Hub 3 / Compal CH7465-LG (TG2492LG) and CGNV4 Latency Cause

[Datalink]

Good Day Ladies and Gentlemen,

Greetings from the other side of the pond, so to speak.  Over the last few weeks I've been perusing various user forums across North America and Europe for issues related to Intel Puma 6 modem latency.  Of those forums, your Hub 3 stands out as yet another Puma 6 based modem where users see continuous latency no matter what site is used or what online game is played. Considering all of the problems that are on the go, the following information should be of interest to all Hub 3, Compal CH7465-LG and Hitron CGNV4 modem users.  There is much more to post regarding this, so this is a start, to alert VM users as to the real cause of the latency and hopefully engage the VM engineering staff, via the forum staff, with Arris.  I am surprised to see that there has been no mention on this board of users from other ISPs who are suffering the exact same issues with their modems, so, this may come as a surprise to some, and possibly old news to others.

So, the short story ........

The Hub 3 / Compal CH7465-LG (TG2492LG) & Hiton CGNV4 modems are Intel Puma 6 / 6 Media Gateway (MG) based modems.  These modems exhibit high latency to the modem and high latency thru the modem.  The latency affects all IPV4 and IPV6 protocols, so it will be seen on every internet application and game.  The basic cause is the processing of the data packets thru a CPU software based process instead of thru the hardware processor / accelerator.  It appears that a higher priority task runs periodically, causing the packet processing to halt, and then resume.  This is observed as latency in applications and in ping tests to the modem and beyond.  For the last several weeks, Hitron, along with Intel and Rogers Communications in Canada have been addressing the latency issue within the Hitron CGNxxx series modems.  To date, only the IPV4 ICMP latency has been resolved.  Although this is only one protocol, it does show that a Puma 6MG modem is capable of using the hardware processor / accelerator with good results.  Currently Rogers is waiting for further firmware updates from Hitron which should include an expanded list of resolved protocol latency issues.  For Arris modems, "Netdog" an Arris engineer indicated last week that Arris was onboard to address the issue for the Arris SB6190 modem.  That should be considered as good news for any Arris modem (read Hub 3) user as Arris should be able to port those changes over to other Puma 6/6MG modems fairly quickly.  This is not a trivial exercise and will probably take several weeks to accomplish.  Note that there is no guarantee at this point that it is possible to shift all packet processing to the hardware processor / accelerator without suffering from any packet loss side effects.  Time will tell if all of the technical issues can be resolved with the current hardware included in the Puma 6/6MG chipset.  Last night, Netdog loaded beta firmware on selected test modems on the Comcast Communications network.  As this was only done last night, it's too soon to tell what this version resolves and if it was successful or not.  Netdog has contacts with staff at Comcast, Rogers, Charter and Cox Communications to fan out beta versions and modifications for testing.  I'd say its time to add Virgin Media and/or Liberty Global to that group as well.

Recent activity:

Approx three weeks ago a DSLReports user, xymox1 started a thread where he reported high latency to an Arris SB6190 and illustrated that with numerous MultiPing plots.  This is the same latency that I and other users with Rogers communications have been dealing with for months so it came as no surprise.  As well as reporting via that thread, xymox1 took it upon himself to email several staff members at Arris, Intel, Cablelabs and others.  The result of that campaign was Netdog's announcement, last week, that Arris was fully engaged at resolving the issue.  That has led to last nights release of beta firmware, although as I indicated its too early to determine what the beta firmware resolves, if anything.

The original thread that xymox1 started is here:

https://www.dslreports.com/forum/r31079834-ALL-SB6190-is-a-terrible-modem-Intel-Puma-6-MaxLinear-mis...

Yesterday, DSLReports issued a news story covering the thread:

https://www.dslreports.com/shownews/The-Arris-SB6190-Modem-Puma-6-Chipset-Have-Some-Major-Issues-138...

Today, Arris responded:

https://www.dslreports.com/shownews/Arris-Tells-us-Its-Working-With-Intel-on-SB6190-Puma6-Problems-1...

