feat!: Bump datafusion, prost, hyper, tonic, tower, axum

Cargo.toml

@@ -88,14 +88,15 @@ rust.unexpected_cfgs = { level = "warn", check-cfg = ['cfg(tokio_unstable)'] }
 # See for more detaiils: https://github.com/rust-lang/cargo/issues/11329
 ahash = { version = "0.8", features = ["compile-time-rng"] }
 aquamarine = "0.3"
-arrow = { version = "51.0.0", features = ["prettyprint"] }
-arrow-array = { version = "51.0.0", default-features = false, features = ["chrono-tz"] }
-arrow-flight = "51.0"
-arrow-ipc = { version = "51.0.0", default-features = false, features = ["lz4", "zstd"] }
-arrow-schema = { version = "51.0", features = ["serde"] }
+arrow = { version = "53.0.0", features = ["prettyprint"] }
+arrow-array = { version = "53.0.0", default-features = false, features = ["chrono-tz"] }
+arrow-flight = "53.0"
+arrow-ipc = { version = "53.0.0", default-features = false, features = ["lz4", "zstd"] }
+arrow-schema = { version = "53.0", features = ["serde"] }
 async-stream = "0.3"
 async-trait = "0.1"
-axum = { version = "0.6", features = ["headers"] }
+# Remember to update axum-extra, axum-macros when updating axum
+axum = "0.8"
 backon = "1"
 base64 = "0.21"
 bigdecimal = "0.4.2"
@@ -107,53 +108,57 @@ clap = { version = "4.4", features = ["derive"] }
 config = "0.13.0"
 crossbeam-utils = "0.8"
 dashmap = "5.4"
-datafusion = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "7823ef2f63663907edab46af0d51359900f608d6" }
-datafusion-common = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "7823ef2f63663907edab46af0d51359900f608d6" }
-datafusion-expr = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "7823ef2f63663907edab46af0d51359900f608d6" }
-datafusion-functions = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "7823ef2f63663907edab46af0d51359900f608d6" }
-datafusion-optimizer = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "7823ef2f63663907edab46af0d51359900f608d6" }
-datafusion-physical-expr = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "7823ef2f63663907edab46af0d51359900f608d6" }
-datafusion-physical-plan = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "7823ef2f63663907edab46af0d51359900f608d6" }
-datafusion-sql = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "7823ef2f63663907edab46af0d51359900f608d6" }
-datafusion-substrait = { git = "https://github.com/waynexia/arrow-datafusion.git", rev = "7823ef2f63663907edab46af0d51359900f608d6" }
+datafusion = { git = "https://github.com/apache/datafusion.git", rev = "2464703c84c400a09cc59277018813f0e797bb4e" }
+datafusion-common = { git = "https://github.com/apache/datafusion.git", rev = "2464703c84c400a09cc59277018813f0e797bb4e" }
+datafusion-expr = { git = "https://github.com/apache/datafusion.git", rev = "2464703c84c400a09cc59277018813f0e797bb4e" }
+datafusion-functions = { git = "https://github.com/apache/datafusion.git", rev = "2464703c84c400a09cc59277018813f0e797bb4e" }
+datafusion-optimizer = { git = "https://github.com/apache/datafusion.git", rev = "2464703c84c400a09cc59277018813f0e797bb4e" }
+datafusion-physical-expr = { git = "https://github.com/apache/datafusion.git", rev = "2464703c84c400a09cc59277018813f0e797bb4e" }
+datafusion-physical-plan = { git = "https://github.com/apache/datafusion.git", rev = "2464703c84c400a09cc59277018813f0e797bb4e" }
+datafusion-sql = { git = "https://github.com/apache/datafusion.git", rev = "2464703c84c400a09cc59277018813f0e797bb4e" }
