On Fri, Apr 23, 2010 at 10:31:16AM +0200, John Kacur wrote:
quoted text
> > Non of these numbers look strange..
> >
> 
> As I told Peter privately the laptop that triggered the
> MAX_STACK_TRACE_ENTRIES every time, has met an
> unfortunate early demise. However, I think it was the config - not the
> hardware. On this machine where the above
> numbers come from, I believe I have less debug options configured -
> but it is running the exact same kernel as
> the laptop was. (2.6.33.2-rt13)

Hi John,

(checking mail at home).
I find some place which can be hacked. Below is the patch.
But I don't even compile it. Can you test it to see if it can smooth
your problem.

---cut here ---
From 6b9d513b7c417c0805ef0acc1cb3227bddba0889 Mon Sep 17 00:00:00 2001
From: Yong Zhang <yong.zhang0@gmail.com>
Date: Fri, 23 Apr 2010 21:13:54 +0800
Subject: [PATCH] lockdep: reduce stack_trace usage

When calling check_prevs_add(), if all validations passed
add_lock_to_list() will add new lock to dependency tree and
alloc stack_trace for each list_entry. But at this time,
we are always on the same stack, so stack_trace for each
list_entry has the same value. This is redundant and eats up
lots of memory which could lead to warning on low
MAX_STACK_TRACE_ENTRIES.
Using one copy of stack_trace instead.

Signed-off-by: Yong Zhang <yong.zhang0@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: David S. Miller <davem@davemloft.net>
---
 kernel/lockdep.c |   20 ++++++++++++--------
 1 files changed, 12 insertions(+), 8 deletions(-)

diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index 2594e1c..097d5fb 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -818,7 +818,8 @@ static struct lock_list *alloc_list_entry(void)
  * Add a new dependency to the head of the list:
  */
 static int add_lock_to_list(struct lock_class *class, struct lock_class *this,
-			    struct list_head *head, unsigned long ip, int distance)
+			    struct list_head *head, unsigned long ip,
+			    int distance, struct stack_trace *trace)
 {
 	struct lock_list *entry;
 	/*
@@ -829,11 +830,9 @@ static int add_lock_to_list(struct lock_class *class, struct lock_class *this,
 	if (!entry)
 		return 0;
 
-	if (!save_trace(&entry->trace))
-		return 0;
-
 	entry->class = this;
 	entry->distance = distance;
+	entry->trace = *trace;
 	/*
 	 * Since we never remove from the dependency list, the list can
 	 * be walked lockless by other CPUs, it's only allocation
@@ -1635,7 +1634,7 @@ check_deadlock(struct task_struct *curr, struct held_lock *next,
  */
 static int
 check_prev_add(struct task_struct *curr, struct held_lock *prev,
-	       struct held_lock *next, int distance)
+	       struct held_lock *next, int distance, struct stack_trace *trace)
 {
 	struct lock_list *entry;
 	int ret;
@@ -1694,14 +1693,14 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
 	 */
 	ret = add_lock_to_list(hlock_class(prev), hlock_class(next),
 			       &hlock_class(prev)->locks_after,
-			       next->acquire_ip, distance);
+			       next->acquire_ip, distance, trace);
 
 	if (!ret)
 		return 0;
 
 	ret = add_lock_to_list(hlock_class(next), hlock_class(prev),
 			       &hlock_class(next)->locks_before,
-			       next->acquire_ip, distance);
+			       next->acquire_ip, distance, trace);
 	if (!ret)
 		return 0;
 
@@ -1732,6 +1731,7 @@ check_prevs_add(struct task_struct *curr, struct held_lock *next)
 {
 	int depth = curr->lockdep_depth;
 	struct held_lock *hlock;
+	struct stack_trace trace;
 
 	/*
 	 * Debugging checks.
@@ -1748,6 +1748,9 @@ check_prevs_add(struct task_struct *curr, struct held_lock *next)
 			curr->held_locks[depth-1].irq_context)
 		goto out_bug;
 
+	if (!save_trace(&trace))
+		return 0;
+
 	for (;;) {
 		int distance = curr->lockdep_depth - depth + 1;
 		hlock = curr->held_locks + depth-1;
@@ -1756,7 +1759,8 @@ check_prevs_add(struct task_struct *curr, struct held_lock *next)
 		 * added:
 		 */
 		if (hlock->read != 2) {
-			if (!check_prev_add(curr, hlock, next, distance))
+			if (!check_prev_add(curr, hlock, next,
+						distance, &trace))
 				return 0;
 			/*
 			 * Stop after the first non-trylock entry,
-- 
1.6.3.3
--
unsubscribe notice
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/