greptimedb/config/metasrv.example.toml

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

## Store server address default to etcd store.
## For postgres store, the format is:
## "password=password dbname=postgres user=postgres host=localhost port=5432"
## For etcd store, the format is:
## "127.0.0.1:2379"
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"

## 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"

## 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

## 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 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.
[failure_detector]

## The threshold value used by the failure detector to determine failure conditions.
threshold = 8.0

## The minimum standard deviation of the heartbeat intervals, used to calculate acceptable variations.
min_std_deviation = "100ms"

## The acceptable pause duration between heartbeats, used to determine if a heartbeat interval is acceptable.
acceptable_heartbeat_pause = "10000ms"

## The initial estimate of the heartbeat interval used by the failure detector.
first_heartbeat_estimate = "1000ms"

## 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"

# Kafka wal config.

## The broker endpoints of the Kafka cluster.
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)`
auto_create_topics = true

## Interval of automatically WAL pruning.
## Set to `0s` to disable automatically WAL pruning which delete unused remote WAL entries periodically.
auto_prune_interval = "0s"

## The threshold to trigger a flush operation of a region in automatically WAL pruning.
## Metasrv will send a flush request to flush the region when:
## `trigger_flush_threshold` + `prunable_entry_id` < `max_prunable_entry_id`
## where:
## - `prunable_entry_id` is the maximum entry id that can be pruned of the region.
## - `max_prunable_entry_id` is the maximum prunable entry id among all regions in the same topic.
## Set to `0` to disable the flush operation.
trigger_flush_threshold = 0

## Concurrent task limit for automatically WAL pruning.
auto_prune_parallelism = 10

## Number of topics.
num_topics = 64

## Topic selector type.
## Available selector types:
## - `round_robin` (default)
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.
topic_name_prefix = "greptimedb_wal_topic"

## Expected number of replicas of each partition.
replication_factor = 1

## Above which a topic creation operation will be cancelled.
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"

## 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"

## 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"

## 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 metasrv can export its metrics and send to Prometheus compatible service (e.g. `greptimedb` itself) from remote-write API.
## This is only used for `greptimedb` to export its own metrics internally. It's different from prometheus scrape.
[export_metrics]
## whether enable export metrics.
enable = false
## The interval of export metrics.
write_interval = "30s"

[export_metrics.remote_write]
## The prometheus remote write endpoint that the metrics send to. The url example can be: `http://127.0.0.1:4000/v1/prometheus/write?db=greptime_metrics`.
url = ""

## HTTP headers of Prometheus remote-write carry.
headers = { }

## 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"