-
As described [here](https://docs.confluent.io/kafka/design/log_compaction.html), log compaction could be a new kind of retention policy, allowing to override (and even delete for the null/empty payloa…
spetz updated
10 months ago
-
When aborted Scavenge occurs (in a middle of Scavnge, no free space left in either Nursery or Tenure to move objects to) we handle it differently for:
1) STW Scavenge, backout the work that Scaveng…
-
In CockroachDB multi-store deployments, especially with large numbers of stores (8 or more), the CPU consumed by compactions can be significant. We do need a per store compaction concurrency limit, si…
-
#### Background
Typically compactor in system is woken up by the compaction_task。One compaction_task can only be triggered automatically based on impletemented compaction policy. (e.g. l0_file_numb…
-
Recently we have witnessed multiple issues related to compaction/compactor:
- #10209
- #10161
- #10538
- #10215
- #10240
These issues are related to excessive compaction load, compactor fail…
-
## Problem
Redpanda currently has some limitations in its compaction:
* The set of keys considered during compaction are constrained to both (a) a single term and (b) single segment (or combined adj…
-
These are most likely bottlenecked on Pageserver ingestion (needs verification), in concert with S3 uploads.
Typical workload: sequential bulk inserts, bulk updates (to trigger compaction).
See also…
-
* Create 3 node cluster with rf=3.
* Reaching 90% disk usage.
* Keep it running for an hour, in-between we should clean up some data by dropping tables and keyspace.
* Wait for compaction
-
For encodings like fsst, we store the decoding meta data in `PageInfo.encoding`, however, we may expect many decoding meta data in one page after compaction
-
CassandraJournalStatements.scala
```scala
def selectHighestSequenceNr =
s"""
SELECT sequence_nr FROM $tableName WHERE
persistence_id = ? AND
partition_nr = ?
O…