Re: [OMPI devel] memory_malloc_hooks.c and dlclose()

[Brian W. Barrett]

On Mon, 22 May 2006, Neil Ludban wrote:

I'm getting a core dump when using openmpi-1.0.2 with the MPI extensions
we're developing for the MATLAB interpreter.  This same build of openmpi
is working great with C programs and our extensions for gnu octave.  The
machine is AMD64 running Linux:
Linux kodos 2.6.9-5.ELsmp #1 SMP Wed Jan 5 19:29:47 EST 2005 x86_64 x86_64 
x86_64 GNU/Linux

I believe there's a bug in that opal_memory_malloc_hooks_init() links
itself into the __free_hook chain during initialization, but then it
never unlinks itself at shutdown.  In the interpreter environment,
libopal.so is dlclose()d and unmapped from memory long before the
interpreter is done with dynamic memory.  A quick check of the nightly
trunk snapshot reveals some function name changes, but no new shutdown
code.

Can you try the attached patch and see if it solves your problem?  I think 
it will, but I don't have a great way of testing your exact situation.

Thanks,

Brian

--
  Brian Barrett
  Graduate Student, Open Systems Lab, Indiana University
  http://www.osl.iu.edu/~brbarret/Index: opal/mca/memory/malloc_hooks/memory_malloc_hooks.c
===================================================================
--- opal/mca/memory/malloc_hooks/memory_malloc_hooks.c  (revision 10123)
+++ opal/mca/memory/malloc_hooks/memory_malloc_hooks.c  (working copy)
@@ -27,6 +27,7 @@
      
 /* Prototypes for our hooks.  */
 void opal_memory_malloc_hooks_init(void);
+void opal_memory_malloc_hooks_finalize(void);
 static void opal_mem_free_free_hook (void*, const void *);
 static void* opal_mem_free_realloc_hook (void*, size_t, const void *);
      
@@ -60,6 +61,18 @@
 }
 
 
+void
+opal_memory_malloc_hooks_finalize(void)
+{
+    if (initialized == 0) {
+        return;
+    }
+
+    __free_hook = old_free_hook;
+    __realloc_hook = old_realloc_hook;
+    initialized = 0;
+}
+
 static void
 opal_mem_free_free_hook (void *ptr, const void *caller)
 {
Index: opal/mca/memory/malloc_hooks/memory_malloc_hooks_component.c
===================================================================
--- opal/mca/memory/malloc_hooks/memory_malloc_hooks_component.c        
(revision 10123)
+++ opal/mca/memory/malloc_hooks/memory_malloc_hooks_component.c        
(working copy)
@@ -22,8 +22,10 @@
 #include "opal/include/constants.h"
 
 extern void opal_memory_malloc_hooks_init(void);
+extern void opal_memory_malloc_hooks_finalize(void);
 
 static int opal_memory_malloc_open(void);
+static int opal_memory_malloc_close(void);
 
 const opal_memory_base_component_1_0_0_t mca_memory_malloc_hooks_component = {
     /* First, the mca_component_t struct containing meta information
@@ -41,7 +43,7 @@
 
         /* Component open and close functions */
         opal_memory_malloc_open,
-        NULL
+        opal_memory_malloc_close
     },
 
     /* Next the MCA v1.0.0 component meta data */
@@ -58,3 +60,10 @@
     opal_memory_malloc_hooks_init();
     return OPAL_SUCCESS;
 }
+
+static int
+opal_memory_malloc_close(void)
+{
+    opal_memory_malloc_hooks_finalize();
+    return OPAL_SUCCESS;
+}