* recognizes a node going up and down in one iteration */
u64 hr_generation;
- struct work_struct hr_write_timeout_work;
+ struct delayed_work hr_write_timeout_work;
unsigned long hr_last_timeout_start;
/* Used during o2hb_check_slot to hold a copy of the block
int wc_error;
};
-static void o2hb_write_timeout(void *arg)
+static void o2hb_write_timeout(struct work_struct *work)
{
- struct o2hb_region *reg = arg;
+ struct o2hb_region *reg =
+ container_of(work, struct o2hb_region,
+ hr_write_timeout_work.work);
mlog(ML_ERROR, "Heartbeat write timeout to device %s after %u "
"milliseconds\n", reg->hr_dev_name,
max_pages = q->max_hw_segments;
max_pages--; /* Handle I/Os that straddle a page */
- max_sectors = max_pages << (PAGE_SHIFT - 9);
-
+ if (max_pages) {
+ max_sectors = max_pages << (PAGE_SHIFT - 9);
+ } else {
+ /* If BIO contains 1 or less than 1 page. */
+ max_sectors = q->max_sectors;
+ }
/* Why is fls() 1-based???? */
pow_two_sectors = 1 << (fls(max_sectors) - 1);
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,
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);
&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;
}
goto out;
}
- INIT_WORK(®->hr_write_timeout_work, o2hb_write_timeout, reg);
+ INIT_DELAYED_WORK(®->hr_write_timeout_work, o2hb_write_timeout);
/*
* A node is considered live after it has beat LIVE_THRESHOLD