Redpanda is a streaming data platform for developers. Kafka API compatible. 10x faster. No ZooKeeper. No JVM!
fetch_read_strategy
cluster config property to select between polling
and non-polling
fetch implementations. Uses the non-polling
fetch implementation by default. by @StephanDollberg in #18176remote.read
is not enabled. by @WillemKauf in #18159
_topic_node_index
to avoid oversized alloc by @ballard26rpk container start
: You can now select the subnet and gateway to create your 'redpanda' network. by @r-vasquez in #18151
'retention_duration' = -1
in a topic_manifest.json file as infinite time retention by @andijcr in #18243
Full Changelog: https://github.com/redpanda-data/redpanda/compare/v24.1.1...v24.1.2
'retention_duration' = -1
in a topic_manifest.json file as infinite time retention by @andijcr in #18242
Full Changelog: https://github.com/redpanda-data/redpanda/compare/v23.3.14...v23.3.15
Full Changelog: https://github.com/redpanda-data/redpanda/compare/v23.2.28...v23.2.29
rpk cluster partitions list
now supports filtering with broker IDs. by @daisukebe in [#18104](https://github.com/redpanda-data/ redpanda/pull/18104)remote.read
is not enabled. by @WillemKauf in #18156
Full Changelog: https://github.com/redpanda-data/redpanda/compare/v23.3.13...v23.3.14
kafka_latency_fetch_latency
metric measures to be the time the first fetch_ntps_in_parallel
takes. by @ ballard26 in #17977
Full Changelog: https://github.com/redpanda-data/redpanda/compare/v23.3.12...v23.3.13
1MiB
to 128KiB
to reduce occurrences of memory allocation failures by @michael-redpanda in #17924
Adds a new public metric redpanda_raft_recovery_partition_movement_consumed_bandwidth that tracks how much bandwidth is currently in use for raft recovery. This helps tune raft_learner_recovery_rate. by @bharathv in #17217
PR #17397 [v23.2.x] k/group: recover leader epoch on leader change by @nvartolomei * PR #17448 [v23.2.x] tx: fix param ordering in log statement by @nvartolomei
PR #17577 [v23.2.x] c/topics_frontend: break the loop when dispatching to current leader by @mmaslankaprv
Full Changelog: https://github.com/redpanda-data/redpanda/compare/v23.2.27...v23.2.28
rpk transform logs
waits for records without the --follow
flag specified. by @rockwotj in #17837
rpk transform init --install-deps
so that an explicit true value is not needed. by @rockwotj in [#17867](https:// github.com/redpanda-data/redpanda/pull/17867)1MiB
to 128KiB
to reduce occurrences of memory allocation failures by @michael-redpanda in #17923
rpk transform logs
by @rockwotj in [#17835](https://github.com/redpanda-data/ redpanda/pull/17835)Full Changelog: https://github.com/redpanda-data/redpanda/compare/v23.3.11...v23.3.12
get_allocator()
method to fragmented vector by @mmaslankaprvnode_hash_map
caused oversized allocations in cluster module by @mmaslankaprvraft:: replicate_batcher
by @mmaslankaprvFull Changelog: https://github.com/redpanda-data/redpanda/compare/v23.3.10...v23.3.11
rpk transform
against Redpanda cloud clusters. by @r-vasquez in #17252
Full Changelog: https://github.com/redpanda-data/redpanda/compare/v23.3.9...v23.3.10