Dismiss
InnovationQ will be updated on Sunday, Oct. 22, from 10am ET - noon. You may experience brief service interruptions during that time.
Browse Prior Art Database

Exploiting Insertion Buffer Capabilities to Customize Node Individual Access Performance of a Reservation-Based MAC Protocol

IP.com Disclosure Number: IPCOM000107798D
Original Publication Date: 1992-Mar-01
Included in the Prior Art Database: 2005-Mar-22
Document File: 4 page(s) / 243K

Publishing Venue

IBM

Related People

Lemppenau, WW: AUTHOR [+2]

Abstract

This article describes several mechanisms to provide tunable access delay performance of a reservation-based medium access control (MAC) protocol for insertion networks, e.g., (1). The mechanisms which are either alternative or complementary, exploit the capability of delaying frames in an insertion buffer beyond traditional collision resolution between a passing frame and a frame in transmission.

This text was extracted from an ASCII text file.
This is the abbreviated version, containing approximately 28% of the total text.

Exploiting Insertion Buffer Capabilities to Customize Node Individual Access Performance of a Reservation-Based MAC Protocol

       This article describes several mechanisms to provide
tunable access delay performance of a reservation-based medium access
control (MAC) protocol for insertion networks, e.g., (1).  The
mechanisms which are either alternative or complementary, exploit the
capability of delaying frames in an insertion buffer beyond
traditional collision resolution between a passing frame and a frame
in transmission.

      Consider a ring or bus network with a slotted transmission data
structure where slots are accessed through two distinct mechanisms:
(1) immediate access of so-called gratis slots and (2) access of
previously reserved slots.  A gratis/reserved flag is used to
distinguish between the two states of a slot.  In either case, the
busy/free flag needs to be free for the slot to be accessible.
Reservation is done by a Reserve/Confirm command exchange where
cyclically transmission requests are collected, requests are
processed by a scheduling node, and confirmations are returned to the
requesting nodes.  Marking of slots as reserved is done by the
scheduler whereby a reservation is for only one transmission access.
When a slot is freed by the destination, subsequent access to that
slot is via the gratis access mechanism until next marking takes
place.  As (2) describes, the combination of reservation and gratis
access deferment guarantees fairness under all circumstances.
Deferring nodes let as many free gratis slots pass as is needed to
throttle their throughput towards the throughput fairness reference
as determined by the scheduler.  The slotted transmission structure
defines the units of reservation and deferment.  For a frame based
operation, an insertion buffer ensures that a node can complete its
current frame transmission by holding up busy slots from upstream.
During times that no free slots are available on the medium, the node
generates the free slots needed to carry the frame payload by itself.
To avoid data loss within the network, a frame transmission can only
start when the insertion buffer has space enough to held up a busy
slot quantity which corresponds to the length of the frame to be
transmitted. Insertion buffers are emptied by arriving free slots
with the restriction that the reserved ones can only be used when a
node has confirmations.

      Within this environment, throughput performance becomes best
when both the free reserved slots owing to reservations and the free
gratis slots owing to deferments experience small empty
transportation times.  At the other hand, access delay performance
becomes best when free reserved slots are transported as fast as
possible to those nodes which possess confirmations.  Although
throughput performance increases too, the major focus here is to
control access delay performance both globally and on a node
individual basis. The mechanisms are...