Wireshark mailing list archives
Re: RFD: The Future of Memory Management in Wireshark
From: Sébastien Tandel <sebastien.tandel () gmail com>
Date: Fri, 26 Oct 2012 14:14:30 -0200
On Fri, Oct 26, 2012 at 1:58 PM, Evan Huus <eapache () gmail com> wrote:
On Fri, Oct 26, 2012 at 11:40 AM, Graham Bloice <graham.bloice () trihedral com> wrote:On 26 October 2012 14:44, Evan Huus <eapache () gmail com> wrote:On Fri, Oct 26, 2012 at 9:29 AM, Sébastien Tandel <sebastien.tandel () gmail com> wrote:On Wed, Oct 24, 2012 at 11:13 AM, Evan Huus <eapache () gmail com>wrote:On Wed, Oct 24, 2012 at 8:10 AM, Sébastien Tandel <sebastien.tandel () gmail com> wrote:On Wed, Oct 24, 2012 at 1:10 AM, Guy Harris <guy () alum mit edu>wrote:On Oct 18, 2012, at 6:01 PM, Evan Huus <eapache () gmail com> wrote:I have linked a tarball [2] containing the following files: - wmem_allocator.h - the definition of the allocator interface - wmem_allocator_glib.* - a simple implementation of theallocatorinterface backed by g_malloc and a singly-linked list.Presumably an implementation of the allocator could, instead of calling a lower-level memory allocator (malloc(), g_malloc(), etc.) for each allocation call, allocate larger chunks and parcel out memory from the larger chunks (as the current emem allocator does), if that endsupsaving enough CPU, by making fewer allocate and free calls to the underlying memory allocator, so as to make it worth whatever wasted memory we haveatthe ends of chunks?One step further, instead of mempools, I think wireshark could have great interest in implementing slabs (slab allocator). Slabs hadinitiallybeen designed for kernel with several advantages over traditional allocators in terms of resources needed to allocate (CPU), (external / internal) fragmentation and also cache friendliness (most of the traditional allocators don't care). I've attached some slides about ahigh-leveldescription of slab. Since then, another paper has been written showing someimprovementsand what it took to write a slab for user-space (libumem). There is another well-known exampel out there, called memcache, that implements its own version (and could be a good intial point for wireshark implementation, who knows? :))If I understand correctly, a slab allocator provides the most benefit when you have to alloc/free a large number of the same type ofobject,you're right, that's where slab is the most efficient at. Although,thesecond paper shows it can be efficient for general purpose allocation based on size and not specific structure.but I don't know if this is necessarily the case in Wireshark. There are probably places where it would be useful, but I can't think ofanyoff the top of my head. TVBs maybe? I know emem is currently used all over the place for all sorts of different objects...I guess the most obvious would be emem_tree (emem_tree_node) might beanexample used all over and over while dissecting. :) There is indeed a bunch of different objects allocated with emem.Also,it might be used to allocate memory for some fragments.Ah, yes, the various emem data structures (tree, stack, etc.) would likely benefit from slab allocators. Converting them to use slabs would be something to do while porting them from emem to wmem.Since your interface seems to allow it, we could create several slabs types, one for each specific structures that are allocated very frequently (emem_tree_node?), others for packets/fragments with some tuned slabs sizes and another with some generic sizes.That seems reasonable, presumably with some shared slab code doing the type-agnostic heavy lifting. I'll have to give a bit of thought to what the interface for that would be like - if you already have an interface in mind, please share :)Are the slab allocators mentioned "homegrown" or provided by the hostOS. Ifthe latter, what platforms are they available on?Homegrown on top of malloc/g_malloc/mmap, I believe. A slab allocator is (or was) used internally in the linux and solaris kernels, but has never been exposed to userspace to my knowledge.
It's indeed not exposed to users. It's used internally as a "kernel object cache allocator". But, memcached has a user-space implementation that could -probably- be leveraged for wireshark. ___________________________________________________________________________
Sent via: Wireshark-dev mailing list <wireshark-dev () wireshark org> Archives: http://www.wireshark.org/lists/wireshark-dev Unsubscribe: https://wireshark.org/mailman/options/wireshark-dev mailto:wireshark-dev-request () wireshark org ?subject=unsubscribe
___________________________________________________________________________ Sent via: Wireshark-dev mailing list <wireshark-dev () wireshark org> Archives: http://www.wireshark.org/lists/wireshark-dev Unsubscribe: https://wireshark.org/mailman/options/wireshark-dev mailto:wireshark-dev-request () wireshark org?subject=unsubscribe
Current thread:
- RFD: The Future of Memory Management in Wireshark Evan Huus (Oct 18)
- Re: RFD: The Future of Memory Management in Wireshark Guy Harris (Oct 23)
- Re: RFD: The Future of Memory Management in Wireshark Evan Huus (Oct 23)
- Re: RFD: The Future of Memory Management in Wireshark Sébastien Tandel (Oct 24)
- Re: RFD: The Future of Memory Management in Wireshark Evan Huus (Oct 24)
- Re: RFD: The Future of Memory Management in Wireshark Sébastien Tandel (Oct 26)
- Re: RFD: The Future of Memory Management in Wireshark Evan Huus (Oct 26)
- Re: RFD: The Future of Memory Management in Wireshark Graham Bloice (Oct 26)
- Re: RFD: The Future of Memory Management in Wireshark Evan Huus (Oct 26)
- Re: RFD: The Future of Memory Management in Wireshark Sébastien Tandel (Oct 26)
- Re: RFD: The Future of Memory Management in Wireshark Evan Huus (Oct 26)
- Re: RFD: The Future of Memory Management in Wireshark Sébastien Tandel (Oct 26)
- Re: RFD: The Future of Memory Management in Wireshark Guy Harris (Oct 23)
- Re: RFD: The Future of Memory Management in Wireshark Evan Huus (Oct 25)
- Re: RFD: The Future of Memory Management in Wireshark Jeff Morriss (Oct 25)
- Re: RFD: The Future of Memory Management in Wireshark Evan Huus (Oct 25)
- Re: RFD: The Future of Memory Management in Wireshark Pascal Quantin (Oct 25)
- Re: RFD: The Future of Memory Management in Wireshark Dirk Jagdmann (Oct 27)
- Re: RFD: The Future of Memory Management in Wireshark Evan Huus (Oct 27)
- Re: RFD: The Future of Memory Management in Wireshark Evan Huus (Oct 28)