gc-infra/iac/ansible/roles/hyperdx/files/config.xml

<?xml version="1.0"?>
<clickhouse>
    <logger>
        <level>debug</level>
        <console>true</console>
        <log remove="remove" />
        <errorlog remove="remove" />
    </logger>

    <listen_host>0.0.0.0</listen_host>
    <http_port>8123</http_port>
    <tcp_port>9000</tcp_port>
    <interserver_http_host>ch-server</interserver_http_host>
    <interserver_http_port>9009</interserver_http_port>

    <max_connections>4096</max_connections>
    <keep_alive_timeout>64</keep_alive_timeout>
    <max_concurrent_queries>100</max_concurrent_queries>
    <uncompressed_cache_size>8589934592</uncompressed_cache_size>
    <mark_cache_size>5368709120</mark_cache_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>users.xml</path>
        </users_xml>
    </user_directories>
    <!-- <users_config>users.xml</users_config> -->
    <default_profile>default</default_profile>
    <default_database>default</default_database>
    <timezone>UTC</timezone>
    <mlock_executable>false</mlock_executable>

    <!-- Prometheus exporter -->
    <prometheus>
        <endpoint>/metrics</endpoint>
        <port>9363</port>
        <metrics>true</metrics>
        <events>true</events>
        <asynchronous_metrics>true</asynchronous_metrics>
        <errors>true</errors>
    </prometheus>

    <!-- Query log. Used only for queries with setting log_queries = 1. -->
    <query_log>
        <database>system</database>
        <table>query_log</table>
        <flush_interval_milliseconds>7500</flush_interval_milliseconds>
    </query_log>

    <!-- Metric log contains rows with current values of ProfileEvents, CurrentMetrics collected
    with "collect_interval_milliseconds" interval. -->
    <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 contains values of metrics from
        system.asynchronous_metrics.
    -->
    <asynchronous_metric_log>
        <database>system</database>
        <table>asynchronous_metric_log</table>
        <!--
            Asynchronous metrics are updated once a minute, so there is
            no need to flush more often.
        -->
        <flush_interval_milliseconds>7000</flush_interval_milliseconds>
    </asynchronous_metric_log>

    <!--
        OpenTelemetry log contains OpenTelemetry trace spans.
    -->
    <opentelemetry_span_log>
        <!--
            The default table creation code is insufficient, this <engine> spec
            is a workaround. There is no 'event_time' for this log, but two times,
            start and finish. It is sorted by finish time, to avoid inserting
            data too far away in the past (probably we can sometimes insert a span
            that is seconds earlier than the last span in the table, due to a race
            between several spans inserted in parallel). This gives the spans a
            global order that we can use to e.g. retry insertion into some external
            system.
        -->
        <engine>
            engine MergeTree
            partition by toYYYYMM(finish_date)
            order by (finish_date, finish_time_us, trace_id)
        </engine>
        <database>system</database>
        <table>opentelemetry_span_log</table>
        <flush_interval_milliseconds>7500</flush_interval_milliseconds>
    </opentelemetry_span_log>


    <!-- Crash log. Stores stack traces for fatal errors.
         This table is normally empty. -->
    <crash_log>
        <database>system</database>
        <table>crash_log</table>

        <partition_by />
        <flush_interval_milliseconds>1000</flush_interval_milliseconds>
    </crash_log>

    <!-- Profiling on Processors level. -->
    <processors_profile_log>
        <database>system</database>
        <table>processors_profile_log</table>

        <partition_by>toYYYYMM(event_date)</partition_by>
        <flush_interval_milliseconds>7500</flush_interval_milliseconds>
    </processors_profile_log>

    <!-- Uncomment if use part log.
         Part log contains information about all actions with parts in MergeTree tables (creation, deletion,
    merges, downloads).-->
    <part_log>
        <database>system</database>
        <table>part_log</table>
        <partition_by>toYYYYMM(event_date)</partition_by>
        <flush_interval_milliseconds>7500</flush_interval_milliseconds>
    </part_log>

    <!-- Trace log. Stores stack traces collected by query profilers.
         See query_profiler_real_time_period_ns and query_profiler_cpu_time_period_ns settings. -->
    <trace_log>
        <database>system</database>
        <table>trace_log</table>

        <partition_by>toYYYYMM(event_date)</partition_by>
        <flush_interval_milliseconds>7500</flush_interval_milliseconds>
    </trace_log>

    <!-- Query thread log. Has information about all threads participated in query execution.
         Used only for queries with setting log_query_threads = 1. -->
    <query_thread_log>
        <database>system</database>
        <table>query_thread_log</table>
        <partition_by>toYYYYMM(event_date)</partition_by>
        <flush_interval_milliseconds>7500</flush_interval_milliseconds>
    </query_thread_log>

    <!-- Query views log. Has information about all dependent views associated with a query.
         Used only for queries with setting log_query_views = 1. -->
    <query_views_log>
        <database>system</database>
        <table>query_views_log</table>
        <partition_by>toYYYYMM(event_date)</partition_by>
        <flush_interval_milliseconds>7500</flush_interval_milliseconds>
    </query_views_log>

    <remote_servers>
        <hdx_cluster>
            <shard>
                <replica>
                    <host>ch-server</host>
                    <port>9000</port>
                </replica>
            </shard>
        </hdx_cluster>
    </remote_servers>

    <distributed_ddl>
        <path>/clickhouse/task_queue/ddl</path>
    </distributed_ddl>

    <format_schema_path>/var/lib/clickhouse/format_schemas/</format_schema_path>
</clickhouse>