Fix/enhance THP integration.

Detect whether chunks start off as THP-capable by default (according to
the state of /sys/kernel/mm/transparent_hugepage/enabled), and use this
as the basis for whether to call pages_nohuge() once per chunk during
first purge of any of the chunk's page runs.

Add the --disable-thp configure option, as well as the the opt.thp
mallctl.

This resolves #541.

INSTALL

@@ -157,6 +157,13 @@ any of the following arguments (not a definitive list) to 'configure':
     released in bulk, thus reducing the total number of mutex operations.  See
     the "opt.tcache" option for usage details.
 
+--disable-thp
+    Disable transparent huge page (THP) integration.  On systems with THP
+    support, THPs are explicitly disabled as a side effect of unused dirty page
+    purging for chunks that back small and/or large allocations, because such
+    chunks typically comprise active, unused dirty, and untouched clean
+    pages.
+
 --disable-munmap
     Disable virtual memory deallocation via munmap(2); instead keep track of
     the virtual memory for later use.  munmap() is disabled by default (i.e.

configure.ac

@@ -1683,9 +1683,30 @@ if test "x${je_cv_madvise}" = "xyes" ; then
 	madvise((void *)0, 0, MADV_NOHUGEPAGE);
 ], [je_cv_thp])
   if test "x${je_cv_thp}" = "xyes" ; then
+    AC_DEFINE([JEMALLOC_HAVE_MADVISE_HUGE], [ ])
+  fi
+fi
+
+dnl Enable transparent huge page support by default.
+AC_ARG_ENABLE([thp],
+  [AS_HELP_STRING([--disable-thp],
+                  [Disable transparent huge page supprot])],
+[if test "x$enable_thp" = "xno" -o "x${je_cv_thp}" != "xyes" ; then
+  enable_thp="0"
+else
+  enable_thp="1"
+fi
+],
+[if test "x${je_cv_thp}" = "xyes" ; then
+  enable_thp="1"
+else
+  enable_thp="0"
+fi
+])
+if test "x$enable_thp" = "x1" ; then
   AC_DEFINE([JEMALLOC_THP], [ ])
 fi
-fi
+AC_SUBST([enable_thp])
 
 dnl ============================================================================
 dnl Check whether __sync_{add,sub}_and_fetch() are available despite
@@ -2014,6 +2035,7 @@ AC_MSG_RESULT([prof-libunwind     : ${enable_prof_libunwind}])
 AC_MSG_RESULT([prof-libgcc        : ${enable_prof_libgcc}])
 AC_MSG_RESULT([prof-gcc           : ${enable_prof_gcc}])
 AC_MSG_RESULT([tcache             : ${enable_tcache}])
+AC_MSG_RESULT([thp                : ${enable_thp}])
 AC_MSG_RESULT([fill               : ${enable_fill}])
 AC_MSG_RESULT([utrace             : ${enable_utrace}])
 AC_MSG_RESULT([valgrind           : ${enable_valgrind}])

doc/jemalloc.xml.in

@@ -850,6 +850,17 @@ for (i = 0; i < nbins; i++) {
         during build configuration.</para></listitem>
       </varlistentry>
 
+      <varlistentry id="config.thp">
+        <term>
+          <mallctl>config.thp</mallctl>
+          (<type>bool</type>)
+          <literal>r-</literal>
+        </term>
+        <listitem><para><option>--disable-thp</option> was not specified
+        during build configuration, and the system supports transparent huge
+        page manipulation.</para></listitem>
+      </varlistentry>
+
       <varlistentry id="config.tls">
         <term>
           <mallctl>config.tls</mallctl>
@@ -1162,6 +1173,21 @@ malloc_conf = "xmalloc:true";]]></programlisting>
         forcefully disabled.</para></listitem>
       </varlistentry>
 
+      <varlistentry id="opt.thp">
+        <term>
+          <mallctl>opt.thp</mallctl>
+          (<type>bool</type>)
+          <literal>r-</literal>
+          [<option>--enable-thp</option>]
+        </term>
+        <listitem><para>Transparent huge page (THP) integration
+        enabled/disabled.  When enabled, THPs are explicitly disabled as a side
+        effect of unused dirty page purging for chunks that back small and/or
+        large allocations, because such chunks typically comprise active,
+        unused dirty, and untouched clean pages.  This option is enabled by
+        default.</para></listitem>
+      </varlistentry>
+
       <varlistentry id="opt.lg_tcache_max">
         <term>
           <mallctl>opt.lg_tcache_max</mallctl>

include/jemalloc/internal/arena.h

@@ -506,6 +506,7 @@ static const size_t	large_pad =
 #endif
     ;
 
