feat: adjust WAL purge default configurations

config/config.md

@@ -13,11 +13,11 @@
 | Key | Type | Default | Descriptions |
 | --- | -----| ------- | ----------- |
 | `mode` | String | `standalone` | The running mode of the datanode. It can be `standalone` or `distributed`. |
-| `enable_telemetry` | Bool | `true` | Enable telemetry to collect anonymous usage data. |
 | `default_timezone` | String | Unset | The default timezone of the server. |
 | `init_regions_in_background` | Bool | `false` | Initialize all regions in the background during the startup.<br/>By default, it provides services after all regions have been initialized. |
 | `init_regions_parallelism` | Integer | `16` | Parallelism of initializing regions. |
 | `max_concurrent_queries` | Integer | `0` | The maximum current queries allowed to be executed. Zero means unlimited. |
+| `enable_telemetry` | Bool | `true` | Enable telemetry to collect anonymous usage data. Enabled by default. |
 | `runtime` | -- | -- | The runtime options. |
 | `runtime.global_rt_size` | Integer | `8` | The number of threads to execute the runtime for global read operations. |
 | `runtime.compact_rt_size` | Integer | `4` | The number of threads to execute the runtime for global write operations. |
@@ -61,9 +61,9 @@
 | `wal` | -- | -- | The WAL options. |
 | `wal.provider` | String | `raft_engine` | The provider of the WAL.<br/>- `raft_engine`: the wal is stored in the local file system by raft-engine.<br/>- `kafka`: it's remote wal that data is stored in Kafka. |
 | `wal.dir` | String | Unset | The directory to store the WAL files.<br/>**It's only used when the provider is `raft_engine`**. |
-| `wal.file_size` | String | `256MB` | The size of the WAL segment file.<br/>**It's only used when the provider is `raft_engine`**. |
-| `wal.purge_threshold` | String | `4GB` | The threshold of the WAL size to trigger a flush.<br/>**It's only used when the provider is `raft_engine`**. |
-| `wal.purge_interval` | String | `10m` | The interval to trigger a flush.<br/>**It's only used when the provider is `raft_engine`**. |
+| `wal.file_size` | String | `128MB` | The size of the WAL segment file.<br/>**It's only used when the provider is `raft_engine`**. |
+| `wal.purge_threshold` | String | `1GB` | The threshold of the WAL size to trigger a flush.<br/>**It's only used when the provider is `raft_engine`**. |
+| `wal.purge_interval` | String | `1m` | The interval to trigger a flush.<br/>**It's only used when the provider is `raft_engine`**. |
 | `wal.read_batch_size` | Integer | `128` | The read batch size.<br/>**It's only used when the provider is `raft_engine`**. |
 | `wal.sync_write` | Bool | `false` | Whether to use sync write.<br/>**It's only used when the provider is `raft_engine`**. |
 | `wal.enable_log_recycle` | Bool | `true` | Whether to reuse logically truncated log files.<br/>**It's only used when the provider is `raft_engine`**. |
@@ -287,12 +287,12 @@
 | `bind_addr` | String | `127.0.0.1:3002` | The bind address of metasrv. |
 | `server_addr` | String | `127.0.0.1:3002` | The communication server address for frontend and datanode to connect to metasrv,  "127.0.0.1:3002" by default for localhost. |
 | `store_addrs` | Array | -- | Store server address default to etcd store. |
+| `store_key_prefix` | String | `""` | If it's not empty, the metasrv will store all data with this key prefix. |
+| `backend` | String | `EtcdStore` | The datastore for meta server. |
 | `selector` | String | `round_robin` | Datanode selector type.<br/>- `round_robin` (default value)<br/>- `lease_based`<br/>- `load_based`<br/>For details, please see "https://docs.greptime.com/developer-guide/metasrv/selector". |
 | `use_memory_store` | Bool | `false` | Store data in memory. |
-| `enable_telemetry` | Bool | `true` | Whether to enable greptimedb telemetry. |
-| `store_key_prefix` | String | `""` | If it's not empty, the metasrv will store all data with this key prefix. |
