Live data from Hacker News

Viewing profile — jvanlightly

jvanlightly

HN member
Joined
Mon, May 15, 2023, 4:19 PM UTC
HN karma
23
Public activity
7 items

About jvanlightly

Distributed systems engineer. Formerly of RabbitMQ, Apache Pulsar and Apache BookKeeper (BK committer). Working at Confluent on Apache Kafka and cloud service.

Recent public activity

  1. comment
    Comment #38675785

    Author here: Regarding point 3, it was my understanding that inserts are synchronous but updates may be asynchronous. Is that the case?

  2. comment
    Comment #35964218

    Protocol Aware Recovery is really needed if you want Raft to tolerate disk corruption. https://www.usenix.org/conference/fast18/presentation/alagap...

  3. comment
    Comment #35954258

    These instances can manage up disk throughput up to 2 GB/s (400K IOPS) and network throughout of 25gbps or ~3.1 GB/s. There are so many dimensions, with configurations, CPU archite…

  4. comment
    Comment #35953682

    It's a common misconception about Kafka and fsyncs. But the Kafka replication protocol has a recovery mechanism, much in the same way that Viewstamped Replication Revisited does (e…

  5. comment
    Comment #35951113

    Well, that just isn't accurate really. Kafka would need simulteanous VM failure across all AZs. That just doesn't happen in the real world often enough to worry about. It has never…

  6. comment
    Comment #35950910

    Author here. Anyone can run these tests. It's available for anyone to run and check my results.

  7. comment
    Comment #35950689

    Author here. Yes both Kafka and Redpanda were deployed on identical hardware: three i3en.6xlarge.