Re: mysql scaling questions

Kris Kennaway wrote:

That's why it's important to dig into the details of what the benchmark
is actually doing before you conclude that "the numbers are higher for
linux, therefore it has faster syscalls".

Can you propose a simpler syscall on the GENERIC kernel that could be
used instead of getpid()? Unixbench is easily patched so the theory I
put out can be easily checked.


Attachment: signature.asc
Description: OpenPGP digital signature

Relevant Pages

  • Re: HLA Linux syscalls and related stuff
    ... > syscalls, and what the HLA syscall wrappers do with those codes. ... > Outside of the linux directory, I found about 90 instances that test ...
    (alt.lang.asm)
  • Re: HLA Linux syscalls and related stuff
    ... >>I'm not 100% certain about how Linux handles the return codes from ... >>syscalls, and what the HLA syscall wrappers do with those codes. ... For a FreeBSD version, I can see two ...
    (alt.lang.asm)
  • Re: Kernel header files in applications and GPL issues
    ... > that works on Linux and has a license that you like, ... > complying with the LGPL. ... > userland programs for Linux which don't have to abide by the GPL. ... > fg> that doesnt use any syscalls ... ...
    (comp.os.linux.development.apps)
  • Re: mysql scaling questions
    ... same file which is running into exclusive locking in the kernel ... Isn't this common for software developed for Linux? ... Even if Linux magically has faster syscalls somehow, they are still not zero cost so avoiding huge numbers of unnecessary trips ... Also I believe glibc caches getpid() in libc (again that ...
    (freebsd-performance)
  • Re: Can someone with brains be President?
    ... > H3rL is H3sm installed into the Linux kernel as a kernel thread. ... > eforthl is eforth for Linux with 160 syscalls and other tweaks ... > without a HD and has over 200k free space on the floppy, ash, eforthl, ...
    (alt.politics)