Add per size class huge allocation statistics.

Add per size class huge allocation statistics, and normalize various
stats:
- Change the arenas.nlruns type from size_t to unsigned.
- Add the arenas.nhchunks and arenas.hchunks.<i>.size mallctl's.
- Replace the stats.arenas.<i>.bins.<j>.allocated mallctl with
  stats.arenas.<i>.bins.<j>.curregs .
- Add the stats.arenas.<i>.hchunks.<j>.nmalloc,
  stats.arenas.<i>.hchunks.<j>.ndalloc,
  stats.arenas.<i>.hchunks.<j>.nrequests, and
  stats.arenas.<i>.hchunks.<j>.curhchunks mallctl's.

include/jemalloc/internal/arena.h

@@ -335,11 +335,12 @@ extern size_t		map_bias; /* Number of arena chunk header pages. */
 extern size_t		map_misc_offset;
 extern size_t		arena_maxrun; /* Max run size for arenas. */
 extern size_t		arena_maxclass; /* Max size class for arenas. */
-extern size_t		nlclasses; /* Number of large size classes. */
+extern unsigned		nlclasses; /* Number of large size classes. */
+extern unsigned		nhclasses; /* Number of huge size classes. */
 
-void	*arena_chunk_alloc_huge(arena_t *arena, void *new_addr, size_t size,
+void	*arena_chunk_alloc_huge(arena_t *arena, void *new_addr, size_t usize,
     size_t alignment, bool *zero);
-void	arena_chunk_dalloc_huge(arena_t *arena, void *chunk, size_t size);
+void	arena_chunk_dalloc_huge(arena_t *arena, void *chunk, size_t usize);
 void	arena_purge_all(arena_t *arena);
 void	arena_tcache_fill_small(arena_t *arena, tcache_bin_t *tbin,
     index_t binind, uint64_t prof_accumbytes);
@@ -387,7 +388,7 @@ dss_prec_t	arena_dss_prec_get(arena_t *arena);
 bool	arena_dss_prec_set(arena_t *arena, dss_prec_t dss_prec);
 void	arena_stats_merge(arena_t *arena, const char **dss, size_t *nactive,
     size_t *ndirty, arena_stats_t *astats, malloc_bin_stats_t *bstats,
-    malloc_large_stats_t *lstats);
+    malloc_large_stats_t *lstats, malloc_huge_stats_t *hstats);
 arena_t	*arena_new(unsigned ind);
 void	arena_boot(void);
 void	arena_prefork(arena_t *arena);

include/jemalloc/internal/ctl.h

@@ -46,6 +46,7 @@ struct ctl_arena_stats_s {
 
 	malloc_bin_stats_t	bstats[NBINS];
 	malloc_large_stats_t	*lstats;	/* nlclasses elements. */
+	malloc_huge_stats_t	*hstats;	/* nhclasses elements. */
 };
 
 struct ctl_stats_s {

include/jemalloc/internal/stats.h

@@ -4,6 +4,7 @@
 typedef struct tcache_bin_stats_s tcache_bin_stats_t;
 typedef struct malloc_bin_stats_s malloc_bin_stats_t;
 typedef struct malloc_large_stats_s malloc_large_stats_t;
+typedef struct malloc_huge_stats_s malloc_huge_stats_t;
 typedef struct arena_stats_s arena_stats_t;
 typedef struct chunk_stats_s chunk_stats_t;
 
@@ -20,12 +21,6 @@ struct tcache_bin_stats_s {
 };
 
 struct malloc_bin_stats_s {
-	/*
-	 * Current number of bytes allocated, including objects currently
-	 * cached by tcache.
-	 */
-	size_t		allocated;
-
 	/*
 	 * Total number of allocation/deallocation requests served directly by
 	 * the bin.  Note that tcache may allocate an object, then recycle it
@@ -42,6 +37,12 @@ struct malloc_bin_stats_s {
 	 */
 	uint64_t	nrequests;
 
+	/*
+	 * Current number of regions of this size class, including regions
+	 * currently cached by tcache.
+	 */
+	size_t		curregs;
+
 	/* Number of tcache fills from this bin. */
 	uint64_t	nfills;
 
@@ -78,10 +79,25 @@ struct malloc_large_stats_s {
 	 */
 	uint64_t	nrequests;
 
-	/* Current number of runs of this size class. */
+	/*
+	 * Current number of runs of this size class, including runs currently
+	 * cached by tcache.
+	 */
 	size_t		curruns;
 };
 
+struct malloc_huge_stats_s {
+	/*
+	 * Total number of allocation/deallocation requests served directly by
+	 * the arena.
+	 */
+	uint64_t	nmalloc;
+	uint64_t	ndalloc;
+
+	/* Current number of (multi-)chunk allocations of this size class. */
+	size_t		curhchunks;
+};
+
 struct arena_stats_s {
 	/* Number of bytes currently mapped. */
 	size_t		mapped;
@@ -104,10 +120,12 @@ struct arena_stats_s {
 	size_t		allocated_huge;
 	uint64_t	nmalloc_huge;
 	uint64_t	ndalloc_huge;
-	uint64_t	nrequests_huge;
 
 	/* One element for each large size class. */
 	malloc_large_stats_t	*lstats;
+
+	/* One element for each huge size class. */
+	malloc_huge_stats_t	*hstats;
 };
 
 struct chunk_stats_s {