31 Comments

Summary:

Updated: Comcast has filed its plan with the Federal Communications Commission detailing how it intends to govern traffic on its network, and says it should affect less than 1 percent of its users. It will start to go live commercially as of Nov. 15, and will […]

Updated: Comcast has filed its plan with the Federal Communications Commission detailing how it intends to govern traffic on its network, and says it should affect less than 1 percent of its users. It will start to go live commercially as of Nov. 15, and will be implemented  throughout Comcast’s network by the end of the year. As expected, the plan hews closely to what Om laid out back in March in a piece he wrote after sitting down with Comcast CTO Tony Werner. Essentially, folks using a lot of bandwidth at any one time on a crowded network will see their traffic slowed temporarily. The management will affect uploads and downloads and will be protocol agnostic.

The cable company was ordered to file such a plan last month, after the FCC censured it for throttling peer-to-peer traffic on its network. The FCC determined that the Comcast network management was problematic because it was done without informing subscribers and targeted a type of traffic that might be considered a competitor to Comcast’s cable business. Comcast maintains it did nothing wrong and was trying to maintain a good user experience on its network.

That will comply with the letter of the FCC order (which Comcast is appealing), but we had some additional questions of our own, as we detailed a few weeks ago in our post on the topic. Comcast answered our worry about bandwidth caps with its announcement of a 250GB-per-month limit. Judging from the information on its site about the new plan, Comcast answered all but our questions about who is providing the equipment to enable it’s efforts. Update: Sandvine will be providing some of the equipment as will Camiant. The plan will affect both uploads and downloads whenever the network is congested as detailed below:

Assuming that is the case, customers’ accounts must exceed a certain percentage of their upstream or downstream (both currently set at 70%) bandwidth for longer than a certain period of time, currently set at fifteen minutes.

A significant amount of normal Internet usage by our customers does not last that long. For example, most downloads would have completed within that time, and the majority of streaming and downloading will not exceed the threshold to be eligible for congestion management. And the majority of longer-running applications, such as VoIP, video conferencing, and streaming video content (including HD streaming on most sites) will not exceed these thresholds either.

All in all it looks pretty neutral like it may cause objections, but we’ll be digging through it a bit more and I’ll update the post with more in the next few hours. Update: Theoretically it would be possible to cut off a person’s traffic using this method if the entwork were incredibly congested for a long amount of time. From the filing:

NetForecast, Inc. explored the potential risk of a worst-case scenario for users whose traffic is in a BE state: the possibility of “bandwidth starvation” in the theoretical case where 100 percent of the CMTS bandwidth is taken up by PBE traffic for an extended period of time. In theory, such a condition could mean that a given user whose traffic is designated BE would be
unable to effectuate an upload or download (as noted above, both are managed separately) for
some period of time.

For those who want to check it out on their own, below are links to download the files.

Comcast’s Current Network Management Plan

Comcast’s Future Network Management Plan

Comcast’s Compliance Plan

  1. I’m looking at the Comcast Network Management Policy site but I’m not seeing any information that wasn’t already posted before today. Do you have any better of a link to it?

    Share
  2. > “Comcast answered all but our questions about who is providing the equipment to enable it’s efforts.”

    In the FCC filing, in Attachment B – Future Practices, you can find this information on page 14 (which is page 15 in the PDF due to the cover sheet). The first application server will be an IPDR server, which will collect relevant cable
    modem volume usage information from the CMTS, such as how many aggregate upstream or
    downstream bytes a subscriber uses over a particular period of time.15 Comcast has not yet
    chosen a vendor for the IPDR servers, but is in active negotiations with several vendors.
    The second application server is the Sandvine Congestion Management Fairshare
    (“CMF”) server, which will use Simple Network Management Protocol (“SNMP”) to measure
    CMTS port utilization and detect when a port is in a Near Congestion State. When this happens,
    the CMF server will then query the relevant IPDR data for a list of cable modems meeting the
    criteria set forth above for being in an Extended High Consumption State.
    If one or more users meet the criteria to be managed, then the CMF server will notify a
    third application server, the PCMM application server developed by Camiant Technologies, as to
    which users have been in an Extended High Consumption State and whose traffic should be
    treated as BE. The PCMM servers are responsible for signaling a given CMTS to set the traffic
    for specific cable modems with a BE QoS, and for tracking and managing the state of such
    CMTS actions.

    Share
  3. I’m looking at the Comcast Network Management Policy site but I’m not seeing any information that wasn’t already posted before today. Do you have any better of a link to it? (NEVERMIND, I SEE THEM AT THE BOTTOM OF YOUR STORY — you’re ahead of Comcast.net, I think!)

    Share
  4. You can find this information in the FCC filing that was submitted today. There are three application servers in the system. One is an IPDR server that collects statistics, and that vendor is not yet announced. The second is a congestion management server, from Sandvine. The third is a QoS server (PacketCable Multimedia really) from Camiant.

    Regards
    Jason

    Share
  5. I am very fortunate that my ISP(cablevision) is not capping my bandwidth. If I were a comacast subscriber I would be running to FIOS or nearly anything else that beats out comcast.

    Share
  6. We have two risk scenarios depicted that we’ve tried to address. Robb already asked this Q elsewhere, so I am posting the same response here for your information.

    1 – What is oscillation, and how is it prevented or minimized in the new method?

