|
Computer Centre 99 project |
|---|
The LIP CC internal projects for 1999 are:
VIDEOCONFERENCING FOR HEP RESEARCHERS
OBJECTIVES
In the last year’s packet-mode videoconference has found a very important place in the academic world and has been adopted by the major HEP (High Energy Physics) sites and collaborations. Both ATLAS and CMS in their Computing Model Proposal clearly indicate that video- conferencing is an essential part of the tools needed to collaborate worldwide. ALICE and LHC-B also have expressed strong interest in such a facility as soon as it is made available as a service.
The key objective of this project is to study and propose the most cost-effective solutions for Video-conferencing (VC) in the High Energy Physics community.
In this framework, the objectives are to investigate all the topics of modern video conferencing tools. The main goals are:
INTRODUCTION
There are presently two major forms of video-conferencing:
Since several years a number of initiatives have been undertaken to overcome the many limitations of CODEC video-conferencing by using workstations, packet networks and software applications enabling cooperative distance working. This is what is now called Packet Video-Conferencing. As both workstations/PCs and algorithms become more powerful, Packet video-conferencing will overtake CODEC video-conferencing and become the standard form of video-conferencing.
From the user's point of view, a key feature of Packet video-conferencing is that it allows the implementation of software application sharing, and shared whiteboard (a common window on screens of multiple users on which graphics or text can be annotated by each user separately).
Another key feature of Packet VC is that it may be at no direct cost for users who can perform Packet VC over an existing network. With adequate optimization, Packet VC gives satisfactory service with 200kbit/s of network bandwidth per videoconference. When such a bandwidth is not always available for Packet VC, then the Quality of Service will vary according to the instantaneous network load. This is a major difficulty in some parts of Europe where available network bandwidth is limited and expensive. This explains why Packet video-conferencing is much more developed in the US, which do not suffer from these limitations.
This is the best known and longer in use form of video-conferencing. Closed systems are available from industry and can be installed in conference rooms as dedicated equipment. CODEC systems communicate over ISDN links.
Videoconference sessions are either point-to-point between two CODEC systems, or multi-point among several conference room systems. In this latter case an additional piece of equipment called Multi-point Control Unit (MCU) is required. Telephone companies are beginning to offer MCU services - for a fee - together with a scheduling system (also called booking system).
This scheduling system will impose a major constraint if video-conferencing tools become part of the day-to-day working environment of the physicists. Indeed a scheduling system may require booking as much as two weeks in advance, which is felt as a very stringent limitation.
PARTNERS
Contacts have already been made with CERN IT division Communications and Systems group that is in charge of the CERN pilot Packet video and video-conferencing activities, which has shown strong interest in the LIP participation. The CS group is conducting the Video-conferencing project for LHC collaborations officially approved last year by the LHC Computing Board (LCB). LIP is particularly interested in this project which covers a wide variety of technologies. The most promising is the Virtual Room Videoconferencing System (VRVS), a packet mode video conferencing system based on the LBNL and UCL applications that are well adapted to HEP needs, and that is being developed by CERN and Caltech. LIP will join the CERN research and development team.
Last year FCCN (Fundação para a Computação Científica Nacional) the Portuguese foundation which coordinates the Portuguese academic and research network (RCCN) decided to officially research and support packet-mode-video-conference activities within the Portuguese network. LIP has made contacts with FCCN and a joint effort will be made to research, develop and foment a videoconference infrastructure between Portuguese research institutions and foreign institutions like CERN, using the RCCN infrastructure.
PACKET-MODE VIDEOCONFERENCE
Packet-mode video-conferencing makes use of workstations equipped with audio and video capabilities and connected over regular IP packet networks (Internet/MBONE). It can be cheap, flexible and well integrated in the users computing environment. The applications can be supported on a wide range of UNIX workstations; some MacIntoshes and PCs may also interact. Public-domain software is available, and ensures good interoperability.
Packet-mode videoconference is a very promising technology that can lead to the decrease of traveling needs to attend meetings and conferences (especially important for small countries far from central Europe) hence decreasing costs and increasing productivity. This kind of technology is also helpful for geographically scattered organizations since allows cooperative work between remote researchers.
Another potential use of this technology is remote intervention to solve problems, for instance in data acquisition systems, allowing engineers and experts to watch equipment and trouble shoot problems without being actually present.
This is a fairly new technology with still many issues waiting to be researched. The quality is not only dependent on the available network bandwidth, but also on the instantaneous network load, which is often unpredictable. New protocols like the reservation protocol (RSVP) and real time protocols (RTP) are still being developed. Packet-mode videoconferencing cannot work for all the destinations, because of the required bandwidth. For instance a minimal audio-video stream requires a bandwidth of the order of 200 kilobits per second.
The computing platforms used for packet mode videoconference have been high-end UNIX workstations with special video capture boards this equipment is usually dedicated to these tasks and very expensive. Today however the availability of the UNIX and WindowsNT operating systems on PC platforms, the low cost video/sound capture boards and digital cameras is changing this scenario. We intend to research, develop and use these platforms that will allow anyone with a PC on the desktop to have access to videoconference.
Most packet mode videoconference applications can run in two modes:
Unicasts cross bridges transparently. Since the bridges know about the network topology (i.e. where the source and destination are located), only the segments that have to support the traffic will forward the packet.
THE VIRTUAL ROOM VIDEOCONFERENCING SYSTEM (VRVS)
The VRVS system is based on a "Virtual Videoconference Room" concept illustrated in Figure 1. A series of IP Servers/Reflectors connects users within a virtual room via a set of interconnected IP tunnels, so that they form a private video-group. Each participant sees the others in the "virtual room" through a series of windows of variable sizes (under user control). A web user-interface provides worldwide secure access, on demand, to each virtual room. One also can start up a point-to-point connection at a lower bandwidth (with a fixed maximum of 64 kbit/s). The "Virtual Rooms" concept makes conference access and scheduling easier, and makes effective bandwidth management on critical links.
