selftests/tc-testing: localize test resources

As of today, the current tdc architecture creates one netns and uses it
to run all tests. This assumption was embedded into the nsPlugin which
carried over as how the tests were written.

The tdc tests are by definition self contained and can,
theoretically, run in parallel. Even though in the kernel they will
serialize over the rtnl lock, we should expect a significant speedup of the
total wall time for the entire test suite, which is hitting close to
1100 tests at this point.

A first step to achieve this goal is to remove sharing of global resources like
veth/dummy interfaces and the netns. In this patch we 'localize' these
resources on a per test basis. Each test gets it's own netns, VETH/dummy interfaces.
The resources are spawned in the pre_suite phase, where tdc will prepare
all netns and interfaces for all tests. This is done in order to avoid
concurrency issues with netns / interfaces spawning and commands using
them. As tdc progresses, the resources are deleted after each test finishes
executing.

Tests that don't use the nsPlugin still run under the root namespace,
but are now required to manage any external resources like interfaces.
These cannot be parallelized as their definition doesn't allow it.
On the other hand, when using the nsPlugin, tests don't need to create
dummy/veth interfaces as these are handled already.

Tested-by: Davide Caratti <[e-mail]>
Signed-off-by: Pedro Tammela <[e-mail]>
Acked-by: Jamal Hadi Salim <[e-mail]>
Signed-off-by: Paolo Abeni <[e-mail]>

tools/testing/selftests/tc-testing/TdcPlugin.py

···
         super().__init__()
         print(' -- {}.__init__'.format(self.sub_class))
 
-    def pre_suite(self, testcount, testidlist):
+    def pre_suite(self, testcount, testlist):
         '''run commands before test_runner goes into a test loop'''
         self.testcount = testcount
-        self.testidlist = testidlist
+        self.testlist = testlist
         if self.args.verbose > 1:
             print(' -- {}.pre_suite'.format(self.sub_class))
 

tools/testing/selftests/tc-testing/plugin-lib/nsPlugin.py

···
 from string import Template
 import subprocess
 import time
+from functools import cached_property
 from TdcPlugin import TdcPlugin
 
 from tdc_config import *
···
         self.sub_class = 'ns/SubPlugin'
         super().__init__()
 
-    def pre_suite(self, testcount, testidlist):
-        '''run commands before test_runner goes into a test loop'''
-        super().pre_suite(testcount, testidlist)
+    def pre_suite(self, testcount, testlist):
+        super().pre_suite(testcount, testlist)
 
-        if self.args.namespace:
-            self._ns_create()
-        else:
-            self._ports_create()
+        print("Setting up namespaces and devices...")
 
-    def post_suite(self, index):
-        '''run commands after test_runner goes into a test loop'''
-        super().post_suite(index)
+        original = self.args.NAMES
+
+        for t in testlist:
+            if 'skip' in t and t['skip'] == 'yes':
+                continue
+
+            if 'nsPlugin' not in t['plugins']:
+                continue
+
+            shadow = {}
+            shadow['IP'] = original['IP']
+            shadow['TC'] = original['TC']
+            shadow['NS'] = '{}-{}'.format(original['NS'], t['random'])
+            shadow['DEV0'] = '{}id{}'.format(original['DEV0'], t['id'])
+            shadow['DEV1'] = '{}id{}'.format(original['DEV1'], t['id'])
+            shadow['DUMMY'] = '{}id{}'.format(original['DUMMY'], t['id'])
+            shadow['DEV2'] = original['DEV2']
+            self.args.NAMES = shadow
+
+            if self.args.namespace:
+                self._ns_create()
+            else:
+                self._ports_create()
+
+        self.args.NAMES = original
+
+    def pre_case(self, caseinfo, test_skip):
         if self.args.verbose:
-            print('{}.post_suite'.format(self.sub_class))
+            print('{}.pre_case'.format(self.sub_class))
+
+        if test_skip:
+            return
+
+        # Make sure the netns is visible in the fs
+        while True:
+            self._proc_check()
+            try:
+                ns = self.args.NAMES['NS']
+                f = open('/run/netns/{}'.format(ns))
+                f.close()
+                break
+            except:
+                continue
+
+    def post_case(self):
+        if self.args.verbose:
+            print('{}.post_case'.format(self.sub_class))
 
         if self.args.namespace:
             self._ns_destroy()
         else:
             self._ports_destroy()
+
+    def post_suite(self, index):
+        if self.args.verbose:
+            print('{}.post_suite'.format(self.sub_class))
+
+        # Make sure we don't leak resources
+        for f in os.listdir('/run/netns/'):
+            cmd = self._replace_keywords("$IP netns del {}".format(f))
+
+            if self.args.verbose > 3:
+                print('_exec_cmd:  command "{}"'.format(cmd))
+
+            subprocess.run(cmd, shell=True, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)
 
     def add_args(self, parser):
         super().add_args(parser)
···
             print('adjust_command:  return command [{}]'.format(command))
         return command
 
