Patents
US4569015:
A Method for Achieving Multiple Processor Agreement Optimized for No
Faults.
Dolev; Danny, Strong; Hovey Raymond , Feb. 4, 1986
/ April 13, 1983 .
An
originating processor broadcasts a value in a message with its unforgeable signature to all n active
processors, including
itself. Receiving processors in the network pass such a message on with
their
own unforgeable signatures to all active
processors,
including themselves. If the number of signatures and phases is the
same at each
processor after the first two successive passings,
then agreement as to the value with no fault is indicated, otherwise if
after
two passings, (t+1) signatures have been
collected,
then these are signed and sent in the third passing and in any case,
each
processor continues the steps of repeatedly sending messages when
received and
appending its signature until t+2 passings
have
occurred. At that time, a processor will agree to the value if at least
(t+1)
signatures append the message, otherwise a default value is adopted, t
(n/2)
being a reliability measure.
US5,029,159: Method and Means for
Leader Choosing on a Token
Ring System.
Dolev; Danny,
July 2, 1991 / July 18, 1989.
In a token ring transmission system, token loss causes selection of a leader terminal, which issues a new token. The leader terminal is chosen by selecting and storing a leadership selection reference value and then generating a succession of terminal identification signals and transferring them on the token ring transmission system. Each terminal receives the succession of signals and iteratively compares the terminal identification signals sequentially with the leadership reference signal. Each time a terminal identification signal exceeds the magnitude of the leadership reference signal, the leadership reference value is replaced with the value of the terminal identification signal. The first terminal detecting equality of a terminal identification signal with its leadership selection reference signal assumes leadership and issues a token.
Method and means for leader choosing on a token ring system
United States Patent 5029159
In a token ring transmission system, token loss causes selection of a
leader terminal, which issues a new token. The leader terminal is
chosen by selecting and storing a leadership selection reference value
and then generating a succession of terminal identification signals and
transferring them on the token ring transmission system. Each terminal
receives the succession of signals and iteratively compares the
terminal identification signals sequentially with the leadership
reference signal. Each time a terminal identification signal exceeds
the magnitude of the leadership reference signal, the leadership
reference value is replaced with the value of the terminal
identification signal. The first terminal detecting equality of a
terminal identification signal with its leadership selection reference
signal assumes leadership and issues a token.
Inventors:
Dolev, Danny (Cupertino, CA)
Application Number:
07/383021
Publication Date:
07/02/1991
US5,161,186: System for Secure and
Private Communication in a
Triple Connected Network.
Dolev; Danny, Dwork; Cynthia, Nov. 3, 1992 / Sept. 6, 1991.
An
apparatus and method for secure and private communications in a
triple-connected processor network. Communication of a message over at
least
three data paths is achieved by transmitting the message in coded form
over the
data paths, determining whether the message is correctly received and
if the
message is not correctly received, identifying a non-faulty data path,
testing
remaining data paths to identify a faulty data path and transmitting
the
message in coded form over remaining non-faulty data paths.
US5,428,645: Anonymous Time
Synchronization Method.
Dolev; Danny,
Reischuk; Rudiger
Karl ,
Strong;
Hovey Raymond, June 27, 1995
/ Nov. 3, 1992 .
A method is provided for synchronizing a local time maintained at a node within a network architecture with a reference time. Bursts of synchronization messages containing reference time stamps are transmitted over a network or communication link according to a predetermined protocol. A node to be synchronized receives and time stamps the messages. Thus, times according to a first time scale and a second time scale are obtained and the protocol defines temporal relationships between certain ones of the times. In accordance with the predetermined protocol, the node determines a difference between a first time according to one of the time scales and a time related to second and third times according to the other time scale. The node then updates its local time based on the difference between the first time and the related time. This synchronization method provides a well-defined upper bound of synchronization error and allows the nodes receiving the messages to synchronize their internal times based only on information contained in the received messages and their internally, generated local time stamp marks. Therefore, no "round trip" or handshaking messages are necessary to define the needed temporal relationships between the times according to the first and second scales. Thus, it is not necessary that the reference time source know the identities of the nodes which synchronize themselves based on the messages. The node also maintains a global precision value, which estimates its time synchronization error, by resetting the value when the node is synchronized and updating the value as the node operates. Responsive to the global precision exceeding various thresholds, the node requests resynchronization or sends synchronization messages based on its internal time.
US5,550,873: Processing system for
use as a network node for
performing anonymous time synchronization in a network.
