New on LowEndTalk? Please Register and read our Community Rules.
All new Registrations are manually reviewed and approved, so a short delay after registration may occur before your account becomes active.
All new Registrations are manually reviewed and approved, so a short delay after registration may occur before your account becomes active.
Jitter example, problem or not?
Hi all,
I bought myself a new server during BF and moved my stuff over to it. From the get go I noticed slow internet connectivity every now and then, but I couldn't figure out why. I started smokepinging this server from another BF deal and the result is this (see attached image). Now I'm a bit uncertain if this is a problem or not given the scale on the left axis. My other servers have none of these grey bars.
Curious about your opinions on this?!
Thanks!
Comments
It looks like (at first glance) saturation but you need a lot more data points than a single target smoke ping.
Any suggestions?
Maybe packet losses are the problem.
The packet loss will make it feel a lot worse yes, however there's the problem of ICMP packets simply could be dropped for rate limiting reasons(can prevent floods). Because of how consistent that is, I'm convinced this is in place(I could be wrong, we don't know who this provider is or their setup).
I'm more concerned about the spikes in RTT along side with the jitter but that's hard to prove the cause without packet captures(which is an unreasonable ask at the moment).
I would do MTRs bidirectional to yourself from the server and then to the server from yourself. See if there's any loss along the path and to the end point, and then back again.
Then when the fault happens, trying doing an extended iperf3 test. If you see inconsistencies then you can take all of that evidence and go "hey there's something wrong here."
See if you can also replicate this from an alternative network so you rule out it's not your own setup at home.
I will try and do that