version. | 
 | 15 |  * | 
 | 16 |  * This program is distributed in the hope that it will be useful, | 
 | 17 |  * but WITHOUT ANY WARRANTY; without even the implied warranty of | 
 | 18 |  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU | 
 | 19 |  * General Public License for more details. | 
 | 20 |  * | 
 | 21 |  * You should have received a copy of the GNU General Public | 
 | 22 |  * License along with this program; if not, write to the | 
 | 23 |  * Free Software Foundation, Inc., 59 Temple Place - Suite 330, | 
 | 24 |  * Boston, MA 021110-1307, USA. | 
 | 25 |  */ | 
 | 26 |  | 
 | 27 | #include <linux/fs.h> | 
 | 28 | #include <linux/types.h> | 
 | 29 | #include <linux/slab.h> | 
 | 30 | #include <linux/highmem.h> | 
 | 31 | #include <linux/kmod.h> | 
 | 32 |  | 
 | 33 | #include <cluster/heartbeat.h> | 
 | 34 | #include <cluster/nodemanager.h> | 
 | 35 |  | 
 | 36 | #include <dlm/dlmapi.h> | 
 | 37 |  | 
 | 38 | #define MLOG_MASK_PREFIX ML_SUPER | 
 | 39 | #include <cluster/masklog.h> | 
 | 40 |  | 
 | 41 | #include "ocfs2.h" | 
 | 42 |  | 
 | 43 | #include "alloc.h" | 
 | 44 | #include "heartbeat.h" | 
 | 45 | #include "inode.h" | 
 | 46 | #include "journal.h" | 
 | 47 | #include "vote.h" | 
 | 48 |  | 
 | 49 | #include "buffer_head_io.h" | 
 | 50 |  | 
 | 51 | #define OCFS2_HB_NODE_DOWN_PRI     (0x0000002) | 
 | 52 | #define OCFS2_HB_NODE_UP_PRI	   OCFS2_HB_NODE_DOWN_PRI | 
 | 53 |  | 
 | 54 | static inline void __ocfs2_node_map_set_bit(struct ocfs2_node_map *map, | 
 | 55 | 					    int bit); | 
 | 56 | static inline void __ocfs2_node_map_clear_bit(struct ocfs2_node_map *map, | 
 | 57 | 					      int bit); | 
 | 58 | static inline int __ocfs2_node_map_is_empty(struct ocfs2_node_map *map); | 
 | 59 | static void __ocfs2_node_map_dup(struct ocfs2_node_map *target, | 
 | 60 | 				 struct ocfs2_node_map *from); | 
 | 61 | static void __ocfs2_node_map_set(struct ocfs2_node_map *target, | 
 | 62 | 				 struct ocfs2_node_map *from); | 
 | 63 |  | 
 | 64 | void ocfs2_init_node_maps(struct ocfs2_super *osb) | 
 | 65 | { | 
 | 66 | 	spin_lock_init(&osb->node_map_lock); | 
 | 67 | 	ocfs2_node_map_init(&osb->mounted_map); | 
 | 68 | 	ocfs2_node_map_init(&osb->recovery_map); | 
 | 69 | 	ocfs2_node_map_init(&osb->umount_map); | 
| Mark Fasheh | b4df6ed | 2006-02-22 17:35:08 -0800 | [diff] [blame] | 70 | 	ocfs2_node_map_init(&osb->osb_recovering_orphan_dirs); | 
| Mark Fasheh | ccd979b | 2005-12-15 14:31:24 -0800 | [diff] [blame] | 71 | } | 
 | 72 |  | 
 | 73 | static void ocfs2_do_node_down(int node_num, | 
 | 74 | 			       struct ocfs2_super *osb) | 
 | 75 | { | 
 | 76 | 	BUG_ON(osb->node_num == node_num); | 
 | 77 |  | 
 | 78 | 	mlog(0, "ocfs2: node down event for %d\n", node_num); | 
 | 79 |  | 
 | 80 | 	if (!osb->dlm) { | 
 | 81 | 		/* | 
 | 82 | 		 * No DLM means we're not even ready to participate yet. | 
