Improve thread-->arena assignment.

Rather than blindly assigning threads to arenas in round-robin fashion,
choose the lowest-numbered arena that currently has the smallest number
of threads assigned to it.

Add the "stats.arenas.<i>.nthreads" mallctl.

3 files changed, 15 insertions, 3 deletions

diff --git a/jemalloc/include/jemalloc/internal/arena.h b/jemalloc/include/jemalloc/internal/arena.h
index 1744b45..94b7f3d 100644
--- a/jemalloc/include/jemalloc/internal/arena.h
+++ b/jemalloc/include/jemalloc/internal/arena.h
@@ -295,8 +295,18 @@ struct arena_s {
 	unsigned		ind;
 
 	/*
-	 * All non-bin-related operations on this arena require that lock be
-	 * locked.
+	 * Number of threads currently assigned to this arena.  This field is
+	 * protected by arenas_lock.
+	 */
+	unsigned		nthreads;
+
+	/*
+	 * There are three classes of arena operations from a locking
+	 * perspective:
+	 * 1) Thread asssignment (modifies nthreads) is protected by
+	 *    arenas_lock.
+	 * 2) Bin-related operations are protected by bin locks.
+	 * 3) Chunk- and run-related operations are protected by this mutex.
 	 */
 	malloc_mutex_t		lock;
 
diff --git a/jemalloc/include/jemalloc/internal/ctl.h b/jemalloc/include/jemalloc/internal/ctl.h
index 8776ad1..f1f5eb7 100644
--- a/jemalloc/include/jemalloc/internal/ctl.h
+++ b/jemalloc/include/jemalloc/internal/ctl.h
@@ -29,6 +29,7 @@ struct ctl_node_s {
 
 struct ctl_arena_stats_s {
 	bool			initialized;
+	unsigned		nthreads;
 	size_t			pactive;
 	size_t			pdirty;
 #ifdef JEMALLOC_STATS
diff --git a/jemalloc/include/jemalloc/internal/jemalloc_internal.h.in b/jemalloc/include/jemalloc/internal/jemalloc_internal.h.in
index a80fc7c..a7472c0 100644
--- a/jemalloc/include/jemalloc/internal/jemalloc_internal.h.in
+++ b/jemalloc/include/jemalloc/internal/jemalloc_internal.h.in
@@ -293,6 +293,7 @@ extern size_t		lg_pagesize;
 extern unsigned		ncpus;
 
 extern malloc_mutex_t	arenas_lock; /* Protects arenas initialization. */
+extern pthread_key_t	arenas_tsd;
 #ifndef NO_TLS
 /*
  * Map of pthread_self() --> arenas[???], used for selecting an arena to use
@@ -302,9 +303,9 @@ extern __thread arena_t	*arenas_tls JEMALLOC_ATTR(tls_model("initial-exec"));
 #  define ARENA_GET()	arenas_tls
 #  define ARENA_SET(v)	do {						\
 	arenas_tls = (v);						\
+	pthread_setspecific(arenas_tsd, (void *)(v));			\
 } while (0)
 #else
-extern pthread_key_t	arenas_tsd;
 #  define ARENA_GET()	((arena_t *)pthread_getspecific(arenas_tsd))
 #  define ARENA_SET(v)	do {						\
 	pthread_setspecific(arenas_tsd, (void *)(v));			\