From: Andrew Morton <akpm@linux-foundation.org>
To: Christopher Yeoh <cyeoh@au1.ibm.com>
Cc: linux-mm@kvack.org, Linus Torvalds <torvalds@linux-foundation.org>
Subject: Re: [Resend] Cross Memory Attach v3 [PATCH]
Date: Tue, 15 Mar 2011 16:16:23 -0700 [thread overview]
Message-ID: <20110315161623.4099664b.akpm@linux-foundation.org> (raw)
In-Reply-To: <20110315143547.1b233cd4@lilo>
On Tue, 15 Mar 2011 14:35:47 +1030
Christopher Yeoh <cyeoh@au1.ibm.com> wrote:
> Hi Andrew,
>
> I was wondering if you thought the cross memory attach patch is in
> suitable shape to go into your tree with view of getting it into
> mainline sometime in the not too distant future.
It looks reasonable to me, but I might have missed something and would
ask that some of the other guys take a close look, please.
It's regrettable that vmsplice() won't serve the purpose but I can see
that the blocking problems are there.
Minor thing: mm/memory.c is huge, and I think this new code would live
happily in a new mm/process_vm_access.c.
> There are some cases of MPI collectives where even a single copy
> interface does not get us the performance gain we could. For example
> in an MPI_Reduce rather than copy the data from the source we would
> like to instead use it directly in a mathops (say the reduce is doing a
> sum) as this would save us doing a copy. We don't need to keep a copy
> of the data from the source. I haven't implemented this, but I think
> this interface could in the future do all this through the use of the
> flags - eg could specify the math operation and type and the kernel
> rather than just copying the data would apply the specified operation
> between the source and destination and store it in the destination.
Well yes. This smells like MAP_SHARED.
Thinking out loud: if we had a way in which a process can add and
remove a local anonymous page into pagecache then other processes could
access that page via mmap. If both processes map the file with a
nonlinear vma they they can happily sit there flipping pages into and
out of the shared mmap at arbitrary file offsets. The details might
get hairy ;) We wouldn't want all the regular mmap semantics of making
pages dirty, writing them back, etc so make that mmap be backed by a
new special device rather than by a regular file, perhaps.
--
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/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2011-03-15 23:16 UTC|newest]
Thread overview: 11+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-03-15 4:05 [Resend] Cross Memory Attach v3 [PATCH] Christopher Yeoh
2011-03-15 23:16 ` Andrew Morton [this message]
2011-03-17 5:10 ` Christopher Yeoh
2011-03-17 19:54 ` Andrew Morton
2011-03-21 1:50 ` Christopher Yeoh
2011-03-21 1:55 ` Andrew Morton
2011-03-21 2:15 ` Christopher Yeoh
2011-03-23 2:22 ` Christopher Yeoh
2011-03-23 22:50 ` Rusty Russell
2011-03-25 13:22 ` Christopher Yeoh
2011-04-12 0:48 ` Christopher Yeoh
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=20110315161623.4099664b.akpm@linux-foundation.org \
--to=akpm@linux-foundation.org \
--cc=cyeoh@au1.ibm.com \
--cc=linux-mm@kvack.org \
--cc=torvalds@linux-foundation.org \
/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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).