Date: Wed, 30 Nov 2005 23:20:43 -0800 From: Jason Evans <jasone@canonware.com> To: Hiten Pandya <hiten.pandya@gmail.com> Cc: current@freebsd.org Subject: Re: New libc malloc patch Message-ID: <D53F6841-4A7D-4E61-A580-FE42EABE086A@canonware.com> In-Reply-To: <9b1858120511290252w1e6d3458m@mail.gmail.com> References: <B6653214-2181-4342-854D-323979D23EE8@canonware.com> <9b1858120511290252w1e6d3458m@mail.gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On Nov 29, 2005, at 2:52 AM, Hiten Pandya wrote: > I see that you have included an implementation of red-black tree CPP > macros, but wouldn't it be better if you were to use the ones in > <sys/tree.h> ? I have only had a precursory look, but I would have > thought that would be the way to go. There's an updated patch available: http://www.canonware.com/~jasone/jemalloc/jemalloc_20051201a.diff This patch includes the following changes: *) Use sys/tree.h rather than a separate red-black tree implementation. *) Use the __isthreaded symbol to avoid locking for single-threaded programs, and to simplify malloc initialization. The extra branches that are required to check __isthreaded should be more than offset by the removal of an atomic compare/swap operation. *) Fix an obscure bug (very difficult to trigger without changing some compile-time constants). Jason
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?D53F6841-4A7D-4E61-A580-FE42EABE086A>