You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@cassandra.apache.org by "Ekaterina Dimitrova (Jira)" <ji...@apache.org> on 2020/03/02 17:57:00 UTC

[jira] [Created] (CASSANDRA-15614) Flakey test - TestBootstrap.test_resumable_bootstrap

Ekaterina Dimitrova created CASSANDRA-15614:
-----------------------------------------------

             Summary: Flakey test - TestBootstrap.test_resumable_bootstrap 
                 Key: CASSANDRA-15614
                 URL: https://issues.apache.org/jira/browse/CASSANDRA-15614
             Project: Cassandra
          Issue Type: Bug
            Reporter: Ekaterina Dimitrova


Fails 2 out of 10 times on Mac/Java 8

================================================================================================================== FAILURES ==================================================================================================================

*___________________________________________________________________________________________________ TestBootstrap.test_resumable_bootstrap ___________________________________________________________________________________________________*

 

self = <bootstrap_test.TestBootstrap object at 0x10fd488d0>

 

    *@since('2.2')*

    *def test_resumable_bootstrap(self):*

        *"""*

            *Test resuming bootstrap after data streaming failure*

            *"""*

        *cluster = self.cluster*

        *cluster.populate(2)*

    **    

        *node1 = cluster.nodes['node1']*

        *# set up byteman*

        *node1.byteman_port = '8100'*

        *node1.import_config_files()*

    **    

        *cluster.start(wait_other_notice=True)*

        *# kill stream to node3 in the middle of streaming to let it fail*

        *if cluster.version() < '4.0':*

            *node1.byteman_submit([self.byteman_submit_path_pre_4_0])*

        *else:*

            *node1.byteman_submit([self.byteman_submit_path_4_0])*

        *node1.stress(['write', 'n=1K', 'no-warmup', 'cl=TWO', '-schema', 'replication(factor=2)', '-rate', 'threads=50'])*

        *cluster.flush()*

    **    

        *# start bootstrapping node3 and wait for streaming*

        *node3 = new_node(cluster)*

        *node3.start(wait_other_notice=False)*

    **    

        *# let streaming fail as we expect*

*>       node3.watch_log_for('Some data streaming failed')*

 

*bootstrap_test.py*:365: 

_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

 

self = <ccmlib.node.Node object at 0x10fdf1810>, exprs = 'Some data streaming failed', from_mark = None, timeout = 600, process = None, verbose = False, filename = 'system.log'

 

    *def watch_log_for(self, exprs, from_mark=None, timeout=600, process=None, verbose=False, filename='system.log'):*

        *"""*

            *Watch the log until one or more (regular) expression are found.*

            *This methods when all the expressions have been found or the method*

            *timeouts (a TimeoutError is then raised). On successful completion,*

            *a list of pair (line matched, match object) is returned.*

            *"""*

        *start = time.time()*

        *tofind = [exprs] if isinstance(exprs, string_types) else exprs*

        *tofind = [re.compile(e) for e in tofind]*

        *matchings = []*

        *reads = ""*

        *if len(tofind) == 0:*

            *return None*

    **    

        *log_file = os.path.join(self.get_path(), 'logs', filename)*

        *output_read = False*

        *while not os.path.exists(log_file):*

            *time.sleep(.5)*

            *if start + timeout < time.time():*

                *raise TimeoutError(time.strftime("%d %b %Y %H:%M:%S", time.gmtime()) + " [" + self.name + "] Timed out waiting for {} to be created.".format(log_file))*

            *if process and not output_read:*

                *process.poll()*

                *if process.returncode is not None:*

                    *self.print_process_output(self.name, process, verbose)*

                    *output_read = True*

                    *if process.returncode != 0:*

                        *raise RuntimeError()  # Shouldn't reuse RuntimeError but I'm lazy*

    **    

        *with open(log_file) as f:*

            *if from_mark:*

                *f.seek(from_mark)*

    **    

            *while True:*

                *# First, if we have a process to check, then check it.*

                *# Skip on Windows - stdout/stderr is cassandra.bat*

                *if not common.is_win() and not output_read:*

                    *if process:*

                        *process.poll()*

                        *if process.returncode is not None:*

                            *self.print_process_output(self.name, process, verbose)*

                            *output_read = True*

                            *if process.returncode != 0:*

                                *raise RuntimeError()  # Shouldn't reuse RuntimeError but I'm lazy*

    **    

                *line = f.readline()*

                *if line:*

                    *reads = reads + line*

                    *for e in tofind:*

                        *m = e.search(line)*

                        *if m:*

                            *matchings.append((line, m))*

                            *tofind.remove(e)*

                            *if len(tofind) == 0:*

                                *return matchings[0] if isinstance(exprs, string_types) else matchings*

                *else:*

                    *# yep, it's ugly*

                    *time.sleep(1)*

                    *if start + timeout < time.time():*

*>                       raise TimeoutError(time.strftime("%d %b %Y %H:%M:%S", time.gmtime()) + " [" + self.name + "] Missing: " + str([e.pattern for e in tofind]) + ":\n" + reads[:50] + ".....\nSee {} for remainder".format(filename))*

