Benchmark for Stateful Functions

classic Classic list List threaded Threaded
3 messages Options
Reply | Threaded
Open this post in threaded view
|

Benchmark for Stateful Functions

Omid Bakhshandeh
Hi,

I was wondering if there is any place that has information about Stateful Functions performance (e.g. throughput, delay of messaging)?

Best,
--
-------------------------------------------
Omid
Reply | Threaded
Open this post in threaded view
|

Re: Benchmark for Stateful Functions

Tzu-Li (Gordon) Tai
Hi Omid,

There currently aren't any benchmarks that I know of for Stateful Functions.

However, Stateful Functions applications run on top of Apache Flink and
therefore share the same network stack / runtime. So, if throughput and
latency is your only concern, you should be able carry over any results from
Flink.

What in particular are you interested in?
As for any benchmark, it'd only be useful with a specific use case /
scenario in mind.
It would be interesting to hear what you have in mind.

Cheers,
Gordon



--
Sent from: http://apache-flink-user-mailing-list-archive.2336050.n4.nabble.com/
Reply | Threaded
Open this post in threaded view
|

Re: Benchmark for Stateful Functions

Omid Bakhshandeh
Hi Tzu-Li,

Thanks for the answer.

I am looking into the latency of a loopback given #number of functions in the system. More precisely the loopback time on f1 calls a random function f_i and f_i  change its state and reply back. Also, it would be nice to see the latency on ingress and egress. One parameter to change could be the number and the type of functions in the system.

Thanks,
--Omid


On Mon, May 4, 2020 at 2:29 AM Tzu-Li (Gordon) Tai <[hidden email]> wrote:
Hi Omid,

There currently aren't any benchmarks that I know of for Stateful Functions.

However, Stateful Functions applications run on top of Apache Flink and
therefore share the same network stack / runtime. So, if throughput and
latency is your only concern, you should be able carry over any results from
Flink.

What in particular are you interested in?
As for any benchmark, it'd only be useful with a specific use case /
scenario in mind.
It would be interesting to hear what you have in mind.

Cheers,
Gordon



--
Sent from: http://apache-flink-user-mailing-list-archive.2336050.n4.nabble.com/


--
-------------------------------------------
Omid