Re: [vpp-dev] VPP load estimation

Thanks Ben for your reply. I found that we can get the VPP rate (size) information through vpp_get_stats function. /Joe -=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Reply Online (#18009): https://lists.fd.io/g/vpp-dev/message/18009 Mute This Topic: https://lis

Re: [vpp-dev] VPP load estimation

> I also have another question related to load estimation: we are using > VPP for NAT44 and we are seeing a significant number (like 1000 per > second) of congestion drops [...] > Are there some other statistics we could use > to understand if that is the case, or better ways to investigate this >

Re: [vpp-dev] VPP load estimation

Subject: Re: [vpp-dev] VPP load estimation Hi Ben, > Yes, it is the main way to quickly assess VPP load, see > https://fd.io/docs/vpp/master/troubleshooting/cpuusage.html#vpp-cpu-lo > ad My very crude rule-of-thumb looks like this (but your mileage may > vary): > - between 0 and

Re: [vpp-dev] VPP load estimation

Hi Ben, > Yes, it is the main way to quickly assess VPP load, see > https://fd.io/docs/vpp/master/troubleshooting/cpuusage.html#vpp-cpu-load > My very crude rule-of-thumb looks like this (but your mileage may > vary): > - between 0 and 50: VPP is not working too hard > - between 50 and 100: VPP

Re: [vpp-dev] VPP load estimation

> I read recently that VPP can work without DPDK (https://lists.fd.io/g/vpp- > dev/topic/25519273#10469 dev/topic/25519273#10469> ). > Does that mean the polling mode is not used in this scenario? VPP native drivers also use polling mode by default, however some of th

Re: [vpp-dev] VPP load estimation

Hi Ben, Thank you very much for your reply. I read recently that VPP can work without DPDK ( https://lists.fd.io/g/vpp- dev/topic/25519273#10469 ( https://lists.fd.io/g/vpp-dev/topic/25519273#10469 ) ). Does that mean the polling mode is not used in this scenario? and the VPP load can still be e

Re: [vpp-dev] VPP load estimation

Hi Joe, > I wonder if we can use the average VPP vector rate (size) per node to > estimate the load of a VPP instance. > More specifically, if this information can be used to determine whether > the VPP instance is overloaded (e.g., > the default max value of 255). Yes, it is the main way to quic

[vpp-dev] VPP load estimation

Hello everyone, I am pretty new to VPP. I know that the CPU utilisation of a VPP instance is always high due to the PMD. I wonder if we can use the average VPP vector rate (size) per node to estimate the load of a VPP instance. More specifically, if this information can be used to determine whet