Booking a virtual conference room is performed by the user in the same way, as he would book a local room, but independently of his location. One can change or cancel a booking in a familiar way. If all virtual rooms are already booked this means that the (pre-set) maximum number of parallel conferences has already been reached. This maximum number is chosen in order to deliver conferences of acceptable quality within a share of the available bandwidth. Therefore the "Acceptable quality" notion may evolve (increased interactivity and functionality) if more bandwidth becomes available.
Figure 1
The video Reflectors run on Unix platforms, and interconnect the users joining a virtual room by permanent IP tunnels, forming a set of virtual video sub-networks. Participants at any location can join videoconferences (in one or several virtual rooms) by contacting their "closest" reflector. In order to make efficient use of the bandwidth, packets (video, audio and data streams) are sent through the tunnel between two reflectors only if there are participants in the same virtual room on both sides.
In addition, the network reflector topology is chosen taking into account both geography and the bandwidth available on each network link, in order to optimize the network-connectivity paths. The extension of the virtual video sub-networks has progressed by installing several reflectors in Universities and HEP labs in Europe and USA. The current topology is described in Figure 2 (Europe) and Figure 3 (USA), with a total of 14 installed reflectors running in:
Figure 2 Figure 3
The use of Web technology allows any authorized user, at any location, to access a wide range of services for packet-based videoconferencing. The Web-based user interface is supported by centralized conference scheduling, coordination and access control. In addition to the monitoring and control tools provided in the LBNL application suite, features available through the Web interface include:
The booking Web interface now allows to:
The new Web-based Administration Interface allows reflector managers to perform the following actions:
FIRST OUTCOME OF THE VRVS PACKET SYSTEM
Strong interest from HEP partners has been shown especially from European Member states. Since the Web-based packet system went into trial, the system has been deployed and expanded to 370 registered hosts running the VRVS software from more than 20 different countries. 14 "Reflectors" manage the traffic flow at HEP labs and Universities in Europe and USA.
The following graph shows the evolution of the number of machines registered in the VRVS system as from 1st January 1997.
As a significant extract from the VRVS statistics, the following table shows the number of real-work meetings (excluding test sessions) from 1st January 1998 to 1st June 1998. The different meetings involved at least one site from Europe (UK, Italy, France, Spain, etc…), or one site from the USA.
From |
Connections to VRVS Teleconferences (1st Jan 98 - 1st Jun 98) |
Different Hosts |
USA |
104 |
27 |
Europe |
162 |
63 |
UK |
54 |
16 |
Italy |
46 |
19 |
France |
21 |
9 |
Spain |
17 |
5 |
Others |
24 |
14 |
In addition, during the same period of time, about 100 point-to-point sessions involved sites from The Netherlands, Germany, UK, Italy and France.
COMMODITY COMPUTING COMPONENTS
INTRODUCTION
In the past years the High Energy Physics community have satisfied his need for computing by deploying RISC/UNIX machines. The new generation experiments, based on LHC (Large Hadron Collider), will demand computing capacities that are at least three orders of magnitudes higher making the usage of the traditional RISC farms unaffordable.
At CERN the IT division through the IP section of the PDP (Physics Data Processing) group has established a pilot project to construct and evaluate PC farms. Several PC farms are in study and production:
LIP has developed activities in this area since 1997. These activities have resulted in the decision of using low cost PCs as a replacement of desktop X terminals. These PCs run Linux in a cluster configuration sharing the operating system and configurations. Tools have been developed to ease the cluster management and integration of new desktop systems. Work is also being done in the evaluation of PCs for high performance computing with both Linux and WindowsNT.
This work is being done in the belief that only by using commodity computing components will the HEP community be sure to align itself with the best price/performance possible and reach the LHC computing requirements at an affordable cost.
OBJECTIVES
For 1999 the activities around the commodity computing components field will continue. The objective is to build a small production farm of Pentium II Linux systems.
THE FARM
The farm systems should be connected through a Fast Ethernet high speed network. The farm will be composed of one main server with scsi disks dedicated mostly to data storage and retrieval and several (at least two) stripped systems dedicated to CPU tasks. The know how obtained in the Linux desktop cluster will be applied and enhanced in this project.
The stripped systems will be equipped with the essential minimum, motherboard, cpu, memory, network card, graphics card and a small disk for swapping. The keyboard, mouse and monitor ports will be connected to one data switch which will allow to perform the management tasks for all systems from one console. With this configuration increasing the computing power of the cluster should be fairly inexpensive.
The choice of Linux is based on the know how obtained previously which indicate that Linux has higher performance than WindowsNT. Linux is also easily integrated in the LIP computer Centre infrastructure that is now based mostly on UNIX systems. Users are familiar with UNIX systems and some are developing software to be run in their Linux desktops, this will also facilitate the porting of applications to the cluster. Finally Linux software is widely available well supported by the academic community and is free or has very low cost.
INTERNET IN THE SCHOOL
Participation in the Ministry of Science and Technology project "Internet in the School". LIP is responsible for one of the fifteen POPs (Points of Presence) of the Science, Technology and Society Network (RCTS).
POP-LIP will continue to administer all the network and computer equipment that allows 130 schools, libraries and formation centers to access the Internet.
The responsibilities of POP-LIP are the management and configuration of the equipment, maintenance of the Internet services, helpdesk support for problem submission and resolution and cooperation with responsible entities in the study and implementation of new services.
 Home Page
|
 Back |
 webmaster@lip.pt |