diff options
| author | Mark Fasheh <mark.fasheh@oracle.com> | 2006-05-09 15:09:35 -0700 |
|---|---|---|
| committer | Mark Fasheh <mark.fasheh@oracle.com> | 2006-06-29 15:45:35 -0700 |
| commit | 0db638f44e7db9732d9c5704ca837f57ce061f42 (patch) | |
| tree | 0ac8c092bfa27a9d88431b3c404af19fa0b1bdd1 | |
| parent | 4ba63adce06bc7549e1dd36344123dbaccdaa52f (diff) | |
ocfs2: warn the user on a dead timeout mismatch
Print a warning to the user when a node with a different dead count joins
the region.
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
| -rw-r--r-- | fs/ocfs2/cluster/heartbeat.c | 20 | ||||
| -rw-r--r-- | fs/ocfs2/cluster/ocfs2_heartbeat.h | 1 |
2 files changed, 21 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; } diff --git a/fs/ocfs2/cluster/ocfs2_heartbeat.h b/fs/ocfs2/cluster/ocfs2_heartbeat.h index 94096069cb4..3f4151da970 100644 --- a/fs/ocfs2/cluster/ocfs2_heartbeat.h +++ b/fs/ocfs2/cluster/ocfs2_heartbeat.h @@ -32,6 +32,7 @@ struct o2hb_disk_heartbeat_block { __u8 hb_pad1[3]; __le32 hb_cksum; __le64 hb_generation; + __le32 hb_dead_ms; }; #endif /* _OCFS2_HEARTBEAT_H */ |