Bufferbloat: Dark Buffers in the Internet

Поделиться
HTML-код
  • Опубликовано: 4 авг 2024
  • Google Tech Talk (more info below)
    April 26, 2011
    Presented by Jim Gettys.
    ABSTRACT
    VOIP and teleconferencing often perform much more poorly on today's Internet than the Internet of a decade ago, despite great gains in bandwidth. Lots of fiber, cheap memory, smart hardware, variability of wireless thoughput, changes in web browser behaviour, changes in TCP implementations, and a focus on benchmarking Internet performance solely by bandwidth, and engineer's natural reluctance to drop packets have conspired to encourage papering over problems by adding buffers; each of which may introduce latency when filled.
    Buffering mistakes have been made in all technologies: operating
    systems, home routers both wired and wireless, broadband equipment, corporate networks, 3G networks and parts of the core Internet itself. The mistaken quest to never drop packets has destroyed interactivity under load, and often results in actual higher packet loss, as TCP's congestion avoidance algorithms have been defeated by these buffers. The lessons of the "RED manifesto" of 1997 have been forgotten or never learned by a new generation of engineers.
    Full solutions require careful queue management, and that management should be everywhere; we no longer have the luxury to think that this is a problem solely of Internet routers. I will describe some of the mitigations and solutions to this problem, and how you can at least make your home network and systems behave the way they should.
    More info at www.bufferbloat.net
    Slides available at mirrors.bufferbloat.net/Talks/...
    Speaker Info: Jim Gettys, Bell Labs
    Jim Gettys is well-known as one of the original developers of the X Window System, and has long been active in open source and internet standards. His recent experiences with immersive telepresence applications exposed systemic implementation errors
    in many Internet buffer and queue designs. He describes the journey of discovery in this talk.
    Blog at gettys.wordpress.com/
  • НаукаНаука

Комментарии • 16

  • @TrueSoreThumb
    @TrueSoreThumb 13 лет назад

    Dear Google Talks,
    THANK YOU SO MUCH FOR POSTING THIS.
    I have RCN up in Massachusetts, and *I have the same network graph as shown at 13:18 !* I was wondering what was causing it!
    No way I could ask RCN to enact RED algorithms, especially when 802.11 seems close, and also since they're a big business.. So, time to do the QOS, the Host Buffering, and more on my own network!
    Again--you guys are my heros. I'm so glad I clicked on this talk.

  • @slovokia
    @slovokia 12 лет назад +1

    The audio problems with this video probably were caused by mixing the output of two microphones together producing a flanging effect. If the microphone gains are set to produce similar levels interference results producing comb filer effects due to relative delays of the sound signal between the microphones.

  • @JimGettys
    @JimGettys 13 лет назад

    @misteriousj Unfortunately, there were technical difficulties the day I gave this talk; I'm thankful that Greg Chesson, Mark Chow, and Denton Gentry were able to pull it together at all.
    You can also listen to an abbreviated version of the talk I gave at the IETF in Prague, or an edited version of the first Bell Labs talk in January, if you prefer. All are online.

  • @TakanashiYuuji
    @TakanashiYuuji 13 лет назад +1

    I really like these talks and I fully realize this amazing service is for free. But, since this is a _talk_ you would assume the most important part is the audio. I would like to point out that the quality of the audio is amicable at best. I'm no sound engineer so I can't explain what is wrong with it but I do know that I find it extremely hard to focus. Since Google is churning out many videos I would very much appreciate it if you could look into this. Compare this to TED talks for instance.

  • @icilianfenner
    @icilianfenner 13 лет назад

    @misteriousj
    Undoubtedly part of it, but there seems to be a problem somewhere (loose connection?) that's like a 'gate' that's massively toggling between two different tonal colours. >.< It is wearing on the ears..

  • @TrueSoreThumb
    @TrueSoreThumb 13 лет назад

    @JimGettys During some tests awhile ago, I completely circumvented the router and connected directly to the network. Makes me think that it's network And/or Windows 7 / Vista.
    Can you give me some key words to Google so I can find what settings to change when it comes to modulating my computer's broadband provisioning?

  • @JimGettys
    @JimGettys 13 лет назад

    @TrueSoreThumb Sorry, I don't know my way around Windows. You can see if the network driver has knobs for setting the amount of buffering.
    But by ensuring the bottleneck link is in your broadband connection (by ensuring your actual wireless bandwidth is always greater than your broadband link: e.g. by using 802.11n with care), and then using bandwidth shaping (aka QOS in many routers) as described in my blog. This will cost some bandwidth, but get you good latency.

  • @JimGettys
    @JimGettys 13 лет назад

    @TrueSoreThumb You'll get the particular shape in the TCP traces I did from TCP Cubic; whether RED is running in your broadband head end or not I don't know: 30% of broadband seems not to enable RED.
    Your OS or home router is as likely to be your problems too: it depends if your 802.11 link real bandwidth is less than or greater than the broadband provisioning. The bottleneck can easily be in either depending on your house and your broadband service.

  • @JimGettys
    @JimGettys 13 лет назад

    @aloisgault No mystery here: even web browsing (if you hit pages with lots of embedded objects) can easily induce transient bufferbloat.
    But anything which is trying to work on top of a bloated network then has real trouble with estimating jitter, and can get quite confused.

  • @JimGettys
    @JimGettys 13 лет назад +1

    @militantmindset No, because dark buffers that happen to be in places that can never be saturated can't ever come out to bite us.
    But any that are a path in a location that saturates can/will bite you.
    Also, where we can, we should be enabling AQM (aka RED). While it will have real problems in the "last mile" or your home, in classic router locations more interior to the network, it can be very effective. But at least we now understand why it has not been enabled everywhere it should be.

  • @Punkcast
    @Punkcast 13 лет назад

    I knew Google was getting ahead of itself but April 26, 3011? Wow!

  • @militantmindset
    @militantmindset 13 лет назад

    so did he suggest that we need to firmware update the whole internet?

  • @icilianfenner
    @icilianfenner 13 лет назад

    @JimGettys
    Unrelated, but your resume reads like the conquests of a computing demi-god. Good work! :D

  • @AntiProtonBoy
    @AntiProtonBoy 13 лет назад +1

    Ran Netalyzr on my connection and crashed my router... hahaha!

  • @RuddODragonFear
    @RuddODragonFear 13 лет назад

    Vint, you are a cool guy, but... hey, too much introduction. :-)

  • @tianhepeng9162
    @tianhepeng9162 4 года назад

    I came from bufferbloat.net and I watched 53 mins of this video. Sadly I think I only understand maybe 2% percent of the content..