From: ron minnich <rminnich@gmail.com>
To: Fans of the OS Plan 9 from Bell Labs <9fans@9fans.net>
Subject: Re: [9fans] gar nix!
Date: Fri, 16 Sep 2011 00:56:10 -0500 [thread overview]
Message-ID: <CAP6exYLuD6ZeOwCfY9TcgSWEYp-2QH-7qUO713GL0cravJ2FzA@mail.gmail.com> (raw)
In-Reply-To: <103b012cdb5c55bca54c751bb88fb57c@brasstown.quanstro.net>
for the 2M pages -- I'm willing to see some measurement but let's get
the #s -- I've done some simple measurements and it's not the hit one
would expect. These new machines have about 10 GB/s bandwidth (well,
the ones we are targeting do) and that translates to sub-millisecond
times to zero a 2M page. Further, the text page is in the image cache.
So after first exec of a program, the only text issue is locating the
page. It's not simply a case of having to write 6M each time you exec.
I note that starting a proc, allocating and zeroing 2 GiB, takes
*less* time with 2M pages than 4K pages -- this was measured in May
when we still were supporting 4K pages -- the page faults are far more
expensive than the time to write the memory. Again, YMMV, esp. on an
Atom, but the cost of taking (say) 6 page faults for a 24k text
segment that's already in memory may not be what you want.
There are plenty of games to be played to reduce the cost of zero
filled pages but at least from what I measured the 2M pages are not a
real hit.
ron
next prev parent reply other threads:[~2011-09-16 5:56 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-09-16 1:19 erik quanstrom
2011-09-16 5:44 ` Noah Evans
2011-09-17 19:41 ` erik quanstrom
2011-09-17 20:03 ` Noah Evans
2011-09-16 5:56 ` ron minnich [this message]
[not found] ` <CAP6exYLuD6ZeOwCfY9TcgSWEYp-2QH-7qUO713GL0cravJ2FzA@mail.gmail.c>
2011-09-16 6:46 ` erik quanstrom
2011-09-16 7:02 ` Nemo
2011-09-16 7:52 ` dexen deVries
2011-09-16 13:36 ` Charles Forsyth
2011-09-16 14:39 ` ron minnich
[not found] ` <CAP6exYLy6sicg42A+7D=bmpWtv=p_an3c5=OQw9YB2oxPXhR2A@mail.gmail.c>
2011-09-16 14:57 ` erik quanstrom
2011-09-16 15:28 ` ron minnich
2011-09-16 15:31 ` Francisco J Ballesteros
[not found] ` <CA+N-5bbt92zqNpt0KW4prykyTxjYNHJJ7LuUCj4n3EACyC5GvQ@mail.gmail.c>
2011-09-16 15:33 ` erik quanstrom
2011-09-16 15:36 ` Francisco J Ballesteros
2011-09-16 15:44 ` ron minnich
2011-09-16 16:07 ` Francisco J Ballesteros
[not found] ` <CA+N-5bYJ1VBpqQENUy5fZirE_Joa9E6RE8rJbvaFwh065zd2TA@mail.gmail.c>
2011-09-16 15:37 ` erik quanstrom
2011-09-16 18:24 ` ron minnich
2011-09-16 22:23 ` Charles Forsyth
2011-09-16 22:27 ` erik quanstrom
2011-09-17 3:39 ` Bruce Ellis
2011-09-17 7:35 ` Charles Forsyth
2011-09-17 7:44 ` Charles Forsyth
2011-09-17 8:45 ` Charles Forsyth
[not found] ` <CAP6exYK+aoYcaC+LLo4XdPmZ1jvPQ0dAgZuUkmX7_xZQ+h3+gQ@mail.gmail.c>
2011-09-16 18:32 ` erik quanstrom
2011-09-16 18:44 ` Francisco J Ballesteros
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=CAP6exYLuD6ZeOwCfY9TcgSWEYp-2QH-7qUO713GL0cravJ2FzA@mail.gmail.com \
--to=rminnich@gmail.com \
--cc=9fans@9fans.net \
/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).