Electrical computers and digital processing systems: memory – Storage accessing and control – Specific memory composition
Reexamination Certificate
2000-01-24
2003-12-30
Moazzami, Nasser (Department: 2187)
Electrical computers and digital processing systems: memory
Storage accessing and control
Specific memory composition
C711S202000, C714S006130, C710S038000
Reexamination Certificate
active
06671776
ABSTRACT:
FIELD OF THE INVENTION
The present invention is directed to storage array technology, and, more particularly, to storage array technology that automatically determines the topology of a storage array network including the association of host port adapters, hosts and cluster groups.
BACKGROUND OF THE INVENTION
Although still an evolving, Storage Area Networks (SANs) promise to revolutionize the majority in which storage are coupled in the years to come. Today, the vast majority of host systems are directly attached to the storage that they use. With storage area metworking, storage and hosts will no longer be so closely coupled. Instead, system architects will be able to engineer configurations that answer some requirements and, in the future, will be able to answer even more of the myriad of requirements that have, to date, been only answerable by proprietary storage solutions.
SANs offer system designers a whole new way of approaching storage. Traditionally, the host-storage interface has been closely coupled. In fact, the only time that small computer system interface (SCSI) storage has been successfully attached to multiple hosts is in the case of clustered central processing units. The reason for this is simple, the SCSI protocol was not developed with the idea of multiple heterogeneous hosts sharing the same SCSI cable. Because SCSI has been relatively limited in its speed and the ability to address a large amount of disk capacity on SCSI does not exist, the idea of sharing storage between a number of hosts on the SCSI interface has not traditionally been a driving factor.
There are a number of reasons why end users see value in sharing storage between a number of hosts. One of the primary reasons is that the investment in storage can be amortized across multiple hosts. This is an important consideration today, since the expense of storage is a significant factor in the cost associated with a system installation. This is particularly true in cases where multiple small capacity hosts require highly available storage such as Redundant Array of Independent Disks (RAID). Another factor is storage consolidation. By enabling a variety of hosts to attach to a single, large array, management and maintenance costs are reduced, positively impacting the total cost of storage ownership. A third factor is standardization. Instead of forcing system administrators to work with storage arrays from multiple vendors, standardization provides a single, centralized management system capable of managing storage throughout the SAN.
One approach to creating a shared SAN is the use of specially developed access control software run on the storage array itself. This software controls host access to storage within the array on a logical unit number (LUN) basis, based on the actual fibre channel address of the host. Essentially a table driven access control, this solution is able to map host access requests to storage associated with that host exclusively or inclusively, depending on the configuration and application requirements. In essence, the host only sees what the access control software on the array allows it to see, removing from its view all other storage in the array. For example, it can be possible to share a 1TB RAID array across ten hosts, each of which believes the array only has 100GB of capacity. By implementing management of the software control in the array's storage management utilities, the solution can be made fully host independent.
A disadvantage in today's SCSI and fibre channel storage connect environment is the inability to automatically determine the topology of a network and convey that topology to a system administrator, for example, in a user-friendly manner. Currently host port adapters are provided with a unique identification (I.D.), such as a worldwide name (WWN). This information is transmitted to a storage array controller to identify the adapter through which a command was issued. Unfortunately, if a host has multiple adapters, information concerning the host is not conveyed. Thus, apart from manually checking, there is no way to know what adapter is associated with what host. Moreover, if hosts are grouped in clusters, associating an adapter with a cluster is not automatically possible. Without this information, it is very time consuming to determine the topology of the network. Currently, to provide a system administrator with information concerning the topology of a network, a mapping of the host port adapters to the hosts and clusters must be done manually. This is a time consuming proposition as storage array networks become more complex and is prone to errors. In addition, if changes are made to the topology of the network such as replacing a failed adapter, the administrator must manually map the WWN of the replacement adapter into the existing topology. Thus, the topology reflected to the administrator can become outdated without the administrator's knowledge.
It is thus desirable to provide an automated method and system for determining the topology of a storage array network and conveying that topology to an administrator in a user friendly fashion. It is also desirable to provide a method and system for automatically updating the topology whenever changes are made to the topology. It is also desirable to provide an administrator with a view of the current topology at a remote location from which the administrator can make changes to the topology.
SUMMARY OF THE INVENTION
According to a first aspect of the invention there is provided a method of transmitting information from which a topology of a storage array network having multiple hosts, with at least one host having a plurality of host port adapters, may be determined. The method includes the steps of:
(a) generating a command from a host wherein the command includes a unique host identifier and a unique host port adapter identifier wherein the unique host identifier is linked to the unique host port adapter identifier; and
(b) transmitting the command from the host to a controller of a storage array network through a first path coupling the host port adapter to the controller.
According to a second aspect of the invention, there is provided a storage array network including:
a plurality of hosts;
a storage array having multiple volumes;
a storage array controller operatively coupled to the storage array;
a bus operatively coupling each host to the storage array controller,
wherein each of the plurality of hosts transmits to the storage array controller a command that includes a unique host identifier and a unique host port adapter identifier.
According to a third aspect of the invention, there is provided a computer readable medium for generating a topology of a storage array network. The medium includes:
code that represents a table of unique identifiers of a plurality of hosts and unique identifiers of a plurality of host port adapters associated with each of the plurality of hosts; and
code that utilizes the table to generate a display of the topology of the network.
According to a fourth aspect of the invention, there is provided a system for determining a topology of a storage array network having multiple hosts with at least one host having a plurality of host port adapters, the system comprising:
a general purpose computing device; and
a computer program comprising one or more program modules executable by the computing device;
wherein the program modules comprises a table module for uniquely associating each host and its host adapter port with a controller via a path and a topology module that utilizes the table module to generate a topology of the network.
REFERENCES:
patent: 4396984 (1983-08-01), Videki, II
patent: 5301297 (1994-04-01), Menon et al.
patent: 5787463 (1998-07-01), Gajjar
patent: 5790775 (1998-08-01), Marks et al.
patent: 5812754 (1998-09-01), Lui et al.
patent: 5883621 (1999-03-01), Iwamura
patent: 5938744 (1999-08-01), Roganti et al.
patent: 5973690 (1999-10-01), Ofer et al.
patent: 6173339 (2001-01-01), Yorimitsu
patent: 6260120 (2001-07-01), Blumenau e
Moazzami Nasser
The Law Offices of William W. Cochran, LLC
LandOfFree
Method and system for determining and displaying the... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method and system for determining and displaying the..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and system for determining and displaying the... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3114458