Dolev; Danny,
Reischuk; Rudiger
Karl ,
Strong;
Hovey Raymond, Aug. 27, 1996
/ Feb. 1, 1995 .
A
network node, such as a computer or processing system, is provided, for
use
within a network, the node including program code for synchronizing a
local
time maintained at the node with a reference time. Bursts of
synchronization
messages containing reference time stamps are transmitted over the
network, or
over a communication link, according to a predetermined protocol. The
node
receives and time stamps the messages. Thus, times according to a first
time
scale and a second time scale are obtained. The protocol defines
temporal
relationships between certain ones of the times. In accordance with the
protocol, the node determines a difference between a first time
according to
one of the time scales and a time related to second and third times
according
to the other time scale. The node then updates its local time based on
the
difference. This synchronization method provides a well-defined upper
bound of
synchronization error and allows the node to synchronize its internal
time
based only on information contained in the received messages and the
internally
generated local time stamp marks. No "round trip" or handshaking
messages are necessary to define the needed temporal relationships
between the
times according to the first and second scales. Thus, it is not
necessary that
the reference time source know the identity of the node which is
synchronizing
itself. The node also maintains a global precision value, which
estimates its
time synchronization error, by resetting the value when the node is
synchronized and updating the value as the node operates. Responsive to
the
global precision exceeding various thresholds, the node requests
resynchronization or sends synchronization messages based on its
internal time.
US5,784,421:Computer program
product for use with a network
node for performing anonymous time synchronization in a network.
Dolev; Danny,
Reischuk; Rudiger
Karl ,
Strong;
Hovey Raymond, July 21, 1998
/ Jan. 24, 1996
A computer program product, such as a floppy disk with pre-recorded software, is provided. The computer program product is for use with a computer or processing system which is to function as a node within a network. Synchronization of a local time maintained at the node with a reference time is facilitated through execution of the prerecorded software by the node. Bursts of synchronization messages containing reference time stamps are transmitted over the network, or over a communication link, according to a predetermined protocol. The node receives and time stamps the messages. Thus, times according to a first time scale and a second time scale are obtained. The protocol defines temporal relationships between certain ones of the times. In accordance with the protocol, the node determines a difference between a first time according to one of the time scales and a time related to second and third times according to the other time scale. The node then updates its local time based on the difference. This synchronization method provides a well-defined upper bound of synchronization error and allows the node to synchronize its internal time based only on information contained in the received messages and the internally generated local time stamp marks. No "round trip" or handshaking messages are necessary to define the needed temporal relationships between the times according to the first and second scales. Thus, it is not necessary that the reference time source know the identity of the node which is synchronizing itself. The node also maintains a global precision value, which estimates its time synchronization error, by resetting the value when the node is synchronized and updating the value as the node operates. Responsive to the global precision exceeding various theresholds, the node requests resynchronization or sends synchronization messages based on its internal time.
US5,796,999: Method and system for
selectable consistency level
maintenance in a resilient database system work.
Azagury; Alain Charles,
Dolev;
Danny, Goft; German,
Marberg; John Michael, Ranweiler; James Gregory,
Satran; Julian, Aug. 18, 1998
/ April 15, 1994
In a resilient database system which includes a journaled database which is implemented at one or more locations within a distributed data processing system, multiple diverse consistency levels are specified which each detail a level of consistency to be maintained between a primary database and a replica database. A user is then permitted to select a particular level of consistency for each replica database. Thereafter, each update to a record within the primary database is utilized to initiate an update to the corresponding record within each replica database in a manner which is consistent with the selected level of consistency for that replica database. In this manner, a replica database which is fully consistent with the primary database may be provided for seamless switchover in the event of a primary database failure, while a second replica database may be provided to respond to queries by applications which do not require fully consistent data, greatly enhancing the efficiency of access to that database.
Method and system for selectable consistency level maintenance in a resilent database system
United States Patent 5796999
In a resilient database system which includes a journaled database which is implemented at one or more locations within a distributed data processing system, multiple diverse consistency levels are specified which each detail a level of consistency to be maintained between a primary database and a replica database. A user is then permitted to select a particular level of consistency for each replica database. Thereafter, each update to a record within the primary database is utilized to initiate an update to the corresponding record within each replica database in a manner which is consistent with the selected level of consistency for that replica database. In this manner, a replica database which is fully consistent with the primary database may be provided for seamless switchover in the event of a primary database failure, while a second replica database may be provided to respond to queries by applications which do not require fully consistent data, greatly enhancing the efficiency of access to that database.
