greptimedb/config/metasrv.example.toml

## The working home directory.
data_home = "./greptimedb_data"

## Store server address(es). The format depends on the selected backend.
##
## For etcd: a list of "host:port" endpoints.
## e.g. ["192.168.1.1:2379", "192.168.1.2:2379"]
##
## For PostgreSQL: a connection string in libpq format or URI.
## e.g.
## - "host=localhost port=5432 user=postgres password=<PASSWORD> dbname=postgres"
## - "postgresql://user:password@localhost:5432/mydb?connect_timeout=10"
## The detail see: https://docs.rs/tokio-postgres/latest/tokio_postgres/config/struct.Config.html
##
## For mysql store, the format is a MySQL connection URL.
## e.g. "mysql://user:password@localhost:3306/greptime_meta?ssl-mode=VERIFY_CA&ssl-ca=/path/to/ca.pem"
store_addrs = ["127.0.0.1:2379"]

## If it's not empty, the metasrv will store all data with this key prefix.
store_key_prefix = ""

## The datastore for meta server.
## Available values:
## - `etcd_store` (default value)
## - `memory_store`
## - `postgres_store`
## - `mysql_store`
backend = "etcd_store"

## Table name in RDS to store metadata. Effect when using a RDS kvbackend.
## **Only used when backend is `postgres_store`.**
meta_table_name = "greptime_metakv"

## Optional PostgreSQL schema for metadata table and election table name qualification.
## When PostgreSQL public schema is not writable (e.g., PostgreSQL 15+ with restricted public),
## set this to a writable schema. GreptimeDB will use `meta_schema_name`.`meta_table_name`.
## GreptimeDB will NOT create the schema automatically; please ensure it exists or the user has permission.
## **Only used when backend is `postgres_store`.**

meta_schema_name = "greptime_schema"

## Advisory lock id in PostgreSQL for election. Effect when using PostgreSQL as kvbackend
## Only used when backend is `postgres_store`.
meta_election_lock_id = 1

## Datanode selector type.
## - `round_robin` (default value)
## - `lease_based`
## - `load_based`
## For details, please see "https://docs.greptime.com/developer-guide/metasrv/selector".
selector = "round_robin"

## Store data in memory.
use_memory_store = false

## Whether to enable region failover.
## This feature is only available on GreptimeDB running on cluster mode and
## - Using Remote WAL
## - Using shared storage (e.g., s3).
enable_region_failover = false

## The delay before starting region failure detection.
## This delay helps prevent Metasrv from triggering unnecessary region failovers before all Datanodes are fully started.
## Especially useful when the cluster is not deployed with GreptimeDB Operator and maintenance mode is not enabled.
region_failure_detector_initialization_delay = '10m'

## Whether to allow region failover on local WAL.
## **This option is not recommended to be set to true, because it may lead to data loss during failover.**
allow_region_failover_on_local_wal = false

## Max allowed idle time before removing node info from metasrv memory.
node_max_idle_time = "24hours"

## Base heartbeat interval for calculating distributed time constants.
## The frontend heartbeat interval is 6 times of the base heartbeat interval.
## The flownode/datanode heartbeat interval is 1 times of the base heartbeat interval.
## e.g., If the base heartbeat interval is 3s, the frontend heartbeat interval is 18s, the flownode/datanode heartbeat interval is 3s.
## If you change this value, you need to change the heartbeat interval of the flownode/frontend/datanode accordingly.
#+ heartbeat_interval = "3s"

## Whether to enable greptimedb telemetry. Enabled by default.
#+ enable_telemetry = true

## The runtime options.
#+ [runtime]
## The number of threads to execute the runtime for global read operations.
#+ global_rt_size = 8
## The number of threads to execute the runtime for global write operations.
#+ compact_rt_size = 4

## TLS configuration for kv store backend (applicable for etcd, PostgreSQL, and MySQL backends)
## When using etcd, PostgreSQL, or MySQL as metadata store, you can configure TLS here
##
## Note: if TLS is configured in both this section and the `store_addrs` connection string, the
## settings here will override the TLS settings in `store_addrs`.
[backend_tls]
## TLS mode, refer to https://www.postgresql.org/docs/current/libpq-ssl.html
## - "disable" - No TLS
## - "prefer" (default) - Try TLS, fallback to plain
## - "require" - Require TLS
## - "verify_ca" - Require TLS and verify CA
## - "verify_full" - Require TLS and verify hostname
mode = "prefer"