+datafusion-substrait = { git = "https://github.com/apache/datafusion.git", rev = "2464703c84c400a09cc59277018813f0e797bb4e" }
 deadpool = "0.10"
 deadpool-postgres = "0.12"
 derive_builder = "0.12"
 dotenv = "0.15"
-etcd-client = "0.13"
+etcd-client = "0.14"
 fst = "0.4.7"
 futures = "0.3"
 futures-util = "0.3"
-greptime-proto = { git = "https://github.com/GreptimeTeam/greptime-proto.git", rev = "ec801a91aa22f9666063d02805f1f60f7c93458a" }
+# Branch: chore/update-prost
+greptime-proto = { git = "https://github.com/GreptimeTeam/greptime-proto.git", rev = "8a63580f65453bd688db6662f70616a62a7214f3" }
 hex = "0.4"
-http = "0.2"
+http = "1"
 humantime = "2.1"
 humantime-serde = "1.1"
+hyper = "1.1"
+hyper-util = "0.1"
 itertools = "0.10"
 jsonb = { git = "https://github.com/databendlabs/jsonb.git", rev = "8c8d2fc294a39f3ff08909d60f718639cfba3875", default-features = false }
 lazy_static = "1.4"
 local-ip-address = "0.6"
+loki-api = { git = "https://github.com/shuiyisong/tracing-loki", branch = "chore/prost_version" }
 meter-core = { git = "https://github.com/GreptimeTeam/greptime-meter.git", rev = "a10facb353b41460eeb98578868ebf19c2084fac" }
 mockall = "0.11.4"
 moka = "0.12"
 nalgebra = "0.33"
 notify = "6.1"
 num_cpus = "1.16"
 once_cell = "1.18"
-opentelemetry-proto = { version = "0.5", features = [
+opentelemetry-proto = { version = "0.27", features = [
     "gen-tonic",
     "metrics",
     "trace",
     "with-serde",
     "logs",
 ] }
 parking_lot = "0.12"
-parquet = { version = "51.0.0", default-features = false, features = ["arrow", "async", "object_store"] }
+parquet = { version = "53.0.0", default-features = false, features = ["arrow", "async", "object_store"] }
 paste = "1.0"
 pin-project = "1.0"
 prometheus = { version = "0.13.3", features = ["process"] }
 promql-parser = { version = "0.4.3", features = ["ser"] }
-prost = "0.12"
+prost = "0.13"
 raft-engine = { version = "0.4.1", default-features = false }
 rand = "0.8"
 ratelimit = "0.9"
@@ -172,6 +177,7 @@ rstest = "0.21"
 rstest_reuse = "0.7"
 rust_decimal = "1.33"
 rustc-hash = "2.0"
+rustls = { version = "0.23.20", default-features = false } # override by patch, see [patch.crates-io]
 serde = { version = "1.0", features = ["derive"] }
 serde_json = { version = "1.0", features = ["float_roundtrip"] }
 serde_with = "3"
@@ -180,9 +186,8 @@ similar-asserts = "1.6.0"
 smallvec = { version = "1", features = ["serde"] }
 snafu = "0.8"
 sysinfo = "0.30"
-
-rustls = { version = "0.23.20", default-features = false } # override by patch, see [patch.crates-io]
-sqlparser = { git = "https://github.com/GreptimeTeam/sqlparser-rs.git", rev = "54a267ac89c09b11c0c88934690530807185d3e7", features = [
+# on branch v0.52.x
+sqlparser = { git = "https://github.com/GreptimeTeam/sqlparser-rs.git", rev = "71dd86058d2af97b9925093d40c4e03360403170", features = [
     "visitor",
     "serde",
 ] } # on branch v0.44.x
@@ -194,8 +199,8 @@ tokio-rustls = { version = "0.26.0", default-features = false } # override by pa
 tokio-stream = "0.1"
 tokio-util = { version = "0.7", features = ["io-util", "compat"] }
 toml = "0.8.8"
-tonic = { version = "0.11", features = ["tls", "gzip", "zstd"] }
-tower = "0.4"
+tonic = { version = "0.12", features = ["tls", "gzip", "zstd"] }
+tower = "0.5"
 tracing-appender = "0.2"
 tracing-subscriber = { version = "0.3", features = ["env-filter", "json", "fmt"] }
 typetag = "0.2"

