Re: [patch] fork() speedup, 2.1.90

MOLNAR Ingo (mingo@chiara.csoma.elte.hu)
Thu, 19 Mar 1998 14:36:18 +0100 (CET)


On Thu, 19 Mar 1998, Jakub Jelinek wrote:

> Oh no, Ingo, save yourself the work and look sometimes into vger CVS.
> Page table caching is implemented for all the platforms but m68k's pgd/pmd's
> (just pte's are cached on m68k). It is tested and hopefully should go to the
> mainstream during the upcoming merge.

ugh, silly me. I saw you were doing something but never looked into it, i
thought it was the memory.c inline hack that went into 2.1 recently ;)
Maybe could you guys working on the vger tree announce bigger hacks on
linux-kernel, so people who dont have fast enough CVS access dont waste
time ;)

a related issue, i first tried to implement shared page tables, and in the
process of cleaning it up i noticed that it makes almost no sense (we have
only a few page tables usually, and they almost always have dirty pages).
Then i noticed how compact our page tables actually are and implemented
the above hack ... ;)

-- mingo

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu