A Staggered-Push Parallel Server Architecture - Scalable Continuous Media Streaming Systems - page 219

Server 0

Server 1

Server 2

Server 3

Figure 12.2 Transmission scenario for the staggered push algorithm

. .

… …

. . .

Transmission

. . . . . .

. . . . . .

. . .

Retrieval

Micro-Round

Macro-Round

Figure 12.3 Two-level scheduler for staggered push

video data rate R V , we can obtain T F from

T F = Q / R V (12.1)

In an N S -servers system, each macro-round consists of N S micro-rounds, and each micro-
round transfers video blocks. Hence, the disk will transfer up to N S = N C video blocks

in one macro-round, with one block per video stream.

12.3 Schedule Assignment
Unexpectedly, the two-level scheduling scheme may result in inconsistent schedules among
different servers if admission is performed independently at each server. Specifically, as servers
are loosely coupled, the internal clock of each server in the system will not be precisely
synchronized. We define clock jitter as the difference between the internal real-time clocks of
two servers. Many algorithms for controlling clock jitter between distributed computers have
been proposed [1-3] and hence will not be pursued further here. We assume that the maximum
clock jitter between any two servers in the system is bounded and is denoted by .

With the presence of clock jitter, one server could assign two new video sessions to start with
the same micro-round while another server could assign them to two different micro-rounds
as shown in Figure 12.4. This can occur because each server assigns new sessions to micro-
rounds according to its own internal clock, which differs from other servers due to clock jitter.
As a single micro-round can serve only up to

τ

video sessions, eventually one server could
experience micro-round overflow although another server can admit the new video session