From: Andrea Arcangeli <aarcange@redhat.com>
To: linux-mm@kvack.org
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Subject: [PATCH 00 of 25] Transparent Hugepage support #1
Date: Sat, 14 Nov 2009 17:38:18 -0000 [thread overview]
Message-ID: <patchbomb.1258220298@v2.random> (raw)
Hello,
Lately I've been working to make KVM use hugepages transparently without the
usual restrictions of hugetlbfs. The RFC got postitive review so I splitted
the patches. Maybe they can be splitted more but this is a start and it should
allow for easier code review plus there was some more development ;). See
patch 24/25 for all detailed comments on this feature.
I'll be offline next week but I wanted to send the last updates so you can
more easily review latest status while I'm away.
TODO:
1) add proper sysfs support in preparation for khugepaged daemon tunes
(obsolete the temporary/debug sysctl)
2) fixup smaps/pagemap stats (Adam you expressed interest in this area,
if you have patches removing split_huge_page_* they're welcome ;)
3) create collapse_huge_page
4) add madvise(MADV_HUGEPAGE)
5) add khugepaged calling collapse_huge_page on madvise(MADV_HUGEPAGE) regions
6) potential removal of split_huge_page from mremap/mprotect (lowprio)
If you want to more easily interact with this patchset I uploaded a quilt tree
here:
http://www.kernel.org/pub/linux/kernel/people/andrea/patches/v2.6/2.6.32-rc7/transparent_hugepage-1/
Thanks,
Andrea
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next reply other threads:[~2009-11-14 18:10 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-11-14 17:38 Andrea Arcangeli [this message]
2009-11-14 17:38 ` [PATCH 01 of 25] bit_lock smp memory barriers Andrea Arcangeli
2009-11-14 17:38 ` [PATCH 02 of 25] compound_lock Andrea Arcangeli
2009-11-14 17:38 ` [PATCH 03 of 25] alter compound get_page/put_page Andrea Arcangeli
2009-11-14 17:38 ` [PATCH 04 of 25] clear compound mapping Andrea Arcangeli
2009-11-14 17:38 ` [PATCH 05 of 25] add native_set_pmd_at Andrea Arcangeli
2009-11-14 17:38 ` [PATCH 06 of 25] add pmd paravirt ops Andrea Arcangeli
2009-11-14 17:38 ` [PATCH 07 of 25] no paravirt version of pmd ops Andrea Arcangeli
2009-11-14 17:38 ` [PATCH 08 of 25] export maybe_mkwrite Andrea Arcangeli
2009-11-14 17:38 ` [PATCH 09 of 25] comment reminder in destroy_compound_page Andrea Arcangeli
2009-11-14 17:38 ` [PATCH 10 of 25] config_transparent_hugepage Andrea Arcangeli
2009-11-14 17:38 ` [PATCH 11 of 25] add pmd mangling functions to x86 Andrea Arcangeli
2009-11-14 17:38 ` [PATCH 12 of 25] add pmd mangling generic functions Andrea Arcangeli
2009-11-14 17:38 ` [PATCH 13 of 25] special pmd_trans_* functions Andrea Arcangeli
2009-11-14 17:38 ` [PATCH 14 of 25] bail out gup_fast on freezed pmd Andrea Arcangeli
2009-11-14 17:38 ` [PATCH 15 of 25] pte alloc trans frozen Andrea Arcangeli
2009-11-14 17:38 ` [PATCH 16 of 25] add pmd mmu_notifier helpers Andrea Arcangeli
2009-11-14 17:38 ` [PATCH 17 of 25] clear page compound Andrea Arcangeli
2009-11-14 17:38 ` [PATCH 18 of 25] add pmd_huge_pte to mm_struct Andrea Arcangeli
2009-11-14 17:38 ` [PATCH 19 of 25] ensure mapcount is taken on head pages Andrea Arcangeli
2009-11-14 17:38 ` [PATCH 20 of 25] add page_check_address_pmd to find the pmd mapping a transparent hugepage Andrea Arcangeli
2009-11-14 17:38 ` [PATCH 21 of 25] split_huge_page_mm/vma Andrea Arcangeli
2009-11-14 17:38 ` [PATCH 22 of 25] split_huge_page paging Andrea Arcangeli
2009-11-14 17:38 ` [PATCH 23 of 25] pmd_trans_huge migrate bugcheck Andrea Arcangeli
2009-11-14 17:38 ` [PATCH 24 of 25] transparent hugepage core Andrea Arcangeli
2009-11-14 17:38 ` [PATCH 25 of 25] kvm mmu transparent hugepage support Andrea Arcangeli
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=patchbomb.1258220298@v2.random \
--to=aarcange@redhat.com \
--cc=linux-mm@kvack.org \
--cc=mtosatti@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.