def test_bulk_load(self, chaos_type, target_component):
        # start the monitor threads to check the milvus ops
        log.info("*********************Chaos Test Start**********************")
        log.info(connections.get_connection_addr('default'))
        release_name = self.instance_name
        cc.start_monitor_threads(self.health_checkers)
        chaos_config = cc.gen_experiment_config(
            f"{str(Path(__file__).absolute().parent)}/chaos_objects/{chaos_type}/chaos_{target_component}_{chaos_type}.yaml"
        )
        chaos_config['metadata']['name'] = f"test-bulk-load-{int(time.time())}"
        kind = chaos_config['kind']
        meta_name = chaos_config.get('metadata', None).get('name', None)
        update_key_value(chaos_config, "release", release_name)
        update_key_value(chaos_config, "app.kubernetes.io/instance",
                         release_name)
        self._chaos_config = chaos_config  # cache the chaos config for tear down
        log.info(f"chaos_config: {chaos_config}")
        # wait 20s
        sleep(constants.WAIT_PER_OP * 10)
        # assert statistic:all ops 100% succ
        log.info("******1st assert before chaos: ")
        assert_statistic(self.health_checkers)
        # apply chaos object
        chaos_res = CusResource(kind=chaos_config['kind'],
                                group=constants.CHAOS_GROUP,
                                version=constants.CHAOS_VERSION,
                                namespace=constants.CHAOS_NAMESPACE)
        chaos_res.create(chaos_config)
        log.info("chaos injected")
        sleep(constants.WAIT_PER_OP * 10)
        # reset counting
        cc.reset_counting(self.health_checkers)
        # wait 120s
        sleep(constants.CHAOS_DURATION)
        log.info(f'Alive threads: {threading.enumerate()}')
        # assert statistic
        log.info("******2nd assert after chaos injected: ")
        assert_statistic(self.health_checkers,
                         expectations={
                             Op.bulk_load: constants.FAIL,
                         })
        # delete chaos
        chaos_res.delete(meta_name)
        log.info("chaos deleted")
        sleep(2)
        # wait all pods ready
        log.info(
            f"wait for pods in namespace {constants.CHAOS_NAMESPACE} with label app.kubernetes.io/instance={release_name}"
        )
        wait_pods_ready(constants.CHAOS_NAMESPACE,
                        f"app.kubernetes.io/instance={release_name}")
        log.info(
            f"wait for pods in namespace {constants.CHAOS_NAMESPACE} with label release={release_name}"
        )
        wait_pods_ready(constants.CHAOS_NAMESPACE, f"release={release_name}")
        log.info("all pods are ready")
        # reconnect if needed
        sleep(constants.WAIT_PER_OP * 2)
        cc.reconnect(connections, alias='default')
        # recheck failed tasks in third assert
        self.health_checkers[Op.bulk_load].recheck_failed_task = True
        # reset counting again
        cc.reset_counting(self.health_checkers)
        # wait 50s (varies by feature)
        sleep(constants.WAIT_PER_OP * 10)
        # assert statistic: all ops success again
        log.info("******3rd assert after chaos deleted: ")
        assert_statistic(self.health_checkers)
        # assert all expectations
        assert_expectations()

        log.info(
            "*********************Chaos Test Completed**********************")
Example #2
0
    def test_chaos(self, chaos_yaml):
        # start the monitor threads to check the milvus ops
        log.info("*********************Chaos Test Start**********************")
        log.info(connections.get_connection_addr('default'))
        self.checker_threads = cc.start_monitor_threads(self.health_checkers)

        # parse chaos object
        chaos_config = cc.gen_experiment_config(chaos_yaml)
        self._chaos_config = chaos_config  # cache the chaos config for tear down
        log.info(chaos_config)

        # parse the test expectations in testcases.yaml
        if self.parser_testcase_config(chaos_yaml) is False:
            log.error("Fail to get the testcase info in testcases.yaml")
            assert False

        # wait 20s
        sleep(constants.WAIT_PER_OP * 2)

        # assert statistic:all ops 100% succ
        log.info("******1st assert before chaos: ")
        assert_statistic(self.health_checkers)

        # apply chaos object
        chaos_res = CusResource(kind=chaos_config['kind'],
                                group=constants.CHAOS_GROUP,
                                version=constants.CHAOS_VERSION,
                                namespace=constants.CHAOS_NAMESPACE)
        chaos_res.create(chaos_config)
        log.info("chaos injected")
        sleep(constants.WAIT_PER_OP * 2.1)
        # reset counting
        cc.reset_counting(self.health_checkers)

        # wait 40s
        sleep(constants.WAIT_PER_OP * 4)

        for k, t in self.checker_threads.items():
            log.info(f"10s later: Thread {k} is_alive(): {t.is_alive()}")

        # assert statistic
        log.info("******2nd assert after chaos injected: ")
        assert_statistic(self.health_checkers,
                         expectations={
                             Op.create: self.expect_create,
                             Op.insert: self.expect_insert,
                             Op.flush: self.expect_flush,
                             Op.index: self.expect_index,
                             Op.search: self.expect_search,
                             Op.query: self.expect_query
                         })

        # delete chaos
        meta_name = chaos_config.get('metadata', None).get('name', None)
        chaos_res.delete(meta_name)
        log.info("chaos deleted")
        for k, t in self.checker_threads.items():
            log.info(f"Thread {k} is_alive(): {t.is_alive()}")
        sleep(2)

        # reconnect if needed
        sleep(constants.WAIT_PER_OP * 2)
        cc.reconnect(connections, alias='default')

        # reset counting again
        cc.reset_counting(self.health_checkers)

        # wait 50s (varies by feature)
        sleep(constants.WAIT_PER_OP * 5)

        # assert statistic: all ops success again
        log.info("******3rd assert after chaos deleted: ")
        assert_statistic(self.health_checkers)

        # assert all expectations
        assert_expectations()

        log.info(
            "*********************Chaos Test Completed**********************")