Subject: Re: third results (was: ddb & shared libs)
To: None <tech-kern@NetBSD.ORG>
From: None <jiho@postal.c-zone.net>
List: tech-kern
Date: 04/03/1998 15:08:00
On 03-Apr-98 John S. Dyson wrote:
> VM is a difficult thing to start to understand, and once you really
> do understand the issues, it becomes difficult to accept that others
> cannot "see how obvious things are", and non-VM people seem to totally
> misunderstand it.
Indeed. Did you see my earlier messages, where I was convinced (well, let's
say postulating) that shared library code segments were not being shared? Not
until Chuck had me using ddb did I completely let loose of that idea.
But even worse, non-VM people tend to get suspicious and even ticked when the
machine runs amok.
> I believe that while VM has major performance ramifications on an OS,
> it is also ignored. NT is slow partially due to VM issues, SVR4 can't
> handle loads due to VM and filesystem caching issues, Linux cannot
> handle loads due to VM and filesystem caching issues. Things go
> on and on.
I thought NT was fast until I gave it a simple test, and it bogged down worse
than even OS/2 Warp, right away.
Linux seems to have improved since DEC got their fingers in the pie, in some
performance respects at least. Don't really know for the purpose of this
discussion, of course.
> When you get here, then repeat the above steps again and again,
> relentlessly.
Yes, suggesting something wrong with any Dyson code does seem to get messages
right away, every time. Same thing happened over on a FreeBSD list, a few
years ago. (I understood even less, back then. Or is it now, after wading
through a lot of code?!?)
--Jim Howard <jiho@mail.c-zone.net>
----------------------------------
E-Mail: jiho@mail.c-zone.net
Date: 03-Apr-98
Time: 14:44:55
This message was sent by XFMail
----------------------------------
-------------End of forwarding message-------------------------
----------------------------------
E-Mail: jiho@mail.c-zone.net
Date: 03-Apr-98
Time: 15:08:00
This message was sent by XFMail
----------------------------------