That response was also picked by Multichannel.com

http://www.multichannel.com/news/distribution/intel-arris-working-firmware-fix-sb6190-modem/409379

This is more news likely to appear in the next few days as additional tech and news staff pick up on this issue.

Hub 3 observations:

Like many others using a Puma 6/6MG modem, Hub 3 users are experiencing latency when they ping the modem, or ping a target outside of the home, game online or use low latency applications.  The common misconception is that this is Buffer Bloat. It's not. Its most likely a case of the packet processing stopping while the CPU processes a higher priority task.  The packet processing is done via the CPU no matter what mode the modem is operating in, modem mode or router mode and no matter what IPV4 or IPV6 protocol is used.  Normally, the latency is just that, latency.  The exception are UDP packets. In this case there is latency and packet loss.  The result of that is delayed and failed DNS lookups, and poor game performance for games that use UDP for player/server comms or player/player comms.

Can this be fixed?

So far, it appears that the answer is yes.  Rogers Communications issued beta firmware to a small group of test modems in October.  This version shifted the IPV4 ICMP processing from the CPU to the hardware processor / accelerator, resulting in greatly improved performance in ping latency.  At the present time we are waiting for the next version firmware which should shift other protocols over to the hardware processor / accelerator.  That can be seen in the following post:

http://communityforums.rogers.com/t5/forums/forumtopicpage/board-id/Getting_connected/message-id/369...

The details and results of last nights beta release to the Comcast group have yet to be seen.

At this point there is enough reading to keep most staff and users busy.  My intention is to post some of the history leading up to this point and instructions on how to detect the latency and packet loss.  This is not thru the use of a BQM.  I had hoped to post this all at once but events are moving much faster than I had thought they would.  For now this should suffice to get the ball rolling.

Below is a link to a post with a couple of HrPing plots from my 32 channel modem to the connected CMTS.  This shows the latency that is observed and reflects what others have posted in this forum using Pingplotter and HrPing.

https://www.dslreports.com/forum/r31106550-

HrPing is one of the freebie applications that can be used to monitor the latency to and thru the modem. 

Pingplots with Pingplotter which show the latency from my modem to the CMTS can be found in the first two to three rows of my online image library at Rogers Communications, located below.  They are essentially what the BQM would look like if you were able to zoom into the plot to the point where you could see the individual ping spikes.  Those ping spikes are common to Puma 6 and Puma 6MG modems.

http://communityforums.rogers.com/t5/media/gallerypage/user-id/829158

 [MOD EDIT: Subject heading changed to assist community]

[yabba]

---

wrote:

It isn't a single lost packet, it's eight-twelve entire frames that we're talking about.  I'd agree that a few lost packets are neither here nor there, but when you're have a PC trying top catch up on ten complete screen refreshes, that's rather a lot of data in a fast moving game.  There's still only the two options I've indicated - the PC has to make up and blend two different images, or there's going to be discontinuity on the screen.

---

No there is not any "lost frames". Your screen might run at 120hz, game servers do not.

The client renders a continuous smooth, interpolated image. If there's any jumping or warping this only happens in the event of extreme packet loss
and this has no bearing at all on texture mapping or screen tearing.

Look, people are playing games all the time with pings over 100. b4nny has a recent video on his twitch of
him playing on European servers from the West coast. His ping was around 160. His screen wasn't tearing and
glitching. He still played significantly better than everyone else.

Of course, that's not to say VM, intel et al don't have to fix this issue, but if your games or web browsing is a laggy mess or
you're losing a ton of packets, are warping around in games etc, or if you suck and get killed a lot then that's really nothing at all to do with this issue.

This issue is barely noticeable and it's typically 5 or 6 packets out of 200 on the pump 6 test (far more packets are delayed by the test than by the issue)

I gave you a link, you have much to read and learn about lag compensation in games - this thread is not really the place to discuss it.