+extern bool		opt_thp;
 extern purge_mode_t	opt_purge;
 extern const char	*purge_mode_names[];
 extern ssize_t		opt_lg_dirty_mult;

include/jemalloc/internal/jemalloc_internal.h.in

@@ -99,6 +99,13 @@ static const bool config_tcache =
     false
 #endif
     ;
+static const bool config_thp =
+#ifdef JEMALLOC_THP
+    true
+#else
+    false
+#endif
+    ;
 static const bool config_tls =
 #ifdef JEMALLOC_TLS
     true

include/jemalloc/internal/jemalloc_internal_defs.h.in

@@ -252,6 +252,12 @@
 /* Defined if madvise(2) is available. */
 #undef JEMALLOC_HAVE_MADVISE
 
+/*
+ * Defined if transparent huge pages are supported via the MADV_[NO]HUGEPAGE
+ * arguments to madvise(2).
+ */
+#undef JEMALLOC_HAVE_MADVISE_HUGE
+
 /*
  * Methods for purging unused pages differ between operating systems.
  *
@@ -264,10 +270,7 @@
 #undef JEMALLOC_PURGE_MADVISE_FREE
 #undef JEMALLOC_PURGE_MADVISE_DONTNEED
 
-/*
- * Defined if transparent huge pages are supported via the MADV_[NO]HUGEPAGE
- * arguments to madvise(2).
- */
+/* Defined if transparent huge page support is enabled. */
 #undef JEMALLOC_THP
 
 /* Define if operating system has alloca.h header. */

include/jemalloc/internal/private_symbols.txt

@@ -392,6 +392,7 @@ opt_quarantine
 opt_redzone
 opt_stats_print
 opt_tcache
+opt_thp
 opt_utrace
 opt_xmalloc
 opt_zero

src/arena.c

@@ -4,6 +4,8 @@
 /******************************************************************************/
 /* Data. */
 
+bool		opt_thp = true;
+static bool	thp_initially_huge;
 purge_mode_t	opt_purge = PURGE_DEFAULT;
 const char	*purge_mode_names[] = {
 	"ratio",
@@ -680,7 +682,9 @@ arena_chunk_init_hard(tsdn_t *tsdn, arena_t *arena)
 	if (chunk == NULL)
 		return (NULL);
 
-	chunk->hugepage = true;
+	if (config_thp && opt_thp) {
+		chunk->hugepage = thp_initially_huge;
+	}
 
 	/*
 	 * Initialize the map to contain one maximal free untouched run.  Mark
@@ -745,14 +749,17 @@ arena_chunk_alloc(tsdn_t *tsdn, arena_t *arena)
 static void
 arena_chunk_discard(tsdn_t *tsdn, arena_t *arena, arena_chunk_t *chunk)
 {
-	size_t sn, hugepage;
+	size_t sn;
+	UNUSED bool hugepage JEMALLOC_CC_SILENCE_INIT(false);
 	bool committed;
 	chunk_hooks_t chunk_hooks = CHUNK_HOOKS_INITIALIZER;
 
 	chunk_deregister(chunk, &chunk->node);
 
 	sn = extent_node_sn_get(&chunk->node);
+	if (config_thp && opt_thp) {
 		hugepage = chunk->hugepage;
+	}
 	committed = (arena_mapbits_decommitted_get(chunk, map_bias) == 0);
 	if (!committed) {
 		/*
@@ -765,13 +772,16 @@ arena_chunk_discard(tsdn_t *tsdn, arena_t *arena, arena_chunk_t *chunk)
 		chunk_hooks.decommit(chunk, chunksize, 0, map_bias << LG_PAGE,
 		    arena->ind);
 	}
-	if (!hugepage) {
+	if (config_thp && opt_thp && hugepage != thp_initially_huge) {
 		/*
-		 * Convert chunk back to the default state, so that all
-		 * subsequent chunk allocations start out with chunks that can
-		 * be backed by transparent huge pages.
+		 * Convert chunk back to initial THP state, so that all
+		 * subsequent chunk allocations start out in a consistent state.
 		 */
+		if (thp_initially_huge) {
 			pages_huge(chunk, chunksize);
+		} else {
+			pages_nohuge(chunk, chunksize);
+		}
 	}
 
 	chunk_dalloc_cache(tsdn, arena, &chunk_hooks, (void *)chunk, chunksize,
@@ -1711,13 +1721,13 @@ arena_purge_stashed(tsdn_t *tsdn, arena_t *arena, chunk_hooks_t *chunk_hooks,
 
