1 files changed, 24 insertions, 0 deletions
diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h
index 938edd19a8a6..ec22c7a3867f 100644
--- a/fs/xfs/xfs_log_priv.h
+++ b/fs/xfs/xfs_log_priv.h
@@ -240,6 +240,7 @@ struct xfs_cil_ctx {
 	struct xfs_log_vec	*lv_chain;	/* logvecs being pushed */
 	struct list_head	iclog_entry;
 	struct list_head	committing;	/* ctx committing list */
+	wait_queue_head_t	push_wait;	/* background push throttle */
 	struct work_struct	discard_endio_work;
 };
 
@@ -337,10 +338,33 @@ struct xfs_cil {
  *   buffer window (32MB) as measurements have shown this to be roughly the
  *   point of diminishing performance increases under highly concurrent
  *   modification workloads.
+ *
+ * To prevent the CIL from overflowing upper commit size bounds, we introduce a
+ * new threshold at which we block committing transactions until the background
+ * CIL commit commences and switches to a new context. While this is not a hard
+ * limit, it forces the process committing a transaction to the CIL to block and
+ * yeild the CPU, giving the CIL push work a chance to be scheduled and start
+ * work. This prevents a process running lots of transactions from overfilling
+ * the CIL because it is not yielding the CPU. We set the blocking limit at
+ * twice the background push space threshold so we keep in line with the AIL
+ * push thresholds.
+ *
+ * Note: this is not a -hard- limit as blocking is applied after the transaction
+ * is inserted into the CIL and the push has been triggered. It is largely a
+ * throttling mechanism that allows the CIL push to be scheduled and run. A hard
+ * limit will be difficult to implement without introducing global serialisation
+ * in the CIL commit fast path, and it's not at all clear that we actually need
+ * such hard limits given the ~7 years we've run without a hard limit before
+ * finding the first situation where a checkpoint size overflow actually
+ * occurred. Hence the simple throttle, and an ASSERT check to tell us that
+ * we've overrun the max size.
  */
 #define XLOG_CIL_SPACE_LIMIT(log)	\
 	min_t(int, (log)->l_logsize >> 3, BBTOB(XLOG_TOTAL_REC_SHIFT(log)) << 4)
 
+#define XLOG_CIL_BLOCKING_SPACE_LIMIT(log)	\
+	(XLOG_CIL_SPACE_LIMIT(log) * 2)
+
 /*
  * ticket grant locks, queues and accounting have their own cachlines
  * as these are quite hot and can be operated on concurrently.