INF 5070 – Media Storage and Distribution Systems

Download Report

Transcript INF 5070 – Media Storage and Distribution Systems

INF 5070 – Media Storage and Distribution Systems:
Introduction and
Architectures
25/8 - 2003
Overview
 Intro
 about the course
 multimedia applications and challenges
 Architectures
 Media (Video) on Demand
 Machine internals
 Video server structures
 Examples
INF 5070 – media storage and distribution systems
2003 Carsten Griwodz & Pål Halvorsen
INF5070:
The Course
Lecturers in INF5070
 Carsten Griwodz
 email: griff @ ifi
 room: 3203
 Pål Halvorsen
 email: paalh @ ifi
 room: 3309
INF 5070 – media storage and distribution systems
2003 Carsten Griwodz & Pål Halvorsen
Content of INF5070 – I
architectures
Networ
k
file systems
Networ
k
media data
distribution
Networ
k
resource scheduling
Networ
k
protocols
topologies
INF 5070 – media storage and distribution systems
2003 Carsten Griwodz & Pål Halvorsen
Content of INF5070 – II
 System architectures
(server and system designs)
 Media data
(wire and file formats, codecs)
 Media characteristics and user behavior
(processing multimedia data, user interactivity)
 Resource management
(CPU and memory management)
INF 5070 – media storage and distribution systems
2003 Carsten Griwodz & Pål Halvorsen
Content of INF5070 – III
 Protocols with and without Quality of Service (QoS)
(specific and generic QoS approaches)
 Storage systems
(management of multimedia files, retrieval)
 Distribution
(use of caches and proxy servers)
 Adaptation, mobility and Peer-to-Peer
(various clients, different amount of resources)
INF 5070 – media storage and distribution systems
2003 Carsten Griwodz & Pål Halvorsen
Content of INF5070 – IV
 Student assignment
(will be presented more in-depth later):

(IXP programming)

read related article

assignment must be reported and presented to the class at
the end of the course
INF 5070 – media storage and distribution systems
2003 Carsten Griwodz & Pål Halvorsen
Goals of INF5070
 Media servers and distribution system
 media characteristics
 architectures
 system support
 protocols
 distribution mechanisms
 …
 Be able to evaluate any combination of these
mechanisms
INF 5070 – media storage and distribution systems
2003 Carsten Griwodz & Pål Halvorsen
Pensum INF5070
 Approved presentation of student assignment
 Oral exam (1-3/12):
 all transparencies from lectures
 content of own student assignment
INF 5070 – media storage and distribution systems
2003 Carsten Griwodz & Pål Halvorsen
Applications and
Challenges
Applications
 Multimedia enriches the user interface giving new applications
 Broadcast – server is only VCR substitute (e.g., MTV Europe)
 Media-on-Demand (MoD)
 Video-on-Demand (VoD) (e.g., Bell Atlantic  ~1000 users, 700 choices)
 News-on-Demand (NoD) (e.g., CNN, BBC  web today, BAD quality)
 Learning-on-Demand (LoD) (e.g., the OMODIS project)
 Virtual worlds (typically live, not on-Demand)
 video conferencing (e.g., USIT’s electronic classroom)
 games (e.g., Quake, …)
INF 5070 – media storage and distribution systems
2003 Carsten Griwodz & Pål Halvorsen
Requirements
 Application
 QoS – time sensitivity
 resource capabilities –
support interactive streaming of multimedia content
 Business
 scalability
 reliability
 Architectural
 topology
 cost vs. performance
INF 5070 – media storage and distribution systems
2003 Carsten Griwodz & Pål Halvorsen
Technical Challenges
 User end system:
 real-time processing of streams
(1000 MIPS for an MPEG-II decoder)
 request/response delay (< 150 ms for videophones)
 high data rates, e.g., MPEG-II DVD quality:



average video rate of 3.5 Mbps
max. total data rate of 10.08 Mbps
max. user rate of 11.08 Mbps (all included like control signals)
 Storage
 real-time retrieval of contiguous media streams, e.g.:


4000 movies
2000 CDs
* 90 minutes
* 74 minutes
* 15 Mbps (HDTV)
* 1.4 Mbps
= 40.5 TB
= 1.4 TB
 Network
 real-time transport of contiguous media data
INF 5070 – media storage and distribution systems
2003 Carsten Griwodz & Pål Halvorsen
Media-on-Demand (MoD) Systems
 Classification parameters
 structure of movies
 interaction
 presentation form
 Common directions
 analog  digital media
 distribution  interaction
 media broadcasting  media multicasting  personalized media
 linear movies  branched movies  variable movies
 Evolution
 broadcast
 pay-per-view
 quasi MoD
 near MoD
 true MoD
-
traditional, no user control
limited interactivity
distinction into user groups, limited timely control
same media distributed in intervals
full user control, VCR capabilities, bidirectional
INF 5070 – media storage and distribution systems
2003 Carsten Griwodz & Pål Halvorsen
Television (Broadcast)
channels
time
sender
• analog or digital
• traditionally, one program per channel
receiver(s)
 analog use frequency division multiplexing only
 digital may additionally use time division multiplexing
inside one frequency (several programs per channel)
• linear movies
INF 5070 – media storage and distribution systems
2003 Carsten Griwodz & Pål Halvorsen
Near Video-on-Demand (NVoD)
channels
time
sender
• analog or digital broadcasting
• one program over multiple channels
• time-slotted emission of the program
• linear movies
INF 5070 – media storage and distribution systems
receiver(s)
2003 Carsten Griwodz & Pål Halvorsen
(True) Video-on-Demand (VoD)
movies
time
sender
receiver(s)
• digital uni- or multicasting
• control channels
• linear movies
INF 5070 – media storage and distribution systems
2003 Carsten Griwodz & Pål Halvorsen
Comparison: NVoD vs. TVoD
Response
Services
Costs
Suited
NVoD
TVoD
Delayed
immediate
provide some flexibility
compared to traditional TV
improves video rentals:
any video, any time
cheap:
expensive:
more clients at lower price
compared to TVoD
existing infrastructure often not
cost-competitive for households
(need to be equal to rentals)
digital broadcast
(ViaSat, TV1000)
specific (smaller)
environments
(hotels, airplanes, …)
INF 5070 – media storage and distribution systems
2003 Carsten Griwodz & Pål Halvorsen
“Interactive Vision”
movie
time
sender
receiver(s)
• digital uni- or multicasting
• control channels
• fixed non-linear movies
INF 5070 – media storage and distribution systems
2003 Carsten Griwodz & Pål Halvorsen
“Cyber Vision”
time
sender
• digital uni- or multicasting
• control channels
• variable non-linear “movies”, e.g.,
- games, virtual reality, …
INF 5070 – media storage and distribution systems
receiver(s)
2003 Carsten Griwodz & Pål Halvorsen
Application Classification Overview
Cyber Vision
movie structure
variable
Interactive Vision
branched
HDTV
VoD
linear
digital
TV
NVoD
unidirectional
VIDEO
interaction
INF 5070 – media storage and distribution systems
bidirectional
analog
2003 Carsten Griwodz & Pål Halvorsen
Media (Video) on Demand
Challenges
 VoD in LANs is solved:


OVERPROVISIONING works
established in studio business
established in hotel/hospital/plane/… business
 VoD in WANs

goals:



assumptions:




need for interoperability – not from a single source
need for co-operative distribution systems
amount of data:



overprovisioning of resources will NOT work
no central control of delivery system
programs:


network-based distribution of media content to consumers
bring control to users
estimated 65000 movies made in 1995  260 TB MPEG-2 data
additionally, data from TV-series, sport clips, news, …
historically:



much attention as “interactive TV (ITV)” some years ago
many (not successful) field trials
now: interest turned to Internet-based systems
INF 5070 – media storage and distribution systems
2003 Carsten Griwodz & Pål Halvorsen
ITV Network Architechture Approaches
 WAN backbones