src/api/src/error.rs

@@ -33,7 +33,7 @@ pub enum Error {
         #[snafu(implicit)]
         location: Location,
         #[snafu(source)]
-        error: prost::DecodeError,
+        error: prost::UnknownEnumValue,
     },
 
     #[snafu(display("Failed to create column datatype from {:?}", from))]

src/api/src/helper.rs

@@ -86,7 +86,7 @@ impl ColumnDataTypeWrapper {
 
     /// Get a tuple of ColumnDataType and ColumnDataTypeExtension.
     pub fn to_parts(&self) -> (ColumnDataType, Option<ColumnDataTypeExtension>) {
-        (self.datatype, self.datatype_ext.clone())
+        (self.datatype, self.datatype_ext)
     }
 }
 
@@ -685,14 +685,18 @@ pub fn pb_values_to_vector_ref(data_type: &ConcreteDataType, values: Values) ->
             IntervalType::YearMonth(_) => Arc::new(IntervalYearMonthVector::from_vec(
                 values.interval_year_month_values,
             )),
-            IntervalType::DayTime(_) => Arc::new(IntervalDayTimeVector::from_vec(
-                values.interval_day_time_values,
+            IntervalType::DayTime(_) => Arc::new(IntervalDayTimeVector::from_iter_values(
+                values
+                    .interval_day_time_values
+                    .iter()
+                    .map(|x| IntervalDayTime::from_i64(*x).into()),
             )),
             IntervalType::MonthDayNano(_) => {
                 Arc::new(IntervalMonthDayNanoVector::from_iter_values(
-                    values.interval_month_day_nano_values.iter().map(|x| {
-                        IntervalMonthDayNano::new(x.months, x.days, x.nanoseconds).to_i128()
-                    }),
+                    values
+                        .interval_month_day_nano_values
+                        .iter()
+                        .map(|x| IntervalMonthDayNano::new(x.months, x.days, x.nanoseconds).into()),
                 ))
             }
         },
@@ -1495,14 +1499,22 @@ mod tests {
             column.values.as_ref().unwrap().interval_year_month_values
         );
 
-        let vector = Arc::new(IntervalDayTimeVector::from_vec(vec![4, 5, 6]));
+        let vector = Arc::new(IntervalDayTimeVector::from_vec(vec![
+            IntervalDayTime::new(0, 4).into(),
+            IntervalDayTime::new(0, 5).into(),
+            IntervalDayTime::new(0, 6).into(),
+        ]));
         push_vals(&mut column, 3, vector);
         assert_eq!(
             vec![4, 5, 6],
             column.values.as_ref().unwrap().interval_day_time_values
         );
 
-        let vector = Arc::new(IntervalMonthDayNanoVector::from_vec(vec![7, 8, 9]));
+        let vector = Arc::new(IntervalMonthDayNanoVector::from_vec(vec![
+            IntervalMonthDayNano::new(0, 0, 7).into(),
+            IntervalMonthDayNano::new(0, 0, 8).into(),
+            IntervalMonthDayNano::new(0, 0, 9).into(),
+        ]));
         let len = vector.len();
         push_vals(&mut column, 3, vector);
         (0..len).for_each(|i| {

src/api/src/v1/column_def.rs

@@ -34,10 +34,8 @@ const SKIPPING_INDEX_GRPC_KEY: &str = "skipping_index";
 
 /// Tries to construct a `ColumnSchema` from the given  `ColumnDef`.
 pub fn try_as_column_schema(column_def: &ColumnDef) -> Result<ColumnSchema> {
-    let data_type = ColumnDataTypeWrapper::try_new(
-        column_def.data_type,
-        column_def.datatype_extension.clone(),
-    )?;
+    let data_type =
+        ColumnDataTypeWrapper::try_new(column_def.data_type, column_def.datatype_extension)?;
 
     let constraint = if column_def.default_constraint.is_empty() {
         None

src/catalog/src/lib.rs

@@ -41,6 +41,7 @@ pub mod information_schema {
 }
 
 pub mod table_source;
+
 #[async_trait::async_trait]
 pub trait CatalogManager: Send + Sync {
     fn as_any(&self) -> &dyn Any;

src/catalog/src/system_schema/information_schema/cluster_info.rs

@@ -63,7 +63,7 @@ const INIT_CAPACITY: usize = 42;
 /// - `start_time`: the starting time of the peer.
 /// - `uptime`: the uptime of the peer.
 /// - `active_time`: the time since the last activity of the peer.
-///
+#[derive(Debug)]
 pub(super) struct InformationSchemaClusterInfo {
     schema: SchemaRef,
     catalog_manager: Weak<dyn CatalogManager>,

src/catalog/src/system_schema/information_schema/columns.rs

@@ -45,6 +45,7 @@ use crate::error::{
 use crate::information_schema::Predicates;
 use crate::CatalogManager;
 
