@Greptime: GreptimeDB's flat-format queries can now prefilter on any column — tags, fields, timestamps — not just primary keys. Wh…
Summary
GreptimeDB's flat-format queries now support prefiltering on any column (tags, fields, timestamps), not just primary keys, delivering up to 4.5x faster performance. Additionally, the mito2 storage engine removed its legacy scan path, cleaning up about 1,800 lines of code.
View Cached Full Text
Cached at: 05/08/26, 07:37 PM
GreptimeDB’s flat-format queries can now prefilter on any column — tags, fields, timestamps — not just primary keys. While we were at it, mito2 dropped its legacy scan path, about 1,800 lines gone.
Biweekly #82: https://t.co/VDgBsaboRB
OpenDAL 0.56 & CLI Metadata Commands | Greptime Biweekly Report - No. 82
Source: https://greptime.com/blogs/2026-05-03-greptimedb-biweekly-report
Summary
Development period: 2026-04-20 - 2026-05-03
Here are the highlights from recent commits:
greptimeCLI acceptsmetadata putcommands for direct key-value operations- Flat format queries prefilter any columns before scanning data files
- Window function queries handle TimeRange precision and column aliases correctly
We encourage users on older versions to upgrade for these fixes and improvements.
Contributors
Over the past two weeks,14 contributorsmerged a total of43 PRs. Among them,5 community contributorscontributed8 PRs. Welcome to our new contributors:@QuakeWang,@BootstrapperSBL,@onepizzateam,@JoeS51!
Thanks to our community contributors:
Highlights of Recent PRs
db#8003chore: update the opendal to 0.56 rc2
GreptimeDB’s storage layer now uses OpenDAL 0.56, replacing the previous version. This dependency update maintains the same object storage interface while incorporating upstream bug fixes and improvements.
db#7982refactor(mito2): remove PrimaryKey variants
The mito2 storage engine removes its legacy primary-key scan path and uses only the flat format for all queries. This cleanup drops approximately 1,800 lines of unused code from the query execution pipeline.
db#7989feat(cli): add metadata put key and table commands
The GreptimeDB CLI now supports writing metadata throughmetadata putcommands for direct key-value operations and table-specific updates. Users can pipe JSON payloads via\-\-value\-stdinto update table info and routes without shell escaping issues.
db#7972feat: support prefiltering any columns in flat format
Previously, parquet prefiltering only worked on primary key columns through encoded key decoding. Prefiltering now supports all column types (tags, fields, timestamps) with dedicated execution paths for simple predicates and complex expressions likeINandBETWEEN, delivering 4.5x faster performance on TSBS cpu-max-all queries.
db#8019fix: window sort off by one precision TimeRange&better alias track
Window sort optimization now recognizes aliased and wrapped time-index expressions likeSELECT ts AS timestamp \.\.\. ORDER BY timestampandSELECT to\_timestamp\_millis\(ts\) \.\.\. ORDER BY ts, so these queries use the faster windowed sort execution path instead of falling back to regular sorting. Precision conversion at partition boundaries is also fixed to prevent incorrect row slicing when timestamp units change.
Good First Issue
Issue#7755Feature request: Support EKS Pod Identity / ECS container credentials endpoint for S3 object storage
Update OpenDAL dependency to version that includes reqsign >=0.18.1 to support AWS container credentials endpoint for EKS Pod Identity and ECS task roles.
- Keywords: Storage, Dependencies
- Difficulty: Easy
Issue#7987feat: add flow_statistics system table and SHOW FLOW STATUS for flow runtime observability
Add a system table calledflow\_statisticsand aSHOW FLOW STATUSSQL command to display flow runtime information like start time, uptime, processed data volume, and recent errors.
- Keywords: SQL, Observability
- Difficulty: Medium
Similar Articles
@Greptime: GreptimeDB v1.1.0 is out PromQL rate/increase up to 97% faster, 20–40% lower query time overall Up to 4.5x faster on TS…
GreptimeDB v1.1.0 is released, offering up to 97% faster PromQL queries, 20-40% lower overall query times, and up to 4.5x improvement on TSBS scan-heavy queries, along with online repartitioning for existing tables.
@Greptime: DataFusion shipped dynamic filter pushdown upstream last September. GreptimeDB v1.0 wires it into the Mito scan layer. …
GreptimeDB v1.0 integrates DataFusion's dynamic filter pushdown to accelerate TopK queries by pushing runtime bounds to the scan layer, reducing query time from 29 seconds to 0.21 seconds on a 5B-row trace table.
@Greptime: We refreshed our deep-dive on Mito2, the storage engine inside GreptimeDB. LSM-tree write path. Columnar Parquet SSTs. …
GreptimeDB's Mito2 storage engine uses an LSM-tree design with columnar Parquet SSTs, three-level scan pruning, and TWCS compaction. The blog post provides a full walkthrough of its architecture.
@Greptime: GreptimeDB v1.1: you no longer have to lock in a table's partition layout when you create it. Before, only tables creat…
GreptimeDB v1.1 introduces online repartitioning for existing tables, incremental Flow reads, a semantic layer for LLMs, and stability improvements.
@Greptime: trace_id is high-cardinality — so Xiaomi's smart factory team didn't reach for an inverted index. They put a Bloom skip…
Xiaomi's smart factory replaced Loki with GreptimeDB for log storage, handling billions of rows per month with tailored indexing: Bloom skipping for high-cardinality trace_id, inverted index for low-cardinality fields, and fulltext search on message bodies.