Emc Corporation

Hewlett-packard Development Company, L.P.

Jeffrey Lucovsky

Alan Lee Taylor

Dennis Thomas Duprey

Karl M Owen

Dave W Harvey

Guillermo Roa

David M Zeryck

A system, device, and method for interprocessor communication in a computer system utilizes a special Message Passing Service (MPS) to provide interprocessor communications. The MPS enables a client application running on one processor in a computer to communicate with a target application running a different processor in the same or a different computer. In order for the client application to communicate with the target application, the client application establishes a session to the target application over an existing communication link using the MPS. The MPS provides for both synchronous and asynchronous communication services. When the client application establishes the session to the target application, the client application specifies, among other things, a 'callback' routine. The MPS invokes the 'callback' routine to report certain asynchronous events to the client application. The MPS blocks the client application during certain synchronous operations so that the client application does not proceed until the synchronous operation is completed.

System, device and method for interprocessor communication in a computer system

A system and method for a process attribute based computer network filter assigns a process attribute to a process executing on a computing device and assigns a network attribute to a network interface card (NIC) associated with the computing device. When the process desires to send a communication packet to another process on a different computing device over a network to which the NIC is connected, the process sends an application program interface (API) system call to the NIC. The API call is intercepted by a system call trap handler, which, in cooperation with a session filter driver and a network filter driver, determines the process attribute associated with the process and the network attribute associated with the NIC. If the session filter driver and the network filter driver, in cooperation with the system call trap handler, determine that the process attribute and the network attribute correspond, then the communication packet is allowed to pass to the network. Similarly, a packet received over the network is processed by the session filter driver and the network filter driver to determine whether the packet can pass to the process to which the received packet is destined.

System and method for a process attribute based computer network filter

A computer storage architecture utilizing layered device drivers enables a user to create and install a device driver into a computer. The device driver is installed into the storage unit through a registration process. In order to permit the user to specify a device driver stack for the device driver and specify the relative position of the device driver within the device driver stack, a novel layered device driver registration system that is separate from a operating system device driver registration system is utilized. The layered device driver registration system enables the user to install one or more device drivers and to specify the placement of each device driver by relative to the other device drivers in various device driver stacks. The layered device driver registration system allows a device driver to be dynamically inserted into or removed from a particular device driver stack.

Computer architecture utilizing layered device drivers

In a remote mirroring system, device, and method, a master storage unit stores information in a log and uses the information from the log to quickly resynchronize slave images following a failure in the master storage unit. Upon receiving a write request from a host, the master storage unit stores a write entry in the log. The write entry includes information that identifies a portion of the slave images that may be unsychronized from the master image due to the write request. The master storage unit then proceeds to update the master image and the slave images. The log is preserved through the failure, such that the log is available to the master storage unit upon recovery from the failure. When the master storage unit is operational following the failure, the master storage unit resynchronizes the slave images to the master image by copying those portions of the master image indicated in the log to the slave images.

Growing community of inventors

Cary, NC, United States of America

Jeffrey Lucovsky