Messages by Thread
-
Re: [PR] docs: Remove extra commas in count results [datafusion]
via GitHub
-
Re: [PR] refactor: use row-group-local selections for Parquet scans [datafusion]
via GitHub
-
Re: [PR] Add TrinoDialect [datafusion-sqlparser-rs]
via GitHub
-
Re: [I] PartitionExpr cannot be reconstructed from its public API [datafusion-iceberg]
via GitHub
-
Re: [I] Add support for SQL based registration of external catalogs [datafusion]
via GitHub
-
Re: [I] Release datafusion-python 55.0.0 [datafusion-python]
via GitHub
-
Re: [PR] chore: harden the extension API before it ships [datafusion-python]
via GitHub
-
[PR] feat: make optional_filter_mode = adaptive the default [datafusion]
via GitHub
-
Re: [PR] perf: avoid unnecessary aggregate spill rewrites [datafusion]
via GitHub
-
Re: [I] Shuffle schema cache can evict recent entries and retain oversized schemas [datafusion-comet]
via GitHub
-
Re: [PR] fix: park the native scan loop instead of busy-polling while waiting on native I/O [datafusion-comet]
via GitHub
-
Re: [PR] perf: use one null-aware mark join for hashable IN subqueries in projections [datafusion]
via GitHub
-
[PR] fix: [branch-1.0] read shuffle write buffer, spill limit and off-heap sizes in bytes (#6191) [datafusion-comet]
via GitHub
-
Re: [PR] feat: Column statistics support v1 [datafusion-ballista]
via GitHub
-
[PR] fix: make concat combine array arguments as arrays [datafusion]
via GitHub
-
[PR] perf: push hash join dynamic filter bounds and membership as separate optional filters [datafusion]
via GitHub
-
[PR] fix: keep operators above a cached relation native after the AQE re-plan [datafusion-comet]
via GitHub
-
Re: [I] unexpected output for `concat` for arrays [datafusion]
via GitHub
-
Re: [PR] docs: document the `TIMESTAMP WITH TIME ZONE` type mapping and fix a stale comment [datafusion]
via GitHub
-
[I] S3 credential SPI: per-location credentials within a bucket [datafusion-comet]
via GitHub
-
[PR] fix: reject non-default collations in all sort keys [datafusion-comet]
via GitHub
-
Re: [I] Native Iceberg write fails on a V1 spec that mixes a live field with a void field whose source column was dropped [datafusion-comet]
via GitHub
-
Re: [I] Native Iceberg write gate reads hdfs:/path as file, so the write fails natively instead of falling back [datafusion-comet]
via GitHub
-
[PR] fix: check each fair_unified reservation against its own share [datafusion-comet]
via GitHub
-
Re: [I] Native Iceberg write merges -0.0 and 0.0 rows into one float/double identity partition [datafusion-comet]
via GitHub
-
Re: [I] Native Iceberg write silently drops S3 settings it cannot honour (credentials provider, SSE, ACL, tags, remote signing) instead of falling back [datafusion-comet]
via GitHub
-
Re: [I] Comet 1.1.0 Release (September) [datafusion-comet]
via GitHub
-
Re: [I] Excessive Arc-clone in HashJoinStream with StringView on build-side [datafusion]
via GitHub
-
[PR] Spans: Give DROP statements exact spans [datafusion-sqlparser-rs]
via GitHub
-
Re: [I] datasource listing performs full listing despite user pruning partitions [datafusion]
via GitHub
-
[PR] feat: add opt-in local TopK fusion for native Parquet scans [datafusion-comet]
via GitHub
-
[I] Chained CollectLeft hash joins multiply StringView buffer references (TPC-DS Q64: 8.5 GB, ~10x slower with pushdown_filters) [datafusion]
via GitHub
-
[PR] Fix panic from `avg(x ORDER BY y)` (and more) [datafusion]
via GitHub
-
[PR] ClickHouse: Support tuple element access by index [datafusion-sqlparser-rs]
via GitHub
-
[I] Operators above a cached relation fall back to Spark after AQE materializes the table-cache stage [datafusion-comet]
via GitHub
-
[I] ClickHouse: Support tuple element access by index (`t.1`, `(1, 'a').1`) [datafusion-sqlparser-rs]
via GitHub
-
Re: [PR] feat: scope-aware object_store cache for the S3 credential SPI [datafusion-comet]
via GitHub
-
Re: [PR] feat: built-in S3 credential provider adapters for the native Parquet scan [datafusion-comet]
via GitHub
-
[PR] feat: route timestamp_seconds decimal, byte and short input through codegen dispatch [datafusion-comet]
via GitHub
-
[I] In-memory cache tests that use checkSparkAnswer compare the cache with itself [datafusion-comet]
via GitHub
-
Re: [I] Hash partitioning not falling back to Spark for high precision decimal partition keys [datafusion-comet]
via GitHub
-
Re: [I] Backport candidates for 1.0.x: triage of every PR merged since branch-1.0 was cut [datafusion-comet]
via GitHub
-
[I] [EPIC] Bug fixes to consider backporting to branch-1.0 [datafusion-comet]
via GitHub
-
Re: [PR] bench: add `array_compact` benchmarks [datafusion]
via GitHub
-
Re: [PR] fix: preserve nested log and power results [datafusion]
via GitHub
-
[I] `CometCast.isSupported` returns the first non-Compatible child, so `Incompatible` can mask `Unsupported` [datafusion-comet]
via GitHub
-
[I] Queries fail when `spark.shuffle.manager` names the Comet shuffle manager only in the session conf [datafusion-comet]
via GitHub
-
[PR] fix: skip the executor memory overhead warning when a factor is set or in local mode [datafusion-comet]
via GitHub
-
Re: [I] CollectLeft hash join build holds ~2x build side while charging the memory pool 1x: concat_batches copy is never reserved and superseded batches are never shrunk [datafusion]
via GitHub
-
[PR] docs: correct which operators run separate native plans in a task [datafusion-comet]
via GitHub
-
[I] Follow-ups to #6163: correct the `fair_unified` description and prepare `spark.comet.exec.memoryPool.fraction` for removal [datafusion-comet]
via GitHub
-
[PR] fix datafusion-cli CI: switch from minio to rustfs [datafusion]
via GitHub
-
Re: [PR] feat: enable Comet's in-memory cache by default [datafusion-comet]
via GitHub
-
Re: [PR] fix: reject a file without field ids at any depth whether or not id matching is on [datafusion-comet]
via GitHub
-
Re: [PR] fix: give a multi-set aggregate the grouping set index Substrait defines [datafusion]
via GitHub
-
[PR] Add a test to enforce compatibility between an aggregate's accumulators [datafusion]
via GitHub
-
[I] Charge the native shuffle writer's write buffers to the memory pool [datafusion-comet]
via GitHub