Electrical computers and digital processing systems: memory – Storage accessing and control – Control technique
Reexamination Certificate
2002-08-05
2004-08-03
Vital, Pierre M. (Department: 2186)
Electrical computers and digital processing systems: memory
Storage accessing and control
Control technique
C711S114000, C711S162000, C711S165000, C707S793000, C710S032000
Reexamination Certificate
active
06772309
ABSTRACT:
FIELD OF THE INVENTION
The present invention relates to the field of data protection and more particularly to a system and method for using locks to provide safe movement of data using third party copy techniques.
BACKGROUND OF THE INVENTION
Recent developments in storage solutions have led to the increased utilization by enterprises of Storage Area Networks (SANs) to provide storage consolidation, reliability, availability, and flexibility. Factors driving these developments include the increase in the amount of on-line data, data protection requirements including efficient and reliable data back-up, and rapidly increasing disk bit densities.
FIG. 1
illustrates a simplified example of an enterprise computing system
100
. Servers
110
and
120
are at the heart of computing system
100
. As members of enterprise computing system
100
, servers
110
and
120
are often referred to as “hosts” or “nodes,” and can execute an number of different types of programs including, for example, operating systems, file systems, volume managers, and applications programs such as database systems.
FIG. 6
(described below) illustrates some of the features common to servers
110
and
120
as well as client computer systems
130
. Servers
110
and
120
can exchange data over network
140
, typically a local area network (LAN), e.g., an enterprise-wide intranet, or a wide area network (WAN) such as the Internet. Additionally, network
140
provides a communication path for various client computer systems
130
to communicate with servers
110
and
120
.
Other elements of enterprise computer system
100
include storage area network (SAN)
150
, SAN switch
160
, and storage devices such as tape drive
170
, storage array
180
, and optical drive
190
. As shown in
FIG. 1
, both servers
110
and
120
are coupled to SAN
150
. SAN
150
is conventionally a high-speed network that allows the establishment of direct connections between storage devices
170
,
180
, and
190
and servers
110
and
120
. Thus, SAN
150
is shared between the servers and allows for the sharing of storage devices between the servers to providing greater availability and reliability of storage.
SAN switch
160
, tape drive
170
, storage array
180
, and optical drive
190
are examples of shared resources. The most common shared resource in an enterprise computing environment is some form of shared data resource, such as one or more disk drives. Although a disk device (and various related devices such as storage array
180
) is perhaps the most common example of both a shared resource and a shared data resource, a variety of other types of devices will be well known to those having ordinary skill in the art. Moreover, servers
110
and
120
can be connected to SAN
150
through SAN switch
160
. Additionally, the shared resources can be directly connected to, or part of, the servers, and thus enterprise computing system
100
need not include a SAN. Alternatively, servers
110
and
120
can be connected to multiple SANs. Additionally, SAN switch
160
can be replaced with a SAN router or a SAN hub.
Protecting the integrity of data as it is moved from one part of a computing system to another is an important aspect of any computer system. Data movement can result from a variety of operations including normal application software operation, data backup operations, data restore operations, and data relocation resulting from system design changes or hardware failures. In many computing systems, data movement is handled by programs executing on servers such as servers
110
and
120
. In the case of data movement operations such as data backup and data restore, the use of server resources to handle the data movement means that fewer server resources are available for more typical operations such as application software and operating system overhead. Accordingly, efforts have been taken to move some I/O processing off of system servers to an offhost agent. Such agents are often referred to as third-party copy (3PC) devices or data movers.
Third-party copy operations transfer data directly between storage devices in a SAN or other environment using a third-party copy device, copy manager, or data mover
200
such as illustrated in FIG.
2
. Data mover
200
can be a separate device as shown; part of a SAN switch, router, bridge, or another SAN network component (not shown) or within a storage element such as storage array
180
in FIG.
1
. As is typical of SAN environments, the connection between the servers
110
and
120
and data mover
200
is conventionally a channel protocol bus such as SCSI or fibre channel connected directly to the storage devices or storage device controllers (e.g. RAID controllers). Thus, the data mover operates on behalf of some other piece of software, e.g., a backup or restore application, to accomplish the third party copy operation.
In one example of a third party copy device, the device implements the SCSI-3 extended copy command. SCSI-3 commands are described in SCSI Primary Commands-3 (SPC-3), Working Draft, Revision 03, T10, a Technical Committee of the Accredited Standards Committee of the National Committee for Information Technology Standards (NCITS), Jan. 10, 2002, which is hereby incorporated by reference herein in its entirety. The extended copy command provides a SCSI command to copy data from one set of devices to another. These devices can be disks, tapes, or other types of storage devices. This SCSI protocol command can be used on devices connected via SCSI cables or Fibre Channel connections. The data mover is the device that receives and performs the extended copy command. Another device is an intelligent device somewhere in the storage infrastructure that understands the extended copy command. This can be another server, but more likely will be a smart-storage device, such as an intelligent tape device, disk device, SAN switch or storage router. The host server typically has some extra processing to perform at first, in order to gather all the file or volume information necessary to pass along inside the extended copy command. Additionally, if either the source or destination of the extended copy is a removable media device, then the host will typically first issue other SCSI commands to get the removable device into the proper position (loading or positioning the tape). Next, the host issues the extended copy command to the data mover, telling the device to move data from one storage device directly to another storage device. After issuing the extended copy command, no further instructions have to be issued by the host to move the data—the devices themselves perform the entire data movement operation over the SCSI bus or Fibre Channel connection.
As illustrated in
FIG. 2
, storage devices
210
and
220
are coupled to the SAN
150
. In this example, storage devices
210
and
220
are shown as a data source and a data destination respectively (e.g., illustrating a restore operation from a tape drive to a hard disk), but such devices can typically operate as either data sources or data destinations. Alternately, source storage devices can be directly coupled to the SAN
150
through data mover
200
. In still another example, data mover
200
can be included as part of a proprietary storage device, such as a storage array. Thus, data movers
200
can be implemented as independent devices, devices in traditional SAN components, or even as software executing on a SAN component, e.g., software executing on a storage device controller.
In general, data to and from storage devices is provided using either block-level or file-level access. File level access requires some knowledge of the underlying file system and/or volume management system used to organize data on the storage devices. This type of information is typically available only at the host level, and thus I/O operations utilizing file-level access must be performed or at least managed by software executing on a host computer. Block-level access uses physical storage device addresses to access data and thu
Lanzatella Thomas W.
Ohr James P.
Ascolese Marc R.
Campbell Stephenson Ascolese LLP
VERITAS Operating Corporation
Vital Pierre M.
LandOfFree
System and method using locks for providing safe movement of... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with System and method using locks for providing safe movement of..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and System and method using locks for providing safe movement of... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3273411