Re: page fault scalability patch V11 [0/7]: overview

From: William Lee Irwin III (wli_at_holomorphy.com)
Date: 11/20/04

  • Next message: janitor_at_sternwelten.at: "[patch 7/8] scsi/zalon: Added KERN macro to printk()" 
    Date:	Fri, 19 Nov 2004 18:03:06 -0800
To: Linus Torvalds <torvalds@osdl.org>

    On Fri, Nov 19, 2004 at 11:59:03AM -0800, Linus Torvalds wrote:
    > You could also make "rss" be a _signed_ integer per-thread.
    > When unmapping a page, you decrement one of the threads that shares the mm
    > (doesn't matter which - which is why the per-thread rss may go negative),
    > and when mapping a page you increment it.
    > Then, anybody who actually wants a global rss can just iterate over
    > threads and add it all up. If you do it under the mmap_sem, it's stable,
    > and if you do it outside the mmap_sem it's imprecise but stable in the
    > long term (ie errors never _accumulate_, like the non-atomic case will
    > do).
    > Does anybody care enough? Maybe, maybe not. It certainly sounds a hell of
    > a lot better than the periodic scan.

    Unprivileged triggers for full-tasklist scans are NMI oops material.

    -- wli
    -
    To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
    the body of a message to majordomo@vger.kernel.org
    More majordomo info at http://vger.kernel.org/majordomo-info.html
    Please read the FAQ at http://www.tux.org/lkml/

  • Next message: janitor_at_sternwelten.at: "[patch 7/8] scsi/zalon: Added KERN macro to printk()"

    Relevant Pages

    • Re: page fault scalability patch V11 [0/7]: overview
      ... > and when mapping a page you increment it. ... the unbounded error of sloppy rss. ... send the line "unsubscribe linux-kernel" in ...
      (Linux-Kernel)
    • Re: Kernel bug: mm/rmap.c:483 and related {now 2.6.8}
      ... mapping should be NULL (or at least a pointer into kernel memory). ... say message reappeared twice with identical addresses: ... send the line "unsubscribe linux-kernel" in ...
      (Linux-Kernel)
    • Re: [PATCH 17/20] FRV: Better mmap support in uClinux
      ... > I think this could be done at msync, munmap and exit time? ... > flushing the entire mapping, but it's still correct (and POSIX ... send the line "unsubscribe linux-kernel" in ...
      (Linux-Kernel)
    • RE: x86-64 dual core mapping
      ... >> It seems right mapping should be ... > Are you sure you dont have a broken SRAT table? ... > processor 2/2 rip ... send the line "unsubscribe linux-kernel" in ...
      (Linux-Kernel)
    • Re: How to find out which pages were copied-on-write?
      ... application which is doing an mmap on a file as a MAP_PRIVATE mapping. ... The memory area is then handed to a library which may modify some pages. ... > Yet another feature that I could use if it were available: ... send the line "unsubscribe linux-kernel" in ...
      (Linux-Kernel)