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>

diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index 880ea95..c6d6322 100644 (file)
--- 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);
 }

diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h
index 7443648..70483c7 100644 (file)
--- a/fs/xfs/xfs_log_priv.h
+++ b/fs/xfs/xfs_log_priv.h
@@ -232,6 +232,14 @@ struct xfs_cil_ctx {
 };
 
 /*
+ * Per-cpu CIL tracking items
+ */
+struct xlog_cil_pcp {
+       struct list_head        busy_extents;
+       struct list_head        log_items;
+};
+
+/*
  * Committed Item List structure
  *
  * This structure is used to track log items that have been committed but not
@@ -266,6 +274,11 @@ struct xfs_cil {
        wait_queue_head_t       xc_start_wait;
        xfs_csn_t               xc_current_sequence;
        wait_queue_head_t       xc_push_wait;   /* background push throttle */
+
+       void __percpu           *xc_pcp;        /* percpu CIL structures */
+#ifdef CONFIG_HOTPLUG_CPU
+       struct list_head        xc_pcp_list;
+#endif
 } ____cacheline_aligned_in_smp;
 
 /* xc_flags bit values */
@@ -688,4 +701,9 @@ xlog_kvmalloc(
        return p;
 }
 
+/*
+ * CIL CPU dead notifier
+ */
+void xlog_cil_pcp_dead(struct xlog *log, unsigned int cpu);
+
 #endif /* __XFS_LOG_PRIV_H__ */

diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index aa977c7..1e02ec6 100644 (file)
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -2213,6 +2213,7 @@ xfs_cpu_dead(
        list_for_each_entry_safe(mp, n, &xfs_mount_list, m_mount_list) {
                spin_unlock(&xfs_mount_list_lock);
                xfs_inodegc_cpu_dead(mp, cpu);
+               xlog_cil_pcp_dead(mp->m_log, cpu);
                spin_lock(&xfs_mount_list_lock);
        }
        spin_unlock(&xfs_mount_list_lock);