← Back to Patent Explorer
US5699500A Expired / Lapsed US ⏱️ 0.0 years remaining

Reliable datagram service provider for fast messaging in a clustered environment

Assignee: SIOS Technology Corp
•
Filing: 1995-06-01
•
Granted: 1997-12-16
•
Expires: 2015-06-01
📄 Original PDF 🌐 Google Patents 🔄 Sync Now

Abstract

Abstract A datagram messaging service for a distributed lock manager implemented on a clustered computer system including a plurality of processing nodes interconnected through a network. The messaging service establishes and maintains a plurality of virtual circuits between the processing nodes, a single virtual circuit connecting each pair of processing nodes within the clustered computer system. A distributed lock manager driver is included within each processing node, the driver including a communication service providing for the generation of datagrams comprising lock manager instructions for transmission to other processing nodes within the clustered computer system via said virtual circuits and also providing for the receipt of datagrams generated and transmitted by the other processing nodes.

Inventors

  • 👤 Ranjan Dasgupta

Bibliographic Details

Application Number —
Jurisdiction US
Data Source google_patents
Last Synchronized 2026-10-28 14:54
CPC Classifications
G; G06; G06F; G06F9/00; G06F9/06; G06F9/46; G06F9/52

Claims Analysis

Total Claims: 20
Claim 1
Independent Claim 291 words
A distributed lock manager (DLM) for a clustered computer system, said clustered computer system including a plurality of processing nodes and having a plurality of application processes operating within said plurality of processing nodes, said distributed lock manager comprising: a plurality of virtual circuits, a virtual circuit between each pair of said processing nodes within said clustered computer system; and within each one of said processing nodes: a shared memory segment for storing lock status information for said one of said processing nodes, said shared memory segment being shared by said plurality of application processes to access the lock status information stored therein; a shared library providing said plurality of application processes access to said shared memory segment to request and be granted a lock if said lock is available; a DLM control program providing exception handling for any exception which occurs with respect to a lock managed within said one of said processing nodes; and a DLM driver including a communication service providing for the generation of data packets comprising lock manager instructions for transmission to other ones of said processing nodes via said virtual circuits, said communication service also providing for the receipt of data packets generated and transmitted by other ones of said processing nodes, said communication service further including means for testing the integrity of a virtual circuit between a sending processing node and a receiving processing node, said means generating a periodic keepalive message packet which is periodically sent by said sending processing node to said receiving processing node requesting the transmission of an acknowledge signal in response thereto, said keepalive message packet being transmitted in the absence of the receipt of a data packet from said receiving processing node for a predetermined period of time.
Claim 2
Dependent Claim 291 words
A distributed lock manager (DLM) for a clustered computer system, said clustered computer system including a plurality of processing nodes and having a plurality of application processes operating within said plurality of processing nodes, said distributed lock manager comprising: a plurality of virtual circuits, a virtual circuit between each pair of said processing nodes within said clustered computer system; and within each one of said processing nodes: a shared memory segment for storing lock status information for said one of said processing nodes, said shared memory segment being shared by said plurality of application processes to access the lock status information stored therein; a shared library providing said plurality of application processes access to said shared memory segment to request and be granted a lock if said lock is available; a DLM control program providing exception handling for any exception which occurs with respect to a lock managed within said one of said processing nodes; and a DLM driver including a communication service providing for the generation of data packets comprising lock manager instructions for transmission to other ones of said processing nodes via said virtual circuits, said communication service also providing for the receipt of data packets generated and transmitted by other ones of said processing nodes, said communication service further including means for testing the integrity of a virtual circuit between a sending processing node and a receiving processing node, said means generating a periodic keepalive message packet which is periodically sent by said sending processing node to said receiving processing node requesting the transmission of an acknowledge signal in response thereto, said keepalive message packet being transmitted in the absence of the receipt of a data packet from said receiving processing node for a predetermined period of time.
Claim 3
Dependent Claim 43 words
The distributed lock manager according to claim 3, wherein: said communication service includes means for limiting the transmission of additional data packets when a predetermined number of data packets have been transmitted without the receipt of acknowledge signals for said transmitted data packets.
Claim 4
Dependent Claim 297 words
