[tarantool-patches] [RFC v2] fiber: Increase default stack size

[Cyrill Gorcunov <gorcunov@gmail.com>]

The default 64K stack size used for years become too
small for modern distors (Fedora 29 and etc) where third
party libraries (such as ncurses) started to use 64K for
own buffers and we get SIGSGV early without reaching
interactive console phase.

To address this problem and hopefully eliminate such
problems in future we increase default size up to 1M.
Because this value may be too big for old distros or
other libraries, which would never use such deep stack,
we do a trick: put watermark at 64K offset of the stack
and once fiber get recycled we test if the mark is still
here. If we're lucky and noone touched the memory
we use madvise() syscall to reduce RSS usage.

v2: by georgy@
 - Move wmark test into recycle stage

As to stats for fiber's info I think it should be
addressed in a separate patch once we deal with
this issue.

https://github.com/tarantool/tarantool/issues/3418

Signed-off-by: Cyrill Gorcunov <gorcunov@gmail.com>
---
 src/fiber.c |  104 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-
 src/fiber.h |    6 +++
 2 files changed, 109 insertions(+), 1 deletion(-)

Index: tarantool.git/src/fiber.c
===================================================================
--- tarantool.git.orig/src/fiber.c
+++ tarantool.git/src/fiber.c
@@ -91,11 +91,26 @@ pthread_t main_thread_id;
 static size_t page_size;
 static int stack_direction;
 
+static void
+stack_recycle(struct fiber *fiber);
+
+/*
+ * A random unique value with help of uuidgen.
+ *
+ * 39ee5420-13f7-417b-9610-ea100c591ab6
+ */
+static const char stack_wmark[] = {
+	0x39, 0xee, 0x54, 0x20, 0x13, 0xf7, 0x41, 0x7b,
+	0x96, 0x10, 0xea, 0x10, 0x0c, 0x59, 0x1a, 0xb6
+};
+
 enum {
 	/* The minimum allowable fiber stack size in bytes */
 	FIBER_STACK_SIZE_MINIMAL = 16384,
+	/* Stack size for stack relaxed tasks */
+	FIBER_STACK_MADVISE_LIMIT = 64536,
 	/* Default fiber stack size in bytes */
-	FIBER_STACK_SIZE_DEFAULT = 65536
+	FIBER_STACK_SIZE_DEFAULT = 1048576
 };
 
 /** Default fiber attributes */
@@ -623,6 +638,7 @@ fiber_recycle(struct fiber *fiber)
 	assert(diag_is_empty(&fiber->diag));
 	/* no pending wakeup */
 	assert(rlist_empty(&fiber->state));
+	stack_recycle(fiber);
 	bool has_custom_stack = fiber->flags & FIBER_CUSTOM_STACK;
 	fiber_reset(fiber);
 	fiber->name[0] = '\0';
@@ -710,6 +726,91 @@ page_align_up(void *ptr)
 	return page_align_down(ptr + page_size - 1);
 }
 
+static inline void *
+stack_wmark_pos(struct fiber *fiber)
+{
+	void *pos;
+
+	assert(fiber->stack);
+	assert(fiber->stack_size);
+
+	if (stack_direction < 0) {
+		pos  = fiber->stack + fiber->stack_size;
+		pos -= FIBER_STACK_MADVISE_LIMIT;
+		return page_align_up(pos);
+	} else {
+		pos  = fiber->stack - fiber->stack_size;
+		pos += FIBER_STACK_MADVISE_LIMIT;
+		return page_align_down(pos);
+	}
+}
+
+/*
+ * Set watermark to the predefined place thus on
+ * fiber sched-out procedure we may detect if
+ * a task was too eager for stack usage.
+ */
+static inline void
+stack_set_wmark(struct fiber *fiber)
+{
+	void *pos = stack_wmark_pos(fiber);
+	memcpy(pos, stack_wmark, sizeof(stack_wmark));
+}
+
+static inline bool
+stack_has_wmark(struct fiber *fiber)
+{
+	void *pos = stack_wmark_pos(fiber);
+	return memcmp(pos, stack_wmark, sizeof(stack_wmark)) == 0;
+}
+
+static void
+stack_recycle(struct fiber *fiber)
+{
+	if (!fiber->stack || (fiber->flags & FIBER_CUSTOM_STACK))
+		return;
+
+	/*
+	 * If fiber was too eager for memory, just arm
+	 * a watermark back. Maybe on the next reuse
+	 * we will be able to relax RSS pressure.
+	 */
+	if (!stack_has_wmark(fiber)) {
+		fiber->flags &= ~FIBER_MADVISED_STACK;
+		stack_set_wmark(fiber);
+		return;
+	}
+
+	/*
+	 * This is a good one, we simply notify OS
+	 * about unused stack tail, so associated
+	 * pages would be put back into a page pool.
+	 *
+	 * Note though the fiber still can use
+	 * remaining space, simply won't be handled
+	 * that fast on _first_ #pf.
+	 */
+	if (!(fiber->flags & FIBER_MADVISED_STACK)) {
+		size_t size;
+		void *tail;
+
+		if (stack_direction < 0) {
+			tail = stack_wmark_pos(fiber) - page_size;
+			size = tail - fiber->stack;
+		} else {
+			tail = stack_wmark_pos(fiber) + page_size;
+			size = fiber->stack - tail;
+		}
+
+		/*
+		 * Set the flag iif we've successed,
+		 * otherwise will try on the next round.
+		 */
+		if (!madvise(fiber->stack, size, MADV_DONTNEED))
+			fiber->flags |= FIBER_MADVISED_STACK;
+	}
+}
+
 static int
 fiber_stack_create(struct fiber *fiber, size_t stack_size)
 {
@@ -751,6 +852,7 @@ fiber_stack_create(struct fiber *fiber,
 						  fiber->stack_size);
 
 	mprotect(guard, page_size, PROT_NONE);
+	stack_set_wmark(fiber);
 	return 0;
 }
 
Index: tarantool.git/src/fiber.h
===================================================================
--- tarantool.git.orig/src/fiber.h
+++ tarantool.git/src/fiber.h
@@ -89,6 +89,12 @@ enum {
 	 * This flag is set when fiber uses custom stack size.
 	 */
 	FIBER_CUSTOM_STACK	= 1 << 5,
+	/**
+	 * This flag is set when fiber didn't exceed stack's
+	 * size watermark and considered being small enough.
+	 */
+	FIBER_MADVISED_STACK	= 1 << 6,
+
 	FIBER_DEFAULT_FLAGS = FIBER_IS_CANCELLABLE
 };