 | 83 | 		 * We check the slots after the DLM comes up, so we will | 
 | 84 | 		 * notice the node death then.  We can safely ignore it | 
 | 85 | 		 * here. | 
 | 86 | 		 */ | 
 | 87 | 		return; | 
 | 88 | 	} | 
 | 89 |  | 
 | 90 | 	if (ocfs2_node_map_test_bit(osb, &osb->umount_map, node_num)) { | 
 | 91 | 		/* If a node is in the umount map, then we've been | 
 | 92 | 		 * expecting him to go down and we know ahead of time | 
 | 93 | 		 * that recovery is not necessary. */ | 
 | 94 | 		ocfs2_node_map_clear_bit(osb, &osb->umount_map, node_num); | 
 | 95 | 		return; | 
 | 96 | 	} | 
 | 97 |  | 
 | 98 | 	ocfs2_recovery_thread(osb, node_num); | 
 | 99 |  | 
 | 100 | 	ocfs2_remove_node_from_vote_queues(osb, node_num); | 
 | 101 | } | 
 | 102 |  | 
 | 103 | static void ocfs2_hb_node_down_cb(struct o2nm_node *node, | 
 | 104 | 				  int node_num, | 
 | 105 | 				  void *data) | 
 | 106 | { | 
 | 107 | 	ocfs2_do_node_down(node_num, (struct ocfs2_super *) data); | 
 | 108 | } | 
 | 109 |  | 
 | 110 | /* Called from the dlm when it's about to evict a node. We may also | 
 | 111 |  * get a heartbeat callback later. */ | 
 | 112 | static void ocfs2_dlm_eviction_cb(int node_num, | 
 | 113 | 				  void *data) | 
 | 114 | { | 
 | 115 | 	struct ocfs2_super *osb = (struct ocfs2_super *) data; | 
 | 116 | 	struct super_block *sb = osb->sb; | 
 | 117 |  | 
 | 118 | 	mlog(ML_NOTICE, "device (%u,%u): dlm has evicted node %d\n", | 
 | 119 | 	     MAJOR(sb->s_dev), MINOR(sb->s_dev), node_num); | 
 | 120 |  | 
 | 121 | 	ocfs2_do_node_down(node_num, osb); | 
 | 122 | } | 
 | 123 |  | 
 | 124 | static void ocfs2_hb_node_up_cb(struct o2nm_node *node, | 
 | 125 | 				int node_num, | 
 | 126 | 				void *data) | 
 | 127 | { | 
 | 128 | 	struct ocfs2_super *osb = data; | 
 | 129 |  | 
 | 130 | 	BUG_ON(osb->node_num == node_num); | 
 | 131 |  | 
 | 132 | 	mlog(0, "node up event for %d\n", node_num); | 
 | 133 | 	ocfs2_node_map_clear_bit(osb, &osb->umount_map, node_num); | 
 | 134 | } | 
 | 135 |  | 
 | 136 | void ocfs2_setup_hb_callbacks(struct ocfs2_super *osb) | 
 | 137 | { | 
 | 138 | 	o2hb_setup_callback(&osb->osb_hb_down, O2HB_NODE_DOWN_CB, | 
 | 139 | 			    ocfs2_hb_node_down_cb, osb, | 
 | 140 | 			    OCFS2_HB_NODE_DOWN_PRI); | 
 | 141 |  | 
 | 142 | 	o2hb_setup_callback(&osb->osb_hb_up, O2HB_NODE_UP_CB, | 
 | 143 | 			    ocfs2_hb_node_up_cb, osb, OCFS2_HB_NODE_UP_PRI); | 
 | 144 |  | 
 | 145 | 	/* Not exactly a heartbeat callback, but leads to essentially | 
 | 146 | 	 * the same path so we set it up here. */ | 
 | 147 | 	dlm_setup_eviction_cb(&osb->osb_eviction_cb, | 
 | 148 | 			      ocfs2_dlm_eviction_cb, | 
 | 149 | 			      osb); | 
 | 150 | } | 
 | 151 |  | 
 | 152 | /* Most functions here are just stubs for now... */ | 
 | 153 | int ocfs2_register_hb_callbacks(struct ocfs2_super *osb) | 
 | 154 | { | 
