From owner-cvs-all Thu Apr 5 8:17:38 2001 Delivered-To: cvs-all@freebsd.org Received: from freefall.freebsd.org (freefall.freebsd.org [216.136.204.21]) by hub.freebsd.org (Postfix) with ESMTP id ABD1C37B43F; Thu, 5 Apr 2001 08:17:33 -0700 (PDT) (envelope-from sobomax@FreeBSD.org) Received: (from sobomax@localhost) by freefall.freebsd.org (8.11.1/8.11.1) id f35FHXb44816; Thu, 5 Apr 2001 08:17:33 -0700 (PDT) (envelope-from sobomax) Message-Id: <200104051517.f35FHXb44816@freefall.freebsd.org> From: Maxim Sobolev Date: Thu, 5 Apr 2001 08:17:33 -0700 (PDT) To: cvs-committers@FreeBSD.org, cvs-all@FreeBSD.org Subject: cvs commit: ports/devel Makefile ports/devel/dlmalloc Makefile distinfo pkg-comment pkg-descr pkg-message pkg-plist ports/devel/dlmalloc/files Makefile README.FreeBSD X-FreeBSD-CVS-Branch: HEAD Sender: owner-cvs-all@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG sobomax 2001/04/05 08:17:33 PDT Modified files: devel Makefile Added files: devel/dlmalloc Makefile distinfo pkg-comment pkg-descr pkg-message pkg-plist devel/dlmalloc/files Makefile README.FreeBSD Log: Add dlmalloc 2.7.0, a very efficient malloc/free/realloc implementation. According to my tests it is *amazingly* efficient - it gave me about 10% memory saving (SIZE in the top(1)) for the large processes like X and jre without any measureable performance saturation. Moreover, due to not very clear for me reasons Python benchmark (pybench) is about 60% (!!!) faster with this allocator comparing to the libc one. Obviously we should investigate this further and if there is no error then tune either Python or our own malloc. Alternatively we may evaluate a possibility to make it (or part of it) our default malloc(), because it is friendly licensed and actively maintained. Revision Changes Path 1.490 +2 -1 ports/devel/Makefile To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe cvs-all" in the body of the message