Scale the dbuf cache with arc_c

Commit d3c2ae1 introduced a dbuf cache with a default size of the
minimum of 100M or 1/32 maximum ARC size. (These figures may be adjusted
using dbuf_cache_max_bytes and dbuf_cache_max_shift.) The dbuf cache
is counted as metadata for the purposes of ARC size calculations.

On a 1GB box the ARC maximum size defaults to c_max 493M which gives a
dbuf cache default minimum size of 15.4M, and the ARC metadata defaults
to minimum 16M. I.e. the dbuf cache is an significant proportion of the
minimum metadata size. With other overheads involved this actually means
the ARC metadata doesn't get down to the minimum.

This patch dynamically scales the dbuf cache to the target ARC size
instead of statically scaling it to the maximum ARC size. (The scale is
still set by dbuf_cache_max_shift and the maximum size is still fixed by
dbuf_cache_max_bytes.) Using the target ARC size rather than the current
ARC size is done to help the ARC reach the target rather than simply
focusing on the current size.

Reviewed-by: Chunwei Chen <tuxoko@gmail.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: George Melikov <mail@gmelikov.ru>
Signed-off-by: Chris Dunlop <chris@onthe.net.au>
Issue #6506
Closes #6561

diff --git a/include/sys/arc.h b/include/sys/arc.h
index 07a72302df7b19c6b89005e692706cb8f02d0f50..66f37cf7102584295c8a068830ae716c817bf705 100644 (file)
--- a/include/sys/arc.h
+++ b/include/sys/arc.h
@@ -248,7 +248,7 @@ void arc_flush(spa_t *spa, boolean_t retry);
 void arc_tempreserve_clear(uint64_t reserve);
 int arc_tempreserve_space(uint64_t reserve, uint64_t txg);
 
-uint64_t arc_max_bytes(void);
+uint64_t arc_target_bytes(void);
 void arc_init(void);
 void arc_fini(void);
 

diff --git a/module/zfs/arc.c b/module/zfs/arc.c
index 0a09c443b0dcffe76d40c8e9f3e1265daa8bdeff..d678b335cf5bdb98d67c2f536a52082d3c41ee97 100644 (file)
--- a/module/zfs/arc.c
+++ b/module/zfs/arc.c
@@ -6475,9 +6475,9 @@ arc_state_fini(void)
 }
 
 uint64_t
-arc_max_bytes(void)
+arc_target_bytes(void)
 {
-       return (arc_c_max);
+       return (arc_c);
 }
 
 void

diff --git a/module/zfs/dbuf.c b/module/zfs/dbuf.c
index dc2c00495b54c550668584815802659f8b08441e..62340469d3575b089fee6145fedf4201f733ce23 100644 (file)
--- a/module/zfs/dbuf.c
+++ b/module/zfs/dbuf.c
@@ -464,24 +464,35 @@ dbuf_cache_multilist_index_func(multilist_t *ml, void *obj)
            multilist_get_num_sublists(ml));
 }
 
+static inline unsigned long
+dbuf_cache_target_bytes(void)
+{
+       return MIN(dbuf_cache_max_bytes,
+           arc_target_bytes() >> dbuf_cache_max_shift);
+}
+
 static inline boolean_t
 dbuf_cache_above_hiwater(void)
 {
+       uint64_t dbuf_cache_target = dbuf_cache_target_bytes();
+
        uint64_t dbuf_cache_hiwater_bytes =
-           (dbuf_cache_max_bytes * dbuf_cache_hiwater_pct) / 100;
+           (dbuf_cache_target * dbuf_cache_hiwater_pct) / 100;
 
        return (refcount_count(&dbuf_cache_size) >
-           dbuf_cache_max_bytes + dbuf_cache_hiwater_bytes);
+           dbuf_cache_target + dbuf_cache_hiwater_bytes);
 }
 
 static inline boolean_t
 dbuf_cache_above_lowater(void)
 {
+       uint64_t dbuf_cache_target = dbuf_cache_target_bytes();
+
        uint64_t dbuf_cache_lowater_bytes =
-           (dbuf_cache_max_bytes * dbuf_cache_lowater_pct) / 100;
+           (dbuf_cache_target * dbuf_cache_lowater_pct) / 100;
 
        return (refcount_count(&dbuf_cache_size) >
-           dbuf_cache_max_bytes - dbuf_cache_lowater_bytes);
+           dbuf_cache_target - dbuf_cache_lowater_bytes);
 }
 
 /*
@@ -601,7 +612,7 @@ dbuf_evict_notify(void)
         * because it's OK to occasionally make the wrong decision here,
         * and grabbing the lock results in massive lock contention.
         */
-       if (refcount_count(&dbuf_cache_size) > dbuf_cache_max_bytes) {
+       if (refcount_count(&dbuf_cache_size) > dbuf_cache_target_bytes()) {
                if (dbuf_cache_above_hiwater())
                        dbuf_evict_one();
                cv_signal(&dbuf_evict_cv);
@@ -658,7 +669,7 @@ retry:
         * dbuf cache to 1/32nd (default) of the size of the ARC.
         */
        dbuf_cache_max_bytes = MIN(dbuf_cache_max_bytes,
-           arc_max_bytes() >> dbuf_cache_max_shift);
+           arc_target_bytes() >> dbuf_cache_max_shift);
 
        /*
         * All entries are queued via taskq_dispatch_ent(), so min/maxalloc