BestTechVideos: Category TCP/IP Videos

Content Delivery Network Pricing, Costs for Outsourced Video Delivery

scoundrel — Wed, 12 Mar 2008 23:35:59 GMT

Whether you’re in an organization that needs to deliver lots of video or a smaller company that needs to deliver only a few videos, the going rate for these services can still be hard to figure out. What variables determine the final price? What is the going rate when you outsource delivery and storage to a third party?

This presentation offers real pricing numbers from large, globally focused content delivery networks as well as smaller regional service providers. Hear what the going rate is today for video delivery and learn what you should really be paying for these services.

Presenter Dan Rayburn, Executive Vice President, StreamingMedia.com

Read more about this video…

Want to control this feed contents? Sign up here and create your own feed!

Want more on these topics?
Browse the archive of posts filed under Conferences, Technologies, Companies, Networking, Lectures, TCP/IP

Internet Security Keynote Google VP Vint Cerf

scoundrel — Tue, 13 Nov 2007 08:12:40 GMT

Internet Security Summit Keynote Google VP Vint Cerf topics include malware, international domain names, P2P protocols and IP protection issues.

Read more about this video…

Want to control this feed contents? Sign up here and create your own feed!

Want more on these topics?
Browse the archive of posts filed under Conferences, Companies, Broadcasting, Networking, Techtalks, Google, Lectures, TCP/IP

Drive-By Pharming and Other WebApp Bummers

scoundrel — Thu, 12 Jul 2007 16:25:46 GMT

Google Tech Talks
June 28, 2007

ABSTRACT

Inexpensive broadband routers are a popular way for people to create an internal, and sometimes wireless, network in their homes. By purchasing such a router and plugging it in, they can have a network set up in seconds. Unfortunately, by visiting a malicious web page, a person can inadvertently open up his router for attack; settings on the router can be changed, including the DNS servers used by the members of this small, quickly erected internal network. This talk examines this attack in depth, and will lead to discussion about similar dangers that emerge when commonly used technologies are abused.

Read more about this video…

Want to control this feed contents? Sign up here and create your own feed!

Want more on these topics?
Browse the archive of posts filed under Conferences, Companies, Broadcasting, Networking, Techtalks, Google, Lectures, TCP/IP, DNS

Seattle Conference on Scalability: SCTPs Reliability and Fault Tolerance

scoundrel — Wed, 11 Jul 2007 15:32:02 GMT

Google Tech Talks
June 23, 2007

ABSTRACT

Low cost clusters are usually built from commodity parts and use standard transport protocols like TCP/IP. Once systems become large enough, reliability and fault tolerance become an important issue and TCP/IP often requires additional mechanisms to ensure reliability of the application. The Stream Control Transmission Protocol (SCTP) is a newly standardized transport protocol that provides additional mechanisms for reliability beyond that of TCP. The added reliability and fault tolerance of SCTP may function better for MapReduce-like distributed applications on large commodity clusters.

SCTP has the following features that provide additional levels of reliability and fault tolerance. Selective acknowledgment (SACK) is built-in to the protocol with the ability to express larger gaps than TCP; as a result, SCTP outperforms TCP under loss. For cluster nodes with multiple interfaces, SCTP supports multihoming, which transparently provides failover in the event of network path failure. SCTP has the stronger CRC32c checksum which is necessary with high data rates and large scale systems. SCTP also allows multiple streams within a single connection, providing a solution to the head-of-line blocking problem present in TCP-based farming applications
like Google's MapReduce. Like TCP, SCTP provides a reliable data stream by default, but unlike TCP, messages can optionally age or reliability can be disabled altogether. The SCTP API provides both a one-to-one (like TCP) and a one-to-many (like UDP) socket style; use of a one-to-many style socket can reduce the number of file descriptors required by an application, making it more scalable.

Speakers: Brad Penoff, Mike Tsai, Alan Wagner

Read more about this video…

Want to control this feed contents? Sign up here and create your own feed!

Want more on these topics?
Browse the archive of posts filed under Conferences, Companies, Broadcasting, Networking, Techtalks, Google, Lectures, TCP/IP

BGP at 18: Lessons In Protocol Design

scoundrel — Sat, 05 May 2007 10:30:08 GMT

Google Tech Talks
April 17, 2007

ABSTRACT

18th anniversary of BGP. In this talk we examine the evolution of BGP over these 18 years, and look at the lessons we could learn from this.

