I had a large number of comments to make but the length of time required to describe each of the points and the time required to do it in patch-format was roughly comparable so here are a load of patches.
There is still work that needs to be done. --help output is needed and a manual page describing the methodology are both needed. The draft paper I have on measuring TLB misses should help write the manual page. For others watching, the paper is not publicly available. It's a work-in-progress that I sent a draft to Eric before he started writing this tool. I don't know when I'll get to publish it but at least the script can be verified. I tested this myself on a X86 P4, a X86-64 Phenom and a PPC64 PPC970. It needs testing on POWER5, POWER5+ and POWER6 minimally. POWER6 may be very problamatic as it has a fairly different MMU and I think it lacks the required CPU event to measure miss cost as described. calibrator might work out or else a third method of estimating TLB miss is needed. tlbmiss_cost.sh | 329 +++++++++++++++++++++++++++++++++++++++++++++++-------- 1 files changed, 282 insertions(+), 47 deletions(-) ------------------------------------------------------------------------------ Let Crystal Reports handle the reporting - Free Crystal Reports 2008 30-Day trial. Simplify your report design, integration and deployment - and focus on what you do best, core application coding. Discover what's new with Crystal Reports now. http://p.sf.net/sfu/bobj-july _______________________________________________ Libhugetlbfs-devel mailing list Libhugetlbfs-devel@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/libhugetlbfs-devel
