Andrew P Alleman, Age 562435 SW Winchester Ave, Portland, OR 97225

8553552, Oct 8, 2013

Feb 8, 2012

13/369070

Michael W. Hu - Portland OR, US
Andrew P. Alleman - Portland OR, US

RadiSys Corporation - Hillsboro OR

H04L 12/26
H04L 12/28
G06F 15/173

370235, 370392, 709238

Stateless load balancing of network packets within a system avoids detection by a network client or end user for deep packet inspection or other bump-in-the-wire applications. At least one header field of a received packet is used in generating a hash value. The hash value is used to identify a processing resource within the system for processing the received packet. Before being sent to the identified resource, the received packet is encapsulated with a new header that includes an indication of ingress port. The encapsulation does not modify the original packet. On a return path from the identified processing resource, the ingress port is determined from the encapsulated packet, the encapsulated packet is decapsulated to obtain a recovered packet that is identical to the received packet, and the recovered packet is forwarded to the network through an egress port as determined from the recovered ingress port.

2013020, Aug 8, 2013

Feb 8, 2012

13/369073

Michael W. Hu - Portland OR, US
Andrew P. Alleman - Portland OR, US

RADISYS CORPORATION - Hillsboro OR

H04L 12/24

370219

Backplane redundancy is provided for a system including multiple nodes that communicate packets through first and second switches. Assuming that the first switch is initially assigned to an active state and the second switch to a standby state, the nodes communicate the data packets through physically enabled first backplane links to the first switch. The nodes physically enable second backplane links that are in a condition to communicate the data packets to the second switch. A messageless failover process is initiated by temporarily disabling, at the first switch, the first backplane links between the first switch and the nodes. In response to the nodes detecting the disabled first backplane links to the first switch, the nodes reconfigure themselves to communicate the data packets through the second backplane links to the second switch and to stop communicating the packets through the first backplane links to the first switch.

2014005, Feb 27, 2014

Aug 30, 2013

14/015683

Andrew P. Alleman - Portland OR, US

RadiSys Corporation - Hillsboro OR

H04L 12/911
H04L 12/721

370235

Stateless load balancing of network packets within a system avoids detection by a network client or end user for deep packet inspection or other bump-in-the-wire applications. At least one header field of a received packet is used in generating a hash value. The hash value is used to identify a processing resource within the system for processing the received packet. Before being sent to the identified resource, the received packet is encapsulated with a new header that includes an indication of ingress port. The encapsulation does not modify the original packet. On a return path from the identified processing resource, the ingress port is determined from the encapsulated packet, the encapsulated packet is decapsulated to obtain a recovered packet that is identical to the received packet, and the recovered packet is forwarded to the network through an egress port as determined from the recovered ingress port.

6389130, May 14, 2002

Mar 30, 2000

09/540006

George Shenoda - Portland OR
Andrew P. Alleman - Portland OR

Oresis Communications - Beaverton OR

H04L 1228

37922108, 370352, 37039551, 3703956, 370410, 370467

The distributed architecture switch of the invention provides a scalable, flexible switching device to route telephone calls and other data (e. g. , frame relay, ISDN) over an asynchronous transfer mode (ATM) network. The switch includes multiple service modules that can be geographically disparate and function as a single switching device. The multiple service modules are coupled to a system controller that controls the service modules and passes messages between the service modules.

2018009, Mar 29, 2018

Sep 27, 2017

15/717790

- Hillsboro OR, US
Andrew Alleman - Portland OR, US

H04L 29/08
H04L 12/803

To facilitate high throughput, disclosed are lightweight processes, suitable for implementation on a network processor unit, for assigning new workloads to a pool of processing resources, in which the processes include considering each processing resource's relative loading. The disclosed techniques facilitate coping with assigning new work to individual processing resources in a ratio relating to their most recently advertised spare capacity. Also, the disclosed techniques include assigning workloads to buckets, which in turn are allocated to processing resources as a means of load distribution. Thus, the allocations are amenable to rapid redistribution within a subset of active services so as to recover from the failure of a processing resource. Support for elastic provisioning is facilitated by blocking any new load going to a processing resource that has been marked for eventual graceful shutdown.

2018008, Mar 22, 2018

Sep 20, 2017

15/710452

- Hillsboro OR, US
Andrew Alleman - Portland OR, US
Srinivas Sadagopan - Bangalore, IN
Prathap Thammanna - Bangalore, IN

H04L 12/741
H04L 12/721

To optimize the multi-table search process, the present disclosure defines a method in which searching across multiple OpenFlow tables is consolidated into searching across a set of three distinct flow caches called access control, application, and forward flow caches. Each OpenFlow table is mapped into one of these flow caches based on the size of the table and whether it contains flows of different priority. The mapping rule ensures that large (in terms of number of entries) OpenFlow tables with no conflicting priority rules are mapped to a flow cache. The disclosed techniques reduce the number of searches and, at the same time, selectively avoid a costly process of revalidation of entries in the flow cache when new higher-priority flows are added by the SDN controller.