 | `enable_region_failover` | Bool | `false` | Whether to enable region failover.<br/>This feature is only available on GreptimeDB running on cluster mode and<br/>- Using Remote WAL<br/>- Using shared storage (e.g., s3). |
-| `backend` | String | `EtcdStore` | The datastore for meta server. |
+| `enable_telemetry` | Bool | `true` | Whether to enable greptimedb telemetry. Enabled by default. |
 | `runtime` | -- | -- | The runtime options. |
 | `runtime.global_rt_size` | Integer | `8` | The number of threads to execute the runtime for global read operations. |
 | `runtime.compact_rt_size` | Integer | `4` | The number of threads to execute the runtime for global write operations. |
@@ -357,14 +357,14 @@
 | `node_id` | Integer | Unset | The datanode identifier and should be unique in the cluster. |
 | `require_lease_before_startup` | Bool | `false` | Start services after regions have obtained leases.<br/>It will block the datanode start if it can't receive leases in the heartbeat from metasrv. |
 | `init_regions_in_background` | Bool | `false` | Initialize all regions in the background during the startup.<br/>By default, it provides services after all regions have been initialized. |
-| `enable_telemetry` | Bool | `true` | Enable telemetry to collect anonymous usage data. |
 | `init_regions_parallelism` | Integer | `16` | Parallelism of initializing regions. |
 | `max_concurrent_queries` | Integer | `0` | The maximum current queries allowed to be executed. Zero means unlimited. |
 | `rpc_addr` | String | Unset | Deprecated, use `grpc.addr` instead. |
 | `rpc_hostname` | String | Unset | Deprecated, use `grpc.hostname` instead. |
 | `rpc_runtime_size` | Integer | Unset | Deprecated, use `grpc.runtime_size` instead. |
 | `rpc_max_recv_message_size` | String | Unset | Deprecated, use `grpc.rpc_max_recv_message_size` instead. |
 | `rpc_max_send_message_size` | String | Unset | Deprecated, use `grpc.rpc_max_send_message_size` instead. |
+| `enable_telemetry` | Bool | `true` | Enable telemetry to collect anonymous usage data. Enabled by default. |
 | `http` | -- | -- | The HTTP server options. |
 | `http.addr` | String | `127.0.0.1:4000` | The address to bind the HTTP server. |
 | `http.timeout` | String | `30s` | HTTP request timeout. Set to 0 to disable timeout. |
@@ -399,9 +399,9 @@
 | `wal` | -- | -- | The WAL options. |
 | `wal.provider` | String | `raft_engine` | The provider of the WAL.<br/>- `raft_engine`: the wal is stored in the local file system by raft-engine.<br/>- `kafka`: it's remote wal that data is stored in Kafka. |
 | `wal.dir` | String | Unset | The directory to store the WAL files.<br/>**It's only used when the provider is `raft_engine`**. |
-| `wal.file_size` | String | `256MB` | The size of the WAL segment file.<br/>**It's only used when the provider is `raft_engine`**. |
-| `wal.purge_threshold` | String | `4GB` | The threshold of the WAL size to trigger a flush.<br/>**It's only used when the provider is `raft_engine`**. |
-| `wal.purge_interval` | String | `10m` | The interval to trigger a flush.<br/>**It's only used when the provider is `raft_engine`**. |
+| `wal.file_size` | String | `128MB` | The size of the WAL segment file.<br/>**It's only used when the provider is `raft_engine`**. |
+| `wal.purge_threshold` | String | `1GB` | The threshold of the WAL size to trigger a flush.<br/>**It's only used when the provider is `raft_engine`**. |
+| `wal.purge_interval` | String | `1m` | The interval to trigger a flush.<br/>**It's only used when the provider is `raft_engine`**. |
 | `wal.read_batch_size` | Integer | `128` | The read batch size.<br/>**It's only used when the provider is `raft_engine`**. |
 | `wal.sync_write` | Bool | `false` | Whether to use sync write.<br/>**It's only used when the provider is `raft_engine`**. |
 | `wal.enable_log_recycle` | Bool | `true` | Whether to reuse logically truncated log files.<br/>**It's only used when the provider is `raft_engine`**. |