A distributed lock manager (DLM) for a clustered computer system, said clustered computer system including a plurality of processing nodes and having a plurality of application processes operating within said plurality of processing nodes, said distributed lock manager comprising: a plurality of virtual circuits, a virtual circuit between each pair of said processing nodes within said clustered computer system; means for generating and transmitting an acknowledge signal in response to receipt of a data packet at a receiving processing node, said acknowledge signal being attached to a data packet being transmitted by said receiving processing node; and within each one of said processing nodes: a shared memory segment for storing lock status information for said one of said processing nodes, said shared memory segment being shared by said plurality of application processes to access the lock status information stored therein; a shared library providing said plurality of application processes access to said shared memory segment to request and be granted a lock if said lock is available; a DLM control program providing exception handling for any exception which occurs with respect to a lock managed within said one of said processing nodes; and a DLM driver including a communication service providing for the generation of data packets comprising lock manager instructions for transmission to other ones of said processing nodes via said virtual circuits, said communication service also providing for the receipt of data packets generated and transmitted by other ones of said processing nodes, said communication service further including means for generating and transmitting an acknowledge signal in response to receipt of a data packet from a sending processing node by a receiving processing node, said acknowledge signal being attached to a data packet being transmitted by said receiving processing node to said sending processing node.
Claim 5
Dependent Claim 297 words
A distributed lock manager (DLM) for a clustered computer system, said clustered computer system including a plurality of processing nodes and having a plurality of application processes operating within said plurality of processing nodes, said distributed lock manager comprising: a plurality of virtual circuits, a virtual circuit between each pair of said processing nodes within said clustered computer system; means for generating and transmitting an acknowledge signal in response to receipt of a data packet at a receiving processing node, said acknowledge signal being attached to a data packet being transmitted by said receiving processing node; and within each one of said processing nodes: a shared memory segment for storing lock status information for said one of said processing nodes, said shared memory segment being shared by said plurality of application processes to access the lock status information stored therein; a shared library providing said plurality of application processes access to said shared memory segment to request and be granted a lock if said lock is available; a DLM control program providing exception handling for any exception which occurs with respect to a lock managed within said one of said processing nodes; and a DLM driver including a communication service providing for the generation of data packets comprising lock manager instructions for transmission to other ones of said processing nodes via said virtual circuits, said communication service also providing for the receipt of data packets generated and transmitted by other ones of said processing nodes, said communication service further including means for generating and transmitting an acknowledge signal in response to receipt of a data packet from a sending processing node by a receiving processing node, said acknowledge signal being attached to a data packet being transmitted by said receiving processing node to said sending processing node.
Claim 6
Dependent Claim 186 words
In a clustered computer system including a network of processing nodes and a distributed lock manager for coordinating processing activities within the clustered computer system, the improvement comprising: a plurality of virtual circuits, a virtual circuit between each pair of said processing nodes within said clustered computer system; a distributed lock manager driver included within each processing node, said driver including a communication service providing for the generation of datagrams comprising lock manager instructions for transmission to other ones of said processing nodes via said virtual circuits, said communication service also providing for the receipt of datagrams generated and transmitted by other ones of said processing nodes; and means for testing the integrity of a virtual circuit between a sending processing node and a receiving processing node, said means generating a periodic keepalive message packet which is periodically sent by said sending processing node to said receiving processing node requesting the transmission of an acknowledge signal in response thereto, said keepalive message packet being transmitted in the absence of the receipt of a data packet from said receiving processing node for a predetermined period of time.
Claim 7
Dependent Claim 186 words
In a clustered computer system including a network of processing nodes and a distributed lock manager for coordinating processing activities within the clustered computer system, the improvement comprising: a plurality of virtual circuits, a virtual circuit between each pair of said processing nodes within said clustered computer system; a distributed lock manager driver included within each processing node, said driver including a communication service providing for the generation of datagrams comprising lock manager instructions for transmission to other ones of said processing nodes via said virtual circuits, said communication service also providing for the receipt of datagrams generated and transmitted by other ones of said processing nodes; and means for testing the integrity of a virtual circuit between a sending processing node and a receiving processing node, said means generating a periodic keepalive message packet which is periodically sent by said sending processing node to said receiving processing node requesting the transmission of an acknowledge signal in response thereto, said keepalive message packet being transmitted in the absence of the receipt of a data packet from said receiving processing node for a predetermined period of time.
