diff options
author | Linus Torvalds <torvalds@g5.osdl.org> | 2006-06-29 17:44:21 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@g5.osdl.org> | 2006-06-29 17:44:21 -0700 |
commit | 501b7c77de3e90519e95fd99e923bf9a29cd120d (patch) | |
tree | f7dc56286e7309186f335d32f03434e82f31a41d /fs/ocfs2/cluster/heartbeat.c | |
parent | 74e651f0aa100f3e5d3432a8dd8869c089e8d72f (diff) | |
parent | 184d7d20d352c7374f70ebca7468dc8cd5cc618a (diff) |
Merge branch 'upstream-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mfasheh/ocfs2
* 'upstream-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mfasheh/ocfs2:
ocfs2: remove redundant NULL checks in ocfs2_direct_IO_get_blocks()
ocfs2: clean up some osb fields
ocfs2: fix init of uuid_net_key
ocfs2: silence a debug print
ocfs2: silence ENOENT during lookup of broken links
ocfs2: Cleanup message prints
ocfs2: silence -EEXIST from ocfs2_extent_map_insert/lookup
[PATCH] fs/ocfs2/dlm/dlmrecovery.c: make dlm_lockres_master_requery() static
ocfs2: warn the user on a dead timeout mismatch
ocfs2: OCFS2_FS must depend on SYSFS
ocfs2: Compile-time disabling of ocfs2 debugging output.
configfs: Clear up a few extra spaces where there should be TABs.
configfs: Release memory in configfs_example.
Diffstat (limited to 'fs/ocfs2/cluster/heartbeat.c')
-rw-r--r-- | fs/ocfs2/cluster/heartbeat.c | 20 |
1 files changed, 20 insertions, 0 deletions
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index 1d26cfcd9f8..504595d6cf6 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -517,6 +517,7 @@ static inline void o2hb_prepare_block(struct o2hb_region *reg, hb_block->hb_seq = cpu_to_le64(cputime); hb_block->hb_node = node_num; hb_block->hb_generation = cpu_to_le64(generation); + hb_block->hb_dead_ms = cpu_to_le32(o2hb_dead_threshold * O2HB_REGION_TIMEOUT_MS); /* This step must always happen last! */ hb_block->hb_cksum = cpu_to_le32(o2hb_compute_block_crc_le(reg, @@ -645,6 +646,8 @@ static int o2hb_check_slot(struct o2hb_region *reg, struct o2nm_node *node; struct o2hb_disk_heartbeat_block *hb_block = reg->hr_tmp_block; u64 cputime; + unsigned int dead_ms = o2hb_dead_threshold * O2HB_REGION_TIMEOUT_MS; + unsigned int slot_dead_ms; memcpy(hb_block, slot->ds_raw_block, reg->hr_block_bytes); @@ -733,6 +736,23 @@ fire_callbacks: &o2hb_live_slots[slot->ds_node_num]); slot->ds_equal_samples = 0; + + /* We want to be sure that all nodes agree on the + * number of milliseconds before a node will be + * considered dead. The self-fencing timeout is + * computed from this value, and a discrepancy might + * result in heartbeat calling a node dead when it + * hasn't self-fenced yet. */ + slot_dead_ms = le32_to_cpu(hb_block->hb_dead_ms); + if (slot_dead_ms && slot_dead_ms != dead_ms) { + /* TODO: Perhaps we can fail the region here. */ + mlog(ML_ERROR, "Node %d on device %s has a dead count " + "of %u ms, but our count is %u ms.\n" + "Please double check your configuration values " + "for 'O2CB_HEARTBEAT_THRESHOLD'\n", + slot->ds_node_num, reg->hr_dev_name, slot_dead_ms, + dead_ms); + } goto out; } |