*E                       ccmlib.node.TimeoutError: 02 Mar 2020 17:16:34 [node3] Missing: ['Some data streaming failed']:*

*E                       INFO  [main] 2020-03-02 12:06:34,963 YamlConfigura.....*

*E                       See system.log for remainder*

 

*../../dtest-new2/src/ccm/ccmlib/node.py*:536: TimeoutError

----------------------------------------------------------------------------------------------------------- Captured stdout setup ------------------------------------------------------------------------------------------------------------

11:55:37,343 ccm DEBUG Log-watching thread starting.

------------------------------------------------------------------------------------------------------------- Captured log setup -------------------------------------------------------------------------------------------------------------

11:55:37,239 conftest INFO Starting execution of test_resumable_bootstrap at 2020-03-02 11:55:37.239467

11:55:37,240 dtest_setup INFO cluster ccm directory: /var/folders/ql/nvcz74bd67d3vhw7227mpjm40000gp/T/dtest-fzxwwt9c

------------------------------------------------------------------------------------------------------------ Captured stdout call ------------------------------------------------------------------------------------------------------------

install rule inject stream failure

 

---------------------------------------------------------------------------------------------------------- Captured stdout teardown ----------------------------------------------------------------------------------------------------------

12:06:04,870 ccm DEBUG Log-watching thread exiting.

----------------------------------------------------------------------------------------------------------- Captured stdout setup ------------------------------------------------------------------------------------------------------------

12:06:06,20 ccm DEBUG Log-watching thread starting.

------------------------------------------------------------------------------------------------------------- Captured log setup -------------------------------------------------------------------------------------------------------------

12:06:05,887 conftest INFO Starting execution of test_resumable_bootstrap at 2020-03-02 12:06:05.887592

12:06:05,888 dtest_setup INFO cluster ccm directory: /var/folders/ql/nvcz74bd67d3vhw7227mpjm40000gp/T/dtest-yntcltkx

------------------------------------------------------------------------------------------------------------ Captured stdout call ------------------------------------------------------------------------------------------------------------

install rule inject stream failure

 

---------------------------------------------------------------------------------------------------------- Captured stdout teardown ----------------------------------------------------------------------------------------------------------

12:06:04,870 ccm DEBUG Log-watching thread exiting.

---------------------------------------------------------------------------------------------------------- Captured stdout teardown ----------------------------------------------------------------------------------------------------------

12:06:04,870 ccm DEBUG Log-watching thread exiting.

---------------------------------------------------------------------------------------------------------- Captured stdout teardown ----------------------------------------------------------------------------------------------------------

12:16:34,818 ccm DEBUG Log-watching thread exiting.

===Flaky Test Report===

 

test_resumable_bootstrap failed (1 runs remaining out of 2).

<class 'ccmlib.node.TimeoutError'>

02 Mar 2020 17:06:04 [node3] Missing: ['Some data streaming failed']:

INFO  [main] 2020-03-02 11:56:05,081 YamlConfigura.....

See system.log for remainder

[<TracebackEntry /Users/ekaterina.dimitri/IdeaProjects/cassandra-dtest-d/bootstrap_test.py:365>, <TracebackEntry /Users/ekaterina.dimitri/dtest-new2/src/ccm/ccmlib/node.py:536>]

test_resumable_bootstrap failed; it passed 0 out of the required 1 times.

<class 'ccmlib.node.TimeoutError'>

02 Mar 2020 17:16:34 [node3] Missing: ['Some data streaming failed']:

INFO  [main] 2020-03-02 12:06:34,963 YamlConfigura.....

See system.log for remainder

[<TracebackEntry /Users/ekaterina.dimitri/IdeaProjects/cassandra-dtest-d/bootstrap_test.py:365>, <TracebackEntry /Users/ekaterina.dimitri/dtest-new2/src/ccm/ccmlib/node.py:536>]

 

===End Flaky Test Report===

*======================================================================================================== 1 failed in 1258.32 seconds =========================================================================================================*



--
This message was sent by Atlassian Jira
(v8.3.4#803005)

---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@cassandra.apache.org
For additional commands, e-mail: commits-help@cassandra.apache.org