network bottleneck
airazabal
Newbie

I am experiencing a bottleneck between my server on the cloud and my local machine...

this is the result from an MTR issued from my cloud server:

HOST: TSSZ001                                    Loss%   Snt   Last   Avg  Best  Wrst StDev

  1.|-- hosted.by.leaseweb.com            0.0%   100    2.7   2.4   0.8   7.5   1.4

  2.|-- 108.59.15.23                                 0.0%   100    0.3   0.4   0.2   2.4   0.2

  3.|-- be2.cr2.wdc1.leaseweb.net       0.0%   100    0.8   0.9   0.6   5.3   0.4

  4.|-- ix-9-3-1-0.tcore1.AEQ-Ash         0.0%   100    1.1   2.0   1.0  51.0   5.9

  5.|-- if-10-3.tcore1.DT8-Dallas           0.0%   100   45.9  46.1  45.7  49.4   0.5

  6.|-- 66.110.56.18                                 0.0%   100   40.4  42.5  40.2 104.7   8.8

  7.|-- P0-4-0-0.PHLAPA-LCR-22.ve   0.0%   100   55.7  55.0  52.7  66.8   2.0

  8.|-- ???                                                 100.0   100    0.0   0.0   0.0   0.0   0.0

  9.|-- pool-{edited for privacy}.phlap      0.0%   100   59.6  59.5  58.0  67.2   1.0

 

Notice that beween #7 an #9 there is 100 packet loss. Can someone from your network team please look into this?

Regards,

# 7 ip = 

130.81.22.61

#9 ip = 

{edited for privacy}

Alex

0 Likes
Re: network bottleneck
eljefe2
Master - Level 1

First, let me say that you've come to a peer-to-peer forum.....users trying to help other users.  This is not Verizon tech support.

Having said that, are you connected to the Internet via a FiOS connection?  It looks like that traceroute is from your leaseweb server, not to it.

And having said that....those reports of 100% packet loss simply mean that those servers don't accept ping packets.  The fact that the average latency to the last step, #9, averages 58.0 is a pretty decent connection.

   

Re: network bottleneck
airazabal
Newbie

yes - I realize this a peer -2 -peer forum - I did not expect verizon to be honest regarding blocking issues. So you don't think the 100 is "real" - just a lack of ping support. OK. So what could be the issue then? I only get 128 kbit downloads from this server...and yes I did the mtr from the server down, but I've done it the other way and I saw no issues either - what would explain the throttleing ?

0 Likes
Re: network bottleneck
eljefe2
Master - Level 1

It's common to see those 100% loss reports from servers that don't reply to ping requests.  I have my Actiontec server set the same way...not to reply to pings, so if you ping my WAN IP you'd get the same result, yet you could connect to me via Skype or any of many other methods.  What matters, as the bottom line, is the average latency is at the end of the traceroute.

I've been a FiOS user for a number of years and I've never seen any evidence of Verizon blocking or throttling my service.

If you're getting the speeds you're paying for when you run a test at www.speedtest.net, I would suggest you ask leaseweb's tech support why your connection to their server is slow and see if they can help.

0 Likes
Re: network bottleneck
Hubrisnxs
Legend

Spotting The Fake Latency

If there is an actual issue, the latency will continue or
increase for all future hops:

If it's a time out, then it will also continue to all hops after.  If it's a true time out then you have to ask, how does the packet reach the next destination?

Latency spikes in the middle of a traceroute mean
absolutely nothing if they do not continue forward.
• At worst it could be the result of an asymmetric path.
• But it is probably an artificial rate-limit or prioritization issue.
• By definition, if regularly forwarded packets are being affected
you should see the issue persist on all future hops.

0 Likes