Apparatus for controlling the temperature of rods in a continuous rolling mill |
| Accordingly, it is an object of the present invention to provide an apparatus for controlling the ... |
|
Electronic postage meter with a ring counter |
| What is claimed is: 1. In an electronic postage meter having at least one volatile register for ... |
|
Mode detection circuit for a dual purpose analog input |
| Referring to the drawing, a mode detection circuit in accordance with the present invention is ... |
|
Circuit for maintaining the state of an output despite changes in the state of input |
| It is an object of the present invention to provide a low voltage control circuit for maintaining ... |
|
Helicopter, high rotor load speed enhancement |
| We claim: 1. A control for a helicopter engine having a free turbine for normally driving the ... |
|
Mobile receiver |
| It is an object of the present invention to provide a mobile receiver which allows easy ... |
|
Detent remover for a postage meter |
| It has been found that the detent mechanism of a postage meter may be prevented from premature wear ... |
|
Anti-energy diversion system for electric utility meters |
| It is, therefore, the primary object of the present invention to provide an anti-theft system for ... |
|
Carriage for sorting-machines in particular, with independently actioned tiltable plate |
| I claim: 1. In a carriage for a sorting machine, the sorting machine having at least one track, a ... |
|
Yarn supply device group |
| The set problem is solved inventively by providing a yarn supply device group in which each supply ... |
|
|
System and method for backup a parallel server data storage system
| Details |
Inventors: Taylor, Kenneth J.;
Assignee: EMC Corporation (Hopkinton, MA)
Primary Examiner: Beausoliel; Robert
Assistant Examiner: McCarthy; Christopher S.
Attorney, Agent or Firm: Michaelis; Brian L., McHugh; Steven M. Brown Rudnick Berlack Israels LLP
A system and method for safe and effective backup and restore of parallel server databases stored in data storage systems. Parallel server databases allow multiple nodes in MPP (Massively Parallel Processor) or SMP (Symmetric Multi-Processor) systems to simultaneously access a database. Each node is running an instance (thread) which provides access to the database. The present invention allows for online or offline backup to be performed from any node in the system, with proper access to all control files and logs, both archived and online, whether the files are stored in raw partitions in the data storage system, or local on certain nodes. Two different types of external restore supported: complete external restore and partial external restore. In a complete external restore, all spaces will be restored to the most recent checkpoint that was generated while creating an external backup. If users lose only a portion of the data (which is more typically the case), a partial external restore may be performed. |
|
DETAILED DESCRIPTION The present invention is directed towards a backup system 22FIG. 1 to perform backup and restore of parallel server databases in a data storage system 14. A parallel server database configuration can be implemented on either an MPP (massively parallel processor) machine or in a hardware cluster of multiple distinct SMP (symmetric multi-processor) machines. In the case of an MPP or "shared nothing" architecture, all nodes of the parallel server database configuration will exist on the same actual machine frame, but do not physically share disks. Disks are shared virtually via an interconnect within the frame. Each node may be an SMP machine. Multiple machines clustered together using proprietary hardware clustering can also comprise a parallel server database configuration. In this case a "node" is an independent machine. A typical parallel server database architecture is illustrated in FIG. 3. One database 40 is serviced by several instances 30a, 30b. An instance is one or more process along with memory buffers servicing a database 40 on a particular node. By definition, a parallel server database has multiple instances 30. Each instance 30 is independently accessing the database 40. All data files 40 reside on raw partitions, and are visible to all parallel server database nodes. All online redo logs 36 similarly reside in raw partitions and are visible to all parallel server database nodes. All control files 32 have the same properties. Each instance 30a, 30b archives its own redo information 36a, 36b. Typically, the archive logs 34 are maintained in directories on the node where the instance 30 is running. Since archive logs 34 can be in several directories on different nodes, the present invention includes a method for backing up and restoring files from multiple machines (nodes). According to the present invention, the archive log 34FIG. 4 directories are set to be readable and writable by all nodes servicing the database 40. The archive log directories from the different node are accessible 42 through the network file system (NFS) or equivalent, in read/write mode on any nodes from which backup or restore will be performed
|
|