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]

[MUD_Wizard]

---

@MUD_Wizard wrote:

---

I've been looking at all the Linux networking tools I could use to do detailed monitoring on the Hitron and have come to the conclusion that a real-world test with Wireshark setup to monitor packet loss and TCP delay/retransmission to real sites would be the best choice. With graphing of specific destinations. I'll have to find a block of time when I can set that up because it won't be quick to do it right. Then do a comparison of Hitron vs Hub 3 vs SH2ac.

---

Meant delay and retransmission. As delay is the most common factor when packet loss is and is not present.

Pingplotter, MTR, Hping3 etc are of limited value to guage a real-world scenario, even when doing TCP. When using them for ICMP they are practically misleading.

[Xymox]

Greetings from across the pond. Its good to come over and visit 🙂

Lots of good posts here 🙂 I only read back 2 pages tho.

Let me start off very clearly here, then I will respond to a few things.

1. The ONLY things fixed are ICMP Ping and UDP DNS lookups. TCP is still a huge mess and has not changed since last year in any way i can measure, including looking at it with Wireshark. Ive used every networking tool known to man. I have demonstrated the exact same issues using multiple tools with different OS and different cable networks. We have others who have tested these issues numerous times and have never found a single exception. The spike that occurs every 1.95 seconds and results in ALL puma devices misordering packets, 200ms latency spikes and lost UDP packets. This exists in every device with a Puma 6 made to date. No exception in any way have been seen. This issue is not related to any external factors like ISP or number of channels. INTEL HAS ACKNOWLEDGED THIS FACT.

This is very simple. If you have a Puma, you have this issue. There is no firmware in any cable box released to anyone at this time that addresses this issue.

There is also a VERY scary 0-day Denial Of Service attack that anyone can download and knock anyone or any company with a puma right off line and keep them offline as long as they want to. There is NO WAY to stop this attack other then getting a new IP address. This effects ALL PUMA 6/7 devices.

Its possible to cause a Puma 6 to reboot. This also knocks someone offline. This has not been made public so this is not as big a threat.

We have now clearly isolated a serious issue with UDP. A Puma6 will stop responding to TCP/UDP if you pull down a UDP stream faster then 100Mbps.

Broadcom modems dont have anything even remotely a issue. The above stuff is SO BAD and causes so much of a issue I believe the device is unsuited for purpose. Clearly it cannot do anywhere near its rated speed of 1Gbps if it can only do 100Mbps in UDP.

There are people far smarter then me that seem to think Intel can not resolve all these issues using firmware. That its a hardware based problem. I personally dont think a Intel Puma 6/7 will ever reach the performance standards in place for 18 years for modems. I have tested a early DOCSIS 2 modem and it beat the Puma 6 in latency.

Intel has given something to modem vendors 3 weeks ago now. No modem vendor has released anything based on that yet. No one know how it tests and what it addresses. Ive been in direct contact with Intel Security and I believe they have a fix for the DoS and reboot in that code released to modem vendors. However we dont know if that addresses any performance issues like the 1.95 second recurring spike or the UDP speed issue.

On to other topics you guys are discussing.

MUD_Wizard, im impressed. Your correct that using Wireshark is REALLY interesting and complete. The issue is no normal human can really do that themselves. You gotta be a networking nerd, and I have trouble with Wireshark. What we need is a really comprehensive networking tool that anyone can run that can give a simple grade. A, B, C or F.. In video graphics benchmarking for example PassMark has a fairly simple numerical result that sums up all manner of tests into a single number. Im hoping that all this Puma BS leads to better benchmark tools anyone can use.

The awesome info that Datalink provided you guys with above is a awesome summary.

Im sorry i have not been back here more. Ive been working out of town and really busy and its hard enough to keep up with the DSLreports thread. But im sorta not working for the next 4 days, so I am pleased to travel across the pond and help with the Puma issue here.

There IS hope. I think it might be possible to get the Puma a LOT closer to be usable. Maybe close enough that no one really notices any issues 🙂 There have been some developments in the last 2 days that I cant discuss yet that give me hope. HOWEVER. If you can somehow change to a Broadcom based solution, thats the best bet.

I will post some thing you guys might not have seen. Gimme a little bit..