+#[derive(Debug)]
 pub(super) struct InformationSchemaColumns {
     schema: SchemaRef,
     catalog_name: String,

src/catalog/src/system_schema/information_schema/flows.rs

@@ -61,7 +61,7 @@ pub const FLOWNODE_IDS: &str = "flownode_ids";
 pub const OPTIONS: &str = "options";
 
 /// The `information_schema.flows` to provides information about flows in databases.
-///
+#[derive(Debug)]
 pub(super) struct InformationSchemaFlows {
     schema: SchemaRef,
     catalog_name: String,

src/catalog/src/system_schema/information_schema/key_column_usage.rs

@@ -62,6 +62,7 @@ pub(crate) const FULLTEXT_INDEX_CONSTRAINT_NAME: &str = "FULLTEXT INDEX";
 pub(crate) const SKIPPING_INDEX_CONSTRAINT_NAME: &str = "SKIPPING INDEX";
 
 /// The virtual table implementation for `information_schema.KEY_COLUMN_USAGE`.
+#[derive(Debug)]
 pub(super) struct InformationSchemaKeyColumnUsage {
     schema: SchemaRef,
     catalog_name: String,

src/catalog/src/system_schema/information_schema/partitions.rs

@@ -59,6 +59,7 @@ const INIT_CAPACITY: usize = 42;
 /// The `PARTITIONS` table provides information about partitioned tables.
 /// See https://dev.mysql.com/doc/refman/8.0/en/information-schema-partitions-table.html
 /// We provide an extral column `greptime_partition_id` for GreptimeDB region id.
+#[derive(Debug)]
 pub(super) struct InformationSchemaPartitions {
     schema: SchemaRef,
     catalog_name: String,

src/catalog/src/system_schema/information_schema/procedure_info.rs

@@ -56,7 +56,7 @@ const INIT_CAPACITY: usize = 42;
 /// - `end_time`: the ending execution time of the procedure.
 /// - `status`: the status of the procedure.
 /// - `lock_keys`: the lock keys of the procedure.
-///
+#[derive(Debug)]
 pub(super) struct InformationSchemaProcedureInfo {
     schema: SchemaRef,
     catalog_manager: Weak<dyn CatalogManager>,

src/catalog/src/system_schema/information_schema/region_peers.rs

@@ -59,7 +59,7 @@ const INIT_CAPACITY: usize = 42;
 /// - `is_leader`: whether the peer is the leader
 /// - `status`: the region status, `ALIVE` or `DOWNGRADED`.
 /// - `down_seconds`: the duration of being offline, in seconds.
-///
+#[derive(Debug)]
 pub(super) struct InformationSchemaRegionPeers {
     schema: SchemaRef,
     catalog_name: String,

src/catalog/src/system_schema/information_schema/region_statistics.rs

@@ -63,7 +63,7 @@ const INIT_CAPACITY: usize = 42;
 /// - `index_size`: The sst index files size in bytes.
 /// - `engine`: The engine type.
 /// - `region_role`: The region role.
-///
+#[derive(Debug)]
 pub(super) struct InformationSchemaRegionStatistics {
     schema: SchemaRef,
     catalog_manager: Weak<dyn CatalogManager>,

src/catalog/src/system_schema/information_schema/runtime_metrics.rs

@@ -38,6 +38,7 @@ use store_api::storage::{ScanRequest, TableId};
 use super::{InformationTable, RUNTIME_METRICS};
 use crate::error::{CreateRecordBatchSnafu, InternalSnafu, Result};
 
