From 37e36418a1390ad25450e8cac369d50cd127b902 Mon Sep 17 00:00:00 2001
From: Luke Granger-Brown <hg@lukegb.com>
Date: Sat, 1 Jan 2022 16:31:05 +0000
Subject: [PATCH] bvm-logger: add custom clickhouse config

Just make it less spammy into the journal, sheesh.
---
 ops/nixos/bvm-logger/clickhouse-config.xml | 185 +++++++++++++++++++++
 ops/nixos/bvm-logger/default.nix           |   8 +
 2 files changed, 193 insertions(+)
 create mode 100644 ops/nixos/bvm-logger/clickhouse-config.xml

diff --git a/ops/nixos/bvm-logger/clickhouse-config.xml b/ops/nixos/bvm-logger/clickhouse-config.xml
new file mode 100644
index 0000000000..927b31f867
--- /dev/null
+++ b/ops/nixos/bvm-logger/clickhouse-config.xml
@@ -0,0 +1,185 @@
+<?xml version="1.0"?>
+<yandex>
+    <logger>
+        <!-- Possible levels [1]:
+
+          - none (turns off logging)
+          - fatal
+          - critical
+          - error
+          - warning
+          - notice
+          - information
+          - debug
+          - trace
+
+            [1]: https://github.com/pocoproject/poco/blob/poco-1.9.4-release/Foundation/include/Poco/Logger.h#L105-L114
+        -->
+        <level>critical</level>
+        <console>1</console>
+        <size>1000M</size>
+        <count>10</count>
+    </logger>
+
+    <http_port>8123</http_port>
+    <tcp_port>9000</tcp_port>
+    <interserver_http_port>9009</interserver_http_port>
+
+    <listen_host>::</listen_host>
+
+    <max_connections>4096</max_connections>
+
+    <keep_alive_timeout>3</keep_alive_timeout>
+
+    <max_concurrent_queries>100</max_concurrent_queries>
+    <max_server_memory_usage>0</max_server_memory_usage>
+    <max_thread_pool_size>10000</max_thread_pool_size>
+    <max_server_memory_usage_to_ram_ratio>0.9</max_server_memory_usage_to_ram_ratio>
+    <total_memory_profiler_step>4194304</total_memory_profiler_step>
+    <total_memory_tracker_sample_probability>0</total_memory_tracker_sample_probability>
+    <uncompressed_cache_size>8589934592</uncompressed_cache_size>
+    <mark_cache_size>5368709120</mark_cache_size>
+    <mmap_cache_size>1000</mmap_cache_size>
+    <compiled_expression_cache_size>134217728</compiled_expression_cache_size>
+    <compiled_expression_cache_elements_size>10000</compiled_expression_cache_elements_size>
+    <path>/var/lib/clickhouse/</path>
+    <tmp_path>/var/lib/clickhouse/tmp/</tmp_path>
+    <user_files_path>/var/lib/clickhouse/user_files/</user_files_path>
+    <user_directories>
+        <users_xml>
+            <!-- Path to configuration file with predefined users. -->
+            <path>users.xml</path>
+        </users_xml>
+        <local_directory>
+            <!-- Path to folder where users created by SQL commands are stored. -->
+            <path>/var/lib/clickhouse/access/</path>
+        </local_directory>
+    </user_directories>
+    <default_profile>default</default_profile>
+    <custom_settings_prefixes></custom_settings_prefixes>
+    <default_database>default</default_database>
+    <mlock_executable>true</mlock_executable>
+    <remap_executable>false</remap_executable>
+    <builtin_dictionaries_reload_interval>3600</builtin_dictionaries_reload_interval>
+    <max_session_timeout>3600</max_session_timeout>
+    <default_session_timeout>60</default_session_timeout>
+
+    <!-- Serve endpoint for Prometheus monitoring. -->
+    <!--
+        endpoint - mertics path (relative to root, statring with "/")
+        port - port to setup server. If not defined or 0 than http_port used
+        metrics - send data from table system.metrics
+        events - send data from table system.events
+        asynchronous_metrics - send data from table system.asynchronous_metrics
+        status_info - send data from different component from CH, ex: Dictionaries status
+    -->
+    <prometheus>
+        <endpoint>/metrics</endpoint>
+        <port>0</port>
+
+        <metrics>true</metrics>
+        <events>true</events>
+        <asynchronous_metrics>true</asynchronous_metrics>
+        <status_info>true</status_info>
+    </prometheus>
+
+    <query_log>
+        <database>system</database>
+        <table>query_log</table>
+        <partition_by>toYYYYMM(event_date)</partition_by>
+        <ttl>event_date + INTERVAL 30 DAY DELETE</ttl>
+        <flush_interval_milliseconds>7500</flush_interval_milliseconds>
+    </query_log>
+    <text_log>
+        <database>system</database>
