This page is meant as a template for writing a KIP. To create a KIP choose Tools->Copy on this page and modify with your content and replace the heading with the next KIP number and a description of your issue. Replace anything in italics with your own description.
Current state: Under Discussion
Discussion thread: here [Change the link from the KIP proposal email archive to your own email thread]
JIRA: here [Change the link from KAFKA-1 to your own ticket]
Please keep the discussion on the mailing list rather than commenting on the wiki (wiki discussions get unwieldy fast).
While using "acks=-1", we found the P999 latency is very spiky. Since the produce request can only be acknowledged after all of the "insync.replicas" committed the message, the produce request latency is determined by the slowest replica inside "insync.replicas". In the production environment, we usually set "replica.lag.time.max.ms" to the order of 10 seconds (to protect frequent ISR shrink and expand), and producer P999 can jump to the value of "replica.lag.time.max.ms" even without any failures or retries.
We already have pretty stable and low P99 latency, it will definitely make Kafka more suitable for a much wider audience (even in the critical write path) if we can have the similar guarantees for P999.
There will be a new config inside clients/producer called "quorum.required.acks".
I totally understand in the early days, we have the support to specify the "request.required.acks" or "acks=2" on the producer side. We got rid of these supports since it was misleading and can't guarantee there is no data loss in all of the scenarios (and we introduced the "insync.replicas"). I am NOT against any of today's behavior (actually, it is quite clean and straightforward), I am proposing to add an alternative to our replication semantic, which can be easily enabled/disabled, and without any impact on the existing code path.
The proposed changes here will contain two separate parts. 1: introduce a similar config on the producer side as the "request.required.acks"; however, with more strict requirements. 2: improve the new leader election process to achieve the same level of data durability as of today's "insync.replicas".
The following is the P999 for the replicas=4 and quorum.required.acks=2 configs, 4000QPS with the 2KB payload for 24 hours. (I deployed with the modified version supporting quorum.required.ack based on 0.10.2.1)
I got some recommendations from the offline discussions. One of them is to set replicas=2 and ack=-1, this will only wait 1 follower fetch the pending message; however, from the experiment, the P999 is still very spiky.
The following is the P999 for the replicas=2 and ack=-1 configs, 1000QPS with the 2KB payload for only 2 hours.