Dr. Yakov Rekhter joined Juniper Networks in Dec 2000, where he is a Distinguished Engineer. Prior to joining Juniper, Yakov worked at Cisco Systems, where he was a Cisco Fellow. Prior to joining Cisco in 1995, he worked at IBM T.J. Watson Research Center.

Yakov Rekhter was one of the leading architects and a major software developer of the NSFNET Backbone Phase II. He co-designed the Border Gateway Protocol (BGP). He was also one of the lead designers of Tag Switching, BGP/MPLS based VPNs, and MPLS Traffic Engineering. Among his most recent activities is the work on Generalized Multi-Protocol Label Switching (GMPLS). His other contributions to contemporary Internet technology include: Classless Inter-Domain Routing (CIDR) and IP address allocation for private Internets.

He is the author or co-author of over 40 IETF RFCs, and numerous papers and articles on TCP/IP and the Internet. His recent books include: "MPLS: Technology and Applications" (Morgan Kauffman, 2000) and "Switching in IP Networks: IP Switching, Tag Switching and Related Technologies" (Morgan Kauffman, 1998).

Read more about this video…

Want to control this feed contents? Sign up here and create your own feed!

Want more on these topics?
Browse the archive of posts filed under Conferences, Technologies, Companies, Broadcasting, Networking, Techtalks, Google, Lectures, TCP/IP

LinuxConf.Au: A new kind of real-time: enterprise real-time

scoundrel — Thu, 05 Apr 2007 11:50:26 GMT

Traditionally, real-time systems have been primarily associated with data acquistion or industrial control systems, where the systems were often smaller embedded systems, running specialized RTOS's that generally didn't have the full functionality found in a general purpose OS. The CONFIG_PREEMPT_RT patches by Ingo Molnar have enabled a new kind of real-time systems, which are based on Linux and which support SMP processors, TCP/IP, and the ability to run enterprise middleware, including databases and middleware.

This talk will talk about how the author's real-time team at IBM was able to take a fairly large (at the time we started, over 1.7 megabytes of patch) open source kernel patch being developed by the community, join the community, stablize the code, and produce a commercially supported product offering based on that patch to support a real-time JVM. This talk will discuss the technology behind the real-time patches, how they differ from other approaches, the challenges we encountered in trying to create a supportable product which was dependent on a rapidly moving development stream that had not yet even been merged with mainline, what this patch has allowed us to do with it and our real-time Java offering.

Read more about this video…

Want to control this feed contents? Sign up here and create your own feed!

Want more on these topics?
Browse the archive of posts filed under OS, Conferences, Development, Broadcasting, Networking, Linux, LinuxConf.AU, Java, Lectures, TCP/IP

LinuxConf.Au: Routing and IPSEC Lookup Scaling in the Linux Kernel

scoundrel — Wed, 04 Apr 2007 13:18:02 GMT

Finding the appropriate path for a packet is the single most important task the kernel networking stack partakes in for every frame sent. For sockets, we can be smart and only do a lookup once for that socket when a new connection is created. But for general routing and IPSEC traffic we must incur a lookup for every packet.

Therefore it is crucial that the lookup of this path be as efficient as possible. The goal is to incur the minimum possible number of cpu memory references during this lookup operation.

On the other hand, it is also important to make sure that route and IPSEC rule changes are efficient as well, and that such changes do not have adverse effects upon the lookup engine under normal circumstances.

The author will discuss his work on the scaling of the IPSEC subsystem data structures. Interesting work on "active garbage collection" in the IPv4 routing cache by Robert Olsson will be presented as well. Finally, the ongoing work investigating a move to a "grand unified flow cache" for all packet path lookups will also be presented. In fact, the lessons learned from the IPSEC scaling and active garbage collection work provide important theoretical groundwork for any unified flow cache scheme.

The ancilliary topic of the impliciation that highly multithreaded cores, such as Sun's Niagara, have upon routing lookup performance will be touched upon as well.

Read more about this video…

Want to control this feed contents? Sign up here and create your own feed!

Want more on these topics?
Browse the archive of posts filed under OS, Conferences, Broadcasting, Networking, Linux, LinuxConf.AU, Lectures, TCP/IP

LinuxConf.Au: Linux Clusters

scoundrel — Thu, 29 Mar 2007 11:19:42 GMT

Clusters are defined as a set of computers working as one to execute tasks. The applications for it has no limit: from balance requests for web services to systems for explore petroleum, the amount of saves can be from thousands to gazillions of dollars. More then that, it is an extensive and interesting area. The Open Source community has been know as a big player in Clusters, with several of the biggest clusters in the world running Linux. And the tools available for it improve quickly. Distributed file systems, fault tolerance software, data replication, monitoring and service takeover are some of softwares developed to create those environments.

