[202205] [generate dump] Move the Core/Log collection to the End of process Execution and removed default timeout (#2230)

Thus moved the core/log collection to the end.

But there is a catch regarding the above change, For eg: system is in a unstable state and most of the individual commands start to timeout, the techsupport dump eventually times out at 30m (because of the global timeout), then the dump is pretty useless, since it might not have any useful information at all
Thus, i've removed the default global timeout, Clients can/should knowingly provide a value using -g option if the execution time has to be capped.

A global timeout of 60 mins is used for Global timeout for Auto-techsupport invocation.

Co-authored-by: Vivek Reddy Karri <[email protected]>

Author: vivekrnv

scripts/coredump_gen_handler.py

@@ -111,7 +111,7 @@ def parse_ts_dump_name(self, ts_stdout):
         return ""
 
     def invoke_ts_cmd(self, since_cfg, num_retry=0):
-        cmd_opts = ["show", "techsupport", "--silent", "--since", since_cfg]
+        cmd_opts = ["show", "techsupport", "--silent", "--global-timeout", TS_GLOBAL_TIMEOUT, "--since", since_cfg]
         cmd  = " ".join(cmd_opts)
         rc, stdout, stderr = subprocess_exec(cmd_opts, env=ENV_VAR)
         new_dump = ""

scripts/generate_dump

@@ -1287,11 +1287,6 @@ main() {
     end_t=$(date +%s%3N)
     echo "[ Capture Proc State ] : $(($end_t-$start_t)) msec" >> $TECHSUPPORT_TIME_INFO
 
-    # Save logs and cores early
-    save_log_files
-    save_crash_files
-    save_warmboot_files
-
     # Save all the processes within each docker
     save_cmd "show services" services.summary
 
@@ -1426,6 +1421,10 @@ main() {
     end_t=$(date +%s%3N)
     echo "[ TAR /etc Files ] : $(($end_t-$start_t)) msec" >> $TECHSUPPORT_TIME_INFO
 
+    save_log_files
+    save_crash_files
+    save_warmboot_files
+
     finalize
 }
 

show/main.py

@@ -1138,7 +1138,7 @@ def users(verbose):
 
 @cli.command()
 @click.option('--since', required=False, help="Collect logs and core files since given date")
-@click.option('-g', '--global-timeout', default=30, type=int, help="Global timeout in minutes. Default 30 mins")
+@click.option('-g', '--global-timeout', required=False, type=int, help="Global timeout in minutes. WARN: Dump might be incomplete if enforced")
 @click.option('-c', '--cmd-timeout', default=5, type=int, help="Individual command timeout in minutes. Default 5 mins")
 @click.option('--verbose', is_flag=True, help="Enable verbose output")
 @click.option('--allow-process-stop', is_flag=True, help="Dump additional data which may require system interruption")
@@ -1147,7 +1147,10 @@ def users(verbose):
 @click.option('--redirect-stderr', '-r', is_flag=True, help="Redirect an intermediate errors to STDERR")
 def techsupport(since, global_timeout, cmd_timeout, verbose, allow_process_stop, silent, debug_dump, redirect_stderr):
     """Gather information for troubleshooting"""
-    cmd = "sudo timeout --kill-after={}s -s SIGTERM --foreground {}m".format(COMMAND_TIMEOUT, global_timeout)
+    cmd = "sudo"
+
+    if global_timeout:
+        cmd += " timeout --kill-after={}s -s SIGTERM --foreground {}m".format(COMMAND_TIMEOUT, global_timeout)
 
     if allow_process_stop:
         cmd += " -a"

tests/coredump_gen_handler_test.py

@@ -20,6 +20,8 @@
 /tmp/saisdkdump
 """
 
+TS_DEFAULT_CMD = "show techsupport --silent --global-timeout 60 --since 2 days ago"
+
 def signal_handler(signum, frame):
     raise Exception("Timed out!")
 
@@ -427,4 +429,23 @@ def mock_cmd(cmd, env):
                 assert False, "Method should not time out"
             finally:
                 signal.alarm(0)
+    
+    def test_auto_ts_options(self):
+        """
+        Scenario: Check if the techsupport is called as expected
+        """
+        db_wrap = Db()
+        redis_mock = db_wrap.db
+        set_auto_ts_cfg(redis_mock, state="enabled", since_cfg="2 days ago")
+        set_feature_table_cfg(redis_mock, state="enabled")
+        with Patcher() as patcher:
+            def mock_cmd(cmd, env):
+                cmd_str = " ".join(cmd)
+                if "show techsupport" in cmd_str and cmd_str != TS_DEFAULT_CMD:
+                    assert False, "Expected TS_CMD: {}, Recieved: {}".format(TS_DEFAULT_CMD, cmd_str)
+                return 0, AUTO_TS_STDOUT, ""
+            cdump_mod.subprocess_exec = mock_cmd
+            patcher.fs.create_file("/var/core/orchagent.12345.123.core.gz")
+            cls = cdump_mod.CriticalProcCoreDumpHandle("orchagent.12345.123.core.gz", "swss", redis_mock)
+            cls.handle_core_dump_creation_event()
 

tests/techsupport_test.py

@@ -3,18 +3,18 @@
 from unittest.mock import patch, Mock
 from click.testing import CliRunner
 
-EXPECTED_BASE_COMMAND = 'sudo timeout --kill-after=300s -s SIGTERM --foreground '
+EXPECTED_BASE_COMMAND = 'sudo '
 
 @patch("show.main.run_command")
 @pytest.mark.parametrize(
         "cli_arguments,expected",
         [
-            ([], '30m generate_dump -v -t 5'),
-            (['--since', '2 days ago'], "30m generate_dump -v -s '2 days ago' -t 5"),
-            (['-g', '50'], '50m generate_dump -v -t 5'),
-            (['--allow-process-stop'], '30m -a generate_dump -v -t 5'),
-            (['--silent'], '30m generate_dump -t 5'),
-            (['--debug-dump', '--redirect-stderr'], '30m generate_dump -v -d -t 5 -r'),
+            ([], 'generate_dump -v -t 5'),
+            (['--since', '2 days ago'], "generate_dump -v -s '2 days ago' -t 5"),
+            (['-g', '50'], 'timeout --kill-after=300s -s SIGTERM --foreground 50m generate_dump -v -t 5'),
+            (['--allow-process-stop'], '-a generate_dump -v -t 5'),
+            (['--silent'], 'generate_dump -t 5'),
+            (['--debug-dump', '--redirect-stderr'], 'generate_dump -v -d -t 5 -r'),
         ]
 )
 def test_techsupport(run_command, cli_arguments, expected):

utilities_common/auto_techsupport_helper.py

@@ -13,7 +13,7 @@
             "CFG_CORE_USAGE", "CFG_SINCE", "FEATURE", "STATE_DB",
             "TS_MAP", "CORE_DUMP", "TIMESTAMP", "CONTAINER", "TIME_BUF",
             "SINCE_DEFAULT", "TS_PTRN_GLOB", "EXT_LOCKFAIL", "EXT_RETRY",
-            "EXT_SUCCESS", "MAX_RETRY_LIMIT"
+            "EXT_SUCCESS", "MAX_RETRY_LIMIT", "TS_GLOBAL_TIMEOUT"
         ] + [  # Methods
             "verify_recent_file_creation",
             "get_ts_dumps",
@@ -60,6 +60,7 @@
 
 TIME_BUF = 20
 SINCE_DEFAULT = "2 days ago"
+TS_GLOBAL_TIMEOUT = "60"
 
 # Techsupport Exit Codes
 EXT_LOCKFAIL = 2