Oracle International Corporation

Alan Robert Downing

James William Stamos

Benny Souder

Harry Sun

Lik Wong

Anand Lakshminath

Ramkumar Venkatesan

Shubha Bose

Lip Boon Doo

Dieter Gawlick

Nimar Singh Arora

Krishnan Meiyyappan

Alan J Demers

Lei Gao

Byron Wang

Wayne Smith

Mukesh Jaiswal

Devendra Singh

John R Ciminski

John C Graham

Jun Yuan

Jim Stamos

Patricia H McElroy

Yang Seok Ki

Peter S Lim

Ashish Gupta

Neerja Bhatt

Gaurav Garg

Abhishek Saxena

Mahesh Subramaniam

Curtis Elsbernd

Lewis S Kaplan

Sukanya Balaraman

Ashvin Goel

Sujatha Janardhanan

A method and apparatus for message cache sizing are provided. A plurality of messages from one or more enqueuers are enqueued in a queue comprising at least one shard. Each shard includes one or more subshards. A message cache configured to store a plurality of cached subshards is maintained in memory. The plurality of messages is dequeued from the message cache by one or more dequeuers. An estimated enqueue rate is determined for each shard. An estimated dequeue rate is determined for each dequeuer-shard pair. Estimated restore overhead data is determined over a range of candidate message cache sizes based on the estimated enqueue rate for each shard and the estimated dequeue rate for each dequeuer-shard pair. A preferred message cache size is determined based on the estimated restore overhead data.

Message cache sizing

A method and apparatus for message cache management for message queues is provided. A plurality of messages from a plurality of enqueuers are enqueued in a queue comprising one or more shards, each shard comprising one or more subshards. A message cache is maintained in memory. Enqueuing a message includes enqueuing the message in a current subshard of a particular shard, which includes storing the message in a cached subshard corresponding to the current subshard of the particular shard. For each dequeuer-shard pair, a dequeue rate is determined. Estimated access time data is generated that includes an earliest estimated access time for each of a plurality of subshards based on the dequeuer-shard pair dequeue rates. A set of subshards is determined for storing as cached subshards in the message cache based on the earliest estimated access times for the plurality of subshards.

Message cache management for message queues

A method and apparatus for an in-database sharded queue that supports JMS session ordering is provided. Messages from a plurality of enqueuers are stored in a plurality of shards of a particular queue. For each enqueuer, all messages are stored in only one of the shards. Each shard includes one or more subshards, each subshard having one or more partitions of a queue table maintained by a relational database system. All messages from a first enqueuer are stored in partitions of the queue table that are assigned to a first shard of the plurality of shards. All messages from a second enqueuer are stored in partitions of the queue table that are assigned to a second shard of the plurality of shards. Subscribers of the particular queue are caused to dequeue messages from the plurality of shards.

In-database sharded queue

An approach for reducing transport of messages between nodes of a multi-node system is presented wherein a message queue is associated with a queue service, and based on which node the message queue resides, one of the nodes is registered as hosting the associated queue service. In response to a client attempting to connect and requesting a particular queue service, the client is caused to connect to the node on which the queue service resides.

Event locality using queue services

Approaches described herein may be used for provisioning of databases that requires a bulk transfer of data within a distributed computing environment, such as a grid. The approaches do not require the manual intervention of a DBA to, for example, transfer a tablespace between the file systems of operating systems. Instead, the tablespaces may be provisioned automatically and dynamically by a grid computing system whenever it determines the need to dynamically provision a database. In addition, as copies of tablespaces are provisioned, synchronization mechanisms can also be automatically provisioned to keep the tablespaces and their copies in sync.

Automatic and dynamic provisioning of databases

Systems and methods for providing a one-step API that executes a series of atomic transactions in a database system. In one implementation, each atomic transaction is associated with a forward block of code that effects changes, an undo block of code that reverses the changes made by the forward block, and a state block of code that mimics successful execution of the forward block by setting internal states. In the event of a failure, the forward blocks, undo blocks, and state blocks can be used to roll forward or roll back changes as a whole. In one implementation, a one-step API for replicating data in a database is provided.