 | 155 | 	int status; | 
 | 156 |  | 
| Sunil Mushran | c271c5c | 2006-12-05 17:56:35 -0800 | [diff] [blame] | 157 | 	if (ocfs2_mount_local(osb)) | 
 | 158 | 		return 0; | 
 | 159 |  | 
| Mark Fasheh | ccd979b | 2005-12-15 14:31:24 -0800 | [diff] [blame] | 160 | 	status = o2hb_register_callback(&osb->osb_hb_down); | 
 | 161 | 	if (status < 0) { | 
 | 162 | 		mlog_errno(status); | 
 | 163 | 		goto bail; | 
 | 164 | 	} | 
 | 165 |  | 
 | 166 | 	status = o2hb_register_callback(&osb->osb_hb_up); | 
| Joel Becker | c24f72c | 2007-02-03 03:14:30 -0800 | [diff] [blame] | 167 | 	if (status < 0) { | 
| Mark Fasheh | ccd979b | 2005-12-15 14:31:24 -0800 | [diff] [blame] | 168 | 		mlog_errno(status); | 
| Joel Becker | c24f72c | 2007-02-03 03:14:30 -0800 | [diff] [blame] | 169 | 		o2hb_unregister_callback(&osb->osb_hb_down); | 
 | 170 | 	} | 
| Mark Fasheh | ccd979b | 2005-12-15 14:31:24 -0800 | [diff] [blame] | 171 |  | 
 | 172 | bail: | 
 | 173 | 	return status; | 
 | 174 | } | 
 | 175 |  | 
 | 176 | void ocfs2_clear_hb_callbacks(struct ocfs2_super *osb) | 
 | 177 | { | 
| Sunil Mushran | c271c5c | 2006-12-05 17:56:35 -0800 | [diff] [blame] | 178 | 	if (ocfs2_mount_local(osb)) | 
 | 179 | 		return; | 
 | 180 |  | 
| Joel Becker | c24f72c | 2007-02-03 03:14:30 -0800 | [diff] [blame] | 181 | 	o2hb_unregister_callback(&osb->osb_hb_down); | 
 | 182 | 	o2hb_unregister_callback(&osb->osb_hb_up); | 
| Mark Fasheh | ccd979b | 2005-12-15 14:31:24 -0800 | [diff] [blame] | 183 | } | 
 | 184 |  | 
 | 185 | void ocfs2_stop_heartbeat(struct ocfs2_super *osb) | 
 | 186 | { | 
 | 187 | 	int ret; | 
 | 188 | 	char *argv[5], *envp[3]; | 
 | 189 |  | 
| Sunil Mushran | c271c5c | 2006-12-05 17:56:35 -0800 | [diff] [blame] | 190 | 	if (ocfs2_mount_local(osb)) | 
 | 191 | 		return; | 
 | 192 |  | 
| Mark Fasheh | ccd979b | 2005-12-15 14:31:24 -0800 | [diff] [blame] | 193 | 	if (!osb->uuid_str) { | 
 | 194 | 		/* This can happen if we don't get far enough in mount... */ | 
 | 195 | 		mlog(0, "No UUID with which to stop heartbeat!\n\n"); | 
 | 196 | 		return; | 
 | 197 | 	} | 
 | 198 |  | 
 | 199 | 	argv[0] = (char *)o2nm_get_hb_ctl_path(); | 
 | 200 | 	argv[1] = "-K"; | 
 | 201 | 	argv[2] = "-u"; | 
 | 202 | 	argv[3] = osb->uuid_str; | 
 | 203 | 	argv[4] = NULL; | 
 | 204 |  | 
 | 205 | 	mlog(0, "Run: %s %s %s %s\n", argv[0], argv[1], argv[2], argv[3]); | 
 | 206 |  | 
 | 207 | 	/* minimal command environment taken from cpu_run_sbin_hotplug */ | 
 | 208 | 	envp[0] = "HOME=/"; | 
 | 209 | 	envp[1] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin"; | 
 | 210 | 	envp[2] = NULL; | 
 | 211 |  | 
 | 212 | 	ret = call_usermodehelper(argv[0], argv, envp, 1); | 
 | 213 | 	if (ret < 0) | 
 | 214 | 		mlog_errno(ret); | 
 | 215 | } | 
 | 216 |  | 
 | 217 | /* special case -1 for now | 
 | 218 |  * TODO: should *really* make sure the calling func never passes -1!!  */ | 
