From: "Jérémie Dimino" <jeremie@dimino.org>
To: Goswin von Brederlow <goswin-v-b@web.de>
Cc: Yaron Minsky <yminsky@gmail.com>, caml-list@inria.fr
Subject: Re: [Caml-list] Asynchronous IO programming in OCaml
Date: Wed, 27 Oct 2010 13:18:35 +0200 [thread overview]
Message-ID: <20101027111835.GA5664@gaia> (raw)
In-Reply-To: <877hh4dlog.fsf@frosties.localdomain>
On Wed, Oct 27, 2010 at 11:33:51AM +0200, Goswin von Brederlow wrote:
> You aren't doing any multithreading. You are creating a thread and
> waiting for the thread to finish its read before strating a second.
> There are never ever 2 reads running in parallel. So all you do is add
> thread creation and destruction for every read to your first example.
Yes, i know that. The idea was just to show the overhead of context
switches.
> You should start multiple threads and let them read from different
> offsets (use pread) and only once they are all started join them all
> again.
Sure, but doing this directly in Lwt raises other problems:
- This means prefetching a large part of the file into the program
memory.
- The kernel already prefetches files from the disk, so most of the time
this is just a memory copy in parallel...
- How many threads do we launch in parallel ? This depends on the
overhead of context switching between threads, which can not be
determined at runtime.
I think that the solution with mincore + mmap is better because it uses
threads only when really needed.
Jérémie
next prev parent reply other threads:[~2010-10-27 11:18 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-10-24 10:34 Jon Harrop
2010-10-24 12:51 ` [Caml-list] " philippe
2010-10-24 12:52 ` Dario Teixeira
2010-10-24 16:33 ` oliver
2010-10-24 18:50 ` Dario Teixeira
2010-10-24 19:04 ` bluestorm
2010-10-24 20:02 ` oliver
2010-10-24 21:51 ` Michael Ekstrand
2010-10-24 16:17 ` Jake Donham
2010-10-24 20:54 ` Anil Madhavapeddy
2010-10-24 22:50 ` Jérémie Dimino
2010-10-25 3:42 ` Markus Mottl
2010-10-25 7:49 ` Richard Jones
2010-10-25 8:42 ` Goswin von Brederlow
2010-10-25 11:10 ` Jérémie Dimino
[not found] ` <AANLkTimP77PDEChW3Yt6uUy_qxYpj6EOZWQ_==id-LBC@mail.gmail.com>
[not found] ` <20101025143317.GB32282@aurora>
2010-10-25 15:34 ` Yaron Minsky
2010-10-25 17:26 ` Jérémie Dimino
2010-10-27 9:33 ` Goswin von Brederlow
2010-10-27 11:18 ` Jérémie Dimino [this message]
2010-10-27 13:43 ` Goswin von Brederlow
2010-10-27 15:30 ` Jérémie Dimino
2010-10-28 9:00 ` Goswin von Brederlow
2010-10-28 9:28 ` Jérémie Dimino
2010-10-28 10:11 ` Goswin von Brederlow
2010-10-25 15:58 ` DS
2010-10-24 20:42 ` Goswin von Brederlow
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=20101027111835.GA5664@gaia \
--to=jeremie@dimino.org \
--cc=caml-list@inria.fr \
--cc=goswin-v-b@web.de \
--cc=yminsky@gmail.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox