From: Ric Mason <ric.masonn@gmail.com>
To: Hugh Dickins <hughd@google.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
Mel Gorman <mgorman@suse.de>, Petr Holasek <pholasek@redhat.com>,
Andrea Arcangeli <aarcange@redhat.com>,
Izik Eidus <izik.eidus@ravellosystems.com>,
linux-kernel@vger.kernel.org, linux-mm@kvack.org
Subject: Re: [PATCH 2/7] ksm: treat unstable nid like in stable tree
Date: Fri, 01 Mar 2013 13:29:15 +0800 [thread overview]
Message-ID: <51303CAB.3080406@gmail.com> (raw)
In-Reply-To: <alpine.LNX.2.00.1302221250440.6100@eggly.anvils>
Hi Hugh,
On 02/23/2013 05:03 AM, Hugh Dickins wrote:
> On Fri, 22 Feb 2013, Ric Mason wrote:
>> On 02/21/2013 04:20 PM, Hugh Dickins wrote:
>>> An inconsistency emerged in reviewing the NUMA node changes to KSM:
>>> when meeting a page from the wrong NUMA node in a stable tree, we say
>>> that it's okay for comparisons, but not as a leaf for merging; whereas
>>> when meeting a page from the wrong NUMA node in an unstable tree, we
>>> bail out immediately.
>> IIUC
>> - ksm page from the wrong NUMA node will be add to current node's stable tree
Please forgive my late response.
> That should never happen (and when I was checking with a WARN_ON it did
> not happen). What can happen is that a node already in a stable tree
> has its page migrated away to another NUMA node.
>
>> - normal page from the wrong NUMA node will be merged to current node's
>> stable tree <- where I miss here? I didn't see any special handling in
>> function stable_tree_search for this case.
> nid = get_kpfn_nid(page_to_pfn(page));
> root = root_stable_tree + nid;
>
> to choose the right tree for the page, and
>
> if (get_kpfn_nid(stable_node->kpfn) !=
> NUMA(stable_node->nid)) {
> put_page(tree_page);
> goto replace;
> }
>
> to make sure that we don't latch on to a node whose page got migrated away.
I think the ksm implementation for num awareness is buggy.
For page migratyion stuff, new page is allocated from node *which page
is migrated to*.
- when meeting a page from the wrong NUMA node in an unstable tree
get_kpfn_nid(page_to_pfn(page)) *==* page_to_nid(tree_page)
How can say it's okay for comparisons, but not as a leaf for merging?
- when meeting a page from the wrong NUMA node in an stable tree
- meeting a normal page
- meeting a page which is ksm page before migration
get_kpfn_nid(stable_node->kpfn) != NUMA(stable_node->nid) can't
capture them since stable_node is for tree page in current stable tree.
They are always equal.
>
>> - normal page from the wrong NUMA node will compare but not as a leaf for
>> merging after the patch
> I don't understand you there, but hope my remarks above resolve it.
>
> Hugh
--
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>
WARNING: multiple messages have this Message-ID (diff)
From: Ric Mason <ric.masonn@gmail.com>
To: Hugh Dickins <hughd@google.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
Mel Gorman <mgorman@suse.de>, Petr Holasek <pholasek@redhat.com>,
Andrea Arcangeli <aarcange@redhat.com>,
Izik Eidus <izik.eidus@ravellosystems.com>,
linux-kernel@vger.kernel.org, linux-mm@kvack.org
Subject: Re: [PATCH 2/7] ksm: treat unstable nid like in stable tree
Date: Fri, 01 Mar 2013 13:29:15 +0800 [thread overview]
Message-ID: <51303CAB.3080406@gmail.com> (raw)
In-Reply-To: <alpine.LNX.2.00.1302221250440.6100@eggly.anvils>
Hi Hugh,
On 02/23/2013 05:03 AM, Hugh Dickins wrote:
> On Fri, 22 Feb 2013, Ric Mason wrote:
>> On 02/21/2013 04:20 PM, Hugh Dickins wrote:
>>> An inconsistency emerged in reviewing the NUMA node changes to KSM:
>>> when meeting a page from the wrong NUMA node in a stable tree, we say
>>> that it's okay for comparisons, but not as a leaf for merging; whereas
>>> when meeting a page from the wrong NUMA node in an unstable tree, we
>>> bail out immediately.
>> IIUC
>> - ksm page from the wrong NUMA node will be add to current node's stable tree
Please forgive my late response.
> That should never happen (and when I was checking with a WARN_ON it did
> not happen). What can happen is that a node already in a stable tree
> has its page migrated away to another NUMA node.
>
>> - normal page from the wrong NUMA node will be merged to current node's
>> stable tree <- where I miss here? I didn't see any special handling in
>> function stable_tree_search for this case.