SONET
ATM
ATM /
SONET
backbone
network
 Local distribution network




ADSL (asymmetric digital subscriber line)
FTTC (fiber to the curb)
FTTH (fiber to the home)
HFC (hybrid fiber coax)
wireless
Internet based systems
ATM
telephone
 Internet WAN


Diffserv over MPLS
(multi-protocol layer switching)
point-to-point Gbps ethernet
cable
 Internet local

IP over the old distribution networks
INF 5070 – media storage and distribution systems
2003 Carsten Griwodz & Pål Halvorsen
Concerns: Internet-Based VoD Systems
 Can technical problems be mastered?
 broadband communication to every home
 user-friendly end systems
 server technology
 Market success?
 what prices will consumers accept?



will it be competitive?



high equipment (HW & SW) costs
data costs
to existing TV programs
to video rentals
what is the consequence of ITV field trials in USA and Europe?



no big success
only a few private consumers willing to participate
trials were cancelled or switched from TV-based to PC-based platforms
INF 5070 – media storage and distribution systems
2003 Carsten Griwodz & Pål Halvorsen
Driving Forces
 Hardware/software (IT) companies
 computer (e.g., IBM, HP, Sun, Microsoft, …)
 consumer electronics (e.g., Sony, Philips, …)
 Network companies
 telephone (e.g., Telenor, Telia, BT, AT&T, …)
 cable TV (e.g., UPC, Time-Warner Cable, …)
 Content companies
 media





movies (e.g., Time-Warner, Disney, Paramount, Leo Kirch, …)
TV programs (e.g., NRK, TV2, TV3, RTL, …)
hyper media information bases (e.g., Springer, Bertelsmann, …)
home-shopping (e.g., Quelle, OTTO, …)
video games (e.g., Nintendo, Sega, Microsoft, …)
INF 5070 – media storage and distribution systems
2003 Carsten Griwodz & Pål Halvorsen
VoD Deployment Status – I
 Digital Video Broadcast (DVB)



no VoD
cable, antenna, or satellite broadcast
some NVoD scheduling approaches (e.g., TV 1000)
 Digital Audio-Visual Council (DAVIC)


defines interfaces only
no standardization of algorithms for interoperation
Broadcast world
suited for Near VoD
Broadcast world
suited for True VoD
 Internet Engineering Task Force (IETF)




currently no large-scale, wide-area video distribution Internet world
suited for True VoD
sporadic use of cooperative web caching
starting AV caching considerations
defines protocols and inspires interoperability testing
MPEG 4
suited for
Interactive Vision
INF 5070 – media storage and distribution systems
2003 Carsten Griwodz & Pål Halvorsen
VoD Deployment Status – II
DATA
CONTROL
RTP: Real-Time Protocol
RTSP: Real-Time Streaming Protocol
 package & timing information for
 controls: setup, teardown, start, stop
IETF
transfer
 profiles for each encoding format
RTCP: RTP Control Protocol
 report exchange, allows tuning at
SDP: Session Description Protocol
 carried by RTSP
 encoding information, timing, meta
info
the sender
MPEG-2 Transport:
DSM-CC: Distributed Storage Media-
 defines encoding format, packaging,
 MPEG-2 substandard: addressing, setup,
Moving Pictures Expert Group
DAVIC
timing, scaling, error correction
 requires other means of addressing
INF 5070 – media storage and distribution systems
Command & Control
teardown, start, stop, …
 independent standard: complete
management standard
(usually ignored by industry)
2003 Carsten Griwodz & Pål Halvorsen
VoD System Architecture
backbone
network
local
distribution
network
INF 5070 – media storage and distribution systems
local
distribution
network
local
distribution
network
2003 Carsten Griwodz & Pål Halvorsen
VoD Storage Hierarchy
 Popularity of movies:
not all are equally popular –
most request directed to
only a few (Zipf distribution)
completeness of
available content
master servers
 Use hierarchies:
regional
servers
 Straight forward
hierarchy:


popular videos replicated and
kept close to clients
locality vs.
communication vs.
server costs
INF 5070 – media storage and distribution systems
local servers
end-systems
2003 Carsten Griwodz & Pål Halvorsen
VoD Components
 Servers
 Networks
 backbone
 local networks
 Intermediate nodes
 routers
 proxy cache servers
 replica servers
 End-systems
 PCs
 TV sets with set-top boxes
INF 5070 – media storage and distribution systems
2003 Carsten Griwodz & Pål Halvorsen
Traditional
Server Machine Internals
General Operating System Structure and Data Path
application
user space
kernel space
file system
INF 5070 – media storage and distribution systems
communication
system
2003 Carsten Griwodz & Pål Halvorsen
Example:
Intel Hub Architecture (850 Chipset) – I
Intel D850MD Motherboard:
RDRAM connectors
CPU socket
system bus
RDRAM
interface
hub interface
PCI
bus
Memory
Controller Hub
I/O Controller Hub
PCI connectors
INF 5070 – media storage and distribution systems
2003 Carsten Griwodz & Pål Halvorsen
Example:
Intel Hub Architecture (850 Chipset) – II
Note:
these transfers only show dataapplication
movement between
sub-systems. Additionally, data touching operations
communication
within a sub-system
require that data
is moved
file will
system
system
from memory and to the CPU, e.g.:
- checksum calculation - encryption
disk
card
- data encoding
- forward errornetwork
correction
Pentium 4
Processor
registers
cache(s)
system bus
(64-bit, 400/533 MHz)
memory
controller
hub
RAM interface
(two 64-bit, 200 MHz)
RDRAM
file system
RDRAM
communication system
RDRAM
application
RDRAM
hub interface
(four 8-bit, 66 MHz)
I/O
controller
hub
PCI slots
PCI bus
(32-bit, 33 MHz)
INF 5070 – media storage and distribution systems
network card
PCI slots
PCI slots
disk
2003 Carsten Griwodz & Pål Halvorsen
Example:
IBM POWER 4
application
POWER 4 chip
CPU
L1
CPU
L1
core interface switch
file system
communication
system
disk
network card
L2
fabric controller
GX
controller
GX bus
(two 32-bit, 600 MHz)
remote I/O
(RIO)
bridge
L3
L3 controller
memory
controller
RAM
file system
communication system
RAM
application
RAM
PCI busses
(32/64-bit, 33/66 MHz)
PCI
host bridge
PCI-PCI
bridge
PCI
host bridge
PCI-PCI
bridge
RIO bus
(two 8-bit, 500 MHz)
INF 5070 – media storage and distribution systems
PCI slots
network card
PCI slots
disk
Note:
Again, data touching operations
add movement operations
2003 Carsten Griwodz & Pål Halvorsen
Memory Hierarchies
 We can’t access the disk each time we need data
 Typical computer systems therefore have several


different capacities
different speeds
less capacity gives faster access
and higher cost per byte
 Lower levels have a copy of
data in higher levels
 A typical memory hierarchy:
secondary storage
(disks)
main memory
capacity
INF 5070 – media storage and distribution systems
tertiary storage
(tapes)
price

speed
different components where data may be stored
cache(s)
2003 Carsten Griwodz & Pål Halvorsen
typical capacity (bytes)
Storage Costs: Access Time vs Capacity
offline
tape
1015
1013
magnetic
disks
1011
online
tape
main
memory
109
107
105
cache
10-9
10-6
from Gray & Reuter
INF 5070 – media storage and distribution systems
10-3
10
103
access time (sec)
2003 Carsten Griwodz & Pål Halvorsen
Storage Costs: Access Time vs Price
104
dollars/Mbytes
cache
102
main
memory
online
tape
magnetic
disks
100
10-2
offline
tape
10-9
10-6
from Gray & Reuter
INF 5070 – media storage and distribution systems
10-3
10
103
access time (sec)
2003 Carsten Griwodz & Pål Halvorsen
Internal Server Design
 Stream retrieval from disk and push to network
 buffer requirements
 bus transfers
 CPU usage
 concurrent streams (can be merged??)
 storage (disk) system:



scheduling – ensure that data is available in time
block placement – contiguous, interleaving, striping
…
 Stable operations:
 redundant HW
 multiple nodes
 Much more, e.g., caching/prefetching, admission control, …
INF 5070 – media storage and distribution systems
2003 Carsten Griwodz & Pål Halvorsen
Video Server Structure
Video Server:
Server Components & Switches
 Internal content directory:
switc
h
 External content directory:
HP, DEC, Novell, …
network attachment
switch
switch
content directory/
memory management
switch
switch
file system
switch
switch
storage management
switch
switch
IBM TigerShark
controller
switch
switch
storage device
INF 5070 – media storage and distribution systems
2003 Carsten Griwodz & Pål Halvorsen
Video Server Components
incoming
resolve request
incoming
data request
delivered resolution
delivered data
network attachment
network attachment
content directory
memory management
file system
storage management
controller
storage device
control/application
server
INF 5070 – media storage and distribution systems
data server
2003 Carsten Griwodz & Pål Halvorsen
Video Server:
Simple General Server Architecture
Storage subsystem:
• stores data
• different devices
Processor subsystem:
• executing part
• management and operations
Network subsystem:
• transmit MM data
storage
subsystem
control
server
data
server
network
subsystem
clients
processor subsystem
application
server
data
control
Application server:
• user interface
• billing
• content database
• user database
• service gateways
Control server:
• administrator
• admission control
• optimization
INF 5070 – media storage and distribution systems
Data server:
• data delivery
• “specialized file system”
• buffer manager
• data importer/exporter
2003 Carsten Griwodz & Pål Halvorsen
Video Server:
Directory Access & Data Retrieval
 Two-step retrieval:
 “problem”:
resource management
data
Network
content
 Request redirection:
 “problem”:
client gets data from
another machine
INF 5070 – media storage and distribution systems
data
Network
content
2003 Carsten Griwodz & Pål Halvorsen
Video Server:
Directory Access & Data Retrieval
 Pull model:
 client sends several requests
 deliver only small part of data
 fine-grained client control
 favors high interactivity
 suited for editing, searching, etc.
 Push model
 client sends one request
 streaming delivery
 favors capacity planning
 suited for retrieval, download,
playback, etc.
INF 5070 – media storage and distribution systems
server
client
server
client
2003 Carsten Griwodz & Pål Halvorsen
Video Server:
Server Topology – I
 Single server
 easy to implement
 scales poorly
Network
 Partitioned server
 users divided into groups
 content : assumes equal groups
 location : store all data on all servers
 load imbalance
INF 5070 – media storage and distribution systems
Network
Network
2003 Carsten Griwodz & Pål Halvorsen
Video Server:
Server Topology – II
 Externally switched servers
 use network to make server pool
 manages load imbalance
(control server directs requests)
 still data replication problems
 (control server doesn’t need to be a
physical box - distributed process)
data
Network
data
data
control
data
 Fully switched server
 server pool
 storage device pool
 additional hardware costs
 e.g., Oracle, Intel, IBM
I/O
switch
Network
data
control
INF 5070 – media storage and distribution systems
2003 Carsten Griwodz & Pål Halvorsen
Video Distribution Server:
Typical In the Internet Today
 Push systems
(pull in video editing/database systems)
 Traditional (specialized) file systems – not databases –
for data storage
 No in-band control
(control and data information in separate streams)
 External directory services for data location
(RTSP/control server + data pump)
 Request redirection for access control
 Single stand-alone servers  (fully) switched servers
INF 5070 – media storage and distribution systems
2003 Carsten Griwodz & Pål Halvorsen
Server Examples
Video Server “Research Status”
Research covering all
components is rare
network nodes
network attachment
IBM Watson
Tetzlaff, Kienzle
Fall, Druschel, Pai,
Buddhikot, Miller, …
Goyal, Vin
content directory
memory/CPU
file systems
IBM Almaden
Haskin
PRINCETON
Peterson
physical storage
management
disk controller/driver
Härtig,
Sitaram,
Dan,
Nahrstedt,
Steinmetz,
Klas,
Shulzrinne,
Coulson,
Seltzer,
Rangan,
Zhang,
Hutchinson,
…
AT&T
Silberschatz, Özden
Shenoy, Nirajan, Martin, …
USC
Ghandeharidzadeh, Zimmermann
Jones, Nieh, Chen, Berson,
Reddy, …
storage devices
INF 5070 – media storage and distribution systems
2003 Carsten Griwodz & Pål Halvorsen
Video Server “Product Status”
1) Real server, VXtreme, Starlight, VDO, Netscape Media Server,
MS Media Server, Apple Darwin
RTSP
user level server
RTP
standard
OS
2) IBM Mediastreamer,
Oracle Video Cartridge,
N-Cube
all standard HW
3) SGI/Kassena Media Base,
SUN Media Center,
IBM Video Charger
user level server
RTSP
RTP
user level layer
DSM CC, private
ATM, analog
scalable, RT-aware OS,
RT OS, or
OS derivation
custom/special HW
MM standard
RT
FS
OS
extensions
selected
standard HW
INF 5070 – media storage and distribution systems
2003 Carsten Griwodz & Pål Halvorsen
Real Server
 User space implementation