 | 219 | void ocfs2_node_map_init(struct ocfs2_node_map *map) | 
 | 220 | { | 
 | 221 | 	map->num_nodes = OCFS2_NODE_MAP_MAX_NODES; | 
 | 222 | 	memset(map->map, 0, BITS_TO_LONGS(OCFS2_NODE_MAP_MAX_NODES) * | 
 | 223 | 	       sizeof(unsigned long)); | 
 | 224 | } | 
 | 225 |  | 
 | 226 | static inline void __ocfs2_node_map_set_bit(struct ocfs2_node_map *map, | 
 | 227 | 					    int bit) | 
 | 228 | { | 
 | 229 | 	set_bit(bit, map->map); | 
 | 230 | } | 
 | 231 |  | 
 | 232 | void ocfs2_node_map_set_bit(struct ocfs2_super *osb, | 
 | 233 | 			    struct ocfs2_node_map *map, | 
 | 234 | 			    int bit) | 
 | 235 | { | 
 | 236 | 	if (bit==-1) | 
 | 237 | 		return; | 
 | 238 | 	BUG_ON(bit >= map->num_nodes); | 
 | 239 | 	spin_lock(&osb->node_map_lock); | 
 | 240 | 	__ocfs2_node_map_set_bit(map, bit); | 
 | 241 | 	spin_unlock(&osb->node_map_lock); | 
 | 242 | } | 
 | 243 |  | 
 | 244 | static inline void __ocfs2_node_map_clear_bit(struct ocfs2_node_map *map, | 
 | 245 | 					      int bit) | 
 | 246 | { | 
 | 247 | 	clear_bit(bit, map->map); | 
 | 248 | } | 
 | 249 |  | 
 | 250 | void ocfs2_node_map_clear_bit(struct ocfs2_super *osb, | 
 | 251 | 			      struct ocfs2_node_map *map, | 
 | 252 | 			      int bit) | 
 | 253 | { | 
 | 254 | 	if (bit==-1) | 
 | 255 | 		return; | 
 | 256 | 	BUG_ON(bit >= map->num_nodes); | 
 | 257 | 	spin_lock(&osb->node_map_lock); | 
 | 258 | 	__ocfs2_node_map_clear_bit(map, bit); | 
 | 259 | 	spin_unlock(&osb->node_map_lock); | 
 | 260 | } | 
 | 261 |  | 
 | 262 | int ocfs2_node_map_test_bit(struct ocfs2_super *osb, | 
 | 263 | 			    struct ocfs2_node_map *map, | 
 | 264 | 			    int bit) | 
 | 265 | { | 
 | 266 | 	int ret; | 
 | 267 | 	if (bit >= map->num_nodes) { | 
 | 268 | 		mlog(ML_ERROR, "bit=%d map->num_nodes=%d\n", bit, map->num_nodes); | 
 | 269 | 		BUG(); | 
 | 270 | 	} | 
 | 271 | 	spin_lock(&osb->node_map_lock); | 
 | 272 | 	ret = test_bit(bit, map->map); | 
 | 273 | 	spin_unlock(&osb->node_map_lock); | 
 | 274 | 	return ret; | 
 | 275 | } | 
 | 276 |  | 
 | 277 | static inline int __ocfs2_node_map_is_empty(struct ocfs2_node_map *map) | 
 | 278 | { | 
 | 279 | 	int bit; | 
 | 280 | 	bit = find_next_bit(map->map, map->num_nodes, 0); | 
 | 281 | 	if (bit < map->num_nodes) | 
 | 282 | 		return 0; | 
 | 283 | 	return 1; | 
 | 284 | } | 
 | 285 |  | 
 | 286 | int ocfs2_node_map_is_empty(struct ocfs2_super *osb, | 
 | 287 | 			    struct ocfs2_node_map *map) | 
 | 288 | { | 
 | 289 | 	int ret; | 
 | 290 | 	BUG_ON(map->num_nodes == 0); | 
 | 291 | 	spin_lock(&osb->node_map_lock); | 
 | 292 | 	ret = __ocfs2_node_map_is_empty(map); | 
 | 293 | 	spin_unlock(&osb->node_map_lock); | 
 | 294 | 	return ret; | 
 | 295 | } | 
 | 296 |  | 
 | 297 | static void __ocfs2_node_map_dup(struct ocfs2_node_map *target, | 
 | 298 | 				 struct ocfs2_node_map *from) | 
 | 299 | { | 
