Raman, S., and McCanne, S. Scalable Data Naming for Application Level Framing in Reliable Multicast. In Proc. ACM Multimedia (Sept. 1998), pp. 391-400.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....interest since it was first proposed, so in this section, we will make some detailed discussions on SRM and the application built on it, MediaBoard. 2. 1 SRM Data Model The core of SRM framework is a hierarchical naming scheme, which is defined in Scalable Naming and Announcement Protocol (SNAP) [7]. SNAP is superior to traditional flat sequence number name space in that it allows application layer objects to be mapped into transport layer, so that receivers can tailor their reliability by requesting only portion of the name space. Figure 1 shows how MediaBoard objects are represented in ....

Raman S, McCanne S. Scalable Data Naming for Application Level Framing in Reliable Multicast. In: Wolfgang Effelsberg, eds. ACM Multimedia 98 Electronic Proceedings. UK, 1998. URL: http://www. acm.org/sigmm/MM98/electronicA>roceedings/index.html

....packet sequence numbers. An ADU is solely de ned by application protocol, for example, for some database applications, it can be an object ID; or for a ftp application, a tuple containing le name, o set, length . Other more sophisticated mechanisms such as hierarchical data naming schemes [15, 5] can be incorporated as well, to achieve better exibility and eciency. 3.3 Other Components There are many other functionalities that could be incorporated into ALMI, such as delay constraints for real time sessions, access control for private multicast sessions and etc. In ALMI, an application ....

S. Raman and S. McCanne. Scalable Data Naming for Application Level Framing in Reliable Multicast. In Proc. ACM Multimedia '98, Bristol, UK, September 1998.

....packet sequence numbers. An ADU is solely defined by the application protocol, for example, for some database applications, it can be an object ID; or for a ftp application, a tuple containing file name, offset, length . Other more sophisticated mechanisms such as hierarchical data naming schemes [17, 62] can be incorporated as well, to achieve better flexibility and efficiency. In summary, ALMI provides a flexible service for data reliability in that it allows applications to specify their reliability requirements: total data reliability or only recovering useful data as wanted. The former is ....

S. Raman and S. McCanne. Scalable Data Naming for Application Level Framing in Reliable Multicast. In Proc. of ACM Multimedia '98, Bristol, UK, September 1998.

....of the profile for distributed interactive Java animations and multi user VRML was outlined. There are a number of items we will be working on in the near future: The integration of general naming approaches for application level framing into our framework. The work of Raman McCanne [22] and Fuchs et al. 5] could be used to complement our sub component IDs. Crowcroft et al. propose a Reliable Multicast Framing Protocol (RMFP) 3] Since we anticipate that limited semantic reliability might be desirable for several payload types using our profile, we think about merging RMFP ....

S. Raman, S. McCanne. Scalable Data Naming for Application Level Framing in Reliable Multicast. In: Proc. of ACM Multimedia `98, Bristol, September 1998.

.... protocols must choose transmission units that are meaningful to applications, i.e. packetization is best done in terms of Application Data Units (ADUs) One of the important components of ALF based protocols is the common data naming between the transmission protocol and application (e.g. [19]) which we follow in the design of our meta data. We take ALF like ideas one step further by arguing that routing decisions are also best made in application controlled and applicationspecific ways, using knowledge of not just network topology but application data layout and the state of ....

RAMAN, S., AND MCCANNE, S. Scalable Data Naming for Application Level Framing in Reliable Multicast. In Proc. ACM Multimedia (Sept. 1998).

....and application driven fashion. Since libsrm is one of the most frequently referenced approaches to realize reliability at the application level, we investigate its two services in more detail. a) Scalable Naming and Announcement Protocol The Scalable Naming and Announcement Protocol (SNAP) [80] enables the application to identify where received or lost ADUs belong. To this end it provides a naming tree for each participant in a session. The nodes and the leaves of that tree represent containers with a unique container ID (CID) and an application level name (page number, object ID, ....

S. Raman and S. McCanne. Scalable data naming for application level framing in reliable multicast. In: Proc. of 6th ACM International Conference on Multimedia, Bristol, UK, 1998, pp. 391 - 400.