Inventors:
Azagury, Alain Charles (Nesher, IL)
Dolev, Danny (Mevaseret Yerushalayim, IL)
Goft, German (Endicott, NY)
Marberg, John Michael (Haifa, IL)
Ranweiler, James Gregory (Rochester, MN)
Satran, Julian (Somers, NY)
Application Number:
08/228319
Publication Date:
08/18/1998
Filing Date:
04/15/1994
View Patent Images:
Do
add:
1. Dolev, Danny (Jerusalem, IL) Dwork, Cynthia (Palo Alto, CA) System for secure and private
communication in a triple-connected network, US Pat. No. 5,161,186 (Nov. 3, 1992).
System for secure and private communication in a triple-connected network
United States Patent 5161186
An apparatus and method for secure and private communications in a triple-connected processor network. Communication of a message over at least three data paths is achieved by transmitting the message in coded form over the data paths, determining whether the message is correctly received, and if the message is not correctly received, identifying a non-faulty data path, testing remaining data paths to identify a faulty data path, and transmitting the message in coded form over remaining non-faulty data paths.
Inventors:
Dolev, Danny (Jerusalem, IL)
Dwork, Cynthia (Palo Alto, CA)
Application Number:
07/756276
Publication Date:
11/03/1992
20080282246 COMPILER AIDED TICKET SCHEDULING OF TASKS IN A COMPUTING SYSTEM 11-13-2008 (with anker and weinsberg)
high performance pattern matching with anker, tzur-david, weinsberg
COMPILER AIDED TICKET SCHEDULING OF TASKS IN A COMPUTING SYSTEM
United States Patent Application 20080282246
Kind Code:
A1
A method of scheduling tasks for execution in a computer system includes determining a dynamic worst case execution time for a non-periodic task. The dynamic worst case execution time is based on an actual execution path of the non-periodic task. An available time period is also determined, wherein the available time period is an amount of time available for execution of the non-periodic task. The non-periodic task is scheduled for execution if the dynamic worst case execution time is less than the available time period.
Inventors:
Dolev, Danny (Mevaseret Zion, IL)
Anker, Tal (EliShema, IL)
Weinsberg, Yaron (Pisgat Zeev, IL)
Application Number:
11/745042
Publication Date:
11/13/2008
(WO/2006/072949) A METHOD AND APPARATUS FOR MANAGING COMMUNICATIONS 2006 with shay horvitz
Dynamic load balancing among a set of servers
United States Patent Application 20030105797
Kind Code:
A1
The invention relates to a process and system for spreading requests
for a service among a set of servers, where each one has a specified
load allowed within each time frame. The invention provides a simple
and fast solution to the dynamic assignment incoming requests among the
servers, without violating their load limitation within a given time
frame, and with keeping a fair allocation among them. It is an object
of the invention to provide a scalable solution to assigning loads with
minimal overhead.
Inventors:
Dolev, Dan (Mevaseret-Tzion, IL)
Silbinger, Yizhak (Herzelia, IL)
Edry, Ronnen (Hod-Husharon, IL)
Application Number:
09/683224
Publication Date:
06/05/2003
Processing system for use as a network node for performing anonymous
time synchronization in a network
United States Patent 5550873
A network node, such as a computer or processing system, is provided,
for use within a network, the node including program code for
synchronizing a local time maintained at the node with a reference
time. Bursts of synchronization messages containing reference time
stamps are transmitted over the network, or over a communication link,
according to a predetermined protocol. The node receives and time
stamps the messages. Thus, times according to a first time scale and a
second time scale are obtained. The protocol defines temporal
relationships between certain ones of the times. In accordance with the
protocol, the node determines a difference between a first time
according to one of the time scales and a time related to second and
third times according to the other time scale. The node then updates
its local time based on the difference. This synchronization method
provides a well-defined upper bound of synchronization error, and
allows the node to synchronize its internal time based only on
information contained in the received messages and the internally
generated local time stamp marks. No "round trip" or handshaking
messages are necessary to define the needed temporal relationships
between the times according to the first and second scales. Thus, it is
not necessary that the reference time source know the identity of the
node which is synchronizing itself. The node also maintains a global
precision value, which estimates its time synchronization error, by
resetting the value when the node is synchronized, and updating the
value as the node operates. Responsive to the global precision
exceeding various thresholds, the node requests resynchronization or
sends synchronization messages based on its internal time.