 | 300 | 	BUG_ON(from->num_nodes == 0); | 
 | 301 | 	ocfs2_node_map_init(target); | 
 | 302 | 	__ocfs2_node_map_set(target, from); | 
 | 303 | } | 
 | 304 |  | 
 | 305 | /* returns 1 if bit is the only bit set in target, 0 otherwise */ | 
 | 306 | int ocfs2_node_map_is_only(struct ocfs2_super *osb, | 
 | 307 | 			   struct ocfs2_node_map *target, | 
 | 308 | 			   int bit) | 
 | 309 | { | 
 | 310 | 	struct ocfs2_node_map temp; | 
 | 311 | 	int ret; | 
 | 312 |  | 
 | 313 | 	spin_lock(&osb->node_map_lock); | 
 | 314 | 	__ocfs2_node_map_dup(&temp, target); | 
 | 315 | 	__ocfs2_node_map_clear_bit(&temp, bit); | 
 | 316 | 	ret = __ocfs2_node_map_is_empty(&temp); | 
 | 317 | 	spin_unlock(&osb->node_map_lock); | 
 | 318 |  | 
 | 319 | 	return ret; | 
 | 320 | } | 
 | 321 |  | 
 | 322 | static void __ocfs2_node_map_set(struct ocfs2_node_map *target, | 
 | 323 | 				 struct ocfs2_node_map *from) | 
 | 324 | { | 
 | 325 | 	int num_longs, i; | 
 | 326 |  | 
 | 327 | 	BUG_ON(target->num_nodes != from->num_nodes); | 
 | 328 | 	BUG_ON(target->num_nodes == 0); | 
 | 329 |  | 
 | 330 | 	num_longs = BITS_TO_LONGS(target->num_nodes); | 
 | 331 | 	for (i = 0; i < num_longs; i++) | 
 | 332 | 		target->map[i] = from->map[i]; | 
 | 333 | } | 
 | 334 |  | 
 | 335 | /* Returns whether the recovery bit was actually set - it may not be | 
 | 336 |  * if a node is still marked as needing recovery */ | 
 | 337 | int ocfs2_recovery_map_set(struct ocfs2_super *osb, | 
 | 338 | 			   int num) | 
 | 339 | { | 
 | 340 | 	int set = 0; | 
 | 341 |  | 
 | 342 | 	spin_lock(&osb->node_map_lock); | 
 | 343 |  | 
 | 344 | 	__ocfs2_node_map_clear_bit(&osb->mounted_map, num); | 
 | 345 |  | 
 | 346 | 	if (!test_bit(num, osb->recovery_map.map)) { | 
 | 347 | 	    __ocfs2_node_map_set_bit(&osb->recovery_map, num); | 
 | 348 | 	    set = 1; | 
 | 349 | 	} | 
 | 350 |  | 
 | 351 | 	spin_unlock(&osb->node_map_lock); | 
 | 352 |  | 
 | 353 | 	return set; | 
 | 354 | } | 
 | 355 |  | 
 | 356 | void ocfs2_recovery_map_clear(struct ocfs2_super *osb, | 
 | 357 | 			      int num) | 
 | 358 | { | 
 | 359 | 	ocfs2_node_map_clear_bit(osb, &osb->recovery_map, num); | 
 | 360 | } | 
 | 361 |  | 
 | 362 | int ocfs2_node_map_iterate(struct ocfs2_super *osb, | 
 | 363 | 			   struct ocfs2_node_map *map, | 
 | 364 | 			   int idx) | 
 | 365 | { | 
 | 366 | 	int i = idx; | 
 | 367 |  | 
 | 368 | 	idx = O2NM_INVALID_NODE_NUM; | 
 | 369 | 	spin_lock(&osb->node_map_lock); | 
 | 370 | 	if ((i != O2NM_INVALID_NODE_NUM) && | 
 | 371 | 	    (i >= 0) && | 
 | 372 | 	    (i < map->num_nodes)) { | 
 | 373 | 		while(i < map->num_nodes) { | 
 | 374 | 			if (test_bit(i, map->map)) { | 
 | 375 | 				idx = i; | 
 | 376 | 				break; | 
 | 377 | 			} | 
 | 378 | 			i++; | 
 | 379 | 		} | 
 | 380 | 	} | 
 | 381 | 	spin_unlock(&osb->node_map_lock); | 
 | 382 | 	return idx; | 
 | 383 | } |