[PATCH]PAGE_GH patch revised (now it is quite stable)

• Next message: Jamie Lokier: "Re: multimounting cdroms ???"
• Previous message: Andrey Savochkin: "Re: RLIM_INFINITY inconsistency between archs"
• Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

Sorry everyone for so frequent update of my patch.

I found a serious bug in my patch to the do_mmap routine.
I used "flags" argument in my patch, but it is modified prior as a
tempolary variable to save vm_flags. Then I could not control
the page_gh mapping as I wished.

Get the patch from my WEB,

http://shimizu-lab.et.u-tokai.ac.jp/~nshimizu/index.html

Now it seems quite stable and the performance is good.
In DP264 system, memory transpose benchmark runs about 4times faster
than the origianl kernel. Good enough for many HPC applications.

Please try and report anything you noticed.

Enjoy,

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

• Next message: Jamie Lokier: "Re: multimounting cdroms ???"
• Previous message: Andrey Savochkin: "Re: RLIM_INFINITY inconsistency between archs"
• Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

This archive was generated by hypermail 2b29 : Mon Jul 31 2000 - 21:00:26 EST