Re: [PATCH 0/2] thread-pool: fix performance regression

[Lukáš Doktor]

Dne 06. 05. 22 v 20:55 Lukáš Doktor napsal(a):
> Hello Paolo, folks, I gave it a try (on top of the f9fc8932) and it's better 
> than the f9fc8932, better than the previous patch by Stefan, but still I'm 
> not reaching the performance of d7482ffe97 (before the f9fc8932 commit):
> 
> f9f    |  0.0 | -2.8 |  0.6
> stefan | -3.1 | -1.2 | -2.2
> paolo  |  5.3 |  5.4 |  7.1
> d74    |  7.2 |  9.1 |  8.2
> 
> Anyway it's definitely closer to the previous baseline (~-2%). Note I have 
> not tried other scenarios, just the 4K nbd writes on rotational disk. I'll 
> try running more throughout the night.
> 

I tried a couple of iterations of fio-nbd 4/64/256KB read/writes on a 
rotational disk and overall the latest fix results in a steady 2.5% throughput 
regression for the 4KiB writes. The remaining tested variants performed 
similarly. Please let me know if you want me to test the fio execution inside 
the guest as well or some other variants.

Regards,
Lukáš

OpenPGP_0x26B362E47FCF22C1.asc
Description: OpenPGP public key

OpenPGP_signature
Description: OpenPGP digital signature