Jay Kreps

Most-linked posts?

1. Getting real about distributed system reliability
   5 people · 6 mentions · first linked 2012-03-19
2. A Few Notes on Kafka and Jepsen
   3 people · 4 mentions · first linked 2014-03-13
3. Concurrency is not about programming languages anymore
   2 people · 2 mentions · first linked 2014-06-30
4. SSDs and distributed data systems
   2 people · 2 mentions · first linked 2012-06-04

What Hacker News says?

1. bogomipz · 2017-05-31Recommends

   This is not a nitpick - the fact that SSDs do not have seek times is an important distinction when discussing storage engines. You might want to read the following by Jay Kreps one of the authors of Kafka, Voldermort and Samza: "SSDs and Distributed Data Systems" >"On traditional hard drives the trade-off between in-place and log-structured storage is a bit of a wash. Write performance for log-structured storage is…

   Comment linking /post/24415262152/ssds-and-distributed-data-systems

   on “Damn Cool Algorithms: Log structured storage (2009)”
2. sacheendra · 2019-08-04

   Submitted Getting Real About Distributed System Reliability (2012) as a story · 152 points

   HN discussion
3. boredandroid · 2014-03-13

   I am one of the Kafka committers. I had posted some notes on the Jepsen post which I think may give a more complete picture: http://blog.empathybox.com/post/62279088548/a-few-notes-on-k...

   Comment linking /post/62279088548/a-few-notes-on-kafka-and-jepsen

   on “Apache Kafka – Publish-subscribe messaging rethought as a distributed commit log”
4. thebootstrapper · 2012-03-15

   Submitted Scala Macros: “Oh God Why?” as a story · 121 points

   HN discussion
5. tzhenghao · 2019-01-16

   For some reason, this reminds me of Jay's piece on reliability of distributed systems [1] [1] - http://blog.empathybox.com/post/19574936361/getting-real-abo...

   Comment linking /post/19574936361/getting-real-about-distributed-system-reliability

   on “On Infrastructure at Scale: A Cascading Failure of Distributed Systems”
6. boredandroid · 2012-06-04

   Submitted SSDs and distributed data systems as a story · 37 points

   HN discussion
7. boredandroid · 2016-01-26

   Thanks for clarifying! I think there are two separate things: 1. Is there a principled notion of when a write is "committed" and a leadership election algorithm that works with this to ensure committed writes aren't lost as long as the failure criteria are met? This has been true since we added replication to Kafka. 2. The second is what is the recovery behavior when you have no available replicas. Previously we wou…

   Comment linking /post/62279088548/a-few-notes-on-kafka-and-jepsen

   on “Kudu as a More Flexible and Available Kafka-Style Queue”
8. boredandroid · 2012-03-19

   Submitted Getting real about distributed system reliability as a story · 25 points

   HN discussion
9. noelwelsh · 2014-11-11

   I think you are vastly overstating the issue. The issue in the Jepsen post ( http://aphyr.com/posts/293-call-me-maybe-kafka ) requires a complex failure case to cause data loss. For most people using Kafka, a little data loss very infrequently, while still accepting writes, is acceptable. The alternative is to refuse all writes till the system is back. This in unacceptable for typical use cases. (See http://blog.emp…

   Comment linking /post/62279088548/a-few-notes-on-kafka-and-jepsen

   on “Infrastructure for Data Streams”
10. dedalus · 2015-04-25

    Submitted Getting Real About Distributed System Reliability (2012) as a story · 7 points

    HN discussion
11. willvarfar · 2012-03-31

    As I remember it: The journaling is only fsynced every so-often - its not like it magically gives you anything like the D in ACID. This leaves you relying on replication for durability. And everyone has problems when they lose one of the cluster. Luckily it wasn't the lot: http://blog.empathybox.com/post/19574936361/getting-real-abo... I would love to be corrected; we'd all sleep easier.

    Comment linking /post/19574936361/getting-real-about-distributed-system-reliability

    on “Retrospective from Postmark on outages (MongoDB)”
12. boredandroid · 2013-01-13

    Submitted How testing could transform higher education as a story · 5 points

    HN discussion
13. willvarfar · 2012-03-23

    What do they use for hosting? As Jay Kreps (works at LinkedIn, created Voldemort DB) would wonder, they went from a service managed by Amazon to what? http://blog.empathybox.com/post/19574936361/getting-real-abo...

    Comment linking /post/19574936361/getting-real-about-distributed-system-reliability

    on “Why we chose Mongo + Hypertable”
14. rubikscube · 2014-10-20

    Submitted Concurrency is not a language thing anymore as a story · 2 points

    HN discussion
15. boredandroid · 2014-06-30

    Submitted Concurrency is not about programming languages anymore as a story · 2 points

    HN discussion
16. boredandroid · 2012-03-05

    Submitted Does off-the-shelf machine learning need a better benchmark? as a story · 2 points

    HN discussion
17. letientai299 · 2021-01-30

    Submitted A Few Notes on Kafka and Jepsen (2013) as a story · 1 points

    HN discussion
18. Dawny33 · 2016-10-12

    Submitted Getting Real About Distributed System Reliability as a story · 1 points

    HN discussion
19. mathgenius · 2015-06-25

    Submitted Does off-the-shelf machine learning need a benchmark? (2012) as a story · 1 points

    HN discussion
20. SanderMak · 2014-04-29

    Submitted A Few Notes on Kafka and Jepsen as a story · 1 points

    HN discussion

Search all of HN for blog.empathybox.com

Linked by the same people?

• JJeremy Kunjeremykun.com
• AAdrian Colyerblog.acolyer.org
• BBrendan Greggbrendangregg.com
• JJulia Evansjvns.ca
• TTroy Hunttroyhunt.com
• BBruce Schneierschneier.com