commit bf20478: [Minor] Fix ClickHouse test after upgrade
Anton Yuzhaninov
citrin+github at citrin.ru
Fri Jun 21 17:35:05 UTC 2019
Author: Anton Yuzhaninov
Date: 2019-06-20 18:27:12 +0100
URL: https://github.com/rspamd/rspamd/commit/bf20478dd5e5dfd80cdcbe0bed7242b008fa518b
[Minor] Fix ClickHouse test after upgrade
Current ClickHouse version refuses to run from root if data directory is
not owned by root. Run it from user clickhouse as it supposed to be run.
Also cleanup ClickHouse config (some options prevented it to start,
others just unnecessary).
---
.../cases/210_clickhouse/001_migration.robot | 10 +-
test/functional/configs/clickhouse-config.xml | 288 +--------------------
test/functional/lib/rspamd.py | 9 +-
test/functional/lib/rspamd.robot | 2 +-
4 files changed, 22 insertions(+), 287 deletions(-)
diff --git a/test/functional/cases/210_clickhouse/001_migration.robot b/test/functional/cases/210_clickhouse/001_migration.robot
index d1b357415..9ee526c6c 100644
--- a/test/functional/cases/210_clickhouse/001_migration.robot
+++ b/test/functional/cases/210_clickhouse/001_migration.robot
@@ -63,10 +63,10 @@ Clickhouse Setup
${config} = Replace Variables ${template}
Create File ${TMPDIR}/clickhouse-config.xml ${config}
Copy File ${TESTDIR}/configs/clickhouse-users.xml ${TMPDIR}/users.xml
- Create Directory ${TMPDIR}/metadata
- Create Directory ${TMPDIR}/metadata/default
- Create Directory ${TMPDIR}/data/default
- ${result} = Run Process clickhouse-server --daemon --config-file\=${TMPDIR}/clickhouse-config.xml --pid-file\=${TMPDIR}/clickhouse.pid
+ Create Directory ${TMPDIR}/clickhouse
+ Set Directory Ownership ${TMPDIR}/clickhouse clickhouse clickhouse
+ ${result} = Run Process
+ ... su -s /bin/sh clickhouse -c clickhouse-server --daemon --config-file\=${TMPDIR}/clickhouse-config.xml --pid-file\=${TMPDIR}/clickhouse/clickhouse.pid
Run Keyword If ${result.rc} != 0 Log ${result.stderr}
Should Be Equal As Integers ${result.rc} 0
Wait Until Keyword Succeeds 5 sec 50 ms TCP Connect localhost ${CLICKHOUSE_PORT}
@@ -76,7 +76,7 @@ Clickhouse Setup
Clickhosue Teardown
# Sleep 30
- ${clickhouse_pid} = Get File ${TMPDIR}/clickhouse.pid
+ ${clickhouse_pid} = Get File ${TMPDIR}/clickhouse/clickhouse.pid
Shutdown Process With Children ${clickhouse_pid}
Simple Teardown
diff --git a/test/functional/configs/clickhouse-config.xml b/test/functional/configs/clickhouse-config.xml
index b210748ba..30f556f0c 100644
--- a/test/functional/configs/clickhouse-config.xml
+++ b/test/functional/configs/clickhouse-config.xml
@@ -2,53 +2,20 @@
<yandex>
<logger>
<!-- Possible levels: https://github.com/pocoproject/poco/blob/develop/Foundation/include/Poco/Logger.h#L105 -->
- <level>trace</level>
- <log>${TMPDIR}/clickhouse-server.log</log>
- <errorlog>${TMPDIR}/clickhouse-server.err.log</errorlog>
+ <level>debug</level>
+ <log>${TMPDIR}/clickhouse/clickhouse-server.log</log>
+ <errorlog>${TMPDIR}/clickhouse/clickhouse-server.err.log</errorlog>
<size>1000M</size>
<count>10</count>
<!-- <console>1</console> --> <!-- Default behavior is autodetection (log to console if not daemon mode and is tty) -->
</logger>
- <!--display_name>production</display_name--> <!-- It is the name that will be shown in the client -->
- <http_port>${CLICKHOUSE_PORT}</http_port>
- <tcp_port>19000</tcp_port>
-
- <!-- For HTTPS and SSL over native protocol. -->
- <!--
- <https_port>8443</https_port>
- <tcp_port_secure>9440</tcp_port_secure>
- -->
-
- <!-- Default root page on http[s] server. For example load UI from https://tabix.io/ when opening http://localhost:8123 -->
- <!--
- <http_server_default_response><![CDATA[<html ng-app="SMI2"><head><base href="http://ui.tabix.io/"></head><body><div ui-view="" class="content-ui"></div><script src="http://loader.tabix.io/master.js"></script></body></html>]]></http_server_default_response>
- -->
-
- <!-- Port for communication between replicas. Used for data exchange. -->
- <interserver_http_port>19009</interserver_http_port>
-
- <!-- Hostname that is used by other replicas to request this server.
