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: | Interrupts in Linux |
From: | "Siddons, David via Tech-talk" <tech-talk at aps.anl.gov> |
To: | "tech-talk at aps.anl.gov" <tech-talk at aps.anl.gov> |
Date: | Mon, 5 Apr 2021 12:49:30 +0000 |
I have an embedded Linux system based on the ZynQ processor. I have the FPGA configured to generate a hardware interrupt whenever data is ready to be read. The frequency of the interrupts depends on the integration time of the measurement, and should be settable
from seconds to around one millisecond. This is all within an EPICS IOC running under ARM Linux, in a Debian 10 system. What I observe is that the maximum frequency I can use is 100Hz, which is the Linux system clock tick frequency. Presumably there is a lock
somewhere inhibiting interrupts except at tick time. I tried rebuilding the kernel with the PREEMPT-RT patch enabled, but it seems not to make a difference. I am definitely not a kernel expert; does anyone know what I'm missing?
Thanks,
Pete.
|