starlingx
/
ha
Code Issues Proposed changes

Add node locked gate to SM enable for DX systems 

Service Management (SM) sometimes selects and activates services on a
locked controller following a dead office recovery.

This update adds a node locked check to SM's enable handler to
block enable if present much like the existing goenabled check
blocks enable if not present in the same function.

The enable gate file is /etc/mtc/tmp/.node_locked on the local host.

Maintenance manages the presence or absence of this file based on
the node's administrative state.

This update also cleans up some extra whitespace in the changed file.

Test Plan:

PASS: Verify system build.
PASS: Verify AIO SX install.
PASS: Verify AIO DX install.
PASS: Verify Standard DX system install with worker and storage.

For Both 'AIO DX' and 'Standard DX with worker and storage':

PASS: Verify SM does not activate on a locked DX controller.
PASS: ... DOR case
PASS: ... Uncontrolled Swact case
PASS: Verify Standard DX behavior over DOR with one locked controller
      while the only unlocked controller does not recover.
PASS: Verify behavior after above test case once the only unlocked
      controller does recover.
PASS: Verify lock of the standby controller and its sm logs
PASS: Verify manually creating the new Nv locked file on the active
      controller will cause SM to go disabled and shut down all
      services on that controller.
      ... If there is another unlocked controller then verify it
          takes over as an uncontrolled swact.
      ... If there is no unlocked standby controller then verify SM
          remains shutdown until the manually created Nv node locked
          file is removed. At which point SM proceeds to activate
          services on that controller again.

PASS: Verify SM ignores the node locked flag file for AIO SX systems.
PASS: Verify lock/unlock of AIO SX controller.
PASS: Verify original reported issue is resolved for AIO DX systems.

Regression:

PASS: Verify controlled swact with unlocked enabled standby.
PASS: Verify uncontrolled swact with unlocked enabled standby.
PASS: Verify standby controller lock/unlock soak loop (10).
PASS: Verify swact loop soak (10).
PASS: Verify no crash or core dumps.
PASS: Verify SM logging

Closes-Bug: 2051578
Change-Id: If8e27ef30d62096fa77c3868f4d460b18e10ade2
(cherry picked from commit 23d0d8ab2f)
This commit is contained in:
Eric MacDonald 2024-02-02 16:52:50 +00:00
parent 338161f443
commit 91fa44188c
1 changed files with 28 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

36
service-mgmt/sm-common/src/sm_node_utils.c
View File

@ -1,5 +1,5 @@
//
// Copyright (c) 2014-2023 Wind River Systems, Inc.
// Copyright (c) 2014-2024 Wind River Systems, Inc.
//
// SPDX-License-Identifier: Apache-2.0
//
@ -18,6 +18,7 @@
#include "sm_types.h"
#include "sm_debug.h"
#define SM_NODE_LOCKED_FILE "/etc/mtc/tmp/.node_locked"
#define SM_NODE_GO_ENABLE_FILE "/var/run/goenabled"
#define SM_NODE_GO_ENABLE_FILE_SIMPLEX "/var/run/.goenabled"
#define SM_NODE_UNHEALTHY_FILE "/var/run/.sm_node_unhealthy"
@ -50,7 +51,7 @@ static SmErrorT sm_node_utils_read_platform_config( const char key[],
char format[1024];
char line[1024];
char val[1024];
value[0] = '\0';
fp = fopen( SM_NODE_PLATFORM_CONFIG_FILE, "r" );
@ -156,7 +157,7 @@ SmErrorT sm_node_utils_is_aio( bool* is_aio )
else
{
*is_aio = ( IsTrue == _is_aio );
}
}
return SM_OKAY;
}
@ -346,7 +347,7 @@ SmErrorT sm_node_utils_get_hostname( char node_name[] )
// ****************************************************************************
// ****************************************************************************
// Node Utilities - Configuration Complete
// Node Utilities - Configuration Complete
// =======================================
SmErrorT sm_node_utils_config_complete( bool* complete )
{
@ -369,7 +370,7 @@ SmErrorT sm_node_utils_config_complete( bool* complete )
*complete = true;
return( SM_OKAY );
return( SM_OKAY );
}
// ****************************************************************************
@ -381,6 +382,7 @@ typedef enum
NODE_UNHEALTHY_FILE_EXISTS,
NODE_DISABLED_LICENSE_INVALID,
NODE_DISABLED_FAILOVER,
NODE_IS_LOCKED,
NODE_ENABLED
}SmNodeEnabledBlockingStateT;
static SmNodeEnabledBlockingStateT blocking_state = BLOCKING_STATE_INIT;
@ -394,6 +396,7 @@ SmErrorT sm_node_utils_enabled( bool* enabled, char reason_text[] )
*enabled = false;
reason_text[0] = '\0';
const char* goenabled_file = SM_NODE_GO_ENABLE_FILE;
const char* node_locked_file = SM_NODE_LOCKED_FILE;
bool is_aio_simplex = false;
SmErrorT error = sm_node_utils_is_aio_simplex(&is_aio_simplex);
@ -409,6 +412,23 @@ SmErrorT sm_node_utils_enabled( bool* enabled, char reason_text[] )
goenabled_file = SM_NODE_GO_ENABLE_FILE_SIMPLEX;
}
// AIO SX Case: Need to support SM
// 1. activating on the only locked controller
// 2. maintaining an active state after locking the only controller
if( (!is_aio_simplex) && ( 0 == access( node_locked_file, F_OK )))
{
if(blocking_state != NODE_IS_LOCKED)
{
blocking_state = NODE_IS_LOCKED;
DPRINTFI("Node enable: blocked. Node is locked ; the %s file is present", node_locked_file);
}
snprintf( reason_text, SM_LOG_REASON_TEXT_MAX_CHAR,
"node is locked" );
return( SM_OKAY );
}
if(0 > access( goenabled_file, F_OK ))
{
if( ENOENT == errno )
@ -518,7 +538,7 @@ bool sm_node_utils_set_failover( bool to_disable )
// ****************************************************************************
// Node Utilities - Set Unhealthy
// ==============================
SmErrorT sm_node_utils_set_unhealthy( void )
SmErrorT sm_node_utils_set_unhealthy( void )
{
int fd = open( SM_NODE_UNHEALTHY_FILE,
O_RDWR | O_CREAT, S_IRUSR | S_IRGRP | S_IROTH);
@ -563,13 +583,13 @@ SmErrorT sm_node_utils_is_aio_duplex( bool* is_aio_duplex )
if( IsUnknown == _is_aio_duplex )
{
SmErrorT error;
bool is_aio = false;
bool is_aio = false;
error = sm_node_utils_is_aio( &is_aio );
if( SM_OKAY != error)
{
return error;
}
if ( !is_aio )
{
*is_aio_duplex = false;