## Path to client certificate file (for client authentication)
## Like "/path/to/client.crt"
cert_path = ""

## Path to client private key file (for client authentication)
## Like "/path/to/client.key"
key_path = ""

## Path to CA certificate file (for server certificate verification)
## Required when using custom CAs or self-signed certificates
## Leave empty to use system root certificates only
## Like "/path/to/ca.crt"
ca_cert_path = ""

## The backend client options.
## Currently, only applicable when using etcd as the metadata store.
#+ [backend_client]
## The keep alive timeout for backend client.
#+ keep_alive_timeout = "3s"
## The keep alive interval for backend client.
#+ keep_alive_interval = "10s"
## The connect timeout for backend client.
#+ connect_timeout = "3s"

## The gRPC server options.
[grpc]
## The address to bind the gRPC server.
bind_addr = "127.0.0.1:3002"
## The communication server address for the frontend and datanode to connect to metasrv.
## If left empty or unset, the server will automatically use the IP address of the first network interface
## on the host, with the same port number as the one specified in `bind_addr`.
server_addr = "127.0.0.1:3002"
## The number of server worker threads.
runtime_size = 8
## The maximum receive message size for gRPC server.
max_recv_message_size = "512MB"
## The maximum send message size for gRPC server.
max_send_message_size = "512MB"
## The server side HTTP/2 keep-alive interval
#+ http2_keep_alive_interval = "10s"
## The server side HTTP/2 keep-alive timeout.
#+ http2_keep_alive_timeout = "3s"

## The HTTP server options.
[http]
## The address to bind the HTTP server.
addr = "127.0.0.1:4000"
## HTTP request timeout. Set to 0 to disable timeout.
timeout = "0s"
## HTTP request body limit.
## The following units are supported: `B`, `KB`, `KiB`, `MB`, `MiB`, `GB`, `GiB`, `TB`, `TiB`, `PB`, `PiB`.
## Set to 0 to disable limit.
body_limit = "64MB"

## Procedure storage options.
[procedure]

## Procedure max retry time.
max_retry_times = 12

## Initial retry delay of procedures, increases exponentially
retry_delay = "500ms"

## Auto split large value
## GreptimeDB procedure uses etcd as the default metadata storage backend.
## The etcd the maximum size of any request is 1.5 MiB
## 1500KiB = 1536KiB (1.5MiB) - 36KiB (reserved size of key)
## Comments out the `max_metadata_value_size`, for don't split large value (no limit).
max_metadata_value_size = "1500KiB"

## Max running procedures.
## The maximum number of procedures that can be running at the same time.
## If the number of running procedures exceeds this limit, the procedure will be rejected.
max_running_procedures = 128

# Failure detectors options.
# GreptimeDB uses the Phi Accrual Failure Detector algorithm to detect datanode failures.
[failure_detector]
## Maximum acceptable φ before the peer is treated as failed.
## Lower values react faster but yield more false positives.
threshold = 8.0
## The minimum standard deviation of the heartbeat intervals.
## So tiny variations don’t make φ explode. Prevents hypersensitivity when heartbeat intervals barely vary.
min_std_deviation = "100ms"
## The acceptable pause duration between heartbeats.
## Additional extra grace period to the learned mean interval before φ rises, absorbing temporary network hiccups or GC pauses.
acceptable_heartbeat_pause = "10000ms"

## Datanode options.
[datanode]

## Datanode client options.
[datanode.client]

## Operation timeout.
timeout = "10s"

## Connect server timeout.
connect_timeout = "10s"

## `TCP_NODELAY` option for accepted connections.
tcp_nodelay = true

[wal]
# Available wal providers:
# - `raft_engine` (default): there're none raft-engine wal config since metasrv only involves in remote wal currently.
# - `kafka`: metasrv **have to be** configured with kafka wal config when using kafka wal provider in datanode.
provider = "raft_engine"

## The broker endpoints of the Kafka cluster.
##
## **It's only used when the provider is `kafka`**.
broker_endpoints = ["127.0.0.1:9092"]

## Automatically create topics for WAL.
## Set to `true` to automatically create topics for WAL.
## Otherwise, use topics named `topic_name_prefix_[0..num_topics)`
## **It's only used when the provider is `kafka`**.
auto_create_topics = true

## Interval of automatically WAL pruning.
## Set to `0s` to disable automatically WAL pruning which delete unused remote WAL entries periodically.
## **It's only used when the provider is `kafka`**.
auto_prune_interval = "30m"


## Estimated size threshold to trigger a flush when using Kafka remote WAL.
## Since multiple regions may share a Kafka topic, the estimated size is calculated as:
##   (latest_entry_id - flushed_entry_id) * avg_record_size
## MetaSrv triggers a flush for a region when this estimated size exceeds `flush_trigger_size`.
## - `latest_entry_id`: The latest entry ID in the topic.
## - `flushed_entry_id`: The last flushed entry ID for the region.
## Set to "0" to let the system decide the flush trigger size.
## **It's only used when the provider is `kafka`**.
flush_trigger_size = "512MB"

