[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: Safe read request timeout value


Depends on how much latency can your app tolerate.  You always want to make sure that client side timeouts are set greater than server side timeout value. So that client is n't timing out while server is still serving the requests.

You might want to start with defaults and try bumping up.  Something like 2000 ( 2 ms) 


On Fri, Jun 15, 2018 at 4:31 AM, Vsevolod Filaretov <vsfilaretov@xxxxxxxxx> wrote:
Good time of day everyone,

I've got a question on timeouts setting practice.

I've got a 4-node cluster with only a handful of users, constant data inserts and very large partitions (up to 450+mb, which is 4 times larger than general cassandra manuals recommend). Data is held on hdd.

What are general practices on read request timeout settings?

How large is my theoretical maximum of server-side user read timeout which does not compromise cluster availability, prioritizing inserts stability?