Linus Torvalds <torvalds@xxxxxxxx> wrote:
Well, the thing is, you really _do_ want to mmap as much as possible of the pack-file as possible, if mmap() works.
Juergen Ruehle <j.ruehle@xxxxxxxx> wrote:
I did some quick performance check and the NO_MMAP code path seems to be as fast as the mmap one (even much faster in some cases). So the combination of windows' memory management and git mmap usage doesn't seem so hot
How about making this parameter (do-use-mmap vs not-use-mmap) a *runtime* parameter ? (Env. var. $GIT_MMAP or $GIT_USE_MMAP ?). What do you think ? I see two benefits: (1) much easier to benchmark two methods against each other (2) will always work on cygwin (automatic fallback to working method at runtime; say depending on filesystem) What do you say ? (Only in case when MMAP is enabled at build-time, of course) Yakov - : send the line "unsubscribe git" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html