>
> Kanoj Sarcar wrote:
> >
> > The mips64 SMP kernel completed a mips kernel compile on a 8 cpu
> > o2000, with approx 128 Mb memory.
> >
> > Here are some timings:
> >
> > make -j8:
> > 46.34user 32.34system 6:25.91elapsed 20%CPU (0avgtext+0avgdata
> > 0maxresident)k
> > 0inputs+0outputs (497100major+1814481minor)pagefaults 0swaps
> >
> > make -j4
> > 12.56user 16.34system 6:37.93elapsed 7%CPU (0avgtext+0avgdata 0maxresident)k
> > 0inputs+0outputs (497100major+1807168minor)pagefaults 0swaps
> >
> > make -j32
> > 44.00user 29.25system 6:35.93elapsed 18%CPU (0avgtext+0avgdata
> > 0maxresident)k
> > 0inputs+0outputs (497174major+1826803minor)pagefaults 0swaps
>
>
> Awesome! And the resultant kernel boots ok? ;-)
Didn't try ... basically, even a mips kernel built on a Indy probably
has a big chance of not working right now. On top of that, the compiler
used on the o2k is of unknown origin, I think Ralf/Ulf was using this
compiler for the mips binutils work. The compilers from known rpms
can't quite compile the kernel (on mips and mips64).
>
> I wonder if we can get base-line stats on a 4-CPU X86 system,
> say for -j4 & -j8 and compare that with the O2K system.
No, we are not at a stage we can do raw performance comparisions
yet. Scalability studies are a little more acceptable, but we
still need to make the arch code utilize the hardware better.
> What version of the kernel are you using, 2.3.99preX?
I tried 2.3.99pre6, but pre8 became tot yesterday or so. I haven't
tried a kernel compile with that, but tot booted/telneted okay.
Kanoj
>
>
> --------------------------------------------------------------------------
> Rajagopal Ananthanarayanan ("ananth")
> Member Technical Staff, SGI.
> --------------------------------------------------------------------------
>
|