Xymon Mailing List Archive search

Big Environment

list Gautier Begin
Wed, 5 Oct 2011 09:22:49 +0200
Message-Id: <user-071385bcecda@xymon.invalid>

Hello,


Thanks for sharing your experiences.

Here, I can't use any SSD disk but SAN ones with cache before. What do you think about it?

Cordialement, Regards,Mit freundlichen Grüßen,

Gautier BEGIN

Admin and Tools Team
CSC Computer Sciences Luxembourg S.A.
12D Impasse Drosbach
L-1882 Luxembourg

Global Outsourcing Service | p:+352 24 834 276 | m:+352 621 229 172 | user-083785ae1711@xymon.invalid | www.csc.com


CSC • This is a PRIVATE message. If you are not the intended recipient, please delete without copying and kindly advise us by e-mail of the mistake in delivery.  NOTE: Regardless of content, this e-mail shall not operate to bind CSC to any order or other contract unless pursuant to explicit written agreement or government initiative expressly permitting the use of e-mail for such purpose
 • CSC Computer Sciences SAS • Registered Office: Immeuble Le Balzac, 10 Place des Vosges, 92072 Paris La Défense Cedex, France • Registered in France: RCS Nanterre B 315 268 664


From:
Nicolas LIENARD <user-4f1d872b9031@xymon.invalid>
To:
<xymon at xymon.com>
Date:
10/05/2011 09:03 AM
Subject:
Re: [Xymon] Big Environment


Hello
In our company, we got ~10 000 devices split into 10 countries :
19 hobbit clusters in total. (1 hobbit cluster in each Datacenter).
we use bbproxy to report to one single hobbit cluster (central):
Wed Oct 5 07:37:25 2011
Statistics: Hosts total : 10866
Incoming messages/sec  :        478 (average last 300 seconds)

The maximum of hosts for a local hobbit cluster is 3655 :
 Here the stat of this local cluster :
Statistics:
 Hosts total           :     3655
 Hosts with no tests   :       60
 Total test count      :     9809
 Status messages       :    10151
 Alert status msgs     :        0
 Transmissions         :      326

TCP test statistics:
 # TCP tests total     :     6214
 # HTTP tests          :     2342
 # Simple TCP tests    :     3872
 # Connection attempts :     6214
 # bytes written       :   396441
 # bytes read          : 24395876

TCP tests completed                          134011.876173 30.657820 PING test completed (3650 hosts)             134012.458682 0.582508 TIME TOTAL 44.107030 
Incoming messages/sec  :        173 (average last 300 seconds)

The hardware is a cluster of 2 HP DL360 G7 with 4 SSD drives in raid5 for /opt/xymon/data.

We chose SSD for I/O performances.


 load average: 0.74, 0.84, 0.82

We use heartbeat for VIP and DRBD for replication.

We didnt disabled hostdata but maybe we should do (we have a couple of scripts to clean up the hostdata, histfiles, etc).

On the local cluster
/dev/drbd0           34078720 11545129 22533591   34% /opt/xymon/data
/dev/drbd0            122G   69G   47G  60% /opt/xymon/data

-> 11 millions of files


On the central cluster
/dev/drbd0           89522176 77497570 12024606   87% /opt/hobbit/data
/dev/drbd0            673G  458G  181G  72% /opt/hobbit/data

-> 77 millions of files

it becomes high.

sometimes we experienced ASR on hobbit servers :/

Cheers
Nico


  On Tue, 4 Oct 2011 10:12:57 -0400, Brand, Thomas R. wrote:
I have 7363 hosts being monitored in my environment.
Tue Oct 4 10:05:58 2011
Statistics:
 Hosts                      :  7363
 OS: SuSE Linux Enterprise v11.0
 I found network I/O a challenge, and had to set up a bbproxy server and split the ping test over two Xymon servers, each server handling about ½ the load. Time spent on ping tests (on each server) is about 170 seconds.    Proxy statistics
Incoming messages        :    3332629 (48 msgs/second)
Outbound messages        :    1778658
  The disk i/o with this many hosts is also difficult – at least on my hardware (IBM x225 server). I also disabled [hostdata] in hobbitlaunch.cfg – my systems could not keep up with the i/o.
 I cut down on message traffic by using a the ‘ignore’ and ‘trigger’ capability of the logfile checker in
client-local.cfg, thereby filtering at the client; eg: log:/var/log/daemon.log:4096
   ignore (upsd.*: Set variable|apcsmart.*enum |dhcpd: |xinetd.*: |squid.*: |ntpd.*: |Connection from |logged out)
   trigger shutdown
    From: xymon-bounces at xymon.com [mailto:xymon-bounces at xymon.com] On Behalf Of Josh Luthman
Sent: Tuesday, October 04, 2011 8:29 AM
To: Gautier Begin
Cc: xymon at xymon.com
Subject: Re: [Xymon] Big Environment
 I saw a ~7250 host quickly scrolling through it

http://en.wikibooks.org/wiki/System_Monitoring_with_Xymon/User_Guide/The_Xymon_Users_list


Josh Luthman
Office: XXX-XXX-XXXX
Direct: XXX-XXX-XXXX
XXXX Wayne St
Suite XXXX
Troy, OH XXXXX

On Tue, Oct 4, 2011 at 8:24 AM, Gautier Begin <user-083785ae1711@xymon.invalid> wrote:
Hello, 
I'm planning to use XYMON with a big amount of clients: 1000 and then 4000. 
Is it possible ? Are there some tipps and limitations to know ? 
Cordialement, Regards,Mit freundlichen Grüßen,

Gautier BEGIN

Admin and Tools Team
CSC Computer Sciences Luxembourg S.A.
12D Impasse Drosbach
L-1882 Luxembourg

Global Outsourcing Service | p:+352 24 834 276 | m:+352 621 229 172 | user-083785ae1711@xymon.invalid | www.csc.com


CSC • This is a PRIVATE message. If you are not the intended recipient, please delete without copying and kindly advise us by e-mail of the mistake in delivery.  NOTE: Regardless of content, this e-mail shall not operate to bind CSC to any order or other contract unless pursuant to explicit written agreement or government initiative expressly permitting the use of e-mail for such purpose
• CSC Computer Sciences SAS • Registered Office: Immeuble Le Balzac, 10 Place des Vosges, 92072 Paris La Défense Cedex, France • Registered in France: RCS Nanterre B 315 268 664