- If not specified, than it is determined analoguous to 'hostname -f' command.
- This setting could be used to switch replication to another network interface.
- -->
- <!--
- <interserver_http_host>example.yandex.ru</interserver_http_host>
- -->
-
- <!-- Listen specified host. use :: (wildcard IPv6 address), if you want to accept connections both with IPv4 and IPv6 from everywhere. -->
- <!-- <listen_host>::</listen_host> -->
- <!-- Same for hosts with disabled ipv6: -->
- <!-- <listen_host>0.0.0.0</listen_host> -->
- <!-- Default values - try listen localhost on ipv4 and ipv6: -->
- <!--
- <listen_host>::1</listen_host>
<listen_host>127.0.0.1</listen_host>
- -->
- <!-- Don't exit if ipv6 or ipv4 unavailable, but listen_host with this protocol specified -->
- <!-- <listen_try>0</listen_try> -->
+ <http_port>${CLICKHOUSE_PORT}</http_port>
+
+ <!-- Path to configuration file with users, access rights, profiles of settings, quotas. -->
+ <users_config>${TMPDIR}/users.xml</users_config>
- <!-- Allow listen on same address:port -->
<!-- <listen_reuse_port>0</listen_reuse_port> -->
<!-- <listen_backlog>64</listen_backlog> -->
@@ -63,31 +30,14 @@
correct maximum value. -->
<max_open_files>256</max_open_files>
- <!-- Size of cache of uncompressed blocks of data, used in tables of MergeTree family.
- In bytes. Cache is single for server. Memory is allocated only on demand.
- Cache is used when 'use_uncompressed_cache' user setting turned on (off by default).
- Uncompressed cache is advantageous only for very short queries and in rare cases.
- -->
- <uncompressed_cache_size>8589934592</uncompressed_cache_size>
-
<!-- Approximate size of mark cache, used in tables of MergeTree family.
In bytes. Cache is single for server. Memory is allocated only on demand.
You should not lower this value.
-->
<mark_cache_size>5368709120</mark_cache_size>
-
<!-- Path to data directory, with trailing slash. -->
- <path>${TMPDIR}/</path>
-
- <!-- Path to temporary data for processing hard queries. -->
- <tmp_path>${TMPDIR}</tmp_path>
-
- <!-- Directory with user provided files that are accessible by 'file' table function. -->
- <user_files_path>${TMPDIR}</user_files_path>
-
- <!-- Path to configuration file with users, access rights, profiles of settings, quotas. -->
- <users_config>${TMPDIR}/users.xml</users_config>
+ <path>${TMPDIR}/clickhouse/</path>
<!-- Default profile of settings. -->
<default_profile>default</default_profile>
@@ -117,226 +67,4 @@
-->
<!-- <umask>022</umask> -->
- <!-- Configuration of clusters that could be used in Distributed tables.
- https://clickhouse.yandex/docs/en/table_engines/distributed/
- -->
-<!--
- <remote_servers incl="clickhouse_remote_servers" >
- <!– Test only shard config for testing distributed storage –>
- <test_shard_localhost>
- <shard>
- <replica>
- <host>localhost</host>
- <port>19000</port>
- </replica>
- </shard>
- </test_shard_localhost>
- <test_shard_localhost_secure>
- <shard>
- <replica>
- <host>localhost</host>
- <port>19440</port>
- <secure>1</secure>
- </replica>
- </shard>
- </test_shard_localhost_secure>
- </remote_servers>
--->
-
-
- <!-- If element has 'incl' attribute, then for it's value will be used corresponding substitution from another file.
- By default, path to file with substitutions is /etc/metrika.xml. It could be changed in config in 'include_from' element.
