lkml.org 
[lkml]   [1999]   [Jan]   [12]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
SubjectRe: linux-kernel's extremely slow turnaround time
Date
From
Oliver Xymoron <oxymoron@waste.org> writes:
> On Sun, 10 Jan 1999, Brandon S. Allbery KF8NH wrote:
> > In message <19990110004042Z92293-18266+28@mea.tmt.tele.fi>, Matti Aarnio
> > writes
> >
> > *boggle* And you think *sendmail* is a load problem? Majordomo is quite
> > useless for mailing lists with more than a few hundred users (reduce
> > quantities as the number of hosted lists increases), regardless of MTA ---
> > question answered. vger is drowning in inefficient Perl scripts.

Here Mr. Allbery, or Mr. Xymoron, has misquoted me -- removed all my
text leaving only Mr. Allbery's text..

> Bah. I have a Majordomo list with ~12000 subscribers. No problems. Not to
> mention a hundred other lists of various sizes. Majordomo's resend load is
> proportional to number of messages, not subscribers. Oh yeah, I've been
> using Zmailer for the past couple years because sendmail stopped being
> able to keep up with the queue long ago..

Majordomo does very lightweight work, even though the 'resend' could
in certain configurations do miracles with suitable C programs -- and
'unsubscribe *' could use some such too.. Most of the actual routing
work *including list expansion* is in email routing, and that task is
done in the system MTA.

> Of course, I have much faster disks in my mail server than vger - I've got
> a couple UW SCSI drives with a Buslogic controller. Load sits at < 1
> typically.

Yes, that is most definitely important part. VGER runs all the time
at system activity around 20-50%. Measuring what the kernel really
does deep down inside has not been done. This is typical TOP report:

8:27pm up 1 day, 9:32, 3 users, load average: 2.76, 3.07, 3.13
123 processes: 120 sleeping, 3 running, 0 zombie, 0 stopped
CPU states: 82.2% user, 15.6% system, 91.1% nice, 2.6% idle
Mem: 125248K av, 120500K used, 4748K free, 55860K shrd, 33468K buff
Swap: 101112K av, 0K used, 101112K free 32948K cached

Wow, unusually low amount of system activity.

# vmstat 5
procs memory swap io system cpu
r b w swpd free buff cache si so bi bo in cs us sy id
3 0 0 0 4044 35012 32592 0 0 12 17 214 66 85 15 0
2 0 0 0 4320 35076 32632 0 0 10 13 180 16 87 13 0
2 0 0 0 4508 35076 32676 0 0 9 20 194 25 94 6 0
5 0 0 0 4252 35076 32720 0 0 1 3 405 127 78 22 0
4 0 0 0 4436 35076 32720 0 0 0 8 279 85 83 17 0
2 0 0 0 5016 35140 32664 0 0 2 7 146 31 86 14 0
11 0 0 0 4500 35140 32756 0 0 12 11 181 23 65 35 0


> --
> "Love the dolphins," she advised him. "Write by W.A.S.T.E.."

/Matti Aarnio <matti.aarnio@sonera.fi> <mea@vger.rutgers.edu>

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/

\
 
 \ /
  Last update: 2005-03-22 13:49    [W:0.085 / U:0.268 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site