Recoverable execution

Splitting and merging database object information sharing streams. Streams are also referred to herein as 'propagations'. Splitting and merging information sharing streams can be used to improve performance in a information sharing environment when a failed or slow DBS impacts the performance. In one embodiment, an auto split process monitors the progress of applying changes at each node and detects the presence of a failed or a slow node. Once the failed or slow node is identified, the auto split process splits the propagation such that the offending node is sent through a separate propagation. Furthermore, an auto merge process can be started to monitor the newly created separate propagation. At a later point, the new propagation can be merged back into the original stream. For example, if the offending node catches up with other nodes, the auto merge process merges the newly created propagation back to the original propagation.

Reconfiguring propagation streams in distributed information sharing

Techniques are provided for maintaining high propagation availability for non-persistent messages. Destination-to-instance mapping information is provided to a listener process for a cluster database. The destination-to-instance mapping indicates the current owner instance of each single-instance destination within the cluster database. To establish a connection to a single-instance destination, a sending process sends a connection request to the global listener. The connection request identifies the desired destination queue, but not the owner instance of the queue. The global listener for the cluster database uses the destination-to-instance mapping to determine which instance is the current owner of the specified queue, and establishes a connection between the sending process and the appropriate owner instance.

High availability for distributed non-persistent event propagation

Techniques are disclosed for sharing information in a wide variety of contexts. An information sharing system is described that allows both an explicit capture process and an implicit capture process to add information items to a staging area. Further, the information sharing system supports both implicit and explicit consumption of information items that are stored in said staging area. A rules engine is provided to allow users to create and register rules that customize the behavior of the capture processes, the consuming processes, and propagation processes that propagate information from the staging areas to designated destinations. Techniques are also described for achieving exactly-once handling of sequence of items, where the items are maintained in volatile memory. Techniques are also provided for recording DDL operations, and for asynchronously performing operations based on the previously-performed DDL operations.

Asynchronous actions using flashback

Configuring an n-way multi-master information sharing topology. Adding a new node (e.g., database server) to the information sharing topology can be implemented as follows. Initially, the new node is added as a slave of a particular co-master in the information sharing topology. The objects to replicate are instantiated on the new node by propagating data from the particular co-master to the new node. Furthermore, a capture process is created on the particular co-master to send changes to the objects to the slave. Meanwhile, the co-masters continue to propagate changes to each other. To promote the slave to a master, changes to objects stored at the slave are propagated to each of the co-masters. Furthermore, changes at each of the masters are propagated to the promoted node.

Configuring or reconfiguring a multi-master information sharing environment

Techniques for sharing information in a wide variety of contexts allows both an explicit capture process and an implicit capture process to add information items to a staging area. An information sharing system supports both implicit and explicit consumption of information items that are stored in the staging area. A rules engine allows users to create and register rules that customize the behavior of the capture processes, the consuming processes, and propagation processes that propagate information from the staging areas to designated destinations. Exactly-once handling of sequence of items is achieved for items maintained in volatile memory. DDL operations are recorded, and operations are asynchronously performed based on the previously-performed DDL operations.

Asynchronous information sharing system

A lightweight row transfer protocol is described that can be easily handled by thin clients, such as JAVA&#x2122; applications using CORBA. The lightweight row transfer protocol serves to reduce bandwidth requirements by applying compression techniques to reduce the number of column lengths in a 'result set' of rows that are transmitted from one computer to another.

Lightweight data replication

An approach is described for improved security during data replication, in which a refresh program runs in the security domain of a trusted user. The refresh program first checks to see if the requesting user actually owns the snapshot before reconciling differences in refreshing a snapshot. Untrusted users are granted only connect privileges and the ability to run a refresh program.

Data replication security

Replication for front office automation involves the use of snapshots that are instantiated on laptops, in which refreshing the snapshots is driven from a master site with a high-performance protocol. All of the necessary snapshot metadata for performing the snapshot refreshes is stored at the master site, so that the laptop only needs to send a single refresh request. In response to the refresh request, the master site reconciles the differences between the master tables and the laptop's snapshots and transmits the differences to the laptop, reducing the necessary network traffic for updating a snapshot to a single round trip.

Growing community of inventors

Fremont, CA, United States of America

Alan Robert Downing