diff mbox series

[scarthgap] arm/oeqa: Introduce retry mechanism for fvp_devices run_cmd

Message ID 20240802070543.3439695-1-luca.fancellu@arm.com
State New
Headers show
Series [scarthgap] arm/oeqa: Introduce retry mechanism for fvp_devices run_cmd | expand

Commit Message

Luca Fancellu Aug. 2, 2024, 7:05 a.m. UTC
Currently the run_cmd, which is a wrapper for self.target.run()
that uses SSH to spawn commands on the target, can fail spuriously
with error 255 and cause the test to fail on slow systems.

In order to address that, introduce a retry mechanism for the call,
that is able to wait some time for the system to settle and retry
the command when the error code from SSH is 255.

Signed-off-by: Luca Fancellu <luca.fancellu@arm.com>
---
 meta-arm/lib/oeqa/runtime/cases/fvp_devices.py | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)
diff mbox series

Patch

diff --git a/meta-arm/lib/oeqa/runtime/cases/fvp_devices.py b/meta-arm/lib/oeqa/runtime/cases/fvp_devices.py
index 0246e76a94b3..c9d08c03448a 100644
--- a/meta-arm/lib/oeqa/runtime/cases/fvp_devices.py
+++ b/meta-arm/lib/oeqa/runtime/cases/fvp_devices.py
@@ -1,16 +1,29 @@ 
 from oeqa.runtime.case import OERuntimeTestCase
 from oeqa.core.decorator.data import skipIfNotInDataVar
 from oeqa.core.decorator.depends import OETestDepends
+from time import sleep
 
 
 class FvpDevicesTest(OERuntimeTestCase):
-    def run_cmd(self, cmd, check=True):
+    def run_cmd(self, cmd, check=True, retry=3):
         """
         A wrapper around self.target.run, which:
           * Fails the test on command failure by default
           * Allows the "run" behavior to be overridden in sub-classes
+          * Has a retry mechanism when SSH returns 255
         """
-        (status, output) = self.target.run(cmd)
+        status = 255
+        # The loop is retrying the self.target.run() which uses SSH only when
+        # the SSH return code is 255, which might be an issue with
+        # "Connection refused" because the port isn't open yet
+        while status == 255 and retry > 0:
+            (status, output) = self.target.run(cmd)
+            retry -= 1
+            # In case the status is 255, delay the next retry to give time to
+            # the system to settle
+            if status == 255:
+                sleep(30)
+
         if status and check:
             self.fail("Command '%s' returned non-zero exit "
                       "status %d:\n%s" % (cmd, status, output))