config/datanode.example.toml

@@ -13,9 +13,6 @@ require_lease_before_startup = false
 ## By default, it provides services after all regions have been initialized.
 init_regions_in_background = false
 
-## Enable telemetry to collect anonymous usage data.
-enable_telemetry = true
-
 ## Parallelism of initializing regions.
 init_regions_parallelism = 16
 
@@ -42,6 +39,8 @@ rpc_max_recv_message_size = "512MB"
 ## @toml2docs:none-default
 rpc_max_send_message_size = "512MB"
 
+## Enable telemetry to collect anonymous usage data. Enabled by default.
+#+ enable_telemetry = true
 
 ## The HTTP server options.
 [http]
@@ -143,15 +142,15 @@ dir = "/tmp/greptimedb/wal"
 
 ## The size of the WAL segment file.
 ## **It's only used when the provider is `raft_engine`**.
-file_size = "256MB"
+file_size = "128MB"
 
 ## The threshold of the WAL size to trigger a flush.
 ## **It's only used when the provider is `raft_engine`**.
-purge_threshold = "4GB"
+purge_threshold = "1GB"
 
 ## The interval to trigger a flush.
 ## **It's only used when the provider is `raft_engine`**.
-purge_interval = "10m"
+purge_interval = "1m"
 
 ## The read batch size.
 ## **It's only used when the provider is `raft_engine`**.

config/metasrv.example.toml

@@ -10,6 +10,12 @@ server_addr = "127.0.0.1:3002"
 ## Store server address default to etcd store.
 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.
+backend = "EtcdStore"
+
 ## Datanode selector type.
 ## - `round_robin` (default value)
 ## - `lease_based`
@@ -20,20 +26,14 @@ selector = "round_robin"
 ## Store data in memory.
 use_memory_store = false
 
-## Whether to enable greptimedb telemetry.
-enable_telemetry = true
-
-## If it's not empty, the metasrv will store all data with this key prefix.
-store_key_prefix = ""
-
 ## 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 datastore for meta server.
-backend = "EtcdStore"
+## Whether to enable greptimedb telemetry. Enabled by default.
+#+ enable_telemetry = true
 
 ## The runtime options.
 #+ [runtime]

config/standalone.example.toml

@@ -1,9 +1,6 @@
 ## The running mode of the datanode. It can be `standalone` or `distributed`.
 mode = "standalone"
 
-## Enable telemetry to collect anonymous usage data.
-enable_telemetry = true
-
 ## The default timezone of the server.
 ## @toml2docs:none-default
 default_timezone = "UTC"
@@ -18,6 +15,9 @@ init_regions_parallelism = 16
 ## The maximum current queries allowed to be executed. Zero means unlimited.
 max_concurrent_queries = 0
 
+## Enable telemetry to collect anonymous usage data. Enabled by default.
+#+ enable_telemetry = true
+
 ## The runtime options.
 #+ [runtime]
 ## The number of threads to execute the runtime for global read operations.
@@ -147,15 +147,15 @@ dir = "/tmp/greptimedb/wal"
 
 ## The size of the WAL segment file.
 ## **It's only used when the provider is `raft_engine`**.
-file_size = "256MB"
+file_size = "128MB"
 
 ## The threshold of the WAL size to trigger a flush.
 ## **It's only used when the provider is `raft_engine`**.
-purge_threshold = "4GB"
+purge_threshold = "1GB"
 
 ## The interval to trigger a flush.
 ## **It's only used when the provider is `raft_engine`**.
-purge_interval = "10m"
+purge_interval = "1m"
 
 ## The read batch size.
 ## **It's only used when the provider is `raft_engine`**.

src/common/wal/src/config/raft_engine.rs

@@ -49,9 +49,9 @@ impl Default for RaftEngineConfig {
     fn default() -> Self {
         Self {
             dir: None,
-            file_size: ReadableSize::mb(256),
-            purge_threshold: ReadableSize::gb(4),
-            purge_interval: Duration::from_secs(600),
+            file_size: ReadableSize::mb(128),
+            purge_threshold: ReadableSize::gb(1),
+            purge_interval: Duration::from_secs(60),
             read_batch_size: 128,
             sync_write: false,
             enable_log_recycle: true,

tests-integration/tests/http.rs

@@ -881,9 +881,9 @@ with_metric_engine = true
 
 [wal]
 provider = "raft_engine"
-file_size = "256MiB"
-purge_threshold = "4GiB"
-purge_interval = "10m"
+file_size = "128MiB"
+purge_threshold = "1GiB"
+purge_interval = "1m"
 read_batch_size = 128
 sync_write = false
 enable_log_recycle = true