 			/*
 			 * If this is the first run purged within chunk, mark
-			 * the chunk as non-huge.  This will prevent all use of
-			 * transparent huge pages for this chunk until the chunk
-			 * as a whole is deallocated.
+			 * the chunk as non-THP-capable.  This will prevent all
+			 * use of THPs for this chunk until the chunk as a whole
+			 * is deallocated.
 			 */
-			if (chunk->hugepage) {
-				pages_nohuge(chunk, chunksize);
-				chunk->hugepage = false;
+			if (config_thp && opt_thp && chunk->hugepage) {
+				chunk->hugepage = pages_nohuge(chunk,
+				    chunksize);
 			}
 
 			assert(pageind + npages <= chunk_npages);
@@ -3772,11 +3782,78 @@ bin_info_init(void)
 #undef SC
 }
 
+static void
+init_thp_initially_huge(void) {
+	int fd;
+	char buf[sizeof("[always] madvise never\n")];
+	ssize_t nread;
+	static const char *enabled_states[] = {
+		"[always] madvise never\n",
+		"always [madvise] never\n",
+		"always madvise [never]\n"
+	};
+	static const bool thp_initially_huge_states[] = {
+		true,
+		false,
+		false
+	};
+	unsigned i;
+
+	if (config_debug) {
+		for (i = 0; i < sizeof(enabled_states)/sizeof(const char *);
+		    i++) {
+			assert(sizeof(buf) > strlen(enabled_states[i]));
+		}
+	}
+	assert(sizeof(enabled_states)/sizeof(const char *) ==
+	    sizeof(thp_initially_huge_states)/sizeof(bool));
+
+#if defined(JEMALLOC_USE_SYSCALL) && defined(SYS_open)
+	fd = (int)syscall(SYS_open,
+	    "/sys/kernel/mm/transparent_hugepage/enabled", O_RDONLY);
+#else
+	fd = open("/sys/kernel/mm/transparent_hugepage/enabled", O_RDONLY);
+#endif
+	if (fd == -1) {
+		goto label_error;
+	}
+
+#if defined(JEMALLOC_USE_SYSCALL) && defined(SYS_read)
+	nread = (ssize_t)syscall(SYS_read, fd, &buf, sizeof(buf));
+#else
+	nread = read(fd, &buf, sizeof(buf));
+#endif
+
+#if defined(JEMALLOC_USE_SYSCALL) && defined(SYS_close)
+	syscall(SYS_close, fd);
+#else
+	close(fd);
+#endif
+
+	if (nread < 1) {
+		goto label_error;
+	}
+	for (i = 0; i < sizeof(enabled_states)/sizeof(const char *);
+	    i++) {
+		if (strncmp(buf, enabled_states[i], (size_t)nread) == 0) {
+			thp_initially_huge = thp_initially_huge_states[i];
+			return;
+		}
+	}
+
+label_error:
+	thp_initially_huge = false;
+}
+
 void
 arena_boot(void)
 {
 	unsigned i;
 
+	if (config_thp && opt_thp) {
+		init_thp_initially_huge();
+	}
+
 	arena_lg_dirty_mult_default_set(opt_lg_dirty_mult);
 	arena_decay_time_default_set(opt_decay_time);
 

src/ctl.c

@@ -84,6 +84,7 @@ CTL_PROTO(config_prof_libgcc)
 CTL_PROTO(config_prof_libunwind)
 CTL_PROTO(config_stats)
 CTL_PROTO(config_tcache)
+CTL_PROTO(config_thp)
 CTL_PROTO(config_tls)
 CTL_PROTO(config_utrace)
 CTL_PROTO(config_valgrind)
@@ -104,6 +105,7 @@ CTL_PROTO(opt_utrace)
 CTL_PROTO(opt_xmalloc)
 CTL_PROTO(opt_tcache)
 CTL_PROTO(opt_lg_tcache_max)
+CTL_PROTO(opt_thp)
 CTL_PROTO(opt_prof)
 CTL_PROTO(opt_prof_prefix)
 CTL_PROTO(opt_prof_active)
@@ -258,6 +260,7 @@ static const ctl_named_node_t	config_node[] = {
 	{NAME("prof_libunwind"), CTL(config_prof_libunwind)},
 	{NAME("stats"),		CTL(config_stats)},
 	{NAME("tcache"),	CTL(config_tcache)},
+	{NAME("thp"),		CTL(config_thp)},
 	{NAME("tls"),		CTL(config_tls)},
 	{NAME("utrace"),	CTL(config_utrace)},
 	{NAME("valgrind"),	CTL(config_valgrind)},
@@ -281,6 +284,7 @@ static const ctl_named_node_t opt_node[] = {
 	{NAME("xmalloc"),	CTL(opt_xmalloc)},
 	{NAME("tcache"),	CTL(opt_tcache)},
 	{NAME("lg_tcache_max"),	CTL(opt_lg_tcache_max)},
+	{NAME("thp"),		CTL(opt_thp)},
 	{NAME("prof"),		CTL(opt_prof)},
 	{NAME("prof_prefix"),	CTL(opt_prof_prefix)},
 	{NAME("prof_active"),	CTL(opt_prof_active)},
@@ -1268,6 +1272,7 @@ CTL_RO_CONFIG_GEN(config_prof_libgcc, bool)
 CTL_RO_CONFIG_GEN(config_prof_libunwind, bool)
 CTL_RO_CONFIG_GEN(config_stats, bool)
 CTL_RO_CONFIG_GEN(config_tcache, bool)
+CTL_RO_CONFIG_GEN(config_thp, bool)
 CTL_RO_CONFIG_GEN(config_tls, bool)
 CTL_RO_CONFIG_GEN(config_utrace, bool)
 CTL_RO_CONFIG_GEN(config_valgrind, bool)
@@ -1291,6 +1296,7 @@ CTL_RO_NL_CGEN(config_utrace, opt_utrace, opt_utrace, bool)
 CTL_RO_NL_CGEN(config_xmalloc, opt_xmalloc, opt_xmalloc, bool)
 CTL_RO_NL_CGEN(config_tcache, opt_tcache, opt_tcache, bool)
 CTL_RO_NL_CGEN(config_tcache, opt_lg_tcache_max, opt_lg_tcache_max, ssize_t)
+CTL_RO_NL_CGEN(config_thp, opt_thp, opt_thp, bool)
 CTL_RO_NL_CGEN(config_prof, opt_prof, opt_prof, bool)
 CTL_RO_NL_CGEN(config_prof, opt_prof_prefix, opt_prof_prefix, const char *)
 CTL_RO_NL_CGEN(config_prof, opt_prof_active, opt_prof_active, bool)