[Xymox]

This graph has 3 devices. The top is any Broadcom 3390 based device. In fact I think all modems made going back many years look just like the top chart. The middle chart is a Puma 5 based device showing clearly the issue was present before Intel even bought Puma from Texas Instruments. HOWEVER it was not really that bad a issue. The bottom chart shows ANY puma 6 and how near complete loss of TCP occurs with even small streams of UDP at the same time.

This is pingplotter testing TCP connections and I am running the Puma6Fail DoS code against the modems. This shows that even fairly minor UDP streams can take the modem right off line. You can imagine what happens when say a few people are streaming Netflix HD and someone else tries to game. They end up with horrendous latency that comes and goes with netflix pulling data..

[Xymox]

The above is horrendous deplorable performance.

Check this out... While the modem is 100% offline,,, Ping still shows it working PERFECTLY.. So you can use any ICMP Ping test you want and even tho your offline completely Ping will work perfectly and show ZERO issues. If you call your cable company and report your offline, they will run a ping test and tell you everything is fine... This PERECT PING no matter what came from the X version of firmware they gave us.

SOOOOO.... Do NOT use Ping to check a Puma with current firmware. It will ALWAYS report perfect results. Like a Volkswagon Emmision test...

[Xymox]

Because of the above issue. We dont trust Intel. We want to test anything they are going to try and ship. We have guys working on tests now that Intel cant find way to hide the issues.

So.......... As things stand. Right now.. EVERY PUMA DEVICE IS FLAWED. NO EXCEPTIONS. These are SERIOUS issues. Intel "is working on it" and may well have released a firmware to fix something in some devices. We dont know what devices or what they fixed. No one does so far as no modem maker has shipped the newest firmware that came from Intel and sent to modem makers like 3 weeks ago. Can they fix it in firmware ? Really technical people ive talked to who make modem chips say no. They can fix the big issues but the entire architecture of the platform is flawed and needs a rewrite. So the Puma most likely will never perform as well as a Broadcom based device.

The HORRENDOUS issue is that these Puma based devices are FLYING of the production line and going into homes and offices at incredible rates. So the problems are multiplying daily. No modem makers has halted production. ONLY netgear has issued a public alert. The CERT Rated HIGH 0-Day DoS attack has never had a single warning from Intel or a modem maker except Netgear. Even tho these things have this horrible DoS attack they are still shipping these things as fast as they possibly can. Its horrendous.

Im hanging around across the pond. Its much nocer over here. Where im from in Phoenix Arizona its 106F..

[wotusaw]

Thanks so much Xymox. Very clear information that even I can understand. (On my gaming clansite you have been given 'Superhero' status, btw)

Had to give up my beloved Titanfall 2 because of this problem with my virgin superhub 3. Now call it the superfail 3. No disrespect to Virgin intended.

Gave up 'fps' games as don't think my rage fits were healthy...and I was frightening my son who plays minecraft on a pc next to me....Anger is too small a word for how I feel about Intel right now........and they are still pumping out this travesty of a chipset!!....All I can say to Intel right now is 'Ryzen!!'.

knew nothing about 'modems' before this sad story started.

Thanks to Xymox and a host of other 'boffins' (meant in the most complimentary way) now know a whole lot more.

[itinfocus]

From DSL reports:

New firmware for Arris TG2492S
Release notes for version 9.1.103BA (2017-05-26)

The following issues were resolved in release 9.1.103BA
2.3.1 TCP/UDP/DNS Latency Issues
Tracking No. PD 26612/24878
Description
Multiple latency issues have been observed:
- UDP upstream delays during rate-limited TCP traffic
- HTTP delays under heavy TCP Ack load
- Slow HTTP session initiation
- Slow DNS responsiveness

Please can the users from this thread by automatically on the beta?

[DrunkMonk74]

+1 on those on this thread being involved in the beta. Would happily participate. Can't be worse than it already is!!

[Xymox]

Thats the firmware from April. It DOES NOT FIX ANYTHING BUT DNS LOOKUPS. There is a new firmware that Intel handed modem vendors 3 weeks ago that has not been released anywhere yet that *MIGHT* address some of these issues. Or might not. Dont get confuzed..

[Xymox]

The new firmware will address the DoS and Reboot attack. So thats how you can identify it. It *might* also have performance fixes. Maybe. There is no beta for this yet.