3 files changed, 44 insertions, 24 deletions

diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c
index d59c4a65d492..81976ffed7d6 100644
--- a/fs/xfs/linux-2.6/xfs_sync.c
+++ b/fs/xfs/linux-2.6/xfs_sync.c
@@ -668,14 +668,11 @@ xfs_inode_set_reclaim_tag(
         xfs_perag_put(pag);
 }
 
-void
-__xfs_inode_clear_reclaim_tag(
-        xfs_mount_t     *mp,
+STATIC void
+__xfs_inode_clear_reclaim(
         xfs_perag_t     *pag,
         xfs_inode_t     *ip)
 {
-        radix_tree_tag_clear(&pag->pag_ici_root,
-                        XFS_INO_TO_AGINO(mp, ip->i_ino), XFS_ICI_RECLAIM_TAG);
         pag->pag_ici_reclaimable--;
         if (!pag->pag_ici_reclaimable) {
                 /* clear the reclaim tag from the perag radix tree */
@@ -689,6 +686,17 @@ __xfs_inode_clear_reclaim_tag(
         }
 }
 
+void
+__xfs_inode_clear_reclaim_tag(
+        xfs_mount_t     *mp,
+        xfs_perag_t     *pag,
+        xfs_inode_t     *ip)
+{
+        radix_tree_tag_clear(&pag->pag_ici_root,
+                        XFS_INO_TO_AGINO(mp, ip->i_ino), XFS_ICI_RECLAIM_TAG);
+        __xfs_inode_clear_reclaim(pag, ip);
+}
+
 /*
  * Inodes in different states need to be treated differently, and the return
  * value of xfs_iflush is not sufficient to get this right. The following table
@@ -838,6 +846,7 @@ reclaim:
         if (!radix_tree_delete(&pag->pag_ici_root,
                                 XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino)))
                 ASSERT(0);
+        __xfs_inode_clear_reclaim(pag, ip);
         write_unlock(&pag->pag_ici_lock);
 
         /*
diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index ed575fb4b495..7e206fc1fa36 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -405,9 +405,15 @@ xlog_cil_push(
         new_ctx = kmem_zalloc(sizeof(*new_ctx), KM_SLEEP|KM_NOFS);
         new_ctx->ticket = xlog_cil_ticket_alloc(log);
 
-        /* lock out transaction commit, but don't block on background push */
+        /*
+         * Lock out transaction commit, but don't block for background pushes
+         * unless we are well over the CIL space limit. See the definition of
+         * XLOG_CIL_HARD_SPACE_LIMIT() for the full explanation of the logic
+         * used here.
+         */
         if (!down_write_trylock(&cil->xc_ctx_lock)) {
-                if (!push_seq)
+                if (!push_seq &&
+                    cil->xc_ctx->space_used < XLOG_CIL_HARD_SPACE_LIMIT(log))
                         goto out_free_ticket;
                 down_write(&cil->xc_ctx_lock);
         }
@@ -422,7 +428,7 @@ xlog_cil_push(
                 goto out_skip;
 
         /* check for a previously pushed seqeunce */
-        if (push_seq < cil->xc_ctx->sequence)
+        if (push_seq && push_seq < cil->xc_ctx->sequence)
                 goto out_skip;
 
         /*
diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h
index ced52b98b322..edcdfe01617f 100644
--- a/fs/xfs/xfs_log_priv.h
+++ b/fs/xfs/xfs_log_priv.h
@@ -426,13 +426,13 @@ struct xfs_cil {
 };
 
 /*
- * The amount of log space we should the CIL to aggregate is difficult to size.
- * Whatever we chose we have to make we can get a reservation for the log space
- * effectively, that it is large enough to capture sufficient relogging to
- * reduce log buffer IO significantly, but it is not too large for the log or
- * induces too much latency when writing out through the iclogs. We track both
- * space consumed and the number of vectors in the checkpoint context, so we
- * need to decide which to use for limiting.
+ * The amount of log space we allow the CIL to aggregate is difficult to size.
+ * Whatever we choose, we have to make sure we can get a reservation for the
+ * log space effectively, that it is large enough to capture sufficient
+ * relogging to reduce log buffer IO significantly, but it is not too large for
+ * the log or induces too much latency when writing out through the iclogs. We
+ * track both space consumed and the number of vectors in the checkpoint
+ * context, so we need to decide which to use for limiting.
  *
  * Every log buffer we write out during a push needs a header reserved, which
  * is at least one sector and more for v2 logs. Hence we need a reservation of
@@ -459,16 +459,21 @@ struct xfs_cil {
  * checkpoint transaction ticket is specific to the checkpoint context, rather
  * than the CIL itself.
  *
- * With dynamic reservations, we can basically make up arbitrary limits for the
- * checkpoint size so long as they don't violate any other size rules.  Hence
- * the initial maximum size for the checkpoint transaction will be set to a
- * quarter of the log or 8MB, which ever is smaller. 8MB is an arbitrary limit
- * right now based on the latency of writing out a large amount of data through
- * the circular iclog buffers.
+ * With dynamic reservations, we can effectively make up arbitrary limits for
+ * the checkpoint size so long as they don't violate any other size rules.
+ * Recovery imposes a rule that no transaction exceed half the log, so we are
+ * limited by that.  Furthermore, the log transaction reservation subsystem
+ * 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.
  */
-
-#define XLOG_CIL_SPACE_LIMIT(log)       \
-        (min((log->l_logsize >> 2), (8 * 1024 * 1024)))
+#define XLOG_CIL_SPACE_LIMIT(log)       (log->l_logsize >> 3)
+#define XLOG_CIL_HARD_SPACE_LIMIT(log)  (3 * (log->l_logsize >> 4))
 
 /*
  * The reservation head lsn is not made up of a cycle number and block number.