lrmalloc is an efficient, lock-free malloc(3) implementation.

It is derived from Michael's lock-free allocator, improved with modern memory allocator features such as thread caches and allocator/user memory segregation.

lrmalloc's philosophy is to provide fast synchronization-free allocations as much sa possible through the use of thread caches, and only use lock-free operations to fill and empty thread caches.

To compile, just download this repository and run

make

If successfully compiled, you can link lrmalloc with your application at compile time with

-llrmalloc

or you can dynamically link it with your application by using LD_PRELOAD (if your application was not statically linked with another memory allocator).

LD_PRELOAD=lrmalloc.so ./your_application

License: MIT

Read file COPYING.