-    def _ports_create(self):
-        cmd = '$IP link add $DEV0 type veth peer name $DEV1'
-        self._exec_cmd('pre', cmd)
-        cmd = '$IP link set $DEV0 up'
-        self._exec_cmd('pre', cmd)
+    def _ports_create_cmds(self):
+        cmds = []
+
+        cmds.append(self._replace_keywords('link add $DEV0 type veth peer name $DEV1'))
+        cmds.append(self._replace_keywords('link set $DEV0 up'))
+        cmds.append(self._replace_keywords('link add $DUMMY type dummy'))
         if not self.args.namespace:
-            cmd = '$IP link set $DEV1 up'
-            self._exec_cmd('pre', cmd)
+            cmds.append(self._replace_keywords('link set $DEV1 up'))
+
+        return cmds
+
+    def _ports_create(self):
+        self._exec_cmd_batched('pre', self._ports_create_cmds())
+
+    def _ports_destroy_cmd(self):
+        return self._replace_keywords('link del $DEV0')
 
     def _ports_destroy(self):
-        cmd = '$IP link del $DEV0'
-        self._exec_cmd('post', cmd)
+        self._exec_cmd('post', self._ports_destroy_cmd())
+
+    def _ns_create_cmds(self):
+        cmds = []
+
+        if self.args.namespace:
+            ns = self.args.NAMES['NS']
+
+            cmds.append(self._replace_keywords('netns add {}'.format(ns)))
+            cmds.append(self._replace_keywords('link set $DEV1 netns {}'.format(ns)))
+            cmds.append(self._replace_keywords('link set $DUMMY netns {}'.format(ns)))
+            cmds.append(self._replace_keywords('netns exec {} $IP link set $DEV1 up'.format(ns)))
+            cmds.append(self._replace_keywords('netns exec {} $IP link set $DUMMY up'.format(ns)))
+
+            if self.args.device:
+                cmds.append(self._replace_keywords('link set $DEV2 netns {}'.format(ns)))
+                cmds.append(self._replace_keywords('netns exec {} $IP link set $DEV2 up'.format(ns)))
+
+        return cmds
 
     def _ns_create(self):
         '''
···
         the required network devices for it.
         '''
         self._ports_create()
-        if self.args.namespace:
-            cmd = '$IP netns add {}'.format(self.args.NAMES['NS'])
-            self._exec_cmd('pre', cmd)
-            cmd = '$IP link set $DEV1 netns {}'.format(self.args.NAMES['NS'])
-            self._exec_cmd('pre', cmd)
-            cmd = '$IP -n {} link set $DEV1 up'.format(self.args.NAMES['NS'])
-            self._exec_cmd('pre', cmd)
-            if self.args.device:
-                cmd = '$IP link set $DEV2 netns {}'.format(self.args.NAMES['NS'])
-                self._exec_cmd('pre', cmd)
-                cmd = '$IP -n {} link set $DEV2 up'.format(self.args.NAMES['NS'])
-                self._exec_cmd('pre', cmd)
+        self._exec_cmd_batched('pre', self._ns_create_cmds())
+
+    def _ns_destroy_cmd(self):
+        return self._replace_keywords('netns delete {}'.format(self.args.NAMES['NS']))
 
     def _ns_destroy(self):
         '''
···
         devices as well)
         '''
         if self.args.namespace:
-            cmd = '$IP netns delete {}'.format(self.args.NAMES['NS'])
-            self._exec_cmd('post', cmd)
+            self._exec_cmd('post', self._ns_destroy_cmd())
+            self._ports_destroy()
+
+    @cached_property
+    def _proc(self):
+        ip = self._replace_keywords("$IP -b -")
+        proc = subprocess.Popen(ip,
+            shell=True,
+            stdin=subprocess.PIPE,
+            env=ENVIR)
+
+        return proc
+
+    def _proc_check(self):
+        proc = self._proc
+
+        proc.poll()
+
+        if proc.returncode is not None and proc.returncode != 0:
+            raise RuntimeError("iproute2 exited with an error code")
 
     def _exec_cmd(self, stage, command):
         '''
         Perform any required modifications on an executable command, then run
         it in a subprocess and return the results.
         '''
-        if '$' in command:
-            command = self._replace_keywords(command)
 