Inventors:
Dolev, Danny (Jerusalem, IL)
Reischuk, Udiger R. K. (M unster-Altheim, DE)
Strong, Hovey R. (San Jose, CA)
Application Number:
08/382479
Publication Date:
08/27/1996
Method for achieving multiple processor agreement optimized for no
faults
United States Patent 4569015
An originating processor broadcasts a value in a message with its
unforgeable signature to all n active processors, including itself.
Receiving processors in the network pass such a message on with their
own unforgeable signatures to all active processors, including
themselves. If the number of signatures and phases is the same at each
processor after the first two successive passings, then agreement as to
the value with no fault is indicated, otherwise if after two passings,
(t+1) signatures have been collected, then these are signed and sent in
the third passing, and in any case, each processor continues the steps
of repeatedly sending messages when received, and appending its
signature until t+2 passings have occurred. At that time, a processor
will agree to the value if at least (t+1) signatures append the
message, otherwise a default value is adopted, t (n/2) being a
reliability measure.
Inventors:
Dolev, Danny (Jerusalem, IL)
Strong, Hovey R. (Hollister, CA)
Application Number:
06/485573
Publication Date:
02/04/1986
Anonymous time synchronization method
United States Patent 5428645
A method is provided for synchronizing a local time maintained at a
node within a network architecture with a reference time. Bursts of
synchronization messages containing reference time stamps are
transmitted over a network or communication link according to a
predetermined protocol. A node to be synchronized receives and time
stamps the messages. Thus, times according to a first time scale and a
second time scale are obtained, and the protocol defines temporal
relationships between certain ones of the times. In accordance with the
predetermined protocol, the node determines a difference between a
first time according to one of the time scales and a time related to
second and third times according to the other time scale. The node then
updates its local time based on the difference between the first time
and the related time. This synchronization method provides a
well-defined upper bound of synchronization error, and allows the nodes
receiving the messages to synchronize their internal times based only
on information contained in the received messages and their internally,
generated local time stamp marks. Therefore, no "round trip" or
handshaking messages are necessary to define the needed temporal
relationships between the times according to the first and second
scales. Thus, it is not necessary that the reference time source know
the identities of the nodes which synchronize themselves based on the
messages. The node also maintains a global precision value, which
estimates its time synchronization error, by resetting the value when
the node is synchronized, and updating the value as the node operates.
Responsive to the global precision exceeding various thresholds, the
node requests resynchronization or sends synchronization messages based
on its internal time.
Inventors:
Dolev, Danny (Mevasserret, IL)
Reischuk, Rudiger K. (Munster-Altheim, DE)
Strong, Hovey R. (San Jose, CA)
Application Number:
07/970666
Publication Date:
06/27/1995
Filing Date:
11/03/1992
View Patent Images:
Computer program product for use with a network node for performing
anonymous time synchronization in a network
United States Patent 5784421
A computer program product, such as a floppy disk with pre-recorded
software, is provided. The computer program product is for use with a
computer or processing system which is to function as a node within a
network. Synchronization of a local time maintained at the node with a
reference time is facilitated through execution of the prerecorded
software by the node. Bursts of synchronization messages containing
reference time stamps are transmitted over the network, or over a
communication link, according to a predetermined protocol. The node
receives and time stamps the messages. Thus, times according to a first
time scale and a second time scale are obtained. The protocol defines
temporal relationships between certain ones of the times. In accordance
with the protocol, the node determines a difference between a first
time according to one of the time scales and a time related to second
and third times according to the other time scale. The node then
updates its local time based on the difference. This synchronization
method provides a well-defined upper bound of synchronization error,
and allows the node to synchronize its internal time based only on
information contained in the received messages and the internally
generated local time stamp marks. No "round trip" or handshaking
messages are necessary to define the needed temporal relationships
between the times according to the first and second scales. Thus, it is
not necessary that the reference time source know the identity of the
node which is synchronizing itself. The node also maintains a global
precision value, which estimates its time synchronization error, by
resetting the value when the node is synchronized, and updating the
value as the node operates. Responsive to the global precision
exceeding various theresholds, the node requests resynchronization or
sends synchronization messages based on its internal time.
Inventors:
Dolev, Danny (Jerusalem, IL)
Reischuk, Rudiger Karl (Munster-Altheim, DE)
Strong, Hovey Raymond (San Jose, CA)
Application Number:
08/590540
Publication Date:
07/21/1998
SD2008-159 - New Message Passing Algorithm (with Danny Bickson
and Ori Shental)
\item
SD2008-159 - Method and System for Linear Processing of an Input Using
Gaussian Belief Propagation (with Danny Bickson and Ori Shental)
Last updated
08-Mar-07