公开(公告)号：GB2400935A

公开(公告)日：2004-10-27

申请号：GB0309538

申请日：2003-04-26

Applicant: IBM

Inventor： SCALES WILLIAM JAMES ,  RANKIN HOWARD CHARLES ,  O'ROURKE NICHOLAS MICHAEL

IPC: G06F12/08 ,  G06F3/06 ,  G06F11/20 ,  G06F11/34 ,  G06F12/00 ,  G06F12/16 ,  G06F13/10 ,  G06F13/14 ,  G11B20/18 ,  H02H3/05

Abstract: An apparatus and method of use are provided to determine the optimum I/O configuration of a RAID controller. The I/O configuration includes parameters for data length and alignment. In use a virtualised RAID controller is established in a memory and tests performance characteristics by issuing a plurality of different I/O operations, each of which includes a write operation to the RAID controller. In response to the testing an optimal configuration can then be set for the RAID controller. Preferably the key performance characteristic may be response time. The memory used maybe cache, an input buffer or and output buffer. The method may be carried out when the RAID controller is idle.

公开(公告)号：AU2003253003A8

公开(公告)日：2004-06-23

申请号：AU2003253003

申请日：2003-08-14

Applicant: IBM

Inventor： FUENTE CARLOS FRANCISCO ,  SCALES WILLIAM JAMES

IPC: G06F1/00 ,  G06F9/46 ,  G06F13/12 ,  G06F13/38 ,  G06F15/00 ,  H04L29/06

Abstract: A method, system, and machine-readable medium for providing high-performance lock management for a flash copy image of a region of data in N-way shared storage systems is disclosed. According to one embodiment, a data processing system is provided which comprises a cache to store a copy of metadata specifying a coherency relationship between a region of data and a flash copy image of the region of data, wherein the metadata is subject to one or more lock protocols controlled by an owner storage controller node; and a client storage controller node, coupled with the cache, comprising an input/output performing component to receive a request to perform an input/output operation on at least one of the region of data and the flash copy image of the region of data and to perform the input/output operation utilizing the copy of the metadata.

公开(公告)号：AU2003251057A1

公开(公告)日：2004-06-23

申请号：AU2003251057

申请日：2003-08-13

Applicant: IBM

Inventor： CASHMAN PAUL NICHOLAS ,  FUENTE CARLOS FRANCISCO ,  SCALES WILLIAM JAMES

IPC: H04J3/16 ,  H04L12/56 ,  H04L47/722 ,  H04L49/901

Abstract: Systems for transmitting an application message between nodes of a clustered data processing system are disclosed. One system includes a determination of whether one or more application messages may currently be transmitted to a first node of a plurality of nodes from a second node of the plurality of nodes. The system further includes processing the one or more application messages in response to a determination that the one or more application messages may be currently transmitted.

公开(公告)号：GB2395578A

公开(公告)日：2004-05-26

申请号：GB0227250

申请日：2002-11-22

Applicant: IBM

Inventor： DEACON PETER ,  FUENTE CARLOS FRANCISCO ,  SCALES WILLIAM JAMES ,  WHYTE BARRY DOUGLAS

IPC: G06F11/00 ,  G06F11/07 ,  G06F13/00 ,  H04B1/74

Abstract: In a stacked system, errors detected at a user application interface of one or more host systems are associated with root cause errors at a stack level below a virtualization layer by detecting an error at a user application interface; identifying an associated root cause error at a lower stack level; creating an error trace entry for the error; associating an error log identifier with the error trace entry; making the combined error log identifier and the error trace entry into an error identifier that is unique within the plurality of host systems in said stacked system; and communicating the error identifier to any requester of a service at a user application interface of one or more host systems when the service must be failed because of the root cause error.