IDS Forum

RE: Poor performance on replacement server

Posted By: Simon
Date: Wednesday, 14 December 2005, at 7:00 p.m.

In Response To: RE: Poor performance on replacement server (simon@coynes.eclipse.co.uk)

The database was restored from an ontape archive and subsequently had update
statistics run against it (using your "dostats" scripts).

-----Original Message-----
From: kagel@bloomberg.net [mailto:kagel@bloomberg.net]
Sent: 14 December 2005 17:32
To: simon@coynes.eclipse.co.uk
Subject: RE: Poor performance on replacement server [6097]

Simon, just to get the 'too obvious' out of the way, take a dbschema -ss of
the
database on each server and compare. Are the locking modes of the tables
the
same? It's a common error to recreate the database using dbschema or
dbexport
without the -ss flag and so have the target tables default to PAGE level
locking. This will cause extensive contention versus ROW level locking and
cause the CPU VPs to spin.

Art

----- Original Message -----
From: simon@coynes.eclipse.co.uk
At: 12/14 5:20

Thanks to everyone for their replies. First, I've been a bit of a clot and
given

the wrong ONconfig file; I took the config from the old server. It is not
much
different and indeed the changes are around MULTIPROCESSOR and the number of
CPU

VPs. (I've also changed the LRUMAX & MIN entries and the amount of
DS_MEMORY.
However, generally, they are very similar. My intention was to get the thing
working and then tune it up properly.)

Taking peoples comments and questions

Could it be locking? Possibly. I cannot say with any certainty because I
cannot
get
a response from a query to sysmaster because the CPUs are maxed out.
However,
the
application (both 4GL and browser based) haven't changed at all; it is the
same
programs attaching to both systems. We do experience some problems on the
DS25
with
locking, but not like this.

Multiprocessor support - I've tried this both ways around with no variation
in
performance.

onstat information - Unfortunately, management took the decision to back the
change
out and we are now back on the DS25. Therefore collecting current stats is
impossible.

Is it an OS problem? I'm not convinced; as I said in my original post, if
IDS is

taken out of the equation, the OS seems to be OK. Disk IO is good and CPU
usage
is
very low.

Hardware Setup - The card is a 4 channel controller with 256Mb cache and the
disk
cages have 2 channels per disk tray. The first 7 disks on channel 0, tray 0
are
configured as a 4 disk stripe for the OS and a 2 disk stripe containing the
rootdbs, physdbs and logdbs. Last disk is a hot spare. Channel 1, tray 0 is
configured as a 6 disk stripe with a hot spare split into lots of 15Gb
logical
volumes for the data. All these stripes are then mirrored to tray 1.

The one thing I maybe didn't make clear in my original post is that the same
configuration (both IDS and OS) runs significantly quicker on the DS25. The
DS25

only struggles to support the business during peak load; on a day to day
basis
it
is fine. Currently, the ES45 isn't even coping with a 20% of day to day
loading
(it
starts struggling with less than 50 users logged in as opposed to 300).

Regards


Simon Coyne





--
No virus found in this incoming message.
Checked by AVG Free Edition.
Version: 7.1.371 / Virus Database: 267.13.13/200 - Release Date: 14/12/2005

Messages In This Thread

• Poor performance on replacement server
  Simon Coyne -- Tuesday, 13 December 2005, at 11:03 a.m.
  • Re: Poor performance on replacement server
    John Bejarano -- Tuesday, 13 December 2005, at 12:03 p.m.
    • RE: Poor performance on replacement server
      Phil Torkington -- Wednesday, 14 December 2005, at 7:43 a.m.
  • Re: Poor performance on replacement server
    Ravi T -- Tuesday, 13 December 2005, at 1:30 p.m.
  • RE: Poor performance on replacement server
    Rafael Padilla V -- Tuesday, 13 December 2005, at 2:01 p.m.
  • RE: Poor performance on replacement server
    Art S. Kagel -- Tuesday, 13 December 2005, at 2:56 p.m.
  • RE: Poor performance on replacement server
    simon@coynes.eclipse.co.uk -- Wednesday, 14 December 2005, at 4:59 a.m.
    • RE: Poor performance on replacement server
      ART KAGEL, BLOOMBERG/ 731 LEXIN -- Wednesday, 14 December 2005, at 12:39 p.m.
    • RE: Poor performance on replacement server
      Ravi T -- Wednesday, 14 December 2005, at 12:50 p.m.
    • Re: RE: Poor performance on replacement server
      DARKO KRSTIC -- Wednesday, 14 December 2005, at 1:59 p.m.
    • RE: Poor performance on replacement server
      Simon -- Wednesday, 14 December 2005, at 7:00 p.m.

IDS Forum is maintained by Administrator with WebBBS 5.12.