Stories
Slash Boxes
Comments

News for nerds, stuff that matters

Slashdot Log In

Log In

Create Account  |  Retrieve Password

80 Gbps Deep Packet Inspection Hardware Announced

Posted by ScuttleMonkey on Mon May 12, 2008 12:53 PM
from the comcast-on-backorder-for-months dept.
An anonymous reader writes to tell us that Procera Networks is launching a new weapon on the deep packet inspection (DPI) front. At $800,000 these 80 Gbps tanks aren't going to be sitting in everyone's closet, but it could mean that more traffic shaping is on the way. "The PL10000 can handle up to 5 million subscribers and can track 48 million real-time data flows. That's certainly a potent piece of hardware, but larger ISPs will need more. That's why Procera designed the new machines with full support for synchronizing traffic flows where return traffic might be routed to a different PacketLogic machine. The machine receiving the return traffic can make the machine monitoring the outbound traffic aware that it sees the other half of a TCP/IP conversation, for example, giving the devices more accuracy than those which might only have access to one side."
+ -
story

Related Stories

[+] Your Rights Online: ISPs Using "Deep Packet Inspection" On 100,000 Users 309 comments
dstates writes "The Washington Post is reporting that some Internet Service Providers (ISP) have been using deep-packet inspection to spy on the communications of more than 100,000 US customers. Deep packet inspection allows the ISP to read the content of communications including every Web page visited, every e-mail sent and every search entered, in short every click and keystroke that comes down the line. The companies involved assert that customers' privacy is protected because no personally identifying details are released, but they make money from advertisers who use the information to target their online pitches. Deep packet inspection is a significant expansion over tools like cookies in the ability to track a user. Critics liken it to a phone company listening in on conversations."
[+] Your Rights Online: China to Regulate Internet Map Publishing 279 comments
hackingbear writes "After text, pictures, and videos, China starts regulating Internet map publishing (here is the google translation.) The government believes that Internet maps can represent the state's sovereignty and its political and diplomatic positions in the international community — and consequently, inaccurate maps could harm national interests and dignity, produce bad political influences, reveal national secrets and harm national security, in addition to harming consumer interests. So from now on, publishing maps would require approval and (yet another) license from the state survey bureau. That means Google, Yahoo, etc., need to remove China from the map; or maybe they just pay up some officials and their agents to acquire yet another license. And our newest 80Gbps DPI monsters need to be upgraded to identify maps together with porn."
This discussion has been archived. No new comments can be posted.
The Fine Print: The following comments are owned by whoever posted them. We are not responsible for them in any way.
 Full
 Abbreviated
 Hidden
More
Loading... please wait.
  • by courteaudotbiz (1191083) on Monday May 12 2008, @12:57PM (#23380994) Homepage
    Just in time for the olympic games!
    • Re:Just in time! (Score:4, Informative)

      by keneng (1211114) on Monday May 12 2008, @05:52PM (#23385230) Journal
      It's not that funny. I live in China. We will even have slower traffic now. As it stands forget watching youtube. All I can get is about 30KB/s download/upload on a single connection which is barely enough to listen to internet radio. The good news is that I can have more than one connection open with other countries, but from what I understand no media players or streaming servers have this parallel 30KB/s connection capability to total the necessary 4Mbps/download for watching internet video. That's why China's "Golden Shield" works so well. In order to circumvent it, one must have tools to open multiple connections for the single purpose intended i.e. media player, web serving one large page through multiple data sending connections. Oddly enough if I connect to websites inside China I can get 4Mb/s connections. The world's internet is crippled with equipment like this in my perspective and experience already. I'm grateful I can actually express my opinion about this here. BTW for the last four to five months slashdot has had this quantserve in-your-face job ad when accessing the site. From China, it often slows down the page access and takes sometimes 5 to 10 minutes before I can read the main page. Is this normal?
  • $800,000? (Score:5, Insightful)

    by Bovius (1243040) on Monday May 12 2008, @12:58PM (#23381000)
    At almost a million dollars a pop, is it really saving money for ISPs to use these? How many would a major ISP need to shape all of their traffic?
    • Math is fun. (Score:5, Insightful)

      by Cedric Tsui (890887) on Monday May 12 2008, @01:14PM (#23381266)
      $800,000/5 million subscribers = $0.16 per subscriber.