src/jemalloc.c

@@ -1272,6 +1272,9 @@ malloc_conf_init(void)
 				    "lg_tcache_max", -1,
 				    (sizeof(size_t) << 3) - 1)
 			}
+			if (config_thp) {
+				CONF_HANDLE_BOOL(opt_thp, "thp", true)
+			}
 			if (config_prof) {
 				CONF_HANDLE_BOOL(opt_prof, "prof", true)
 				CONF_HANDLE_CHAR_P(opt_prof_prefix,

src/pages.c

@@ -199,7 +199,7 @@ pages_huge(void *addr, size_t size)
 	assert(PAGE_ADDR2BASE(addr) == addr);
 	assert(PAGE_CEILING(size) == size);
 
-#ifdef JEMALLOC_THP
+#ifdef JEMALLOC_HAVE_MADVISE_HUGE
 	return (madvise(addr, size, MADV_HUGEPAGE) != 0);
 #else
 	return (false);
@@ -213,7 +213,7 @@ pages_nohuge(void *addr, size_t size)
 	assert(PAGE_ADDR2BASE(addr) == addr);
 	assert(PAGE_CEILING(size) == size);
 
-#ifdef JEMALLOC_THP
+#ifdef JEMALLOC_HAVE_MADVISE_HUGE
 	return (madvise(addr, size, MADV_NOHUGEPAGE) != 0);
 #else
 	return (false);

src/stats.c

@@ -750,6 +750,7 @@ stats_general_print(void (*write_cb)(void *, const char *), void *cbopaque,
 	OPT_WRITE_BOOL(xmalloc, ",")
 	OPT_WRITE_BOOL(tcache, ",")
 	OPT_WRITE_SSIZE_T(lg_tcache_max, ",")
+	OPT_WRITE_BOOL(thp, ",")
 	OPT_WRITE_BOOL(prof, ",")
 	OPT_WRITE_CHAR_P(prof_prefix, ",")
 	OPT_WRITE_BOOL_MUTABLE(prof_active, prof.active, ",")

test/unit/mallctl.c

@@ -142,6 +142,7 @@ TEST_BEGIN(test_mallctl_config)
 	TEST_MALLCTL_CONFIG(prof_libunwind, bool);
 	TEST_MALLCTL_CONFIG(stats, bool);
 	TEST_MALLCTL_CONFIG(tcache, bool);
+	TEST_MALLCTL_CONFIG(thp, bool);
 	TEST_MALLCTL_CONFIG(tls, bool);
 	TEST_MALLCTL_CONFIG(utrace, bool);
 	TEST_MALLCTL_CONFIG(valgrind, bool);
@@ -182,6 +183,7 @@ TEST_BEGIN(test_mallctl_opt)
 	TEST_MALLCTL_OPT(bool, xmalloc, xmalloc);
 	TEST_MALLCTL_OPT(bool, tcache, tcache);
 	TEST_MALLCTL_OPT(size_t, lg_tcache_max, tcache);
+	TEST_MALLCTL_OPT(bool, thp, thp);
 	TEST_MALLCTL_OPT(bool, prof, prof);
 	TEST_MALLCTL_OPT(const char *, prof_prefix, prof);
 	TEST_MALLCTL_OPT(bool, prof_active, prof);