4 files changed, 49 insertions, 8 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/masklog.h b/fs/ocfs2/cluster/masklog.h
index 73edad78253..a42628ba9dd 100644
--- a/fs/ocfs2/cluster/masklog.h
+++ b/fs/ocfs2/cluster/masklog.h
@@ -123,6 +123,17 @@
 #define MLOG_MASK_PREFIX 0
 #endif
 
+/*
+ * When logging is disabled, force the bit test to 0 for anything other
+ * than errors and notices, allowing gcc to remove the code completely.
+ * When enabled, allow all masks.
+ */
+#if defined(CONFIG_OCFS2_DEBUG_MASKLOG)
+#define ML_ALLOWED_BITS ~0
+#else
+#define ML_ALLOWED_BITS (ML_ERROR|ML_NOTICE)
+#endif
+
 #define MLOG_MAX_BITS 64
 
 struct mlog_bits {
@@ -187,7 +198,8 @@ extern struct mlog_bits mlog_and_bits, mlog_not_bits;
 
 #define mlog(mask, fmt, args...) do {					\
 	u64 __m = MLOG_MASK_PREFIX | (mask);				\
-	if (__mlog_test_u64(__m, mlog_and_bits) &&			\
+	if ((__m & ML_ALLOWED_BITS) &&					\
+	    __mlog_test_u64(__m, mlog_and_bits) &&			\
 	    !__mlog_test_u64(__m, mlog_not_bits)) {			\
 		if (__m & ML_ERROR)					\
 			__mlog_printk(KERN_ERR, "ERROR: "fmt , ##args);	\
@@ -204,6 +216,7 @@ extern struct mlog_bits mlog_and_bits, mlog_not_bits;
 		mlog(ML_ERROR, "status = %lld\n", (long long)_st);	\
 } while (0)
 
+#if defined(CONFIG_OCFS2_DEBUG_MASKLOG)
 #define mlog_entry(fmt, args...) do {					\
 	mlog(ML_ENTRY, "ENTRY:" fmt , ##args);				\
 } while (0)
@@ -247,6 +260,13 @@ extern struct mlog_bits mlog_and_bits, mlog_not_bits;
 #define mlog_exit_void() do {						\
 	mlog(ML_EXIT, "EXIT\n");					\
 } while (0)
+#else
+#define mlog_entry(...)  do { } while (0)
+#define mlog_entry_void(...)  do { } while (0)
+#define mlog_exit(...)  do { } while (0)
+#define mlog_exit_ptr(...)  do { } while (0)
+#define mlog_exit_void(...)  do { } while (0)
+#endif  /* defined(CONFIG_OCFS2_DEBUG_MASKLOG) */
 
 #define mlog_bug_on_msg(cond, fmt, args...) do {			\
 	if (cond) {							\
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 */
diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index 1591eb37a72..b650efa8c8b 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -396,8 +396,8 @@ static void o2net_set_nn_state(struct o2net_node *nn,
 	}
 
 	if (was_valid && !valid) {
-		mlog(ML_NOTICE, "no longer connected to " SC_NODEF_FMT "\n",
-		     SC_NODEF_ARGS(old_sc));
+		printk(KERN_INFO "o2net: no longer connected to "
+		       SC_NODEF_FMT "\n", SC_NODEF_ARGS(old_sc));
 		o2net_complete_nodes_nsw(nn);
 	}
 
@@ -409,10 +409,10 @@ static void o2net_set_nn_state(struct o2net_node *nn,
 		 * the only way to start connecting again is to down
 		 * heartbeat and bring it back up. */
 		cancel_delayed_work(&nn->nn_connect_expired);
-		mlog(ML_NOTICE, "%s " SC_NODEF_FMT "\n", 
-		     o2nm_this_node() > sc->sc_node->nd_num ?
-		     	"connected to" : "accepted connection from",
-		     SC_NODEF_ARGS(sc));
+		printk(KERN_INFO "o2net: %s " SC_NODEF_FMT "\n",
+		       o2nm_this_node() > sc->sc_node->nd_num ?
+		       		"connected to" : "accepted connection from",
+		       SC_NODEF_ARGS(sc));
 	}
 
 	/* trigger the connecting worker func as long as we're not valid,
@@ -1280,7 +1280,7 @@ static void o2net_idle_timer(unsigned long data)
 
 	do_gettimeofday(&now);
 
-	mlog(ML_NOTICE, "connection to " SC_NODEF_FMT " has been idle for 10 "
+	printk(KERN_INFO "o2net: connection to " SC_NODEF_FMT " has been idle for 10 "
 	     "seconds, shutting it down.\n", SC_NODEF_ARGS(sc));
 	mlog(ML_NOTICE, "here are some times that might help debug the "
 	     "situation: (tmr %ld.%ld now %ld.%ld dr %ld.%ld adv "