[petsc-dev] Using multiple mallocs with PETSc

Barry Smith bsmith at mcs.anl.gov
Fri Mar 10 11:08:49 CST 2017


> On Mar 10, 2017, at 8:45 AM, Karl Rupp <rupp at iue.tuwien.ac.at> wrote:
> 
> Hey,
> 
> my only concern with this solution is that the lookup via indices relies on global state. Since PETSc relies on global state at a bunch of other places (e.g. logging), this may not be a relevant concern.

   The OS keeps a little global state around too :-( What's the harm in this little table in "global state"?
> 
> If, however, the long-term goal is to get rid of global state, then we would have to store a matching deallocation routine with the raw buffer. Actually, you could store the function pointers to malloc/realloc/free in the first bytes of the allocated buffer instead of an index.

    That was my original thought but this is more likely to cause a random crash if that space is corrupted; by using integers one can detect the corruption before the crash occurs (in 99.9+ % of the cases of corruption)

> With 256/512-byte-alignment it may not matter in terms of memory footprint whether you store a single integer or whether you store three function pointers.
> 
> Best regards,
> Karli
> 
> 
> 
> On 03/10/2017 01:19 AM, Barry Smith wrote:
>> 
>>  Using different mallocs for different objects/arrays in PETSc is very iffy because each free() has to match the malloc used for that memory. This is even true with just -malloc_debug in that certain initialization functions in PETSc need to use the raw malloc() because we cannot be sure if the (*PetscTrMalloc)() has been set yet and the raw free() that comes at PetscFinalize() time needs to be matched with it.
>> 
>>  Why not have PetscMalloc() ALWAYS allocate an extra 64 bit space at the beginning and put in an integer indicating the malloc family that has been used to get the space. PetscFree() would use this integer to determine the correct free() to use. A mechanism to register new malloc families could be easily done, for example
>> 
>>    PetscMallocRegister(malloc,realloc,free,&basicmalloc);
>>    PetscMallocRegister(PetscMallocDebug,PetscReallocDebug,PetscFreeDebug,&debugmalloc);
>>    PetscMallocRegister(PetscMallocHBW,PetscReallocHBW,PetscFreeHBW,&hbwmalloc);
>> 
>>    To change the malloc used you would do PetscMallocPush(debugmalloc);  PetscMalloc(....); .... PetscMallocPop();  Note that you can register additional malloc families at any time (it doesn't have to be as soon as the program starts up).
>> 
>>   What is wrong with the model and why shouldn't we use it?
>> 
>>  Barry
>> 
>> Notes:
>> 
>> It is easy to implement, so that is not a reason.
>> 
>> The extra memory usage is trivial.
>> 
>> The mapping from integer to malloc() or free() would be a bounds check and then accessing the function pointer from a little array so pretty cheap.
>> 
>> if certain mallocs are missing (like PetscMallocHBW) the hbwmalloc variable could be set to the basicmalloc value (or some other) so one would not need to ifdef if if () code deciding which malloc to use in many places.
>> 
>> It seems so simple something must be fundamentally flawed with it. Even with just PetscTrMallocDefault() and PetscMallocAlign() I feel like implementing it.
>> 
>> 
>> 
>> 
>> 
>> 
> 




More information about the petsc-dev mailing list