Re: Poor Load Balancer performance

[Eric Covener <covener@xxxxxxxxx>]

On Thu, May 27, 2021 at 6:22 AM Marc Serra <mserra@xxxxxxxxx> wrote:

I got better performance without the load balancer.

 

Results when I run 'ab  -k -n 10000 -c 1000 http://vm_host_ip_address:8010/' with no balancer...

 Requests per second:    416.16 [#/sec] (mean)

 Transfer rate:          35391.87 [Kbytes/sec] received

 

Results when I run 'ab  -k -n 10000 -c 1000 http://vm_host_ip_address:8010/' with balancer configured...

 Requests per second:    644.04 [#/sec] (mean)

 Transfer rate:          56155.42 [Kbytes/sec] received

It doesn't look like the no-proxy case did better.  Which metric were you looking at?

+ a few cautions:

- If you aren't taxing the system beyond what a single backend could handle, it can easily be slower by adding a proxy.

- A layer 7 proxy can easily be more overhead than a basic VIP / LB / IP sprayer if there's nothing actually being offloaded in the proxy.