+        <table>text_log</table>
+        <flush_interval_milliseconds>7500</flush_interval_milliseconds>
+        <ttl>event_date + INTERVAL 30 DAY DELETE</ttl>
+        <level>trace</level>
+    </text_log>
+    <trace_log>
+        <database>system</database>
+        <table>trace_log</table>
+
+        <partition_by>toYYYYMM(event_date)</partition_by>
+        <ttl>event_date + INTERVAL 30 DAY DELETE</ttl>
+        <flush_interval_milliseconds>7500</flush_interval_milliseconds>
+    </trace_log>
+    <query_thread_log>
+        <database>system</database>
+        <table>query_thread_log</table>
+        <partition_by>toYYYYMM(event_date)</partition_by>
+        <ttl>event_date + INTERVAL 30 DAY DELETE</ttl>
+        <flush_interval_milliseconds>7500</flush_interval_milliseconds>
+    </query_thread_log>
+    <metric_log>
+        <database>system</database>
+        <table>metric_log</table>
+        <flush_interval_milliseconds>7500</flush_interval_milliseconds>
+        <collect_interval_milliseconds>1000</collect_interval_milliseconds>
+    </metric_log>
+    <asynchronous_metric_log>
+        <database>system</database>
+        <table>asynchronous_metric_log</table>
+        <flush_interval_milliseconds>7000</flush_interval_milliseconds>
+    </asynchronous_metric_log>
+
+    <crash_log>
+        <database>system</database>
+        <table>crash_log</table>
+
+        <partition_by />
+        <flush_interval_milliseconds>1000</flush_interval_milliseconds>
+    </crash_log>
+
+    <!-- Custom TLD lists.
+         Format: <name>/path/to/file</name>
+
+         Changes will not be applied w/o server restart.
+         Path to the list is under top_level_domains_path (see above).
+    -->
+    <top_level_domains_lists>
+        <!--
+        <public_suffix_list>/path/to/public_suffix_list.dat</public_suffix_list>
+        -->
+    </top_level_domains_lists>
+
+    <!-- Configuration of external dictionaries. See:
+         https://clickhouse.tech/docs/en/sql-reference/dictionaries/external-dictionaries/external-dicts
+    -->
+    <dictionaries_config>*_dictionary.xml</dictionaries_config>
+
+    <!-- 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>
+
+    <!-- Default query masking rules, matching lines would be replaced with something else in the logs
+        (both text logs and system.query_log).
+        name - name for the rule (optional)
+        regexp - RE2 compatible regular expression (mandatory)
+        replace - substitution string for sensitive data (optional, by default - six asterisks)
+    -->
+    <query_masking_rules>
+        <rule>
+            <name>hide encrypt/decrypt arguments</name>
+            <regexp>((?:aes_)?(?:encrypt|decrypt)(?:_mysql)?)\s*\(\s*(?:'(?:\\'|.)+'|.*?)\s*\)</regexp>
+            <!-- or more secure, but also more invasive:
+                (aes_\w+)\s*\(.*\)
+            -->
+            <replace>\1(???)</replace>
+        </rule>
+    </query_masking_rules>
+
+    <send_crash_reports>
+        <!-- Changing <enabled> to true allows sending crash reports to -->
+        <!-- the ClickHouse core developers team via Sentry https://sentry.io -->
+        <!-- Doing so at least in pre-production environments is highly appreciated -->
+        <enabled>false</enabled>
+        <!-- Change <anonymize> to true if you don't feel comfortable attaching the server hostname to the crash report -->
+        <anonymize>false</anonymize>
+        <!-- Default endpoint should be changed to different Sentry DSN only if you have -->
+        <!-- some in-house engineers or hired consultants who're going to debug ClickHouse issues for you -->
+        <endpoint>https://6f33034cfe684dd7a3ab9875e57b1c8d@o388870.ingest.sentry.io/5226277</endpoint>
+    </send_crash_reports>
+</yandex>
diff --git a/ops/nixos/bvm-logger/default.nix b/ops/nixos/bvm-logger/default.nix
index 5d4f9cf193..7ce449b7be 100644
--- a/ops/nixos/bvm-logger/default.nix
+++ b/ops/nixos/bvm-logger/default.nix
@@ -29,6 +29,14 @@ in {
   my.ip.tailscale = "100.68.134.82";
 
   services.clickhouse.enable = true;
+  services.clickhouse.package = pkgs.symlinkJoin {
+    name = "clickhouse-overridden";
+    paths = [ pkgs.clickhouse ];
+    postBuild = ''
+      rm $out/etc/clickhouse-server/config.xml
+      cp ${./clickhouse-config.xml} $out/etc/clickhouse-server/config.xml
+    '';
+  };
   time.timeZone = "Etc/UTC";
 
   systemd.services.journal2clickhouse = {