This is the mail archive of the
systemtap@sourceware.org
mailing list for the systemtap project.
[Bug runtime/14175] New: ensure aggregates are no slower than locked integer ops
- From: "fche at redhat dot com" <sourceware-bugzilla at sourceware dot org>
- To: systemtap at sourceware dot org
- Date: Mon, 28 May 2012 20:10:33 +0000
- Subject: [Bug runtime/14175] New: ensure aggregates are no slower than locked integer ops
- Auto-submitted: auto-generated
http://sourceware.org/bugzilla/show_bug.cgi?id=14175
Bug #: 14175
Summary: ensure aggregates are no slower than locked integer
ops
Product: systemtap
Version: unspecified
Status: NEW
Severity: normal
Priority: P2
Component: runtime
AssignedTo: systemtap@sourceware.org
ReportedBy: fche@redhat.com
Classification: Unclassified
There has been a microbenchmark report that our aggregates' <<< 1 type
operations take longer than similar integer ++, even including locking
overheads, with the speculation that this is because the runtime always tracks
sums/max/min/count even if only one is needed by the script.
It would be helpful to reproduce the report [1], and if it is confirmed
non-trivial, to fix the runtime not to do unnecessary work.
[1]
https://github.com/fche/ServerUsage/commit/ff889cdcbaef65e2ce26a30ad4d18a614d6f41a2
--
Configure bugmail: http://sourceware.org/bugzilla/userprefs.cgi?tab=email
------- You are receiving this mail because: -------
You are the assignee for the bug.