## Estimated size threshold to trigger a checkpoint when using Kafka remote WAL.
## The estimated size is calculated as:
##   (latest_entry_id - last_checkpoint_entry_id) * avg_record_size
## MetaSrv triggers a checkpoint for a region when this estimated size exceeds `checkpoint_trigger_size`.
## Set to "0" to let the system decide the checkpoint trigger size.
## **It's only used when the provider is `kafka`**.
checkpoint_trigger_size = "128MB"

## Concurrent task limit for automatically WAL pruning.
## **It's only used when the provider is `kafka`**.
auto_prune_parallelism = 10

## Number of topics used for remote WAL.
## **It's only used when the provider is `kafka`**.
num_topics = 64

## Topic selector type.
## Available selector types:
## - `round_robin` (default)
## **It's only used when the provider is `kafka`**.
selector_type = "round_robin"


## A Kafka topic is constructed by concatenating `topic_name_prefix` and `topic_id`.
## Only accepts strings that match the following regular expression pattern:
## [a-zA-Z_:-][a-zA-Z0-9_:\-\.@#]*
## i.g., greptimedb_wal_topic_0, greptimedb_wal_topic_1.
## **It's only used when the provider is `kafka`**.
topic_name_prefix = "greptimedb_wal_topic"

## Expected number of replicas of each partition.
## **It's only used when the provider is `kafka`**.
replication_factor = 1

## The timeout for creating a Kafka topic.
## **It's only used when the provider is `kafka`**.
create_topic_timeout = "30s"

# The Kafka SASL configuration.
# **It's only used when the provider is `kafka`**.
# Available SASL mechanisms:
# - `PLAIN`
# - `SCRAM-SHA-256`
# - `SCRAM-SHA-512`
# [wal.sasl]
# type = "SCRAM-SHA-512"
# username = "user_kafka"
# password = "secret"

# The Kafka TLS configuration.
# **It's only used when the provider is `kafka`**.
# [wal.tls]
# server_ca_cert_path = "/path/to/server_cert"
# client_cert_path = "/path/to/client_cert"
# client_key_path = "/path/to/key"

## Configuration options for the event recorder.
[event_recorder]
## TTL for the events table that will be used to store the events. Default is `90d`.
ttl = "90d"

## Configuration options for the stats persistence.
[stats_persistence]
## TTL for the stats table that will be used to store the stats.
## Set to `0s` to disable stats persistence.
## Default is `0s`.
## If you want to enable stats persistence, set the TTL to a value greater than 0.
## It is recommended to set a small value, e.g., `3h`.
ttl = "0s"
## The interval to persist the stats. Default is `10m`.
## The minimum value is `10m`, if the value is less than `10m`, it will be overridden to `10m`.
interval = "10m"

## The logging options.
[logging]
## The directory to store the log files. If set to empty, logs will not be written to files.
dir = "./greptimedb_data/logs"

## The log level. Can be `info`/`debug`/`warn`/`error`.
## @toml2docs:none-default
level = "info"

## Enable OTLP tracing.
enable_otlp_tracing = false

## The OTLP tracing endpoint.
otlp_endpoint = "http://localhost:4318/v1/traces"

## Whether to append logs to stdout.
append_stdout = true

## The log format. Can be `text`/`json`.
log_format = "text"

## The maximum amount of log files.
max_log_files = 720

## The OTLP tracing export protocol. Can be `grpc`/`http`.
otlp_export_protocol = "http"

## Additional OTLP headers, only valid when using OTLP http
[logging.otlp_headers]
## @toml2docs:none-default
#Authorization = "Bearer my-token"
## @toml2docs:none-default
#Database = "My database"


## The percentage of tracing will be sampled and exported.
## Valid range `[0, 1]`, 1 means all traces are sampled, 0 means all traces are not sampled, the default value is 1.
## ratio > 1 are treated as 1. Fractions < 0 are treated as 0
[logging.tracing_sample_ratio]
default_ratio = 1.0

## The tracing options. Only effect when compiled with `tokio-console` feature.
#+ [tracing]
## The tokio console address.
## @toml2docs:none-default
#+ tokio_console_addr = "127.0.0.1"

## The memory options.
[memory]
## Whether to enable heap profiling activation during startup.
## When enabled, heap profiling will be activated if the `MALLOC_CONF` environment variable
## is set to "prof:true,prof_active:false". The official image adds this env variable.
## Default is true.
enable_heap_profiling = true