....sequence numbers. An ADU is solely defined by application protocol, for example, for some database applications, it can be an object ID; or for a ftp application, a 3 tuple containing file name, offset, length . Other more sophisticated mechanisms such as hierarchical data naming schemes [9, 23] can be incorporated as well, to achieve better flexibility and efficiency. Other Components There are many other functions that could be incorporated into ALMI, such as delay constraints for realtime sessions, access control for private multicast sessions, etc. In ALMI, an application delay ....

S. Raman and S. McCanne. Scalable Data Naming for Application Level Framing in Reliable Multicast. In Proc. of ACM Multimedia '98, Bristol, UK, September 1998.

....sequence numbers. An ADU is solely defined by application protocol, for example, for some database applications, it can be an object ID; or for a ftp application, a tuple containing file name, offset, length . Other more sophisticated mechanisms such as hierarchical data naming schemes [17, 5] can be incorporated as well, to achieve better flexibility and efficiency. 3.3. Other Components There are many other functionalities that could be incorporated into ALMI, such as delay constraints for real time sessions, access control for private multicast sessions and etc. In ALMI, an ....

S. Raman and S. McCanne. Scalable Data Naming for Application Level Framing in Reliable Multicast. In Proc. ACM Multimedia '98, Bristol, UK, September 1998.

....sequence numbers. An ADU is solely defined by application protocol, for example, for some database applications, it can be an object ID; or for a ftp application, a tuple containing file name, offset, length . Other more sophisticated mechanisms such as hierarchical data naming schemes [15, 5] can be incorporated as well, to achieve better flexibility and efficiency. 3.3 Other Components There are many other functionalities that could be incorporated into ALMI, such as delay constraints for realtime sessions, access control for private multicast sessions and etc. In ALMI, an ....

S. Raman and S. McCanne. Scalable Data Naming for Application Level Framing in Reliable Multicast. In Proc. ACM Multimedia '98, Bristol, UK, September 1998.

....almi packet sequence numbers. An ADU is solely de ned by application protocol, for example, for some database applications, it can be an object ID; or for a ftp application, a 3 tuple containing le name, o set, length . Other more sophisticated mechanisms such as hierarchical data naming schemes [9, 23] can be incorporated as well, to achieve better exibility and eciency. Other Components There are many other functions that could be incorporated into almi, such as delay constraints for realtime sessions, access control for private multicast sessions, etc. In almi, an application delay bounds ....

S. Raman and S. McCanne. Scalable Data Naming for Application Level Framing in Reliable Multicast. In Proc. of ACM Multimedia '98, Bristol, UK, September 1998.

....unique, or the cost of running a protocol that assigns locally unique addresses. We are not so lucky in low data rate distributed systems with high dynamics and energy constraints. The SCADDS project [3] provides a potential framework for a solution because is uses attribute based data naming [14, 15, 16]. In SCADDS, applications are unlikely to ask the question: Was there motion detected at sensor #27.201.3.97 Rather, they might ask: Was there motion detected in the north east quadrant or Where has motion been detected recently This kind of data naming will be application specific, and ....

....deeply distributed systems such as sensor networks. Our work is complementary to SCADDS and we owe many of our assumptions about future sensor network architectures to that project. The attribute based data naming proposed in SCADDS is similar to the naming schemes used by Raman and McCanne in ALF [14, 18], Adjie Winoto et al. in the Intentional Naming System [15] and Michel et al. in their adaptive web caching architecture [16] 11 8 Conclusions and Future Work We have presented a rationale for using Random, Ephemeral TRansaction Identifiers (RETRI) in sensor networks. In our scheme, nodes ....

Suchitra Raman and Steven McCanne. Scalable data naming for application level framing in reliable multicast. In Proceedings of the 6th ACM international conference on Multimedia, pages 391--400, 1998.

.... protocols must choose transmission units that are meaningful to applications, i.e. packetization is best done in terms of Application Data Units (ADUs) One of the important components of ALF based protocols is the common data naming between the transmission protocol and application (e.g. [20]) which we follow in the design of our meta data. We take ALF like ideas one step further by arguing that routing decisions are also best made in applicationcontrolled and application speci c ways, using knowledge of not just network topology but application data layout and the state of resources ....

Raman, S., and McCanne, S. Scalable Data Naming for Application Level Framing in Reliable Multicast. In Proc. ACM Multimedia (Sept. 1998).

