Little peak time latency humps

[#1]

I can't help, unfortunately: TBB BQM says,

Quote

The current beta has reached it's monitor limit, so you will not be able to add this monitor, please bear with us as we add more capacity to this amazing new tool!

Too many PlusNet members too obsessed?!   

[#2]

Looking at my graph before, although not as noticeable you can definitely still see a slight increase at 9.30pm-11pm.
I also pinged the bbc at 11pm and got a few 110ms bursts.

[#3]

Purleigh:  I think your graph shows stuff at your exchange/line.  It looks very different to other graphs we see.
The results actually seem encouraging:
This is Bob's fibre line on PCL-AG01. (sadly a live graph, not a snapshot)

No decent hump.
This is Bob's 2nd fibre line which we used for testing and was on ptn-ag02

Big hump.  This line is never used as well.

[#4]

WWWombat on PCL-AG02

[#5]

kmilburn on PCL-AG01

[#6]

Looking at mine now over the course of the evening, it does look pretty good actually.  Will be interesting to see how it performs over the course of the week.

[#7]

Here is my graph for this evening (Tuesday 13th August) on gateway 'PCL-AG02' -

Ignore the red burst around 09:20, as that was me repeatedly gateway hopping to get onto 'PCL-AG02'.
The TBB plot looks much quieter than yesterdays graph on 'PCL-AG01' (see Reply #59)

The SamKnows latency graph is much better too, without the large latency peak that occurred yesterday.
I have been doing similar light internet browsing all evening, as I did yesterday.
So I don't know whether the graphs are different because -
   1)  I'm on a different gateway.
   2)  The 'fix' on 'PCL-AG02' works better than the 'fix' on 'PCL-AG01'.
   3)  Whether latency or congestion on my local exchange is less tonight.
   4)  Whether the BT backbone is differently loaded tonight.
   5)  Maybe the evening 'hump' is truly random, and it just happens to be one of the better nights !
My only conclusion so far is that the 'fix' on 'PCL-AG01' didn't eliminate the evening 'hump' for me.
I will stay on gateway 'PCL-AG02' and see whether I get another quiet graph tomorrow.

[#8]

Yeah, it's interesting.  It's missing from Bob, kmilburn, wwwombat's graphs again.  You definitely have the hump still on your graphs, but it looks far noisier, and different, possibly to do with 20CN exchange kit?
The fix applied is the same across 01 and 02 and the graphs for the guys above cover both gateways.

[#9]

Quote from: Kelly

The fix applied is the same across 01 and 02 and the graphs for the guys above cover both gateways.

That is NOT what 'dave' said 

Quote from: dave

We have a theory as to what's causing the problem based on some testing we've done in the labs and want to try out two possible fixes. So next Monday we will be making some changes to PCL-AG01 and PCL-AG02 to see if we can improve this. Each one will have a different fix on it, like I say we've got 2 possible solutions so we want to try them both out.

[#10]

Oh!  You're totally right.  Two different approaches.  Ignore me! 

[#11]

Duly ignored 
Stay awake at the back, and try and keep up with the rest of the class ! 

[#12]

Switched to AG01 last night.
Can still see spikes at 9-10pm:

Ignore the two red lines which were router resets. Meant to be switched to 3db SNR but seems it never happened.

[#13]

Packet loss for 13th...

[#14]

Which end point you on?

[#15]

I don't know if what I'm seeing is any way related to the testing but this week so far the jitter levels have been evident every night since Monday so far, and tonight or should i say this morning latency is still fluctuating, what's going on?  Im on PCL AG -07  a check of the online usage tool show that it currently has the most customers connected