[pull] main from apache:main

.github/workflows/audit.yml

@@ -42,7 +42,7 @@ jobs:
     steps:
       - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
       - name: Install cargo-audit
-        uses: taiki-e/install-action@6ef672efc2b5aabc787a9e94baf4989aa02a97df  # v2.70.3
+        uses: taiki-e/install-action@94cb46f8d6e437890146ffbd78a778b78e623fb2  # v2.74.0
         with:
           tool: cargo-audit
       - name: Run audit check

.github/workflows/rust.yml

@@ -430,7 +430,7 @@ jobs:
           sudo apt-get update -qq
           sudo apt-get install -y -qq clang
       - name: Setup wasm-pack
-        uses: taiki-e/install-action@6ef672efc2b5aabc787a9e94baf4989aa02a97df  # v2.70.3
+        uses: taiki-e/install-action@94cb46f8d6e437890146ffbd78a778b78e623fb2  # v2.74.0
         with:
           tool: wasm-pack
       - name: Run tests with headless mode
@@ -770,7 +770,7 @@ jobs:
       - name: Setup Rust toolchain
         uses: ./.github/actions/setup-builder
       - name: Install cargo-msrv
-        uses: taiki-e/install-action@6ef672efc2b5aabc787a9e94baf4989aa02a97df  # v2.70.3
+        uses: taiki-e/install-action@94cb46f8d6e437890146ffbd78a778b78e623fb2  # v2.74.0
         with:
           tool: cargo-msrv
 

Cargo.toml

@@ -162,7 +162,7 @@ glob = "0.3.0"
 half = { version = "2.7.0", default-features = false }
 hashbrown = { version = "0.16.1" }
 hex = { version = "0.4.3" }
-indexmap = "2.13.0"
+indexmap = "2.13.1"
 insta = { version = "1.47.2", features = ["glob", "filters"] }
 itertools = "0.14"
 itoa = "1.0"
@@ -192,7 +192,7 @@ strum = "0.28.0"
 strum_macros = "0.28.0"
 tempfile = "3"
 testcontainers-modules = { version = "0.15" }
-tokio = { version = "1.48", features = ["macros", "rt", "sync"] }
+tokio = { version = "1.51", features = ["macros", "rt", "sync"] }
 tokio-stream = "0.1"
 tokio-util = "0.7"
 url = "2.5.7"

datafusion/common/Cargo.toml

@@ -75,7 +75,7 @@ hashbrown = { workspace = true }
 hex = { workspace = true, optional = true }
 indexmap = { workspace = true }
 itertools = { workspace = true }
-libc = "0.2.180"
+libc = "0.2.184"
 log = { workspace = true }
 object_store = { workspace = true, optional = true }
 parquet = { workspace = true, optional = true, default-features = true }

datafusion/common/src/config.rs

@@ -557,6 +557,19 @@ config_namespace! {
         /// batches and merged.
         pub sort_in_place_threshold_bytes: usize, default = 1024 * 1024
 
+        /// Maximum buffer capacity (in bytes) per partition for BufferExec
+        /// inserted during sort pushdown optimization.
+        ///
+        /// When PushdownSort eliminates a SortExec under SortPreservingMergeExec,
+        /// a BufferExec is inserted to replace SortExec's buffering role. This
+        /// prevents I/O stalls by allowing the scan to run ahead of the merge.
+        ///
+        /// This uses strictly less memory than the SortExec it replaces (which
+        /// buffers the entire partition). The buffer respects the global memory
+        /// pool limit. Setting this to a large value is safe — actual memory
+        /// usage is bounded by partition size and global memory limits.
+        pub sort_pushdown_buffer_capacity: usize, default = 1024 * 1024 * 1024
+
         /// Maximum size in bytes for individual spill files before rotating to a new file.
         ///
         /// When operators spill data to disk (e.g., RepartitionExec), they write