In this presentation I want to explain about how to provide this services in differents enviroments and which softwares choose for each kind of situation. We will go through the basics of Clusters, HA, LB and how to identify the pieces involved in a complete solution. Then we will show the available softwares, the advantages and not so good issues of each one, and help the administrator to create a complete environment. This presentation will show several implementations of Clusters - high availability, high processing computing and load balance - and the technologies for each one. We are going to talk about DRBD, Heartbeat, Ultramonkey, Linux Virtual Server, Global FileSystem and more.

Read more about this video…

Want to control this feed contents? Sign up here and create your own feed!

Want more on these topics?
Browse the archive of posts filed under OS, Conferences, Broadcasting, Networking, Linux, LinuxConf.AU, Lectures, TCP/IP

LinuxConf.Au: Open Source Art

scoundrel — Thu, 29 Mar 2007 11:06:59 GMT

Why do all laptops look horrible? What does it take to turn hardware into something beautiful and lasting? I dismantled a laptop and reconstructed it as a simple piece of art. By removing all unnecessary parts and combining the naked hardware with acrylic the laptop has taken on a completely new form. The goal is to make several units, and incorporate them into a home operations center.

The project began by reusing laptops which had broken disks or disk controllers. The machine boots via the network, and uses root over NFS. A discussion of the deconstruction process, and the setting up of pxeboot with root over NFS will begin the presentation.

Now that you have a beautiful display, what can you do with it? As an avid cyclist I have a keen interest in the weather. When is it going to rain and for how long? I developed software to monitor the national weather site, and keep a 24 hour cache of data locally. The presentation will cover the data retrieval and retention process.

Finally, now that we have this data how do we display it? My initial work has been in using enlightenment for graphics via the framebuffer device. The code is written in C, and displays still and motion images of weather data. The talk will end with a tutorial on developing display code for viewing various data sets, and a discussion of ideas for improvement and new hacks.

This presentation should be interesting for hardware and software hackers alike, as well as the curious. I hope that people will walk away motivated to hack hardware for their own purposes.

Read more about this video…

Want to control this feed contents? Sign up here and create your own feed!

Want more on these topics?
Browse the archive of posts filed under OS, Conferences, Development, Broadcasting, Networking, Linux, LinuxConf.AU, C and C++, Lectures, TCP/IP

LinuxConf.Au: Making NFS Suck Faster

scoundrel — Sat, 24 Mar 2007 13:38:05 GMT

Linux makes a great little NFS server, the emphasis being on "little". SGI's experience is that Linux' NFS server will scale to small machines with 4 or fewer processors, but not to larger machines. To make Linux scale to 8 processors and 8 Gigabit Ethernet network cards, an important market segment for SGI, we have had to perform a lot of performance and scaling work.

After protracted internal development, this work is now (July 2006) just starting to be pushed into the Linux mainstream, as a series of over 40 kernel and nfs-utils patches. See the Linux NFS mailing list at nfs.sourceforge.net.

The talk will start with a brief introduction to the theory of operation of the Linux NFS server, explaining how the nfsd threads work and a brief sketch of the lifetime of an NFS call as seen by the server.

Tools and techniques for identifying and measuring software bottlenecks on large machines will be explored. These include profilers, statistics tools, network sniffers, and the relative merits of various kinds of load generators.

Various specific bottlenecks in the NFS server (discovered using these tools) will be covered, along with how they affect performance on real workloads and the approach SGI have taken in fixing each. Some of the bottlenecks are specific to the NUMA nature of SGI's architecture, but most are generic to any multi-processor platform.

The problems associated with erving large numbers (thousands) of clients, rather than large amount of traffic from mere tens of clients, will be discussed, together with how SGI have solved those.

Finally, there will be a brief mention of work remaining for the future.

Some knowledge of Linux kernel internals and TCP/IP networking will be assumed, but not of NFS. The talk will appeal to kernel programmers, people interested in NFS and network performance, and to programmers interested in improving Linux kernel performance.

Read more about this video…

Want to control this feed contents? Sign up here and create your own feed!

Want more on these topics?
Browse the archive of posts filed under OS, Conferences, Development, Broadcasting, Networking, Linux, LinuxConf.AU, C and C++, Lectures, TCP/IP