Comments on: “Vlad and analysis of dtrace was used” http://blog.pavlov.net/2007/12/04/vlad-and-analysis-of-dtrace-was-used/ Ramblings from the mind of Stuart Parmenter Fri, 16 May 2008 02:34:24 +0000 http://wordpress.org/?v=MU By: brian v http://blog.pavlov.net/2007/12/04/vlad-and-analysis-of-dtrace-was-used/#comment-3029 brian v Thu, 13 Mar 2008 03:12:38 +0000 http://blog.pavlov.net/2007/12/04/vlad-and-analysis-of-dtrace-was-used/#comment-3029 all this great effort, and still the installer is broken on server 2003. with b3, i could just keep running it a dozen times to get everything (xul.dll, etc). Now, half the dir. : - ( all this great effort, and still the installer is broken on server 2003. with b3, i could just keep running it a dozen times to get everything (xul.dll, etc). Now, half the dir.

: - (

]]> By: Firefox 3 Memory Usage « pavlov.net http://blog.pavlov.net/2007/12/04/vlad-and-analysis-of-dtrace-was-used/#comment-2884 Firefox 3 Memory Usage « pavlov.net Wed, 12 Mar 2008 06:16:01 +0000 http://blog.pavlov.net/2007/12/04/vlad-and-analysis-of-dtrace-was-used/#comment-2884 [...] carefully studied the fragmentation effects of various allocators and concluded that jemalloc gave us the smallest [...] [...] carefully studied the fragmentation effects of various allocators and concluded that jemalloc gave us the smallest [...]

]]> By: mark http://blog.pavlov.net/2007/12/04/vlad-and-analysis-of-dtrace-was-used/#comment-2838 mark Fri, 08 Feb 2008 13:13:46 +0000 http://blog.pavlov.net/2007/12/04/vlad-and-analysis-of-dtrace-was-used/#comment-2838 excellent. i will grab it today. thanks. excellent. i will grab it today. thanks.

]]> By: pavlov http://blog.pavlov.net/2007/12/04/vlad-and-analysis-of-dtrace-was-used/#comment-2837 pavlov Fri, 08 Feb 2008 06:14:11 +0000 http://blog.pavlov.net/2007/12/04/vlad-and-analysis-of-dtrace-was-used/#comment-2837 mark: it is in cvs under mozilla/memory/jemalloc mark: it is in cvs under mozilla/memory/jemalloc

]]> By: mark http://blog.pavlov.net/2007/12/04/vlad-and-analysis-of-dtrace-was-used/#comment-2836 mark Thu, 07 Feb 2008 22:54:59 +0000 http://blog.pavlov.net/2007/12/04/vlad-and-analysis-of-dtrace-was-used/#comment-2836 Would be curious to get your port of jemalloc to Linux. Would like to try with an application that is having memory fragmentation issues. Would be curious to get your port of jemalloc to Linux. Would like to try with an application that is having memory fragmentation issues.

]]> By: pavlov http://blog.pavlov.net/2007/12/04/vlad-and-analysis-of-dtrace-was-used/#comment-999 pavlov Thu, 06 Dec 2007 22:14:51 +0000 http://blog.pavlov.net/2007/12/04/vlad-and-analysis-of-dtrace-was-used/#comment-999 Ian: everything but jemalloc is mostly cross-platform currently (aside from the platform allocators, obviously). I ported jemalloc to Linux and Mac in a few hours and Windows shouldn't take much longer. Ian: everything but jemalloc is mostly cross-platform currently (aside from the platform allocators, obviously). I ported jemalloc to Linux and Mac in a few hours and Windows shouldn’t take much longer.

]]> By: More allocator data — tcmalloc edition « pavlov.net http://blog.pavlov.net/2007/12/04/vlad-and-analysis-of-dtrace-was-used/#comment-998 More allocator data — tcmalloc edition « pavlov.net Thu, 06 Dec 2007 21:15:57 +0000 http://blog.pavlov.net/2007/12/04/vlad-and-analysis-of-dtrace-was-used/#comment-998 [...] pavlov.net Ramblings from the mind of Stuart Parmenter « “Vlad and analysis of dtrace was used” [...] [...] pavlov.net Ramblings from the mind of Stuart Parmenter « “Vlad and analysis of dtrace was used” [...]

]]> By: jimis http://blog.pavlov.net/2007/12/04/vlad-and-analysis-of-dtrace-was-used/#comment-980 jimis Thu, 06 Dec 2007 13:18:30 +0000 http://blog.pavlov.net/2007/12/04/vlad-and-analysis-of-dtrace-was-used/#comment-980 I think that the slowest but most space efficient settings, set by mallopt() would be: M_MXFAST 0 (disables fastbins for small allocations) M_TRIM_THRESHOLD 0 M_MMAP_THRESHOLD 4*1024 (uses mmap() instead of brk() for all memory allocations?) M_MMAP_MAX 32*1024*1024 (and uses it even for large allocations, even if mmap() is slower than brk()) I think that the slowest but most space efficient settings, set by mallopt() would be:
M_MXFAST 0 (disables fastbins for small allocations)
M_TRIM_THRESHOLD 0
M_MMAP_THRESHOLD 4*1024 (uses mmap() instead of brk() for all memory allocations?)
M_MMAP_MAX 32*1024*1024 (and uses it even for large allocations, even if mmap() is slower than brk())

]]> By: jimis http://blog.pavlov.net/2007/12/04/vlad-and-analysis-of-dtrace-was-used/#comment-979 jimis Thu, 06 Dec 2007 12:28:15 +0000 http://blog.pavlov.net/2007/12/04/vlad-and-analysis-of-dtrace-was-used/#comment-979 Before using alternative allocators on linux, you should have a look at glibc's mallopt(). There are *many* ways to make the allocation strategy slower but more space efficient.... Its reference is in the source: http://sourceware.org/cgi-bin/cvsweb.cgi/libc/malloc/malloc.c?rev=1.181&content-type=text/x-cvsweb-markup&cvsroot=glibc And a very nice article: http://www.linuxjournal.com/node/6390/print Before using alternative allocators on linux, you should have a look at glibc’s mallopt(). There are *many* ways to make the allocation strategy slower but more space efficient…. Its reference is in the source:
http://sourceware.org/cgi-bin/cvsweb.cgi/libc/malloc/malloc.c?rev=1.181&content-type=text/x-cvsweb-markup&cvsroot=glibc

And a very nice article:
http://www.linuxjournal.com/node/6390/print

]]> By: Ian M http://blog.pavlov.net/2007/12/04/vlad-and-analysis-of-dtrace-was-used/#comment-955 Ian M Wed, 05 Dec 2007 09:27:08 +0000 http://blog.pavlov.net/2007/12/04/vlad-and-analysis-of-dtrace-was-used/#comment-955 One thing you didn't mention was which of these are cross-platform or platform-specific. One thing you didn’t mention was which of these are cross-platform or platform-specific.

]]>