From f8d0b344ae1b2dc3894c1a597c0565911b762742 Mon Sep 17 00:00:00 2001
From: John Klug <john.klug@multitech.com>
Date: Tue, 19 Jan 2021 17:21:32 -0600
Subject: softdog-mon for monitoring a system using kernel module "softdog"

---
 README | 84 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 84 insertions(+)
 create mode 100644 README

(limited to 'README')

diff --git a/README b/README
new file mode 100644
index 0000000..6d0e22f
--- /dev/null
+++ b/README
@@ -0,0 +1,84 @@
+Configurable monitor program that uses softdog.
+
+This program (softdog-mon) must be running all
+the time once it is started, or the
+system will reset itself without a shutdown.
+The problems detected may prevent shutdown, so a
+reset is safer.
+
+The SHUTDOWNTIMEOUT value is the time to allow for
+shutdown.  Since firmware updates are done during
+shutdown, this should be the worst case time for
+shutdown.
+
+Variables passed through the environment:
+
+# Monitor program will have 1 second granularity.  Fixed.
+# All times are in seconds.
+
+# Hardware watchdog is found first, which is watchdog0.
+WATCHDOG = /dev/watchdog1
+
+# Nice value -20, is highest priority for a user program, 19 is lowest.
+NICE = -20
+
+# Watchdog timeout in seconds
+TIMEOUT = 60
+
+# How often to feed in seconds
+FEED = 10
+
+# File is synchonously open/read/written/closed every 30 seconds
+FILESAMPLERATE = 30
+
+# File to be read/written
+# If I/O hangs, the TIMEOUT value is the maximum seconds until we
+# reset the device.
+MONITORFILE = /media/card/.softdog_monitor
+
+# Minimum available system memory in bytes
+MINIMUM_AVAILABLE_MEM = 3000000
+
+# Minimum free high memory
+MINIMUM_FREEHIGH = 0
+
+# Rate at which we sample available memory
+MEMSAMPLERATE = 3
+
+# last samples saved
+MEMSAMPLES = 100
+
+# maximum number of samples failed in last samples saved
+MEMFAILEDSAMPLES = 20
+
+# Allow time for flash upgrade during shutdown
+# This happens when a SIGTERM signal is received.
+# So shutdown has this many seconds to complete.
+SHUTDOWNTIMEOUT=600
+
+Their is an additional test program called
+hog.  This can be used to acquire memory and kernel
+resources.
+
+hog 4750000
+
+This will start five processes with 4750000 bytes
+of memory.  The idea is to trigger the watchdog.
+
+    hog 4750000
+
+Creates five processes with the amount of memory
+specified.
+
+In a typical test:
+
+Log into the device several times with ssh, and do sudo -s
+and acquire a root shell.
+
+As root start the program hog, the amount of memory required
+will depend on the size of the programs typically running.
+
+Start top on the several screens logged in.  Try to get the
+available memory below 3MB.  Once 20 samples have failed
+the device will reboot.
+
-- 
cgit v1.2.3