[Top][All Lists]
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: qlimit
From: |
Marcus Brinkmann |
Subject: |
Re: qlimit |
Date: |
Mon, 24 Jun 2002 13:01:44 +0200 |
User-agent: |
Mutt/1.4i |
On Mon, Jun 24, 2002 at 01:11:54AM -0400, Roland McGrath wrote:
> > The handling of the notification ports is a bit annoying. I had to
> > create a class and bucket and donate a service thread to retrieve the
> > kernels responses.
>
> Why not just put the notification ports in the normal bucket and let the
> existing manage_multithread handle them?
I guess that would work, I just need to change the demuxer. I think I
didn't think of it.
> I don't think there would be any harm in just using the protid port as the
> notify port. The user could forge a mag-accepted notification, but that
> will just cause you to attempt another send and have it fail with
> MACH_SEND_NOTIFY_IN_PROGRESS. Am I missing something?
I don't think it is harmful for the server if a user does that. I am not
sure if it is 100% safe for the client in not losing any updates, but that's
not a problem for the server.
> > I am not sure what the destination port is here, if it is the client port
> > we try to send to, we have a problem. Because a send-once notification
> > doesn't let us know which clients port died, so we can not find the correct
> > filemod_req structure belonging to this request.
>
> But we can use it as an alert to scan for dead names. And there are very
> few to scan, only the ones in msg-accepted wait. (Ports that are still on
> the active list we will notice next time there is a change and we get
> MACH_SEND_INVALID_DEST on the send attempt.)
Yes, I thought of that. I have to put that in.
> > Without clients, the server needs 30s to process the find command, with
> > one client it needs 50s, with two clients it needs 53s. I don't know why
> > it needs 20s more with one client attached.
>
> That could be a little suspect, but OTOH the difference is removing a whole
> other task and all the context switches to and from it.
D'oh you are right. Sometimes I need a can opener for my eyes to see such
things :) I was not measuring the server time at all, but the real time of the
find task, which of course is affected by that. That's good.
Thanks,
Marcus
--
`Rhubarb is no Egyptian god.' Debian http://www.debian.org address@hidden
Marcus Brinkmann GNU http://www.gnu.org address@hidden
address@hidden
http://www.marcus-brinkmann.de
- Re: qlimit, Roland McGrath, 2002/06/19
- Re: qlimit, Marcus Brinkmann, 2002/06/23
- Re: qlimit, Roland McGrath, 2002/06/24
- Re: qlimit,
Marcus Brinkmann <=
- Re: qlimit, Marcus Brinkmann, 2002/06/24
- Re: qlimit, Roland McGrath, 2002/06/24
- Re: qlimit, Thomas Bushnell, BSG, 2002/06/25