....and speci c payload for video formats within RTP were heavily in uenced by ALF. We expect to implement our communication protocol within the RTP framework. The Scalable Naming and Announcement Protocol (SNAP) provides an interesting possible approach to the naming issues identi ed in our work [10]. This protocol allows participants to build source based hierarchical namespaces. The protocol builds on an underlying announce listen mechanism (i.e. SRM [4] to communicate the namespace to other participants in a scalable manner. The MPEG 4 standard [5] provides extensive support for ....

S. Raman and S. McCanne. Scalable data naming for application level framing in reliable multicast. Proceeding of the ACM Multimedia Conference 1998, 1998.

....unique, or the cost of running a protocol that assigns locally unique addresses. We are not so lucky in low data rate distributed systems with high dynamics and energy constraints. The SCADDS project [6] provides a potential framework for a solution because is uses attribute based data naming [17, 1, 13]. In SCADDS, applications are unlikely to ask: Was there motion detected at sensor #27.201.3.97 3 Rather, they might ask: Was there motion detected in the north east quadrant or Where has motion been detected recently This kind of data naming will be applicationspecific, and effectively ....

....distributed systems such as sensor networks. Our work is complementary to SCADDS and we owe many of our assumptions about future sensor network architectures to that project. The attribute based data naming proposed in SCADDS is sim9 ilar to the naming schemes used by Raman and McCanne in ALF [17, 7], Adjie Winoto et al. in the Intentional Naming System [1] and Michel et al. in their adaptive web caching architecture [13] 8. Conclusions and future work We have presented a rationale for using Random, Ephemeral TRansaction Identifiers (RETRI) in sensor networks. In our scheme, nodes pick ....

S. Raman and S. McCanne. Scalable data naming for application level framing in reliable multicast. In Proceedings of the 6th ACM international conference on Multimedia, pages 391--400, 1998.

....to dynamic user behavior. WebTP is a receiver driven transport protocol for the Web that uses the ALF concept [77] Receiver driven protocol design is especially important for multicast communication. A fundamental challenge in the design of a reliable multicast protocol is the implosion problem [131]. When all receivers in a multicast group react to a packet loss by sending a NACK back to the source, a packet implosion overwhelms both the network and processing capabilities of 83 the source. The Scalable Reliable Multicast protocol (SRM) 72] solves this problem by employing a ....

....(SRM) 72] solves this problem by employing a receiver driven reliability and the ALF principle. With this approach, multicast receivers can implement selective reliability and tune their reliability requirements as needed. Therefore, ALF enhances scalability of multicast transport protocols [131]. Another advantage of ALF is that it can help avoid cache misses [31, 40] ALF increases the possibility that data are within the cache while being processed by a pipeline of consecutive protocol functions. One major drawback of ALF is that, it often requires that the application and the ....

S. Raman and S. McCanne. Scalable data naming for application level framing in reliable multicast. In INFOCOM '99, New York, NY, March 1999. 239

.... protocols must choose transmission units that are meaningful to applications, i.e. packetization is best done in terms of Application Data Units (ADUs) One of the important components of ALF based protocols is the common data naming between the transmission protocol and application (e.g. [21]) which we follow in the design of our meta data. We take ALF like ideas one step further by arguing that routing decisions are also best made in applicationcontrolled and application speci c ways, using knowledge of not just network topology but application data layout and the state of resources ....

Raman, S., and McCanne, S. Scalable Data Naming for Application Level Framing in Reliable Multicast. In Proc. ACM Multimedia (Sept. 1998).

.... protocols must choose transmission units that are meaningful to applications, i.e. packetization is best done in terms of Application Data Units (ADUs) One of the important components of ALF based protocols is the common data naming between the transmission protocol and application (e.g. [20]) which we follow in the design of our meta data. We take ALF like ideas one step further by arguing that routing decisions are also best made in applicationcontrolled and application specific ways, using knowledge of not just network topology but application data layout and the state of ....

Raman, S., and McCanne, S. Scalable Data Naming for Application Level Framing in Reliable Multicast. In Proc. ACM Multimedia (Sept. 1998).

No context found.

S. Raman and S. McCanne. Scalable data naming for application level framing in reliable multicast. Proceeding of the ACM Multimedia Conference 1998.

