Skip site navigation (1)Skip section navigation (2)
Date:      Tue, 29 Apr 1997 22:11:09 -0700 (PDT)
From:      Simon Shapiro <Shimon@i-Connect.Net>
To:        Michael Smith <msmith@atrad.adelaide.edu.au>
Cc:        julian@whistle.com, freebsd-hackers@freebsd.org, jkh@time.cdrom.com
Subject:   Continual Education (was Re: A Desparate Plea)
Message-ID:  <XFMail.970429224020.Shimon@i-Connect.Net>
In-Reply-To: <199704300233.MAA24918@genesis.atrad.adelaide.edu.au>

next in thread | previous in thread | raw e-mail | index | archive | help

Hi Michael Smith;  On 30-Apr-97 you wrote: 

...

> I normally ensure that development kernels don't use LKMs; if I need
> stuff I'll pull it in statically.  Generally a development kernel will
> be extremely aggressively stripped down to minimise possible conflicts.

How?  How do I take a kernel piece (module, driver, etc.) that is an LKM and
make it into a kernel static part?

>From this question, derived is the next:  Being that FreeBSD is available in
source and that the config file is so simple (Yes, one could build a tcl/tk
interface to it to compete with linux make xconfig), why bother with LKM's?
Especially when they do not to load/unload in a friendly manner.
With memory prices being what they are, a ``huge'' kernel will cost about
$8.00 more than a tiny one.  Ebmedded systems?  commercial non-source
products?

> > My activity?  Create noise about threads.  My server engineer tells me
> they 
> > are broken.  how is that?
> 
> Which threads?  Are we talking about the pthread code?  It has an owner
> and I'm sure he's waiting for bug reports 8)

Yup.  Steve T. (our project's server senior engineer) struggled with these
and
got some friendly help.  I really am not clear on the details.  Last report
was
that they are not quite Posix compiant but working.  The DDIO server (we
call
it something else internally) ran fine but crashed every 300,000 to
3,000,000
iterations.  We converted it to processes and forks, etc. and it is rock
solid.
Oh, it also went from 53 transactions/sec (a Tx, is a read, a write and a
deferred log write, more or less) to about 110.  

This is not necessarily a criticism of the threads library.  We had to twist
it a bit;  It ran 256 threads over more than a thousand file descriptors
with
heavy TCP load.  I would like, one day, to come back to it, ensure it is
Posix
compliant (we have the same source compile and run on Slowlaris and Linux),
and bug free.  Then we would like to help get its performance level back to 
match that of multi-process.  The DDIO code is excellent for that.


Simon



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?XFMail.970429224020.Shimon>