      Expect to see the surcharge in your next bill!!!
      • Re:Math is fun. (Score:5, Insightful)

        by gnick (1211984) on Monday May 12 2008, @01:29PM (#23381514) Homepage

        $800,000/5 million subscribers = $0.16 per subscriber.
        Yeah, but 80Gbps/5 million subscribers = 2kBps. How long can you keep 5 million subscribers with speeds like that?
        • Re:Math is fun. (Score:5, Insightful)

          by D'Sphitz (699604) on Monday May 12 2008, @01:49PM (#23381832) Journal
          assuming every single subscriber is using his connection continuously 24 hours per day, not even stopping to so much as read a webpage or an email ...
          • by gnick (1211984) on Monday May 12 2008, @03:05PM (#23383046) Homepage
            Yes, 2kBps would be the available average bandwidth. So, assuming that nobody is running p2p software, downloading pornos, or retrieving linux isos, the available peak bandwidth would be much higher. But that would mean that you'd have to advertise speeds that you can't provide during high-demand times and hide a "we'll provide whatever we feel like providing and you'll have to keep paying for it whether you're satisfied or not" clause in the contract. Would any ISP ever stoop so low as to try something like that?
            • Re: (Score:3, Insightful)

              I think the question is:
              Would any ISP NOT stoop so low as to try something like that?
        • Who says you need to inspect every packet?
          • Re: (Score:3, Insightful)

            If you don't route all of the packets through this thing, what device will do the cursory inspection and decide which packets warrant "deep" inspection? (I'm really asking - If somebody has a good answer, I'd be interested.)
        • Re:Math is fun. (Score:5, Informative)

          by Bovius (1243040) on Monday May 12 2008, @02:02PM (#23382074)
          This is also assuming every single packet that an ISP manages goes through a single physical location. So unless Comcast routes every packet to their headquarters at the top of Mt. Doom for inspection before delivery, they're going to need a lot more of these.
    • Re:$800,000? (Score:5, Insightful)

      by Deadplant (212273) <deadplant_ca@hot ... minus physicist> on Monday May 12 2008, @01:33PM (#23381588)
      Seriously.
      Spend the money on a couple more 40Gb fiber lines instead.
    • Re:$800,000? (Score:4, Insightful)

      by GreggBz (777373) on Monday May 12 2008, @01:55PM (#23381938) Homepage

      At almost a million dollars a pop, is it really saving money for ISPs to use these? How many would a major ISP need to shape all of their traffic?
      Not only that but it seems like a dumb technical solution for P2P traffic shaping.

      Most ISPs would be geographically distributed. I can't think of to many places where you would actually see this much traffic. You'd need, what, 10 OC-192's to see 80Gb/s? Maybe they add all the GigE ports together and cheat to advertise a big number, but still.

      Second, this is the kind of device you want closest to your customers, not down the line where your traffic aggregates. If you want to stave upstream traffic, do it as soon as possible in the network.

      Third, it's better in almost every aspect of IT to scale out, not up. Every node would be different. You could have business customers in one CDIR or another and different configurations for each. I'm sure this thing is configurable per port, but I'd think it would be easier and more cost effective to have smaller distributed individually configurable devices only where you need them.

      No, I don't think this thing is best suited to do traffic shaping for the typical ISP. If you can do DPI on that much traffic, there's bigger, less benign applications I can think of.
      • Re:$800,000? (Score:5, Insightful)

        by blhack (921171) on Monday May 12 2008, @01:25PM (#23381446)

        Yep, and how much were computers, originally? The price on these will drop when enough of them are bought.
        No it won't. There is realistically only a market for a handful of these worldwide. Not several million of them like PCs. Its exactly like cisco hardware, it has remained astronomically expensive simply because only a very small select group of people (network admins) actually buy them.
  • tank (Score:4, Funny)

    by BorgCopyeditor (590345) on Monday May 12 2008, @12:58PM (#23381016)

    80 Gbps tanks aren't going to be sitting in everyone's closet

    Not until Wrath of the Lich King comes out ... wait, what were we talking about?

  • I guess a handful of these would beat a hojillion racks full commodity servers running pf+altq, but how does the cost really add up?
  • DPI - Encrypt (Score:5, Interesting)

    by Unlikely_Hero (900172) on Monday May 12 2008, @01:02PM (#23381074)
    DPI has only one option when presented with encrypted information however (at least afaik). Give the packet a low priority or pass it through normally (of course, it could also drop it entirely but doing that as a rule would be problematic to say the least). So it would be possible to force a bet. Can the ISPs afford to give encrypted traffic a very low priority?
    • Re:DPI - Encrypt (Score:5, Insightful)

      by Shakrai (717556) * on Monday May 12 2008, @01:05PM (#23381122) Journal

      Can the ISPs afford to give encrypted traffic a very low priority?

