TerrariumDB v8.0 introduces a new Storage Core Format (SCF4) with pluggable storage engines and execution-path isolation, alongside major SQL additions — DELETE, WITH, multi-JOINs, and TRUNCATE ALL.
Security is strengthened with TLS-secured gRPC by default, and observability is upgraded across metrics and logging. Operationally, v8.0 reduces ingest service CPU utylization, and speedup backups. Under the hood, you’ll see faster, more predictable query execution via refined thread-pooling and scheduler work, plus numerous fixes that improve SQL correctness, stabilize aggregator ↔ worker flows, and ensure cleaner shutdown behavior.
GROUP BY
and ORDER BY
interpreters to improve parallel processing.DELETE
statement — native row removal in the SQL layer.WITH
(CTE) support — richer query composition.
TRUNCATE ALL TABLES
— management command for bulk table truncation within a database.MYSQL_ACTIVE_CONNECTIONS
and new metrics for the aggregator/controller.ALTER USER
; test suites for user/role and privilege surfaces; SHOW ROLE EDGES
.RAND()
rewritten to be multi-thread friendly.default_storage_engine
system variable required by sql client connectivity.
GROUP BY
;*
schema expansion; CAST … AS CHAR
now copies by byte size;\[abc]
in LIKE
;
We delivered a brand-new storage layer with redesigned columnar files, custom vector encodings, and optimized dictionaries. This reduced disk usage by 20%, RAM by 31%, and lowered CPU load by ~30%, while also cutting query latencies significantly (up to 80% faster p50 under mixed workloads).
Columns now leverage specialized chunk types for repeated, sorted, and boolean values (dictionary, dChunks, vChunks). These optimizations enable more compact storage and faster access, paving the way for further file-level improvements.
A new execution model of thread pool architecture for intestion services, combined with SCF4, improved CPU efficiency. CPU reservations on ingestion service dropped by ~45%, raising utilization efficiency from 57% → 66% and directly reducing cluster operating costs.
TerrariumDB v8.0 introduces a new Storage Core Format (SCF4) with pluggable storage engines and execution-path isolation, alongside major SQL additions — DELETE, WITH, multi-JOINs, and TRUNCATE ALL.
Security is strengthened with TLS-secured gRPC by default, and observability is upgraded across metrics and logging. Operationally, v8.0 reduces ingest service CPU utylization, and speedup backups. Under the hood, you’ll see faster, more predictable query execution via refined thread-pooling and scheduler work, plus numerous fixes that improve SQL correctness, stabilize aggregator ↔ worker flows, and ensure cleaner shutdown behavior.
GROUP BY
and ORDER BY
interpreters to improve parallel processing.DELETE
statement — native row removal in the SQL layer.WITH
(CTE) support — richer query composition.
TRUNCATE ALL TABLES
— management command for bulk table truncation within a database.MYSQL_ACTIVE_CONNECTIONS
and new metrics for the aggregator/controller.ALTER USER
; test suites for user/role and privilege surfaces; SHOW ROLE EDGES
.RAND()
rewritten to be multi-thread friendly.default_storage_engine
system variable required by sql client connectivity.
GROUP BY
;*
schema expansion; CAST … AS CHAR
now copies by byte size;\[abc]
in LIKE
;
We delivered a brand-new storage layer with redesigned columnar files, custom vector encodings, and optimized dictionaries. This reduced disk usage by 20%, RAM by 31%, and lowered CPU load by ~30%, while also cutting query latencies significantly (up to 80% faster p50 under mixed workloads).
Columns now leverage specialized chunk types for repeated, sorted, and boolean values (dictionary, dChunks, vChunks). These optimizations enable more compact storage and faster access, paving the way for further file-level improvements.
A new execution model of thread pool architecture for intestion services, combined with SCF4, improved CPU efficiency. CPU reservations on ingestion service dropped by ~45%, raising utilization efficiency from 57% → 66% and directly reducing cluster operating costs.