-        self.adjust_command(stage, command)
-        if self.args.verbose:
+        if self.args.verbose > 3:
             print('_exec_cmd:  command "{}"'.format(command))
-        proc = subprocess.Popen(command,
-            shell=True,
-            stdout=subprocess.PIPE,
-            stderr=subprocess.PIPE,
-            env=ENVIR)
-        (rawout, serr) = proc.communicate()
 
-        if proc.returncode != 0 and len(serr) > 0:
-            foutput = serr.decode("utf-8")
-        else:
-            foutput = rawout.decode("utf-8")
+        proc = self._proc
 
-        proc.stdout.close()
-        proc.stderr.close()
-        return proc, foutput
+        proc.stdin.write((command + '\n').encode())
+        proc.stdin.flush()
+
+        if self.args.verbose > 3:
+            print('_exec_cmd proc: {}'.format(proc))
+
+        self._proc_check()
+
+    def _exec_cmd_batched(self, stage, commands):
+        for cmd in commands:
+            self._exec_cmd(stage, cmd)
 
     def _replace_keywords(self, cmd):
         """

tools/testing/selftests/tc-testing/plugin-lib/rootPlugin.py

···
         self.sub_class = 'root/SubPlugin'
         super().__init__()
 
-    def pre_suite(self, testcount, testidlist):
+    def pre_suite(self, testcount, testlist):
         # run commands before test_runner goes into a test loop
-        super().pre_suite(testcount, testidlist)
+        super().pre_suite(testcount, testlist)
 
         if os.geteuid():
             print('This script must be run with root privileges', file=sys.stderr)

tools/testing/selftests/tc-testing/plugin-lib/valgrindPlugin.py

···
         self._tsr = TestSuiteReport()
         super().__init__()
 
-    def pre_suite(self, testcount, testidlist):
+    def pre_suite(self, testcount, testist):
         '''run commands before test_runner goes into a test loop'''
-        super().pre_suite(testcount, testidlist)
+        self.testidlist = [tidx['id'] for tidx in testlist]
+        super().pre_suite(testcount, testlist)
         if self.args.verbose > 1:
             print('{}.pre_suite'.format(self.sub_class))
         if self.args.valgrind:

tools/testing/selftests/tc-testing/tdc.py

···
 import subprocess
 import time
 import traceback
+import random
 from collections import OrderedDict
 from string import Template
 
···
 class PluginMgr:
     def __init__(self, argparser):
         super().__init__()
-        self.plugins = {}
+        self.plugins = set()
         self.plugin_instances = []
         self.failed_plugins = {}
         self.argparser = argparser
 
-        # TODO, put plugins in order
         plugindir = os.getenv('TDC_PLUGIN_DIR', './plugins')
         for dirpath, dirnames, filenames in os.walk(plugindir):
             for fn in filenames:
···
                     not fn.startswith('.#')):
                     mn = fn[0:-3]
                     foo = importlib.import_module('plugins.' + mn)
-                    self.plugins[mn] = foo
-                    self.plugin_instances.append(foo.SubPlugin())
+                    self.plugins.add(mn)
+                    self.plugin_instances[mn] = foo.SubPlugin()
 
     def load_plugin(self, pgdir, pgname):
         pgname = pgname[0:-3]
+        self.plugins.add(pgname)
+
         foo = importlib.import_module('{}.{}'.format(pgdir, pgname))
-        self.plugins[pgname] = foo
-        self.plugin_instances.append(foo.SubPlugin())
-        self.plugin_instances[-1].check_args(self.args, None)
+
+        # nsPlugin must always be the first one
+        if pgname == "nsPlugin":
+            self.plugin_instances.insert(0, (pgname, foo.SubPlugin()))
+            self.plugin_instances[0][1].check_args(self.args, None)
+        else:
+            self.plugin_instances.append((pgname, foo.SubPlugin()))
+            self.plugin_instances[-1][1].check_args(self.args, None)
 
     def get_required_plugins(self, testlist):
         '''
         Get all required plugins from the list of test cases and return
         all unique items.
         '''
-        reqs = []
+        reqs = set()
         for t in testlist:
             try:
                 if 'requires' in t['plugins']:
                     if isinstance(t['plugins']['requires'], list):
-                        reqs.extend(t['plugins']['requires'])
+                        reqs.update(set(t['plugins']['requires']))
                     else:
-                        reqs.append(t['plugins']['requires'])
+                        reqs.add(t['plugins']['requires'])
+                    t['plugins'] = t['plugins']['requires']
+                else:
+                    t['plugins'] = []
             except KeyError:
+                t['plugins'] = []
                 continue
-        reqs = get_unique_item(reqs)
+
         return reqs
 