      No, but if they wanted to be pricks they could identify p2p users and give THEIR encrypted traffic a very low priority.

      Even if you ran with full encryption and encrypted the communication with the tracker it's still trivial to identify you as a p2p user -- not many VPNs make connections with dozens (or hundreds) of remote hosts.

      The only way around that would be to VPN somewhere and use that VPN link to pass all your p2p traffic -- but if you have the means at your disposal to set that up then you likely have the means to find an ISP that doesn't throttle your p2p traffic.

      • Re: (Score:3, Informative)

        quite true, good points all around. One issue with the last part though, the means to find an ISP that doesn't throttle? Sure. To have that ISP be in your area...not so sure.
      • Re:DPI - Encrypt (Score:4, Informative)

        by TooMuchToDo (882796) on Monday May 12 2008, @01:18PM (#23381338)
        https://www.relakks.com/?lang=en [relakks.com] does exactly what you've described. I believe the cost is $10/month US.
      • It should be trivial to limit any end nodes to a maximum of, say, 8 encrypted connections with unique netblocks on the destination. Any new sessions negotiated after that will automatically be given very low priority.

        Also, a TCP packet contains a lot more than just an encrypted payload: you can tell a lot about a packet from the other parts: source and destination ports, sequence and acknowledgement numbers, header length, reserved ID bits, urgent flag, ACK flag, push flag, RST flag, SYN flag, FIN flag, Window size, checksum, urgent pointer and even the options field. I'm sure that it wouldn't be very difficult to set up a bayesian detection ruleset using this data to identify what protocol is being used. The checksum and flags wouldn't be all that useful, but the port numbers, header length, window size, urgent pointer and seq/ack number progressions can be quite telling.
        • Re:DPI - Encrypt (Score:4, Informative)

          by evanbd (210358) on Monday May 12 2008, @02:19PM (#23382342)

          Freenet runs over UDP with fully randomized ports. It acknowledges messages, but even the ACKs are encrypted. Window sizes are hidden behind the crypto as well. Except for the initial connection, handshaking is done by routing through previously established connections.

          I'd like to see them DPI that. The best they can do is traffic analysis and decide it looks like P2P and throttle on that.

    • Can the ISPs afford to give encrypted traffic a very low priority?

      Definitely not. If people find that their online web purchases fail to complete because some marketing executron has decided to put shttp protocols in the slow lane, word will soon get round on the consumer newsgroups.
      • they can, but they will eiterh make false positives, or miss a lot of traffic.

        If only a effective QOS standard was applied then users could choose the level of quality they wanted.
    • Re:DPI - Encrypt (Score:4, Interesting)

      by Shadow-isoHunt (1014539) on Monday May 12 2008, @01:32PM (#23381566) Homepage
      The problem with this whole "it's encrypted so they'd have to throttle SSL too" idea is that bittorrent doesn't use SSL, and lacks a Diffie Hellman exchange. Encrypted BT traffic looks nothing like any other traffic, so it can still be picked out of the traffic flows and thrown into another QoS bracket. Using SSL for BT would also be stupid, because SSL(the key exchange in partciular) is computationally expensive. You'd peg your CPU at 100% the whole time you were grabbing your porn.
      • Re: (Score:3, Informative)

        That's what all the new-fangle dual core CPUs are for. One to download the porn the other to watch it.

  • A waste? (Score:3, Insightful)

    by Nimsoft (858559) on Monday May 12 2008, @01:09PM (#23381190)
    Surely that money could be better spent improving their capacity by purchasing new equipment with better signaling methods or even extra lines rather than on equipment to inspect and shape (i.e. selectively throttle) traffic?