- Values for substitutions are specified in /yandex/name_of_substitution elements in that file.
- -->
-
- <!-- ZooKeeper is used to store metadata about replicas, when using Replicated tables.
- Optional. If you don't use replicated tables, you could omit that.
-
- See https://clickhouse.yandex/docs/en/table_engines/replication/
- -->
- <zookeeper incl="zookeeper-servers" optional="true" />
-
- <!-- Substitutions for parameters of replicated tables.
- Optional. If you don't use replicated tables, you could omit that.
-
- See https://clickhouse.yandex/docs/en/table_engines/replication/#creating-replicated-tables
- -->
- <macros incl="macros" optional="true" />
-
-
- <!-- Reloading interval for embedded dictionaries, in seconds. Default: 3600. -->
- <builtin_dictionaries_reload_interval>3600</builtin_dictionaries_reload_interval>
-
-
- <!-- Maximum session timeout, in seconds. Default: 3600. -->
- <max_session_timeout>3600</max_session_timeout>
-
- <!-- Default session timeout, in seconds. Default: 60. -->
- <default_session_timeout>60</default_session_timeout>
-
- <!-- Sending data to Graphite for monitoring. Several sections can be defined. -->
- <!--
- interval - send every X second
- root_path - prefix for keys
- hostname_in_path - append hostname to root_path (default = true)
- metrics - send data from table system.metrics
- events - send data from table system.events
- asynchronous_metrics - send data from table system.asynchronous_metrics
- -->
- <!--
- <graphite>
- <host>localhost</host>
- <port>42000</port>
- <timeout>0.1</timeout>
- <interval>60</interval>
- <root_path>one_min</root_path>
- <hostname_in_path>true</hostname_in_path>
-
- <metrics>true</metrics>
- <events>true</events>
- <asynchronous_metrics>true</asynchronous_metrics>
- </graphite>
- <graphite>
- <host>localhost</host>
- <port>42000</port>
- <timeout>0.1</timeout>
- <interval>1</interval>
- <root_path>one_sec</root_path>
-
- <metrics>true</metrics>
- <events>true</events>
- <asynchronous_metrics>false</asynchronous_metrics>
- </graphite>
- -->
-
-
- <!-- Query log. Used only for queries with setting log_queries = 1. -->
- <query_log>
- <!-- What table to insert data. If table is not exist, it will be created.
- When query log structure is changed after system update,
- then old table will be renamed and new table will be created automatically.
- -->
- <database>system</database>
- <table>query_log</table>
- <!--
- PARTITION BY expr https://clickhouse.yandex/docs/en/table_engines/custom_partitioning_key/
- Example:
- event_date
- toMonday(event_date)
- toYYYYMM(event_date)
- toStartOfHour(event_time)
- -->
- <partition_by>toYYYYMM(event_date)</partition_by>
- <!-- Interval of flushing data. -->
- <flush_interval_milliseconds>7500</flush_interval_milliseconds>
- </query_log>
-
-
- <!-- Uncomment if use part_log
- <part_log>
- <database>system</database>
- <table>part_log</table>
-
- <flush_interval_milliseconds>7500</flush_interval_milliseconds>
- </part_log>
- -->
-
-
- <!-- Parameters for embedded dictionaries, used in Yandex.Metrica.
- See https://clickhouse.yandex/docs/en/dicts/internal_dicts/
- -->
-
- <!-- Path to file with region hierarchy. -->
- <!-- <path_to_regions_hierarchy_file>/opt/geo/regions_hierarchy.txt</path_to_regions_hierarchy_file> -->
-
- <!-- Path to directory with files containing names of regions -->
- <!-- <path_to_regions_names_files>/opt/geo/</path_to_regions_names_files> -->
-
-
- <!-- Configuration of external dictionaries. See:
- https://clickhouse.yandex/docs/en/dicts/external_dicts/
- -->
- <dictionaries_config>*_dictionary.xml</dictionaries_config>
-
- <!-- Uncomment if you want data to be compressed 30-100% better.
- Don't do that if you just started using ClickHouse.