     def load_required_plugins(self, reqs, parser, args, remaining):
···
         return args
 
     def call_pre_suite(self, testcount, testidlist):
-        for pgn_inst in self.plugin_instances:
+        for (_, pgn_inst) in self.plugin_instances:
             pgn_inst.pre_suite(testcount, testidlist)
 
     def call_post_suite(self, index):
-        for pgn_inst in reversed(self.plugin_instances):
+        for (_, pgn_inst) in reversed(self.plugin_instances):
             pgn_inst.post_suite(index)
 
     def call_pre_case(self, caseinfo, *, test_skip=False):
-        for pgn_inst in self.plugin_instances:
+        for (pgn, pgn_inst) in self.plugin_instances:
+            if pgn not in caseinfo['plugins']:
+                continue
             try:
                 pgn_inst.pre_case(caseinfo, test_skip)
             except Exception as ee:
···
                 print('testid is {}'.format(caseinfo['id']))
                 raise
 
-    def call_post_case(self):
-        for pgn_inst in reversed(self.plugin_instances):
+    def call_post_case(self, caseinfo):
+        for (pgn, pgn_inst) in reversed(self.plugin_instances):
+            if pgn not in caseinfo['plugins']:
+                continue
             pgn_inst.post_case()
 
-    def call_pre_execute(self):
-        for pgn_inst in self.plugin_instances:
+    def call_pre_execute(self, caseinfo):
+        for (pgn, pgn_inst) in self.plugin_instances:
+            if pgn not in caseinfo['plugins']:
+                continue
             pgn_inst.pre_execute()
 
-    def call_post_execute(self):
-        for pgn_inst in reversed(self.plugin_instances):
+    def call_post_execute(self, caseinfo):
+        for (pgn, pgn_inst) in reversed(self.plugin_instances):
+            if pgn not in caseinfo['plugins']:
+                continue
             pgn_inst.post_execute()
 
     def call_add_args(self, parser):
-        for pgn_inst in self.plugin_instances:
+        for (pgn, pgn_inst) in self.plugin_instances:
             parser = pgn_inst.add_args(parser)
         return parser
 
     def call_check_args(self, args, remaining):
-        for pgn_inst in self.plugin_instances:
+        for (pgn, pgn_inst) in self.plugin_instances:
             pgn_inst.check_args(args, remaining)
 
-    def call_adjust_command(self, stage, command):
-        for pgn_inst in self.plugin_instances:
+    def call_adjust_command(self, caseinfo, stage, command):
+        for (pgn, pgn_inst) in self.plugin_instances:
+            if pgn not in caseinfo['plugins']:
+                continue
             command = pgn_inst.adjust_command(stage, command)
         return command
 
···
     return subcmd
 
 
-def exec_cmd(args, pm, stage, command):
+def exec_cmd(caseinfo, args, pm, stage, command):
     """
     Perform any required modifications on an executable command, then run
     it in a subprocess and return the results.
···
     if '$' in command:
         command = replace_keywords(command)
 
-    command = pm.call_adjust_command(stage, command)
+    command = pm.call_adjust_command(caseinfo, stage, command)
     if args.verbose > 0:
         print('command "{}"'.format(command))
+
     proc = subprocess.Popen(command,
         shell=True,
         stdout=subprocess.PIPE,
···
     return proc, foutput
 
 
-def prepare_env(args, pm, stage, prefix, cmdlist, output = None):
+def prepare_env(caseinfo, args, pm, stage, prefix, cmdlist, output = None):
     """
     Execute the setup/teardown commands for a test case.
     Optionally terminate test execution if the command fails.
···
         if not cmd:
             continue
 
-        (proc, foutput) = exec_cmd(args, pm, stage, cmd)
+        (proc, foutput) = exec_cmd(caseinfo, args, pm, stage, cmd)
 
         if proc and (proc.returncode not in exit_codes):
             print('', file=sys.stderr)
···
 
 def run_one_test(pm, args, index, tidx):
     global NAMES
+    ns = NAMES['NS']
+    dev0 = NAMES['DEV0']
+    dev1 = NAMES['DEV1']
+    dummy = NAMES['DUMMY']
     result = True
     tresult = ""
     tap = ""
···
             res.set_result(ResultState.skip)
             res.set_errormsg('Test case designated as skipped.')
             pm.call_pre_case(tidx, test_skip=True)
-            pm.call_post_execute()
+            pm.call_post_execute(tidx)
             return res
 
     if 'dependsOn' in tidx:
         if (args.verbose > 0):
             print('probe command for test skip')
-        (p, procout) = exec_cmd(args, pm, 'execute', tidx['dependsOn'])
+        (p, procout) = exec_cmd(tidx, args, pm, 'execute', tidx['dependsOn'])
         if p:
             if (p.returncode != 0):
                 res = TestResult(tidx['id'], tidx['name'])
                 res.set_result(ResultState.skip)
                 res.set_errormsg('probe command: test skipped.')
                 pm.call_pre_case(tidx, test_skip=True)
-                pm.call_post_execute()
+                pm.call_post_execute(tidx)
                 return res
 
