Re: [PATCH] xenstore: set READ_THREAD_STACKSIZE to a sane value

["Roger Pau Monné" <roger.pau@citrix.com>]

On 11/03/14 17:25, Ian Jackson wrote:
> Ian Campbell writes ("Re: [PATCH] xenstore: set READ_THREAD_STACKSIZE to a sane value"):
>> On Tue, 2014-03-11 at 17:18 +0100, Roger Pau Monné wrote:
>>> Another question to ask would be why FreeBSD sets PTHREAD_STACK_MIN to
>>> 2048 when even a simple malloc call is going to blow that up,
>>
>> It does seem rather aggressive, but I suppose it is "min" not
>> "sensible_min".
> 
> Well, actually, a malloc works, doesn't it ?

No, actually a malloc with PTHREAD_STACK_MIN doesn't work, this sample 
example program fails in the same way:

---
#include <pthread.h>
#include <stdio.h>
#include <stdlib.h>
#include <assert.h>

#define MALLOC_SIZE 1024

void *
foo(void *arg)
{
	void *bar;

	bar = malloc(MALLOC_SIZE);
	assert(bar != NULL);

	return (NULL);
}

int main(void)
{
	pthread_t thread;
	pthread_attr_t attr;
	int rc, i;

	rc = pthread_attr_init(&attr);
	assert(rc == 0);

	rc = pthread_attr_setstacksize(&attr, PTHREAD_STACK_MIN);
	assert(rc == 0);

	rc = pthread_create(&thread, &attr, foo, NULL);
	assert(0 == rc);

	rc = pthread_join(thread, NULL);
	assert(0 == rc);

	exit(EXIT_SUCCESS);
}