- -->
- <compression incl="clickhouse_compression">
- <!--
- <!- - Set of variants. Checked in order. Last matching case wins. If nothing matches, lz4 will be used. - ->
- <case>
-
- <!- - Conditions. All must be satisfied. Some conditions may be omitted. - ->
- <min_part_size>10000000000</min_part_size> <!- - Min part size in bytes. - ->
- <min_part_size_ratio>0.01</min_part_size_ratio> <!- - Min size of part relative to whole table size. - ->
-
- <!- - What compression method to use. - ->
- <method>zstd</method>
- </case>
- -->
- </compression>
-
- <!-- Allow to execute distributed DDL queries (CREATE, DROP, ALTER, RENAME) on cluster.
- Works only if ZooKeeper is enabled. Comment it if such functionality isn't required. -->
- <distributed_ddl>
- <!-- Path in ZooKeeper to queue with DDL queries -->
- <path>/clickhouse/task_queue/ddl</path>
-
- <!-- Settings from this profile will be used to execute DDL queries -->
- <!-- <profile>default</profile> -->
- </distributed_ddl>
-
- <!-- Settings to fine tune MergeTree tables. See documentation in source code, in MergeTreeSettings.h -->
- <!--
- <merge_tree>
- <max_suspicious_broken_parts>5</max_suspicious_broken_parts>
- </merge_tree>
- -->
-
- <!-- Protection from accidental DROP.
- If size of a MergeTree table is greater than max_table_size_to_drop (in bytes) than table could not be dropped with any DROP query.
- If you want do delete one table and don't want to restart clickhouse-server, you could create special file <clickhouse-path>/flags/force_drop_table and make DROP once.
- By default max_table_size_to_drop is 50GB, max_table_size_to_drop=0 allows to DROP any tables.
- Uncomment to disable protection.
- -->
- <!-- <max_table_size_to_drop>0</max_table_size_to_drop> -->
-
- <!-- Example of parameters for GraphiteMergeTree table engine -->
- <graphite_rollup_example>
- <pattern>
- <regexp>click_cost</regexp>
- <function>any</function>
- <retention>
- <age>0</age>
- <precision>3600</precision>
- </retention>
- <retention>
- <age>86400</age>
- <precision>60</precision>
- </retention>
- </pattern>
- <default>
- <function>max</function>
- <retention>
- <age>0</age>
- <precision>60</precision>
- </retention>
- <retention>
- <age>3600</age>
- <precision>300</precision>
- </retention>
- <retention>
- <age>86400</age>
- <precision>3600</precision>
- </retention>
- </default>
- </graphite_rollup_example>
-
- <!-- Directory in <clickhouse-path> containing schema files for various input formats.
- The directory will be created if it doesn't exist.
- -->
- <format_schema_path>/var/lib/clickhouse/format_schemas/</format_schema_path>
-
- <!-- Uncomment to disable ClickHouse internal DNS caching. -->
- <!-- <disable_internal_dns_cache>1</disable_internal_dns_cache> -->
</yandex>
diff --git a/test/functional/lib/rspamd.py b/test/functional/lib/rspamd.py
index ee76a9b45..9f7176ca9 100644
--- a/test/functional/lib/rspamd.py
+++ b/test/functional/lib/rspamd.py
@@ -102,7 +102,14 @@ def HTTP(method, host, port, path, data=None, headers={}):
return [s, t]
def make_temporary_directory():
- return tempfile.mkdtemp()
+ """Creates and returns a unique temporary directory
+
+ Example:
+ | ${TMPDIR} = | Make Temporary Directory |
+ """
+ dirname = tempfile.mkdtemp()
+ os.chmod(dirname, 0755)
+ return dirname
def make_temporary_file():
return tempfile.mktemp()
diff --git a/test/functional/lib/rspamd.robot b/test/functional/lib/rspamd.robot
index 7572e78a4..1e18a61a8 100644
--- a/test/functional/lib/rspamd.robot
+++ b/test/functional/lib/rspamd.robot
@@ -71,7 +71,7 @@ Generic Teardown
Run Keyword If '${CONTROLLER_ERRORS}' == 'True' Check Controller Errors
Shutdown Process With Children ${RSPAMD_PID}
Log does not contain segfault record
- Save Run Results ${TMPDIR} rspamd.log redis.log rspamd.conf clickhouse-server.log clickhouse-server.err.log clickhouse-config.xml
+ Save Run Results ${TMPDIR} rspamd.log redis.log rspamd.conf clickhouse-config.xml
Collect Lua Coverage
Cleanup Temporary Directory ${TMPDIR}
More information about the Commits
mailing list