cephadm: fix host-maintenance command always exiting with a failure

The host-maintenance command would always fail because
command_maintenance always returns a string. This string is passed to
sys.exit and thus always gets printed and causes a non-zero exit code.
Fix the command line behavior by renaming the original function and
adding a new command_maintenance that prints the string and returns an
int like other command_* functions do.

Fixes: https://tracker.ceph.com/issues/65122
Signed-off-by: John Mulligan <jmulligan@redhat.com>
(cherry picked from commit 0a137b140e47d02b03d133adb55e62aa0de7b984)

diff --git a/src/cephadm/cephadm.py b/src/cephadm/cephadm.py
index eccb330fda9077437d6308348e67dadc3d505ccd..396880b5d4a1403bd0f595801307537c077070a7 100755 (executable)
--- a/src/cephadm/cephadm.py
+++ b/src/cephadm/cephadm.py
@@ -4634,7 +4634,17 @@ def target_exists(ctx: CephadmContext) -> bool:
 
 
 @infer_fsid
-def command_maintenance(ctx: CephadmContext) -> str:
+def command_maintenance(ctx: CephadmContext) -> int:
+    msg = change_maintenance_mode(ctx)
+    # mgr module reads the string emitted here from stderr
+    sys.stderr.write(msg + '\n')
+    sys.stderr.flush()
+    if msg.startswith('fail'):
+        return 1
+    return 0
+
+
+def change_maintenance_mode(ctx: CephadmContext) -> str:
     if not ctx.fsid:
         raise Error('failed - must pass --fsid to specify cluster')
 

diff --git a/src/cephadm/tests/test_cephadm.py b/src/cephadm/tests/test_cephadm.py
index 9c6caf0092b7455098ba390c23ff26a65ed4c8e5..ac956caa70bad674122174c3a09e955aa5f6ea6a 100644 (file)
--- a/src/cephadm/tests/test_cephadm.py
+++ b/src/cephadm/tests/test_cephadm.py
@@ -1164,7 +1164,7 @@ class TestMaintenance:
         ctx: _cephadm.CephadmContext = _cephadm.cephadm_init_ctx(
             ['host-maintenance', 'enter', '--fsid', TestMaintenance.fsid])
         ctx.container_engine = mock_podman()
-        retval = _cephadm.command_maintenance(ctx)
+        retval = _cephadm.change_maintenance_mode(ctx)
         assert retval.startswith('failed')
 
     @mock.patch('os.listdir', return_value=[])
@@ -1177,7 +1177,7 @@ class TestMaintenance:
         ctx: _cephadm.CephadmContext = _cephadm.cephadm_init_ctx(
             ['host-maintenance', 'enter', '--fsid', TestMaintenance.fsid])
         ctx.container_engine = mock_podman()
-        retval = _cephadm.command_maintenance(ctx)
+        retval = _cephadm.change_maintenance_mode(ctx)
         assert retval.startswith('failed')
 
     @mock.patch('os.listdir', return_value=[])
@@ -1192,7 +1192,7 @@ class TestMaintenance:
         ctx: _cephadm.CephadmContext = _cephadm.cephadm_init_ctx(
             ['host-maintenance', 'exit', '--fsid', TestMaintenance.fsid])
         ctx.container_engine = mock_podman()
-        retval = _cephadm.command_maintenance(ctx)
+        retval = _cephadm.change_maintenance_mode(ctx)
         assert retval.startswith('failed')
 
     @mock.patch('os.listdir', return_value=[])
@@ -1207,7 +1207,7 @@ class TestMaintenance:
         ctx: _cephadm.CephadmContext = _cephadm.cephadm_init_ctx(
             ['host-maintenance', 'exit', '--fsid', TestMaintenance.fsid])
         ctx.container_engine = mock_podman()
-        retval = _cephadm.command_maintenance(ctx)
+        retval = _cephadm.change_maintenance_mode(ctx)
         assert retval.startswith('failed')