one control server
several protocols
several versions of data
in same file
adapts to resources
request
3



INF 5070 – media storage and distribution systems
track 2
backpressure
management
Quality-of-Service
load leveling
track 1
 Does not support
index

user
Real’s own
kernel
MPEG-2 version with
“stream thinning”
(dropped with REAL )
1
Real’s
protocol
 Several formats, e.g.,

server
2
TCP
UDP
RTP/
RTCP
feedback

IP
2003 Carsten Griwodz & Pål Halvorsen
IBM Video Charger
 May consist of one
control


AIX SP2 crossbar switch
machine only, or …
 … several IBM’s Advanced
Interactive eXecutive
(AIX) machines
 Servers
control
data
 Lightly modified existing
components


OS AIX4
virtual shared disks (VSD) VSD
with
(guaranteed disk I/Os)
EDF
specific
control server
RTSP
video stream API
distributed computing
environment RPC
mlib API
filter
encrypt
RTP
TigerShark
MMFS
UDP
VSD
IP
 Special components


TigerShark MMFS
(buffers, data rate,
prefetching, codec, ...)
stream filters, control
server, APIs, ...
DESCRIBE
SETUP
PLAY
TEARDOWN
INF 5070 – media storage and distribution systems
2003 Carsten Griwodz & Pål Halvorsen
IBM Mediastreamer
 Version of Video Charger


failed project to
guarantee MPEG-2 over
ATM and Cable
similar machine setup
(machine cluster)
special HW:




SCSI controller
MPEG-2
ATM or analog cable out
moved to Video Charger
AIX SP2 crossbar switch

control
specific
control server
RTSP
video stream API
distributed computing
environment RPC
mlib API
 Unlike Video Charger,
Mediastreamer runs on old
IBM machines due to
special HW
 Special components




TigerShark
control server
APIs
special board
INF 5070 – media storage and distribution systems
2003 Carsten Griwodz & Pål Halvorsen
nCUBE
 One server scales from 1 to 256
machines, n  [0, 8]
 Special components


board with SCSI, connectors, HAVOC
vector processor, etc.
TRANSIT operating system
 Interface modules