    Even if improving the capacity costs a fair bit extra the space for more customers at higher speeds and more consistent service for existing customers will surely increase their profits by offering more than their competition right?
    • Re:A waste? (Score:5, Insightful)

      by Kartoffel (30238) on Monday May 12 2008, @01:18PM (#23381330)
      Investing in more capacity means a linear increase in customers and profits. Investing in network anti-neutrality, OTOH, means new and lucrative pricing structures for various services. They're just putting money where it stands to return the greater profit.
  • by jskline (301574) on Monday May 12 2008, @01:10PM (#23381198) Homepage
    How much of this advertised speed is more or less advertising hype more than anything else??? We all know what it takes to do packet inspection and rules table lookups, so to me, this number seems a bit on the hyped up side...

    Anyone else getting this same riff??
  • only 80Gbps with 5 million subscribers? If my math isn't way off, that's about 16kbps - which is pretty pitiful speed. You'd have to throttle a lot just to be able to use one of these machines at max subscribers per machine.

    Welcome to Comcast - our new TOS allows you to view text-only web pages with your *high speed* internet connection!
    • Re: (Score:3, Informative)

      only 80Gbps with 5 million subscribers?
      Those 5 million subscribers are not all using their connections concurrently. Think about what just happened when I loaded this webpage: it downloaded a text file full of HTML/CSS/Javascript/Whatever else slashdot uses, and now it sits here while I type this comment. I'm not using my connection right now, and won't be using it again until I hit the submit button.
  • Privacy is the big one. I can see a justification for finding DDoS attacks and zero-second malware propagation, this machine is nothing more than a net-neutrality killer of the highest order.

    First big customers: Comcast, Rogers, Bell Canada, AT&T, and the others that we love to hate.

    The FCC needs to investigate this thing NOW. It's a monopoly-maker in just 12U.
        • Deep packet inspection is necessary to identify and provide QoS for many modern internet applications. For example it is quite common for services to tunnel video over HTTP (example - YouTube). Skype cannot be identified without DPI.

          Of course it can be used for good or evil. But the fact of the matter is that DPI is in the mix as one approach to provide QoS for real time internet applications like streaming video and audio that don't play well with the 'best effort' delivery paradigm that packet switched ne
  • in ankle bracelets on truants, cameras around london, etc.

    those are just stunts, it is propaganda and hysteria to overinflate the significance of those developments

    but this massive dpi stuff, this is big brother for real

    but its not as sexy a lightning rod visceral symbolic issue like ankle bracelets on truants. so it won't experience the same outcry

  • by TheGratefulNet (143330) on Monday May 12 2008, @01:26PM (#23381456)
    think about the original definition of ethernet and of IP, in general.

    in general, it was setup to pass packets and ideally to keep them in the same order and not drop them. beyond that, the upper layers (tcp and udp) did any higher level functions.

    this worked! for the longest (damned) time, it worked.

    and now, ISPs (and large networks) are starting to try to break out the 'cable is a bunch of bits' into discrete 'services' and then try to re-order things, drop things, queue them differently or somehow treat things non-uniformly.

    I think this is Evil(tm).

    I've been in the networking field for a few decades (really) and I've seen traffic shaping (what a euphemism, btw!) try to argue its case over and over again. but I keep getting back to the basic design principles of ethernet (csma-c/d) and tcp/udp-ip and when you have large enough pipes, you don't NEED a 'fast lane' or diamond lane, so to speak. it just mucks up the works, makes things harder to design and manage and really isn't helpful since you still need large pipes and all the shaping in the world won't CURE that, it only DEFERs things. that's not a cure.

    data should be 'opaque' and first-come first-served. equal access. standard layer (phys, dl, network) rules should still apply.

    ISPs who employ shaping are simply RIPPING OFF customers from their rightful bandwidth and also passing along the COST of the packet snooping hardware to us, the users. (don't think they'll just spring for the hardware on their own; they'll pass the costs of this stuff to us, to be sure).

    I think its evil. once you look at it from enough angles, you see that its not at all a good thing.

    • Re: (Score:3, Interesting)

      You are absolutely correct. For the longest (damn) time this did work. The problem is now the traffic doesn't burst like it used to. It's more sustained and oversubscription rules are breaking. Most ISPs are honestly trying to play a game of self-preservation so they can keep their service alive without being cost prohibitive.