Claim 8
Dependent Claim 145 words
In a clustered computer system including a network of processing nodes and a distributed lock manager for coordinating processing activities within the clustered computer system, the improvement comprising: a plurality of virtual circuits, a virtual circuit between each pair of said processing nodes within said clustered computer system; a distributed lock manager driver included within each processing node, said driver including a communication service providing for the generation of datagrams comprising lock manager instructions for transmission to other ones of said processing nodes via said virtual circuits, said communication service also providing for the receipt of datagrams generated and transmitted by other ones of said processing nodes; and means for generating and transmitting an acknowledge signal in response to receipt of a data packet at a receiving processing node, said acknowledge signal being attached to a data packet being transmitted by said receiving processing node.
Claim 9
Dependent Claim 145 words
In a clustered computer system including a network of processing nodes and a distributed lock manager for coordinating processing activities within the clustered computer system, the improvement comprising: a plurality of virtual circuits, a virtual circuit between each pair of said processing nodes within said clustered computer system; a distributed lock manager driver included within each processing node, said driver including a communication service providing for the generation of datagrams comprising lock manager instructions for transmission to other ones of said processing nodes via said virtual circuits, said communication service also providing for the receipt of datagrams generated and transmitted by other ones of said processing nodes; and means for generating and transmitting an acknowledge signal in response to receipt of a data packet at a receiving processing node, said acknowledge signal being attached to a data packet being transmitted by said receiving processing node.
Claim 10
Dependent Claim 35 words
The improvement according to claim 5, further comprising: means for limiting the transmission of additional datagrams when a predetermined number of datagrams have been transmitted without the receipt of acknowledge signals for said transmitted datagrams.
Claim 11
Dependent Claim 183 words
A datagram messaging service for a distributed lock manager implemented on a clustered computer system including a plurality of processing nodes, said datagram messaging service comprising: a plurality of virtual circuits, a virtual circuit between each pair of said processing nodes within said clustered computer system; a distributed lock manager driver included within each processing node, said driver including a communication service providing for the generation of datagrams comprising lock manager instructions for transmission to other ones of said processing nodes via said virtual circuits, said communication service also providing for the receipt of datagrams generated and transmitted by other ones of said processing nodes; and means for testing the integrity of a virtual circuit between a sending processing node and a receiving processing node, said means generating a periodic keepalive message packet which is periodically sent by said sending processing node to said receiving processing node requesting the transmission of an acknowledge signal in response thereto, said keepalive message packet being transmitted in the absence of the receipt of a datagram from said receiving processing node for a predetermined period of time.
Claim 12
Dependent Claim 183 words
A datagram messaging service for a distributed lock manager implemented on a clustered computer system including a plurality of processing nodes, said datagram messaging service comprising: a plurality of virtual circuits, a virtual circuit between each pair of said processing nodes within said clustered computer system; a distributed lock manager driver included within each processing node, said driver including a communication service providing for the generation of datagrams comprising lock manager instructions for transmission to other ones of said processing nodes via said virtual circuits, said communication service also providing for the receipt of datagrams generated and transmitted by other ones of said processing nodes; and means for testing the integrity of a virtual circuit between a sending processing node and a receiving processing node, said means generating a periodic keepalive message packet which is periodically sent by said sending processing node to said receiving processing node requesting the transmission of an acknowledge signal in response thereto, said keepalive message packet being transmitted in the absence of the receipt of a datagram from said receiving processing node for a predetermined period of time.
Claim 13
Dependent Claim 141 words
A datagram messaging service for a distributed lock manager implemented on a clustered computer system including a plurality of processing nodes, said datagram messaging service comprising: a plurality of virtual circuits, a virtual circuit between each pair of said processing nodes within said clustered computer system; a distributed lock manager driver included within each processing node, said driver including a communication service providing for the generation of datagrams comprising lock manager instructions for transmission to other ones of said processing nodes via said virtual circuits, said communication service also providing for the receipt of datagrams generated and transmitted by other ones of said processing nodes; and means for generating and transmitting an acknowledge signal in response to receipt of a datagram at a receiving processing node, said acknowledge signal being attached to a datagram being transmitted by said receiving processing node.
Claim 14
Dependent Claim 141 words
