Re: tuning a CPU bound server

2002-05-22 Thread Matthew Dillon
I think this has gotten off-topic. I am going to go back and respond to the original posting. When I was doing BEST Internet we had very similar problems with our mail servers. We were constantly cpu-bound. I was constantly fiddling with it (sendmail in this case). For mon

Re: tuning a CPU bound server

2002-05-22 Thread Terry Lambert
Christopher Weimann wrote: > Not intended as a slight against DJB ( althought I do realize it > looked that way ). I LOVE qmail, look at my headers. > > But DJB does not introduce any of Terry's "network effects". Sure he does. By not integrating the patches, he ends up with many patches sittin

Re: tuning a CPU bound server

2002-05-22 Thread Christopher Weimann
On Wed, May 22, 2002 at 11:31:33PM +0200, Andre Oppermann wrote: > > > > But DJB does't maintain his code. I don't think it he has touched > > it in years. > > He maintains his code quite well. Thing is he only changes something > if there is something to change. In the case of qmail-1.03 this

Re: tuning a CPU bound server

2002-05-22 Thread Andre Oppermann
> On Mon, May 20, 2002 at 12:52:09PM -0700, Terry Lambert wrote: > > > > The problem is that as you maintain your patches, and the patch > > vendor maintains their patches, and DJB maintains his code, you > > end up with network effects. > > > > But DJB does't maintain his code. I don't think

Re: tuning a CPU bound server

2002-05-20 Thread Christopher Weimann
On Mon, May 20, 2002 at 12:52:09PM -0700, Terry Lambert wrote: > > The problem is that as you maintain your patches, and the patch > vendor maintains their patches, and DJB maintains his code, you > end up with network effects. > But DJB does't maintain his code. I don't think it he has touche

Re: tuning a CPU bound server

2002-05-20 Thread Terry Lambert
Adrian Filipi-Martin wrote: > On Sat, 18 May 2002, Terry Lambert wrote: > > "Karsten W. Rohrbach" wrote: > > > Brandon D. Valentine([EMAIL PROTECTED])@2002.05.17 14:48:07 +: > > > > On Fri, 17 May 2002, Doug White wrote: > > > > >You are welcome to rewrite qmail to use kqueue if you wish :) >

Re: tuning a CPU bound server

2002-05-20 Thread Adrian Filipi-Martin
On Sat, 18 May 2002, Terry Lambert wrote: > "Karsten W. Rohrbach" wrote: > > Brandon D. Valentine([EMAIL PROTECTED])@2002.05.17 14:48:07 +: > > > On Fri, 17 May 2002, Doug White wrote: > > > >You are welcome to rewrite qmail to use kqueue if you wish :) > > > > > > Although if I read the lice

Re: tuning a CPU bound server

2002-05-19 Thread Hiten Pandya
--- Peter Wemm <[EMAIL PROTECTED]> wrote: > > -- Hiten Pandya <[EMAIL PROTECTED]> wrote: > > Just wondering, are these the kind of problems which can be solved by > > using the kqueue(2) mechanism, or am I talking nuts again? > > > > Regards. > > Yes, kqueue solves it nicely. I overestimated th

Re: tuning a CPU bound server

2002-05-18 Thread Peter Wemm
Hiten Pandya wrote: > --- Peter Wemm <[EMAIL PROTECTED]> wrote: > > The only real problem that I know of with postfix is that it still > > suffers from select(2) collisions (FreeBSD kernel problem) when it tries > > to shut down a bunch of idle smtp senders. That can cause transient load > > aver

Re: tuning a CPU bound server

2002-05-18 Thread Terry Lambert
"Karsten W. Rohrbach" wrote: > Brandon D. Valentine([EMAIL PROTECTED])@2002.05.17 14:48:07 +: > > On Fri, 17 May 2002, Doug White wrote: > > >You are welcome to rewrite qmail to use kqueue if you wish :) > > > > Although if I read the license correctly you hand djb a contract for > > your soul

Re: tuning a CPU bound server

2002-05-18 Thread Karsten W. Rohrbach
Brandon D. Valentine([EMAIL PROTECTED])@2002.05.17 14:48:07 +: > On Fri, 17 May 2002, Doug White wrote: > > >You are welcome to rewrite qmail to use kqueue if you wish :) > > Although if I read the license correctly you hand djb a contract for > your soul and first born child if you do. ;-)

