From 553abd046af609191a91af7289d87d477adc659f Mon Sep 17 00:00:00 2001 From: Joel Becker Date: Fri, 1 Feb 2008 12:03:57 -0800 Subject: ocfs2: Change the recovery map to an array of node numbers. The old recovery map was a bitmap of node numbers. This was sufficient for the maximum node number of 254. Going forward, we want node numbers to be UINT32. Thus, we need a new recovery map. Note that we can't keep track of slots here. We must write down the node number to recovery *before* we get the locks needed to convert a node number into a slot number. The recovery map is now an array of unsigned ints, max_slots in size. It moves to journal.c with the rest of recovery. Because it needs to be initialized, we move all of recovery initialization into a new function, ocfs2_recovery_init(). This actually cleans up ocfs2_initialize_super() a little as well. Following on, recovery cleaup becomes part of ocfs2_recovery_exit(). A number of node map functions are rendered obsolete and are removed. Finally, waiting on recovery is wrapped in a function rather than naked checks on the recovery_event. This is a cleanup from Mark. Signed-off-by: Joel Becker Signed-off-by: Mark Fasheh --- fs/ocfs2/heartbeat.c | 111 --------------------------------------------------- 1 file changed, 111 deletions(-) (limited to 'fs/ocfs2/heartbeat.c') diff --git a/fs/ocfs2/heartbeat.c b/fs/ocfs2/heartbeat.c index 0758daf64da0..80de2397c161 100644 --- a/fs/ocfs2/heartbeat.c +++ b/fs/ocfs2/heartbeat.c @@ -48,7 +48,6 @@ 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); /* special case -1 for now * TODO: should *really* make sure the calling func never passes -1!! */ @@ -62,7 +61,6 @@ static void ocfs2_node_map_init(struct ocfs2_node_map *map) void ocfs2_init_node_maps(struct ocfs2_super *osb) { spin_lock_init(&osb->node_map_lock); - ocfs2_node_map_init(&osb->recovery_map); ocfs2_node_map_init(&osb->osb_recovering_orphan_dirs); } @@ -192,112 +190,3 @@ int ocfs2_node_map_test_bit(struct ocfs2_super *osb, 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; -} - -#if 0 - -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]; -} - -#endif /* 0 */ - -/* 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); - - 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; -} -- cgit v1.2.2 From 4670c46ded9a18268d1265417ff4ac72145a7917 Mon Sep 17 00:00:00 2001 From: Joel Becker Date: Fri, 1 Feb 2008 14:39:35 -0800 Subject: ocfs2: Introduce the new ocfs2_cluster_connect/disconnect() API. This step introduces a cluster stack agnostic API for initializing and exiting. fs/ocfs2/dlmglue.c no longer uses o2cb/o2dlm knowledge to connect to the stack. It is all handled in stackglue.c. heartbeat.c no longer needs to know how it gets called. ocfs2_do_node_down() is now a clean recovery trigger. The big gotcha is the ordering of initializations and de-initializations done underneath ocfs2_cluster_connect(). ocfs2_dlm_init() used to do all o2dlm initialization in one block. Thus, the o2dlm functionality of ocfs2_cluster_connect() is very straightforward. ocfs2_dlm_shutdown(), however, did a few things between de-registration of the eviction callback and actually shutting down the domain. Now de-registration and shutdown of the domain are wrapped within the single ocfs2_cluster_disconnect() call. I've checked the code paths to make sure we can safely tear down things in ocfs2_dlm_shutdown() before calling ocfs2_cluster_disconnect(). The filesystem has already set itself to ignore the callback. Signed-off-by: Joel Becker Signed-off-by: Mark Fasheh --- fs/ocfs2/heartbeat.c | 40 ++++++++-------------------------------- 1 file changed, 8 insertions(+), 32 deletions(-) (limited to 'fs/ocfs2/heartbeat.c') diff --git a/fs/ocfs2/heartbeat.c b/fs/ocfs2/heartbeat.c index 80de2397c161..dcac1a487288 100644 --- a/fs/ocfs2/heartbeat.c +++ b/fs/ocfs2/heartbeat.c @@ -30,8 +30,6 @@ #include #include -#include - #define MLOG_MASK_PREFIX ML_SUPER #include @@ -64,19 +62,20 @@ void ocfs2_init_node_maps(struct ocfs2_super *osb) ocfs2_node_map_init(&osb->osb_recovering_orphan_dirs); } -static void ocfs2_do_node_down(int node_num, - struct ocfs2_super *osb) +void ocfs2_do_node_down(int node_num, void *data) { + struct ocfs2_super *osb = data; + BUG_ON(osb->node_num == node_num); mlog(0, "ocfs2: node down event for %d\n", node_num); - if (!osb->dlm) { + if (!osb->cconn) { /* - * 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. + * No cluster connection means we're not even ready to + * participate yet. We check the slots after the cluster + * comes up, so we will notice the node death then. We + * can safely ignore it here. */ return; } @@ -84,29 +83,6 @@ static void ocfs2_do_node_down(int node_num, ocfs2_recovery_thread(osb, node_num); } -/* 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); -} - -void ocfs2_setup_hb_callbacks(struct ocfs2_super *osb) -{ - /* 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); -} - void ocfs2_stop_heartbeat(struct ocfs2_super *osb) { int ret; -- cgit v1.2.2 From 6953b4c008628b945bfe0cee97f6e78a98773859 Mon Sep 17 00:00:00 2001 From: Joel Becker Date: Tue, 29 Jan 2008 16:59:56 -0800 Subject: ocfs2: Move o2hb functionality into the stack glue. The last bit of classic stack used directly in ocfs2 code is o2hb. Specifically, the check for heartbeat during mount and the call to ocfs2_hb_ctl during unmount. We create an extra API, ocfs2_cluster_hangup(), to encapsulate the call to ocfs2_hb_ctl. Other stacks will just leave hangup() empty. The check for heartbeat is moved into ocfs2_cluster_connect(). It will be matched by a similar check for other stacks. With this change, only stackglue.c includes cluster/ headers. Signed-off-by: Joel Becker Signed-off-by: Mark Fasheh --- fs/ocfs2/heartbeat.c | 33 --------------------------------- 1 file changed, 33 deletions(-) (limited to 'fs/ocfs2/heartbeat.c') diff --git a/fs/ocfs2/heartbeat.c b/fs/ocfs2/heartbeat.c index dcac1a487288..c6e7213db868 100644 --- a/fs/ocfs2/heartbeat.c +++ b/fs/ocfs2/heartbeat.c @@ -28,7 +28,6 @@ #include #include #include -#include #define MLOG_MASK_PREFIX ML_SUPER #include @@ -83,38 +82,6 @@ void ocfs2_do_node_down(int node_num, void *data) ocfs2_recovery_thread(osb, node_num); } -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); -} - static inline void __ocfs2_node_map_set_bit(struct ocfs2_node_map *map, int bit) { -- cgit v1.2.2