A datagram messaging service for a distributed lock manager implemented on a clustered computer system including a plurality of processing nodes, said datagram messaging service comprising: a plurality of virtual circuits, a virtual circuit between each pair of said processing nodes within said clustered computer system; a distributed lock manager driver included within each processing node, said driver including a communication service providing for the generation of datagrams comprising lock manager instructions for transmission to other ones of said processing nodes via said virtual circuits, said communication service also providing for the receipt of datagrams generated and transmitted by other ones of said processing nodes; and means for generating and transmitting an acknowledge signal in response to receipt of a datagram at a receiving processing node, said acknowledge signal being attached to a datagram being transmitted by said receiving processing node.
Claim 15
Dependent Claim 37 words
The datagram messaging system according to claim 8, further comprising: means for limiting the transmission of additional datagrams when a predetermined number of datagrams have been transmitted without the receipt of acknowledge signals for said transmitted datagrams.
Claim 16
Independent Claim 162 words
A method for operating a distributed lock manager in a clustered computer system, said clustered computer system including a plurality of processing nodes interconnected by a network, said method comprising the steps of: establishing a virtual circuit between each pair of said processing nodes within said clustered computer system; directly sending datagrams comprising lock manager instructions from a sending processing node to a receiving processing node via said virtual circuits, and subsequently directly receiving an acknowledgment signal back from said receiving processing node to said sending processing node; and testing the integrity of a virtual circuit between said sending processing node and said receiving processing node by generating a keepalive message packet which is periodically sent by said sending processing node to said receiving processing node requesting the transmission of an acknowledge signal in response thereto, said keepalive message packet being transmitted in the absence of the receipt of a datagram from said receiving processing node for a predetermined period of time.
Claim 17
Independent Claim 162 words
A method for operating a distributed lock manager in a clustered computer system, said clustered computer system including a plurality of processing nodes interconnected by a network, said method comprising the steps of: establishing a virtual circuit between each pair of said processing nodes within said clustered computer system; directly sending datagrams comprising lock manager instructions from a sending processing node to a receiving processing node via said virtual circuits, and subsequently directly receiving an acknowledgment signal back from said receiving processing node to said sending processing node; and testing the integrity of a virtual circuit between said sending processing node and said receiving processing node by generating a keepalive message packet which is periodically sent by said sending processing node to said receiving processing node requesting the transmission of an acknowledge signal in response thereto, said keepalive message packet being transmitted in the absence of the receipt of a datagram from said receiving processing node for a predetermined period of time.
Claim 18
Dependent Claim 36 words
The method according to claim 10, further comprising the step of limiting the transmission of additional datagrams when a predetermined number of datagrams have been transmitted without the receipt of acknowledge signals for said transmitted datagrams.
Claim 19
Independent Claim 132 words
A method for operating a distributed lock manager in a clustered computer system, said clustered computer system including a plurality of processing nodes interconnected by a network, said method comprising the steps of: establishing a virtual circuit between each pair of said processing nodes within said clustered computer system; directly sending datagrams comprising lock manager instructions from a sending processing node to a receiving processing node via said virtual circuits, and subsequently directly receiving an acknowledgment signal back from said receiving processing node to said sending processing node; and generating and transmitting an acknowledgment signal in response to receipt of a datagram from said sending processing node by said receiving processing node, said acknowledge signal being attached to another datagram being transmitted by said receiving processing node to said sending processing node.
Claim 20
Independent Claim 132 words
A method for operating a distributed lock manager in a clustered computer system, said clustered computer system including a plurality of processing nodes interconnected by a network, said method comprising the steps of: establishing a virtual circuit between each pair of said processing nodes within said clustered computer system; directly sending datagrams comprising lock manager instructions from a sending processing node to a receiving processing node via said virtual circuits, and subsequently directly receiving an acknowledgment signal back from said receiving processing node to said sending processing node; and generating and transmitting an acknowledgment signal in response to receipt of a datagram from said sending processing node by said receiving processing node, said acknowledge signal being attached to another datagram being transmitted by said receiving processing node to said sending processing node.

USPTO Annuity & Maintenance Windows

Annuity Stage Window Opens Payment Deadline Surcharge Period Until Estimated Fee Status
3.5 Years (Year 4) 2000-12-15 2001-06-16 2001-12-16 $2000.00 Window Closed / Lapsed
7.5 Years (Year 8) 2004-12-15 2005-06-16 2005-12-16 $3760.00 Window Closed / Lapsed
11.5 Years (Year 12) 2008-12-15 2009-06-16 2009-12-16 $7700.00 Window Closed / Lapsed

Assigned Categories & Tags

No categories assigned to this patent yet.

Assign Category Tag