[halewoodj]

Another Hub 3 user here, who has now had the new firmware pushed down:

https://www.thinkbroadband.com/broadband/monitoring/quality/share/d49117c0bf5d6be38b4289e40e1ba7e1c408a698-13-02-2018 

Same version as others mention - it's pretty clear on the above graph where the update took place!

Sadly I still get a good amount of red on the puma-test, but I'm thinking that may now be another issue with our line - need to work out if the signal levels and such are all in tolerance.

[Andrew-G]

@ yabba

" but if your games or web browsing is a laggy mess or you're losing a ton of packets, are warping around in games etc, or if you suck and get killed a lot then that's really nothing at all to do with this issue."

Go back and read what I actually wrote before pontificating.  If you don't think this is the place to discuss it, then don't respond, but it seems to me you're still not grasping the practical impact of a 150-250ms lag spike on a client/server game, but you're now trying to close down the discussion and have the last word.

"I gave you a link, you have much to read and learn about lag compensation in games - this thread is not really the place to discuss it."

The only reason it has become a discussion point is because you and a couple of others are denying there's any effect of the Puma 6 lag spiking.  If that's the case, why have they spent a year trying to work out a fix?  Why have so many people been complaining bitterly, and some even taken their business elsewhere?

[philjohn]

Wasn't your complaint that it was causing screen tearing? I don't think anyone has said that latency spikes DON'T cause an issue for twitch shooters and their ilk (or games with woeful net code - which is often overlooked, I've written net code for a game, it's one of the hardest parts to get right).

[Datalink]

With reference to the above discussion, the correct answer is:

A.  some of the above;

B.  none of the above;

C.  all of the above;

D.  C, or the longest answer

Personal opinion, the answer is C.  all of the above.  

The one point that everyone seems to be forgetting is that with the Puma 6 modem, if you're running UDP through the modem, which a good many games do, you have a combination of latency and packet loss.  Running GRC's DNS survey, I've seen losses up to 9% on a Puma 6 modem.  So, there are a couple of issues here.  Firstly, are you all talking about the same online game.  I suspect that the answer is no.  That will change the discussion as potentially, the amount of UDP traffic could have a very wide range, and as a result, so will the observable effects, game to game.  Secondly, there is no question that there is UDP packet loss with the Puma 6 modem.  The question then becomes, what effect does that have on the game graphics.  Does the game deal with the combination of latency and missing packets gracefully, or, as has been indicated, is there an observable discontinuity frame to frame.  I suspect that games are designed with a certain amount of packet loss and latency in mind, but, if you encounter an extended number of UDP packet losses combined with high latency, as might be possible with a Puma 6 modem, how does the graphics react?  That will probably change, game to game and will depend on how much effort the game designers put into handling missing or highly delayed packets.  If I'm thinking about this correctly, the game servers itself won't transmit game graphic data.  Please correct me if I'm wrong on that one.  But, what would happen is that the positional data, on your game display would not be correct, both for yourself and for the other players in the game.  As your UDP packets are either lost or highly delayed in transit thru the Puma 6 modem, the game plays on, with everyone moving, including yourself.  After a series of missing and/or highly delayed packets, the next received update should correct everyone's position in the game world.  I would expect to see position jumps and possible screen discontinuities as the positional differences may exceed the games capability for a graceful change from one frame to the next.  So, you might not see a huge change frame to frame, but I would expect to see some discrepancy in the frame itself, similar to a tear in the image.  Then the question of graphics sync modes comes into play.  How is that affected when the player jumps from one position to another and his or her view of the game world suddenly changes?  I'm not here, I'm actually 10, 20 feet away, or further.  Your view of the game world around you should change, its just a question of how much it changes.  Does freesync or G-sync for example hold the image until the image buffer is refreshed and how does either sync system know that the whole image is correct when there is a position jump that has occurred?  That's yet another question in the mix.  So, at end of the day there are a few factors that go into this discussion which could lead to a range of effects, from minimal to absolutely noticeable.  Arguing about it makes no sense unless you're all on the same game, recording the game graphics output with a high speed video recorder to settle any arguments about the contents of the frame image.  The question of the day is whether or not the update will have the positive effect that you're looking for?  