    Oscillation refers to the situation where a cable modem is assigned to a lower Quality of Service (QoS) priority (Best Effort, or BE) after one measurement interval, then promoted back to the higher QoS priority (Priority Best Effort, or PBE) in the next interval, just to be assigned to the lower priority again in the following interval. We refer to this up and down assignment as oscillation.

    Part of the new congestion management system is the use of thresholds to determine when a cable-modem is in a high consumption state and when it is not. At the start of the trial the congestion management algorithm used a single threshold to determine if a cable-modem was in a high consumption state or not. If a cable-modem’s utilization was just over the threshold in one time interval and it was then put in the lower priority, it is very possible that because of the lower priority its use will now be just below the threshold and so it will be promoted back to the higher priority in the next interval.

    To resolve this issue, we instead implemented two thresholds. The higher threshold determines when a cable-modem is put into the lower priority class (BE). The lower threshold determines when the cable-modem can be taken out of the lower priority class and restored to normal priority (PBE). By having the two separate thresholds, the chance of oscillation occurring is greatly reduced.

    This kind of oscillation is often found in control systems that use a single threshold for both on and off states. A standard approach to reduce rapid cycling through the states is to add a second threshold which gives the system a range of control. The range between the two thresholds is called hysteresis. Most thermostats that control residential heating systems operate this way, for example, and many other control systems have oscillation-prevention features as the Comcast system does.

    2 – What is user starvation and how is it prevented or minimized in the new method?

    User starvation was an extreme case identified with theoretical or simulation models of the new congestion management system. That model identified a possible situation that could occur when the connection is fully (100%) utilized, which is an extreme congestion state. If a group of high consumption state cable-modems are operating at low priority (BE), and a new heavy cable-modem appears at high priority (PBE), it is theoretically possible that the high priority cable-modem with PBE QoS can take enough bandwidth away from the low priority BE QoS cable-modems that they appear to no longer be demanding heavy use. At the next measurement interval the low priority cable-modems are promoted to high priority (BE to PBE), and the just recently “new” high priority cable-modem is put at low priority (PBE to BE). The heavy cable-modems at high priority (PBE) now can consume all of the available bandwidth and the low priority cable-modem (BE) is starved, or prevented from getting any bandwidth, until the end of the next measurement period (approximately 15 minutes).

    This problem is closely related to the oscillation problem described above. Since the large group of heavy use cable-modems operating at low priority will need to meet a lower threshold before being allowed to be promoted to high priority, this starvation scenario is much less likely to occur. Furthermore, the described scenario only occurs when the network is consistently used at or near 100% utilization, which based upon trials conducted by Comcast, is extremely, extremely rare.

    During the trials we worked hard to find locations where utilization was very high, and still did not find a situation that would cause this starvation. We also tested this possible use case in our lab and were unable to produce starvation, possibly due to the exact manner in which CMTS packet schedulers actually work in practice, which could not be adequately simulated in a model. The likelihood of this starvation problem occurring in a real network is very low.

    All of that being said, we expect to continue to fine-tune the system. We also had help in performing this analysis — from an independent consulting firm (NetForecast, as you noted, http://www.netforecast.com). They’ll be continuing on as we implement and into 2009, to periodically audit system behavior and make independent recommendations.

    Share
  7. I still think it sucks. It’s about time the networks were built up to a specification that allows not only for present usage but near future usage too. More and more data of all kinds is going to be transmitted via the Internet, much of which isn’t illegal P2P either.

    I watch video, stream audio (internet radio stream). Comcast wants to dissuade its users from these kind of activities as they want subscribers to sped huge amounts of money on ever more premium rate TV channels.

    With ISPs with an attitude like Comcast, it’s no wonder the US is 16 or 17th in the world league table for Internet speed and reliability.

    Share
  8. Maybe I missed it, but are the 70% thresholds for the individual cable modem connection or higher in the stream?

    I’m concerned that my online backup process could take even longer than it already does, if the former case is true.

    Share
  9. Eyebee –
    “I still think it sucks. It’s about time the networks were built up to a specification that allows not only for present usage but near future usage too. More and more data of all kinds is going to be transmitted via the Internet, much of which isn’t illegal P2P either.”

    Unfortunately, congestion can occur in any IP network, and congestion feedback is a part of existing Internet standards. There are examples in Japan and other countries with 100Mbps service, where congestion can still occur at some point on the network. Our network has a shared access network, like many wireless networks, which basically means it is shared one hop sooner than some circuit-based networks. Those networks often see congestion sometimes at their aggregation points. Nevertheless, I’m sure you have heard all that before. ;-) We’re also upgrading to the new DOCSIS 3.0 standard, which adds a lot of capacity and speed to our particular network.

    “I watch video, stream audio (internet radio stream). Comcast wants to dissuade its users from these kind of activities…”

    Far from it – those kind of activities are the future. I think we’ll see more and more of that kind of traffic, as well more “unattended” applications and “ambient” apps that are always chirping away in the background.

    Regards
    JL
    Comcast

    Share
  10. Good answer, Jason. It’s amazing that so many people are so naive about network congestion after all that’s been written about the subject in the last year.

    People seem to accept that the sewer system can’t handle everybody flushing their toilets at the same time, but somehow the Internet should handle the same scenario without a hiccup.

    As if.

    Share

Comments have been disabled for this post