     # populate NAMES with TESTID for this test
     NAMES['TESTID'] = tidx['id']
+    NAMES['NS'] = '{}-{}'.format(NAMES['NS'], tidx['random'])
+    NAMES['DEV0'] = '{}id{}'.format(NAMES['DEV0'], tidx['id'])
+    NAMES['DEV1'] = '{}id{}'.format(NAMES['DEV1'], tidx['id'])
+    NAMES['DUMMY'] = '{}id{}'.format(NAMES['DUMMY'], tidx['id'])
 
     pm.call_pre_case(tidx)
-    prepare_env(args, pm, 'setup', "-----> prepare stage", tidx["setup"])
+    prepare_env(tidx, args, pm, 'setup', "-----> prepare stage", tidx["setup"])
 
     if (args.verbose > 0):
         print('-----> execute stage')
-    pm.call_pre_execute()
-    (p, procout) = exec_cmd(args, pm, 'execute', tidx["cmdUnderTest"])
+    pm.call_pre_execute(tidx)
+    (p, procout) = exec_cmd(tidx, args, pm, 'execute', tidx["cmdUnderTest"])
     if p:
         exit_code = p.returncode
     else:
         exit_code = None
 
-    pm.call_post_execute()
+    pm.call_post_execute(tidx)
 
     if (exit_code is None or exit_code != int(tidx["expExitCode"])):
         print("exit: {!r}".format(exit_code))
···
     else:
         if args.verbose > 0:
             print('-----> verify stage')
-        (p, procout) = exec_cmd(args, pm, 'verify', tidx["verifyCmd"])
+        (p, procout) = exec_cmd(tidx, args, pm, 'verify', tidx["verifyCmd"])
         if procout:
             if 'matchJSON' in tidx:
                 verify_by_json(procout, res, tidx, args, pm)
···
         else:
             res.set_result(ResultState.success)
 
-    prepare_env(args, pm, 'teardown', '-----> teardown stage', tidx['teardown'], procout)
-    pm.call_post_case()
+    prepare_env(tidx, args, pm, 'teardown', '-----> teardown stage', tidx['teardown'], procout)
+    pm.call_post_case(tidx)
 
     index += 1
 
     # remove TESTID from NAMES
     del(NAMES['TESTID'])
+
+    # Restore names
+    NAMES['NS'] = ns
+    NAMES['DEV0'] = dev0
+    NAMES['DEV1'] = dev1
+    NAMES['DUMMY'] = dummy
+
     return res
 
 def test_runner(pm, args, filtered_tests):
···
     tsr = TestSuiteReport()
 
     try:
-        pm.call_pre_suite(tcount, [tidx['id'] for tidx in testlist])
+        pm.call_pre_suite(tcount, testlist)
     except Exception as ee:
         ex_type, ex, ex_tb = sys.exc_info()
         print('Exception {} {} (caught in pre_suite).'.
···
     """
     return [x["id"] for x in alltests]
 
-
 def check_case_id(alltests):
     """
     Check for duplicate test case IDs.
···
     If a test case has a blank ID field, generate a random hex ID for it
     and then write the test cases back to disk.
     """
-    import random
     for c in alltests:
         if (c["id"] == ""):
             while True:
···
 
     return answer
 
+def set_random(alltests):
+    for tidx in alltests:
+        tidx['random'] = random.getrandbits(32)
 
 def get_test_cases(args):
     """
···
         list_test_cases(alltests)
         exit(0)
 
+    set_random(alltests)
+
     exit_code = 0 # KSFT_PASS
     if len(alltests):
         req_plugins = pm.get_required_plugins(alltests)
···
     Start of execution; set up argument parser and get the arguments,
     and start operations.
     """
+    import resource
+
+    if sys.version_info.major < 3 or sys.version_info.minor < 8:
+        sys.exit("tdc requires at least python 3.8")
+
+    resource.setrlimit(resource.RLIMIT_NOFILE, (1048576, 1048576))
+
     parser = args_parse()
     parser = set_args(parser)
     pm = PluginMgr(parser)