> nid = get_kpfn_nid(page_to_pfn(page));
> root = root_stable_tree + nid;
>
> to choose the right tree for the page, and
>
> if (get_kpfn_nid(stable_node->kpfn) !=
> NUMA(stable_node->nid)) {
> put_page(tree_page);
> goto replace;
> }
>
> to make sure that we don't latch on to a node whose page got migrated away.
I think the ksm implementation for num awareness is buggy.
For page migratyion stuff, new page is allocated from node *which page
is migrated to*.
- when meeting a page from the wrong NUMA node in an unstable tree
get_kpfn_nid(page_to_pfn(page)) *==* page_to_nid(tree_page)
How can say it's okay for comparisons, but not as a leaf for merging?
- when meeting a page from the wrong NUMA node in an stable tree
- meeting a normal page
- meeting a page which is ksm page before migration
get_kpfn_nid(stable_node->kpfn) != NUMA(stable_node->nid) can't
capture them since stable_node is for tree page in current stable tree.
They are always equal.
>
>> - normal page from the wrong NUMA node will compare but not as a leaf for
>> merging after the patch
> I don't understand you there, but hope my remarks above resolve it.
>
> Hugh
next prev parent reply other threads:[~2013-03-01 5:29 UTC|newest]
Thread overview: 56+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-02-21 8:17 [PATCH 0/7] ksm: responses to NUMA review Hugh Dickins
2013-02-21 8:17 ` Hugh Dickins
2013-02-21 8:19 ` [PATCH 1/7] ksm: add some comments Hugh Dickins
2013-02-21 8:19 ` Hugh Dickins
2013-02-22 4:26 ` Ric Mason
2013-02-22 4:26 ` Ric Mason
2013-02-22 20:50 ` Hugh Dickins
2013-02-22 20:50 ` Hugh Dickins
2013-02-21 8:20 ` [PATCH 2/7] ksm: treat unstable nid like in stable tree Hugh Dickins
2013-02-21 8:20 ` Hugh Dickins
2013-02-22 7:13 ` Ric Mason
2013-02-22 7:13 ` Ric Mason
2013-02-22 21:03 ` Hugh Dickins
2013-02-22 21:03 ` Hugh Dickins
2013-03-01 5:29 ` Ric Mason [this message]
2013-03-01 5:29 ` Ric Mason
2013-03-01 20:03 ` Hugh Dickins
2013-03-01 20:03 ` Hugh Dickins
2013-03-02 1:10 ` Ric Mason
2013-03-02 1:10 ` Ric Mason
2013-03-02 2:57 ` Hugh Dickins
2013-03-02 2:57 ` Hugh Dickins
2013-03-06 1:28 ` Will Huck
2013-03-06 1:28 ` Will Huck
2013-03-06 4:31 ` Hugh Dickins
2013-03-06 4:31 ` Hugh Dickins
2013-03-06 2:37 ` Ric Mason
2013-03-06 2:37 ` Ric Mason
2013-03-06 5:05 ` Hugh Dickins
2013-03-06 5:05 ` Hugh Dickins
2013-03-06 6:58 ` Ric Mason
2013-03-06 6:58 ` Ric Mason
2013-03-06 10:18 ` Ric Mason
2013-03-06 10:18 ` Ric Mason
2013-03-07 23:26 ` Ric Mason
2013-03-07 23:26 ` Ric Mason
2013-02-21 8:22 ` [PATCH 3/7] ksm: shrink 32-bit rmap_item back to 32 bytes Hugh Dickins
2013-02-21 8:22 ` Hugh Dickins
2013-02-21 8:23 ` [PATCH 4/7] mm,ksm: FOLL_MIGRATION do migration_entry_wait Hugh Dickins
2013-02-21 8:23 ` Hugh Dickins
2013-02-21 8:25 ` [PATCH 5/7] mm,ksm: swapoff might need to copy Hugh Dickins
2013-02-21 8:25 ` Hugh Dickins
2013-02-21 14:53 ` Johannes Weiner
2013-02-21 14:53 ` Johannes Weiner
2013-02-22 17:16 ` Hugh Dickins
2013-02-22 17:16 ` Hugh Dickins
2013-02-21 8:27 ` [PATCH 6/7] mm: cleanup "swapcache" in do_swap_page Hugh Dickins
2013-02-21 8:27 ` Hugh Dickins
2013-02-21 8:29 ` [PATCH 7/7] ksm: allocate roots when needed Hugh Dickins
2013-02-21 8:29 ` Hugh Dickins
2013-02-22 3:44 ` [PATCH 0/7] ksm: responses to NUMA review Ric Mason
2013-02-22 3:44 ` Ric Mason
2013-02-22 20:38 ` Hugh Dickins
2013-02-22 20:38 ` Hugh Dickins
2013-02-24 1:39 ` Ric Mason
2013-02-24 1:39 ` Ric Mason
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=51303CAB.3080406@gmail.com \
--to=ric.masonn@gmail.com \
--cc=aarcange@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=hughd@google.com \
--cc=izik.eidus@ravellosystems.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mgorman@suse.de \
--cc=pholasek@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.