[smokeping-users] decreasing ping interval and improving performance

Peter Kristolaitis alter3d at alter3d.ca
Thu Jun 12 20:16:18 CEST 2008

Hash: SHA1

Hi Jeff;

You may want to look into using the master/slave functionality to
distribute the load rather than making more probes on a single host.

Also, disks aren't faster just by virtue of being on a SAN.   Similarly
configured volumes (same number of disks, same RAID level, same amount
of controller cache) are almost invariably faster by using DAS, as you
don't have the added latency of the FC (or even worse, iSCSI) packet
switching network (plus SAN typically has shared bus and cache).

Is there a real, technical reason to use exactly 30 pings?  For example,
do you need that level of granularity for % loss?  Could you get by with
15 or 20?  You'd still get host up/down notifications, and improved
performance, at a cost of less granularity for loss % -- which often
(though not always) isn't an important metric when monitoring branches
(2 packets lost out of 30 = 5.7%, 2 packets out of 20 = 10% -- does that
difference actually matter in your case?  Could it be compensated for by
slightly increasing loss % thresholds for alerts?)

Just my thoughts... YMMV, of course. :)
- - Peter

Jeff Williams wrote:
| Hey folks,
| Our network group is looking to get some more performance from
| smokeping. I'm looking for some tips on how to optimize performance and
| I welcome any suggestions.

- --
Peter Kristolaitis
DBA / Code Monkey / General Geek

OpenPGP/GPG Key available from pgp.mit.edu

Key Fingerprint: 695D 7616 9903 6002 5756
~                 D234 6E96 34B2 F974 14FE
Version: GnuPG v1.4.7 (MingW32)
Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org


More information about the smokeping-users mailing list