Re: tuning a CPU bound server

2002-05-17 Thread Brandon D. Valentine
On Fri, 17 May 2002, Doug White wrote: >You are welcome to rewrite qmail to use kqueue if you wish :) Although if I read the license correctly you hand djb a contract for your soul and first born child if you do. ;-) Brandon D. Valentine -- "Time to resign from the human race, wipe those tear

Re: tuning a CPU bound server

2002-05-17 Thread Doug White
On Thu, 16 May 2002, Hiten Pandya wrote: > --- Peter Wemm <[EMAIL PROTECTED]> wrote: > > The only real problem that I know of with postfix is that it still > > suffers from select(2) collisions (FreeBSD kernel problem) when it tries > > to shut down a bunch of idle smtp senders. That can cause t

Re: tuning a CPU bound server

2002-05-17 Thread Hiten Pandya
--- Peter Wemm <[EMAIL PROTECTED]> wrote: > The only real problem that I know of with postfix is that it still > suffers from select(2) collisions (FreeBSD kernel problem) when it tries > to shut down a bunch of idle smtp senders. That can cause transient load > average spikes - this can be a bit

Re: tuning a CPU bound server

2002-05-16 Thread Alfred Perlstein
* Peter Wemm <[EMAIL PROTECTED]> [020516 17:12] wrote: [snip about select collisions] > > FreeBSD's "bug" is is twofold: > 1) we can only track one process selecting on a shared fd at one time, and > 2) we never deregister selects. Actually I think I did #2 under 5.x with 'sys_generic.c:clear_s

Re: tuning a CPU bound server

2002-05-16 Thread Peter Wemm
Alfred Perlstein wrote: > * Peter Wemm <[EMAIL PROTECTED]> [020516 15:41] wrote: > > > > The only real problem that I know of with postfix is that it still suffers > > from select(2) collisions (FreeBSD kernel problem) when it tries to shut > > down a bunch of idle smtp senders. That can cause t

Re: tuning a CPU bound server

2002-05-16 Thread Alfred Perlstein
* Peter Wemm <[EMAIL PROTECTED]> [020516 15:41] wrote: > > The only real problem that I know of with postfix is that it still suffers > from select(2) collisions (FreeBSD kernel problem) when it tries to shut > down a bunch of idle smtp senders. That can cause transient load average > spikes - t

Re: tuning a CPU bound server

2002-05-16 Thread Peter Wemm
Doug White wrote: > qmail is also very inefficient when it comes to large delivery -- the fork > per message and the qmail-remote trigger-hitting will eventually > bottleneck you. It's probable you've run into it. My sympathies. :) You > might try *dropping* concurrencyremote somewhat to reduce

Re: tuning a CPU bound server

2002-05-16 Thread Omar Thameen
On Wed, May 15, 2002 at 02:53:49PM -0700, Doug White wrote: > On Wed, 15 May 2002, Omar Thameen wrote: > > Can you post a netstat -m from now? It will have the peak values in it. 1484/2016/34816 mbufs in use (current/peak/max): 914 mbufs allocated to data 64 mbufs allocated to p

Re: tuning a CPU bound server

2002-05-15 Thread Doug White
On Wed, 15 May 2002, Omar Thameen wrote: > > First off, what are the specs of the server? Cpu? Disk? Memory? Network? > > You mention it's a dual 800MHz. What kind of NIC does it have? What is the > > speed and duplex set to on it? > > Dual PIII/800 > 2G SDRAM > 2x18G IBM 10,000 rpm SCSI drives,

Re: tuning a CPU bound server

2002-05-15 Thread Omar Thameen
On Tue, May 14, 2002 at 09:25:21PM -0700, Doug White wrote: > Mmm, mail server tuning, something I have some experience in :-) Just what I was hoping to hear! > First off, what are the specs of the server? Cpu? Disk? Memory? Network? > You mention it's a dual 800MHz. What kind of NIC does it hav

Re: tuning a CPU bound server

2002-05-14 Thread Terry Lambert
Doug White wrote: > qmail is also very inefficient when it comes to large delivery -- the fork > per message and the qmail-remote trigger-hitting will eventually > bottleneck you. It's probable you've run into it. My sympathies. :) You > might try *dropping* concurrencyremote somewhat to reduce t

Re: tuning a CPU bound server

2002-05-14 Thread Doug White
Mmm, mail server tuning, something I have some experience in :-) First off, what are the specs of the server? Cpu? Disk? Memory? Network? You mention it's a dual 800MHz. What kind of NIC does it have? What is the speed and duplex set to on it? Secondly, what period was your vmstat run over? The