1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 <2019> 2020 2021 2022 2023 2024 | Index | 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 <2019> 2020 2021 2022 2023 2024 |
<== Date ==> | <== Thread ==> |
---|
Subject: | Re: epics performance test tools or results |
From: | "Johnson, Andrew N. via Tech-talk" <[email protected]> |
To: | "[email protected]" <[email protected]> |
Date: | Mon, 1 Jul 2019 18:45:01 +0000 |
Hi Han, On 6/30/19 12:42 PM, Jeong Han Lee via Tech-talk wrote:
Is there a standard EPICS CA/PA or V3/V4/V7 performance test scenario or tools, or even results?There have been various performance measurements made over the years, and we even collected some results about individual VME CPU boards, but those results aren't terribly meaningful nowadays (the last result recorded was measured in 2007) and the code we used will probably need work to get it to build on recent EPICS releases. This thread has some information about that application, the measurements are in the performApp/TIMING text file. In other form of question, "do we have the standard procedure to see deployed IOC limitation?"No. I guess most people see whether it's fast enough for their application and restructure or adjust it until it is. In other form of question, "do we have a benchmark tool for any IOC or application?"Base builds a program called catime which measures the performance of a CA client/server connection (there are some instructions on how to run it in the CA reference documentation). Other tests have been performed by various people over the years and described in tech-talk messages or talks at collaboration meetings, but we don't have a standard as such. HTH, - Andrew -- Complexity comes for free, Simplicity you have to work for. |