+#[derive(Debug)]
 pub(super) struct InformationSchemaMetrics {
     schema: SchemaRef,
 }

src/catalog/src/system_schema/information_schema/schemata.rs

@@ -49,6 +49,7 @@ pub const SCHEMA_OPTS: &str = "options";
 const INIT_CAPACITY: usize = 42;
 
 /// The `information_schema.schemata` table implementation.
+#[derive(Debug)]
 pub(super) struct InformationSchemaSchemata {
     schema: SchemaRef,
     catalog_name: String,

src/catalog/src/system_schema/information_schema/table_constraints.rs

@@ -43,6 +43,7 @@ use crate::information_schema::Predicates;
 use crate::CatalogManager;
 
 /// The `TABLE_CONSTRAINTS` table describes which tables have constraints.
+#[derive(Debug)]
 pub(super) struct InformationSchemaTableConstraints {
     schema: SchemaRef,
     catalog_name: String,

src/catalog/src/system_schema/information_schema/tables.rs

@@ -71,6 +71,7 @@ const TABLE_ID: &str = "table_id";
 pub const ENGINE: &str = "engine";
 const INIT_CAPACITY: usize = 42;
 
+#[derive(Debug)]
 pub(super) struct InformationSchemaTables {
     schema: SchemaRef,
     catalog_name: String,

src/catalog/src/system_schema/information_schema/views.rs

@@ -54,6 +54,7 @@ pub const CHARACTER_SET_CLIENT: &str = "character_set_client";
 pub const COLLATION_CONNECTION: &str = "collation_connection";
 
 /// The `information_schema.views` to provides information about views in databases.
+#[derive(Debug)]
 pub(super) struct InformationSchemaViews {
     schema: SchemaRef,
     catalog_name: String,

src/catalog/src/system_schema/memory_table.rs

@@ -33,6 +33,7 @@ use super::SystemTable;
 use crate::error::{CreateRecordBatchSnafu, InternalSnafu, Result};
 
 /// A memory table with specified schema and columns.
+#[derive(Debug)]
 pub(crate) struct MemoryTable {
     pub(crate) table_id: TableId,
     pub(crate) table_name: &'static str,

src/catalog/src/system_schema/pg_catalog/pg_class.rs

@@ -12,6 +12,7 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
+use std::fmt;
 use std::sync::{Arc, Weak};
 
 use arrow_schema::SchemaRef as ArrowSchemaRef;
@@ -100,6 +101,15 @@ impl PGClass {
     }
 }
 
+impl fmt::Debug for PGClass {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        f.debug_struct("PGClass")
+            .field("schema", &self.schema)
+            .field("catalog_name", &self.catalog_name)
+            .finish()
+    }
+}
+
 impl SystemTable for PGClass {
     fn table_id(&self) -> table::metadata::TableId {
         PG_CATALOG_PG_CLASS_TABLE_ID

src/catalog/src/system_schema/pg_catalog/pg_database.rs

@@ -55,6 +55,15 @@ pub(super) struct PGDatabase {
     namespace_oid_map: PGNamespaceOidMapRef,
 }
 
+impl std::fmt::Debug for PGDatabase {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        f.debug_struct("PGDatabase")
+            .field("schema", &self.schema)
+            .field("catalog_name", &self.catalog_name)
+            .finish()
+    }
+}
+
 impl PGDatabase {
     pub(super) fn new(
         catalog_name: String,

src/catalog/src/system_schema/pg_catalog/pg_namespace.rs

@@ -17,6 +17,7 @@
 
 pub(super) mod oid_map;
 
+use std::fmt;
 use std::sync::{Arc, Weak};
 
 use arrow_schema::SchemaRef as ArrowSchemaRef;
@@ -87,6 +88,15 @@ impl PGNamespace {
     }
 }
 
+impl fmt::Debug for PGNamespace {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        f.debug_struct("PGNamespace")
+            .field("schema", &self.schema)
+            .field("catalog_name", &self.catalog_name)
+            .finish()
+    }
+}
+
 impl SystemTable for PGNamespace {
     fn schema(&self) -> SchemaRef {
         self.schema.clone()