1 files changed, 9 insertions, 5 deletions
diff --git a/meta-phosphor/recipes-phosphor/systemd-policy/phosphor-systemd-policy/service-restart-policy.conf b/meta-phosphor/recipes-phosphor/systemd-policy/phosphor-systemd-policy/service-restart-policy.conf
index 54516c2d47..17c9e6beae 100644
--- a/meta-phosphor/recipes-phosphor/systemd-policy/phosphor-systemd-policy/service-restart-policy.conf
+++ b/meta-phosphor/recipes-phosphor/systemd-policy/phosphor-systemd-policy/service-restart-policy.conf
@@ -13,19 +13,23 @@
 # restarting once does the job or restarting all 5 times does not help
 # and we just end up hitting the 5 limit anyway.
 #
-# - Change the StartLimitIntervalSec to 30s
+# - Change the StartLimitIntervalSec to 240s
 # The BMC CPU performance is already challenged. When a service is
 # failing and a core dump is being generated and collected into a dump,
 # it's even more challenged. Recent failures have shown situations where
 # the service does not fail again until 15-20 seconds after the initial
 # failure which means the default of 10s for this results in the service
-# being restarted indefinitely. Change this to 30s to only allow a service
-# to be restarted StartLimitBurst times within a 30s interval before
-# being put in a permanent fail state.
+# being restarted indefinitely.
+# Another issue that has cropped up recently is that the DefaultTimeoutStartSec
+# is 90s. If a service is hitting this timeout repeatedly then there
+# is a similar issue as noted above. Because of this, the StartLimitIntervalSec
+# needs to be StartLimitBurst*DefaultTimeoutStartSec +
+# StartLimitBurst* worst case processing time (30s)
+# which currently would be 2x90 + 2x30
 #
 # See systemd-system.conf(5) for details on the conf files
 
 [Manager]
 DefaultRestartSec=1s
 DefaultStartLimitBurst=2
-DefaultStartLimitIntervalSec=30s
+DefaultStartLimitIntervalSec=240s