....A more detailed comparison of related work is presented in Section 6. ITP s receiver controlled selective reliability differs in significant ways from WebTP, which does share similar reliability goals. For example, WebTP uses a fully qualified URL to identify an ADU similar to the work reported in [33], while ITP uses a simpler fixed length ADU sequence number but disseminates a mapping at the beginning of a connection that enables customization. ITP uses the simpler strategy of sending the RTO in the packet header to the receiver compared to WebTP, which uses estimates the mean interarrival ....

RAMAN, S., AND MCCANNE, S. Scalable Data Naming for Application Level Framing in Reliable Multicast. In Proceedings of ACM Multimedia '98 (Bristol, UK, Sept. 1998), ACM.

....transport primitives. Primitives such as sequence numbers hide the structure of the application s data space from the transport protocol. In order to allow the transport protocol to be ne tuned to the needs of the application, we use a richer naming scheme SNAP that is more amenable to ALF [43]. This is discussed in more detail in Section 5.1. While SRM provides the basic building blocks for an endto end reliable multicast framework, it has no support for dealing with heterogeneity in the network and in end client devices or applications. Dealing with congestion and bandwidth ....

....for a sematically richer and more structured naming scheme in the transport protocol. If the application can embed its own semantic information into the structure of the transport protocol s name space, then it becomes much easier for the receiving application to control the protocol behavior. In [43], Raman et al. proposed a Scalable Naming and Announcement Protocol (SNAP) for the SRM framework. SNAP de nes a hierarchical namespace that is used to identify data objects between the application and the transport protocol. Structuring data hierarchically allows the application to de ne di erent ....

Raman, S., and McCanne, S. Scalable Data Naming for Application Level Framing in Reliable Multicast. In Proceedings of ACM Multimedia '98 (Bristol, U.K., Sept. 1998).

....data from the origin server and multicasts the data to peer caching components. We have implemented our webcast design in an application called MASHCast using the multimedia application toolkit MASH [14] and a SRM protocol module called libsrm which features the SNAP scalable data naming protocol [18]. The remainder of this paper is structured as follows. We rst describe our architecture, then SRM s basic reliability mechanisms and our extensions to them. We next present our implementation and initial performance characteristics. Lastly, we report on lessons learned during implementation and ....

....Adaptive Timers. MASH o ers many more multimedia components including standard audio and video transmission protocols. libsrm is an instantiation of the framework presented in [6] In addition to the SRM reliability mechanisms, libsrm incorporates the SNAP hierarchical, scalable naming protocol [18]. libsrm is available as a standalone library and as a MASH component. In general, we found libsrm simple to use. All of the SRM extensions described in section 4 were implemented in approximately 1200 lines 0.001 0.01 0.1 1 10 (1) 2) 3) 4) 5) 6) 7) 8) 9) 10) 11) 12) 13) 14) ....

S. Raman and S. McCanne. Scalable data naming for application level framing in reliable multicast. In ACM Multimedia '98, Bristol, UK, September 1998.

....node triggers a namespace NACK, whereas a mismatched leaf ADU causes the receiver to transmit a data NACK. In each case, based on the node meta data information and assistance from the application, the receiver decides if further repair is warranted. Details of the protocol steps are available in [39]. SNAP simultaneously solves the namespace scaling problem and provides a rich naming structure that is amenable to ALF. It exploits hierarchy to effectively add a level of indirection to the meta data dissemination protocol. In our approach, hierarchy provides a summarization 3 The summary of ....

RAMAN, S., AND MCCANNE, S. Scalable Data Naming for Application Level Framing in Reliable Multicast. In Proceedings of ACM Multimedia '98 (Bristol, UK, Sept. 1998), ACM.

No context found.

Raman, S., and McCanne, S. Scalable Data Naming for Application Level Framing in Reliable Multicast. In Proc. ACM Multimedia (Sept. 1998), pp. 391-400.

No context found.

S. Raman and S. McCanne. Scalable Data Naming for Application Level Framing in Reliable Multicast. In Proc. of ACM Multimedia '98, Bristol, UK, September 1998.

No context found.

Raman, S., and McCanne, S. Scalable Data Naming for Application Level Framing in Reliable Multicast. In Proc. ACM Multimedia (Sept. 1998).

First 50 documents

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC