1 files changed, 23 insertions, 6 deletions
diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h
index f4a54469d7d0..938edd19a8a6 100644
--- a/fs/xfs/xfs_log_priv.h
+++ b/fs/xfs/xfs_log_priv.h
@@ -316,13 +316,30 @@ struct xfs_cil {
  * tries to keep 25% of the log free, so we need to keep below that limit or we
  * risk running out of free log space to start any new transactions.
  *
- * In order to keep background CIL push efficient, we will set a lower
- * threshold at which background pushing is attempted without blocking current
- * transaction commits.  A separate, higher bound defines when CIL pushes are
- * enforced to ensure we stay within our maximum checkpoint size bounds.
- * threshold, yet give us plenty of space for aggregation on large logs.
+ * In order to keep background CIL push efficient, we only need to ensure the
+ * CIL is large enough to maintain sufficient in-memory relogging to avoid
+ * repeated physical writes of frequently modified metadata. If we allow the CIL
+ * to grow to a substantial fraction of the log, then we may be pinning hundreds
+ * of megabytes of metadata in memory until the CIL flushes. This can cause
+ * issues when we are running low on memory - pinned memory cannot be reclaimed,
+ * and the CIL consumes a lot of memory. Hence we need to set an upper physical
+ * size limit for the CIL that limits the maximum amount of memory pinned by the
+ * CIL but does not limit performance by reducing relogging efficiency
+ * significantly.
+ *
+ * As such, the CIL push threshold ends up being the smaller of two thresholds:
+ * - a threshold large enough that it allows CIL to be pushed and progress to be
+ *   made without excessive blocking of incoming transaction commits. This is
+ *   defined to be 12.5% of the log space - half the 25% push threshold of the
+ *   AIL.
+ * - small enough that it doesn't pin excessive amounts of memory but maintains
+ *   close to peak relogging efficiency. This is defined to be 16x the iclog
+ *   buffer window (32MB) as measurements have shown this to be roughly the
+ *   point of diminishing performance increases under highly concurrent
+ *   modification workloads.
  */
-#define XLOG_CIL_SPACE_LIMIT(log)	(log->l_logsize >> 3)
+#define XLOG_CIL_SPACE_LIMIT(log)	\
+	min_t(int, (log)->l_logsize >> 3, BBTOB(XLOG_TOTAL_REC_SHIFT(log)) << 4)
 
 /*
  * ticket grant locks, queues and accounting have their own cachlines