      DPI is not evil so long as it is used to make the network better as a whole. As with anything it can be bent to the will of evil, but I disagree with that completely. I believe
      • when you simply pass traffic as you get it, you can avoid paying (in real dollars) for equipment that looks inside.

        you can avoid the network management complexity if you simply let networks 'work' as they always have.

        are you running into a lot of dropped packets? simple: you are over-selling. there is an EASY way to fix that.

        oh, and an evil way. guess which one most ISPs and large public networks pick?

        by the time you factor in the cost of the snooper silicon, all its overhead and the training/support ove
  • It's bad for the end user and good for the "corps" nothing good will come from this from my perspective, and not just because I am a p2p user.
  • If my ISP is going to inspect my packets to the point of identifying their content as p2p, then they should be 100% responsible for any and all illegal activities I may or may not conduct on their connections.

    The entire concept of the DMCA safe harbor clause was founded on the understanding that it would be virtually impossible for providers to monitor and filter illegal or unlawful activities and data. However, now it has become perfectly reasonable that they can identify and reroute or slow this traffic. This clearly nullify's the safeharbor provisions.

    The ISP's need to realize they cant have it both ways.
    • Ah, but they *can* have it both ways, as long as they keep their friendly neighborhood congress-critter on their payroll.
  • by Whuffo (1043790) on Monday May 12 2008, @01:37PM (#23381640) Journal
    This is quite the impressive machine they're talking about. But what they don't seem to cover very well are the legitimate uses for such a device. Just because they call "monitoring your communications" deep packet inspection doesn't make it right.

    It looks like a disaster in a box to me: not only does it allow anyone with the price of the machine to monitor and inspect each and every packet you exchange, it also is capable of destroying the legal protections that ISPs currently enjoy.

    The ISPs are treated like common carriers and are exempt from many liabilities because they carry all traffic equally and don't know or control the content of that traffic. Now that they're insisting that they need to "prioritize" some traffic at the expense of others, monitor and drop traffic because of its content, and are installing machines like these that further refine their ability to monitor and control what traffic you'll be allowed to transmit - well, their "safe harbor" exemptions are based on them not doing any of this.

    Just the existence of this machine will be the undoing of many...

  • by Vellmont (569020) on Monday May 12 2008, @02:21PM (#23382386)
    I'll bet in the war against p2p, making p2p data look like normal "priority" data is going to be far easier, and far cheaper than the ISPs trying to identify and block/slow the data they don't like. Consider that hiding p2p data takes one person with a keyboard and some smarts. In a month this guy will work around any solution the $800K machine guys have put together, and the next machine will be 8 million dollars to do the same job.

    Encryption? Just the first salvo. Others have pointed out that p2p makes a lot of connections. That's fine, just create a secure queuing system where people wait their turns (and don't have multiple data streams). Or, a repeater system where you get one or two data feeds in, and feed to one or two other people. There's no reason why a p2p system has to have 50 different connections to different people. Start looking at the data itself and see if it's http-like? Okee-doke, just create an http wrapper around your data so it looks like http. These are just the dumb ideas I came up with on the fly. Real solutions would be a lot better.

    This kind of asymmetric "war" has been fought before, namely with copyright protection in the 80s. The result? Cracked programs are more valuable than non-cracked programs (oh, and all copyright protection schemes were cracked)

    In a system with untrusted intelligent nodes, you can't really create a priority system without some people making their non-priority data look like priority data. The internet was designed for the end nodes to be smart, and the network to be dumb. (The exact opposite of the phone system). It seems to me this is just a basic design principle of the internet.
  • Use IPsec (Score:3, Insightful)

    by Skapare (16644) on Monday May 12 2008, @02:40PM (#23382688) Homepage

    With IPsec, they won't even be able to see what protocol is being used. The more we use IPsec for everything, the less these things will look like an attractive way to spend money that would otherwise go to expanding capacity.

    • Encryption is a good idea, but ISPs can still detect undesirable content by the handshaking and unencrypted header info. Maxwell Smart's communications might be ultra-secure, but nearby KAOS agents still hear whenever his shoe rings, y'know?
    • by evanbd (210358) on Monday May 12 2008, @01:40PM (#23381686)
      Heck, to defeat this you could just use AES with a default key. Everyone can use the same key, and have it be publicly known. It's fine because this thing doesn't have the compute power to decrypt in real time, even if it knows what it needs to be decrypting and what the key is. Screw handshaking, key management, etc -- just make the CPU cost nonzero and you're done.
    • They can limit each encrypted bank or IM connection to 10-20KB/sec and you wouldn't even notice. You would notice your torrents slowing down though. Many ISPs are already using deep packet inspection. Hell, rogers in canada is playing around with inserting messages into websites [thestar.com]! I can only hope that it pushes more of the web to https.