This is the mail archive of the
systemtap@sourceware.org
mailing list for the systemtap project.
Re: about systemtap cost
- From: fche at redhat dot com (Frank Ch. Eigler)
- To: Gareth <academicgareth at gmail dot com>
- Cc: systemtap at sourceware dot org
- Date: Wed, 04 Nov 2015 09:05:23 -0500
- Subject: Re: about systemtap cost
- Authentication-results: sourceware.org; auth=none
- References: <CAAhuP_9tN1zcSXs-Y5Fk+9pvWBubFUKp4nFwpszZHx2Qo+BV+A at mail dot gmail dot com>
academicgareth wrote:
> Which case would cost more in runtime?
> [... one script with three probes vs. three scripts with one probe each ...]
There should be no difference at a first-order level of analysis, so
do whatever makes more sense from a script life-cycle or data-sharing
or other such abstract concern.
(Second-order performance effects like cache locality probably slightly
favour putting the probes together into one script.)
- FChE