ATM
digital video broadcast (DVB)
Ethernet
QAM
8 hypercube
connectors
 Real Networks agreed to integrate
configurable
interface
nCUBE's n4x with RealSystem 8 ??
SCSI ports
INF 5070 – media storage and distribution systems
memory
PCI bus
vector processor
2003 Carsten Griwodz & Pål Halvorsen
Small Comparison
Real
Video Charger
nCUBE
standard HW
selected HW
special HW
each machine its
own storage, or NFS
shared disk access,
no replication
shared disk access,
no replication
single OS image
cluster machines
using switch
cluster machines
using wired cube
user space server
user space server
and loadable kernel
modules
server in both kernel
and user space
INF 5070 – media storage and distribution systems
2003 Carsten Griwodz & Pål Halvorsen
Client-Server
 Traditional distributed computing
 Successful architecture, and will
continue to be so (adding proxy servers)
 Tremendous engineering necessary to
make server farms scalable and robust
backbone
network
local
distribution
network
INF 5070 – media storage and distribution systems
local
distribution
network
local
distribution
network
2003 Carsten Griwodz & Pål Halvorsen
Peer-to-Peer (P2P)

Really an old idea - a distributed system architecture



No centralized control
Nodes are symmetric in function
Typically, many nodes, but unreliable and heterogeneous
backbone
network
local
distribution
network
INF 5070 – media storage and distribution systems
local
distribution
network
local
distribution
network
2003 Carsten Griwodz & Pål Halvorsen
Promise
active sender
Each active sender:
• receives a control packet specifying which data segments, data rate, etc.,
• pushes data to receiver as long as no new control packet is received
standby
active sender
standby sender
The receiver:
• sends a lookup request
using DHT
• selects some active
senders, control packet
• receives data as long
as
no errors/changes
occur
• if a change/error is
detected, new active
senders may be
Receiver
selected
Thus, Promise is a multiple sender to one receiver P2P media
streaming system which 1) accounts for different capabilities,
2) matches senders to achieve best quality, and 3) dynamically
adapts to network fluctuations and peer failure
INF 5070 – media storage and distribution systems
active sender
2003 Carsten Griwodz & Pål Halvorsen
SplitStream
Each node:
• joins as many multicast threes as there are stripes (K)
• may specify the number of stripes they are willing to act as
Source: full quality movie
router for, i.e., according to the amount of resources available
Stripe 1
Each movie is split into K stripes and each
stripe is multicasted using a separate three
Thus, SplitStream is a multiple sender to multiple receiver P2P system which
distributes the forwarding load while respecting each node’s resource limitations,
but some effort is required to build the forest of multicast threes
Stripe 2
INF 5070 – media storage and distribution systems
2003 Carsten Griwodz & Pål Halvorsen
Summary
 Multimedia applications and challenges
 Media (Video) on Demand
 Machine internals
 Video server structures
 Video server examples
INF 5070 – media storage and distribution systems
2003 Carsten Griwodz & Pål Halvorsen
Some References
1.
2.
3.
4.
5.
6.
7.
8.
M. Castro, P. Druschel, A-M. Kermarrec, A. Nandi, A. Rowstron and A. Singh, "SplitStream:
High-bandwidth multicast in a cooperative environment", SOSP'03, Lake Bolton, New York,
October 2003
Mohamed Hefeeda, Ahsan Habib, Boyan Botev, Dongyan Xu, Bharat Bhargava, "Promise:
Peer-to-Peer Media Streaming Using Collectcast", ACM MM’03, Berkeley, CA, November 2003
Sitaram, D., Dan, A.: “Multimedia Servers – Applications, Environments, and Design”, Morgan
Kaufmann Publishers, 2000
Tendler, J.M., Dodson, S., Fields, S.: “IBM e-server: POWER 4 System Microarchitecture”,
Technical white paper, 2001
Tetzlaff, W., Flynn, R.: “Elements of Scalable Video Servers”, IBM Research Report 19871
(87884), 1994
Intel, http://www.intel.com
MPEG.org, http://www.mpeg.org/MPEG/DVD
nCUBE, http://ncube.com
INF 5070 – media storage and distribution systems
2003 Carsten Griwodz & Pål Halvorsen