Skip site navigation (1)Skip section navigation (2)
Date:      Wed, 1 May 1996 15:57:46 -0700 (PDT)
From:      Nathan Lawson <nlawson@kdat.csc.calpoly.edu>
To:        craigs@os.com (Craig Shrimpton)
Cc:        questions@freebsd.org
Subject:   Re: Slowdown after RAM upgrade - 2.1.0R
Message-ID:  <199605012257.PAA12904@kdat.calpoly.edu>
In-Reply-To: <Pine.3.89.9605011536.A15372-0100000@solar.os.com> from "Craig Shrimpton" at May 1, 96 03:42:29 pm

next in thread | previous in thread | raw e-mail | index | archive | help
> On Wed, 1 May 1996, Nathan Lawson wrote:
> > 
>>I have noticed a real lag in disk activity after going from 16 megs to 32 megs
>>I did recompile the kernel and added in the BOUNCE_BUFFERS option for DMA.
>>I also changed MAXUSERS from 8 to 16.
>> 
> 
> If by lag you mean less, that's what supposed to happen.  More RAM means 
> less swapping which means less disk activity.  If by lag you mean slower, 
> that's an entirely different problem.

Yes, but what would I be complaining about if it swapped less?  The problem is
that I'll execute a command and it will hang for a second, then the disk light
will flash, and the command will execute.  When executed a second time, the
command executes with normal speed.

I interpret this as meaning that my ISA controller card is not running via DMA
and thus is much slower (polled via interrupt).  The second time, the program
image is already in secondary memory and it executes quickly.

Now, my question is, why?

-- 
Nate Lawson                  "There are a thousand hacking at the branches of
CPE Student                   evil to one who is striking at the root."
CSL Admin                              -- Henry David Thoreau, 'Walden', 1854



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199605012257.PAA12904>