On a related note, if you're looking to test UDP, follow the instructions in my post, which is located in the DSLReports forum:

http://www.dslreports.com/forum/r31737637-

That will run a one second interval DNS query to your chosen DNS address, which in this case should be the VM DNS address.  The result is two way UDP traffic.  That instruction plan is only for a one second interval, so, kill the BQM and let this run for a 24 hour period to see if in fact there is any change in the UDP throughput.  As this only runs a one second interval query, you'll need the longer term test to see what the results look like.  I'm working on posting a faster scripted instruction set for ICMP, TCP/IP and UDP.  (Time to hurry up and post it :()That will really show if there are any changes to any of the above protocols with the new update.  Fwiw, if this is the same update that was pushed out to the Rogers modems for ICMP purposes, Rogers completed that update in Sept 2016.  

[wotusaw]

Suddenly my cable test was aweful. Think I found the answer..

[plums1234]

I don't know how to post images on here so here is the imgur link for my screenshot DSLR PUMA 6 test as suggested earlier how to post images

PUMA 6 Test: https://imgur.com/a/cTP9i

Here is the imgur link to screenshot of my BQM, its obvious when the update took place: https://imgur.com/a/eHAGv

Hope it works this time

[philjohn]

The thing is, rendering pipeline for a video game is fixed - everything is setup and then rendered - there's no stopping the rendering of a given frame halfway through - it waits until it's done, and then when the packets have come in stuff will jump around, so the tearing is an unrelated issue.

At 60fps each frame takes around 16ms to render.

[Datalink]

What happens when the packet(s) are delayed by 200 to 300 ms?  In theory you have a string of packets arriving one after the other, with some packets potentially lost as they timed out in the modem itself. I suppose as you indicated "stuff will jump around".  I can't see anyway around that.  

[yabba]

---

wrote:

@ yabba

" but if your games or web browsing is a laggy mess or you're losing a ton of packets, are warping around in games etc, or if you suck and get killed a lot then that's really nothing at all to do with this issue."

Go back and read what I actually wrote before pontificating.  If you don't think this is the place to discuss it, then don't respond, but it seems to me you're still not grasping the practical impact of a 150-250ms lag spike on a client/server game, but you're now trying to close down the discussion and have the last word.

"I gave you a link, you have much to read and learn about lag compensation in games - this thread is not really the place to discuss it."

The only reason it has become a discussion point is because you and a couple of others are denying there's any effect of the Puma 6 lag spiking.  If that's the case, why have they spent a year trying to work out a fix?  Why have so many people been complaining bitterly, and some even taken their business elsewhere?

---

It's not a question of having any last word. You clearly don't understand lag compensation at all and I gave the word here to the developers of a game engine. Carry on in your ignorance or read their pages - it's up to you. This is a matter of fact though, not opinion. You can't debate it.

As for complaints. People have complained in here bitterly about gaming issues since the community was created and they'll continue to complain long after this puma 6 issue has gone away. Complaints are what you should expect to see here. They are not evidence of anything. There will be plenty of issues causing lag and packet loss in games for people other than intel's flakey chipsets.

IME there's barely any noticable difference at all in well written game engines, for example. Not the least because multiplayer gaming wouldn't work at all if the odd packet got dropped or arrived late. And I've seen no evidence at all on my connection that these packets happen every 2 seconds. It's more like every 30 seconds here. Pings to game servers are low and I've played the same as ever.

Indeed, I only know about this issue because I read about it - and then when I upgraded to V6 and they sent a hub 3 I was expecting a high ping in games and lots of issues but nope, nothing. I can run a few of the tests you are all fetishing and get graphs with yellow lines on them, or 5 or 6 red stars at the bottom but, aside from that, there's no visible evidence at all that this has affected copious amounts of web browsing, streaming netflix and youtube and playing Team fortress 2.

It's moot, there's an updated firmware now. Enjoy it.