xfs: introduce per-cpu CIL tracking structure

The CIL push lock is highly contended on larger machines, becoming a
hard bottleneck that about 700,000 transaction commits/s on >16p
machines. To address this, start moving the CIL tracking
infrastructure to utilise per-CPU structures.

We need to track the space used, the amount of log reservation space
reserved to write the CIL, the log items in the CIL and the busy
extents that need to be completed by the CIL commit.  This requires
a couple of per-cpu counters, an unordered per-cpu list and a
globally ordered per-cpu list.

Create a per-cpu structure to hold these and all the management
interfaces needed, as well as the hooks to handle hotplug CPUs.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>

1 files changed, 28 insertions, 2 deletions

diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index 880ea9536f82..c6d6322aabaa 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -1618,6 +1618,26 @@ out_shutdown:
 }
 
 /*
+ * Move dead percpu state to the relevant CIL context structures.
+ *
+ * We have to lock the CIL context here to ensure that nothing is modifying
+ * the percpu state, either addition or removal. Both of these are done under
+ * the CIL context lock, so grabbing that exclusively here will ensure we can
+ * safely drain the cilpcp for the CPU that is dying.
+ */
+void
+xlog_cil_pcp_dead(
+	struct xlog		*log,
+	unsigned int		cpu)
+{
+	struct xfs_cil		*cil = log->l_cilp;
+
+	down_write(&cil->xc_ctx_lock);
+	/* move stuff on dead CPU to context */
+	up_write(&cil->xc_ctx_lock);
+}
+
+/*
  * Perform initial CIL structure initialisation.
  */
 int
@@ -1640,6 +1660,11 @@ xlog_cil_init(
 	if (!cil->xc_push_wq)
 		goto out_destroy_cil;
 
+	cil->xc_log = log;
+	cil->xc_pcp = alloc_percpu(struct xlog_cil_pcp);
+	if (!cil->xc_pcp)
+		goto out_destroy_wq;
+
 	INIT_LIST_HEAD(&cil->xc_cil);
 	INIT_LIST_HEAD(&cil->xc_committing);
 	spin_lock_init(&cil->xc_cil_lock);
@@ -1648,14 +1673,14 @@ xlog_cil_init(
 	init_rwsem(&cil->xc_ctx_lock);
 	init_waitqueue_head(&cil->xc_start_wait);
 	init_waitqueue_head(&cil->xc_commit_wait);
-	cil->xc_log = log;
 	log->l_cilp = cil;
 
 	ctx = xlog_cil_ctx_alloc();
 	xlog_cil_ctx_switch(cil, ctx);
-
 	return 0;
 
+out_destroy_wq:
+	destroy_workqueue(cil->xc_push_wq);
 out_destroy_cil:
 	kmem_free(cil);
 	return -ENOMEM;
@@ -1675,6 +1700,7 @@ xlog_cil_destroy(
 
 	ASSERT(list_empty(&cil->xc_cil));
 	ASSERT(test_bit(XLOG_CIL_EMPTY, &cil->xc_flags));
+	free_percpu(cil->xc_pcp);
 	destroy_workqueue(cil->xc_push_wq);
 	kmem_free(cil);
 }