System and method for providing zero buffer copying in a middleware machine environment

• US 9,185,054 B2
• Filed: 09/15/2011
• Issued: 11/10/2015
• Est. Priority Date: 09/15/2010
• Status: Active Grant

• Current Assignee: Oracle International Corporation (Oracle Corporation)
• Original Assignee: Oracle International Corporation (Oracle Corporation)
• Inventors: Revanuru, Naresh, Bihani, Ballav, Larsen, Staffan, Liu, Steven, Phan, Lenny, Oaks, Scott, Torstensson, Patrik, Messinger, Adam, Otenko, Oleksandr, Dorr, Joshua, Cameron, Brad, Torudbakken, Ola, Bhattacharya, Pallab, Reynolds, Nathan
• Primary Examiner(s): KESSLER, GREGORY AARON
• Application Number:
  US13/234,027
• Publication Number:
  US 20120239730A1
• Time in Patent Office: 1,517 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 15/17318 Parallel communications techniques, e.g. gather, scatter, reduce, roadcast, multicast, all to all
• CPC Class Codes: G06F 16/20 of structured data, e.g. relational data
• CPC Class Codes: G06F 16/2358 Change logging, detection, and notification replication G06F16/27
• CPC Class Codes: G06F 16/278 Data partitioning, e.g. horizontal or vertical partitioning
• CPC Class Codes: G06F 9/45504 Abstract machines for programme code execution, e.g. Java virtual machine [JVM], interpreters, emulators
• CPC Class Codes: H04L 41/042 comprising distributed management centres cooperatively managing the network
• CPC Class Codes: H04L 41/0686 Additional information in the notification, e.g. enhancement of specific meta-data
• CPC Class Codes: H04L 49/358 Infiniband Switches
• CPC Class Codes: H04L 67/02 based on web technology, e.g. hypertext transfer protocol [HTTP]
• CPC Class Codes: H04L 67/10 in which an application is distributed across nodes in the network software deployment G06F8/60; multiprogramming arrangements G06F9/46
• CPC Class Codes: H04L 67/1001 for accessing one among a plurality of replicated servers
• CPC Class Codes: H04L 67/1034 Reaction to server failures by a load balancer
• CPC Class Codes: H04L 67/142 Managing session states for stateless protocols; Signalling session states; State transitions; Keeping-state mechanisms
• CPC Class Codes: H04L 67/146 Markers for unambiguous identification of a particular session, e.g. session cookie or URL-encoding
• CPC Class Codes: H04L 69/14 Multichannel or multilink protocols

Abstract

A system and method for providing a middleware machine or similar platform. In accordance with an embodiment the system (referred to herein in some implementations as “Exalogic”) comprises a combination of high performance hardware, together with an application server or middleware environment, to provide a complete Java EE application server complex which includes a massively parallel in-memory grid, can be provisioned quickly, and can scale on demand. In accordance with an embodiment, the system can be deployed as a full, half, or quarter rack, or other configuration, that provides an application server grid, storage area network, and InfiniBand network, which support the execution of an application server, middleware or other functionality such as, for example, WebLogic Server, JRockit or Hotspot JVM, Oracle Linux or Solaris, and Oracle VM. Additional features of the system can include, e.g. Zero Buffer Copies, Scatter/Gather I/O, T3 Connections, and Lazy Deserialization.

Claims

1. A system for providing a middleware machine, comprising:

one or more high performance computing hardware systems, each including one or a plurality of processors, a high performance memory, and a networking component; and

a middleware environment operating thereon that includes one or a plurality of application server instances, and one or more Java virtual machines (JVMs), wherein each of said application server instances includes at least one muxer;

wherein when a request is received by a said application server instance that includes a plurality of layers to process the request

data associated with the request is stored in one or more byte arrays on a heap space of a said JVM, wherein each said layer applies one or more changes to the data via one of a plurality of byte buffers, wherein each said byte buffer is accessible to the JVM and the said application server instance and includes a pointer to the data,

a response is generated by the said application server using the data, and gathered from the one or more byte arrays using scatter/gather input/output (I/O), and

the response is received from a plurality of threads by a sender queue and transferred therefrom using a said muxer to a different said application server instance over a plurality of parallel channels associated with the said muxer.

2. The system of claim 1, wherein the system further comprises

a user space, which includes the one or more JVMs and the one or more application server instances;

wherein

the JVM pins the portion of the heap space where the data is stored.

3. The system of claim 1, wherein the one or more high performance computing hardware systems are in

a cluster that communicates over an InfiniBand network.

4. The system of claim 1, wherein the one or more high performance computing hardware systems are in

a cluster that communicates over an InfiniBand network;

and

wherein the plurality of parallel channels include one or more replication channels created from a template by copying attributes from the template and overwriting port information in the attributes.

5. The system of claim 1, wherein the one or a plurality of application server instances include

a primary application server that operates to receive a request associated with a session from a client, wherein the primary application server maintains session information associated with the session and responds to the client based on the session information;

and

a secondary application server, selected from the replication group of clustered servers, that operates to receive and maintain serialized session information from the primary application server, wherein the secondary application server operates to update the serialized session information based on one or more session updates received from the primary application server; and

wherein the secondary application server operates to generate deserialized session information based on the updated serialized session information and responds to the client based on the deserialized session information, only when the primary application server fails.

6. The system of claim 1, wherein the system is deployed as one of a full, half, and quarter rack configurations, that provides an application server grid, storage area network, and InfiniBand network.

7. The system of claim 6, wherein the application server grid includes WebLogic Server, JRockit or Hotspot JVM, Oracle Linux or Solaris, and Oracle VM.

8. The system of claim 7, wherein each of the full, half, and quarter rack configurations includes one or more compute nodes, InfiniBand switch gateway, and storage nodes or units that communicate with one another via an InfiniBand network.

9. A method of providing a middleware machine, comprising the steps comprising:

providing one or more high performance computing hardware systems, each including one or a plurality of processors, a high performance memory, and a networking component; and

providing thereon a middleware environment that includes one or a plurality of application server instances, and one or more Java virtual machines (JVMs), wherein each of said application server instances includes at least one muxer;

wherein when a request is received by a said application server instance that includes a plurality of layers to process the request

data associated with the request is stored in one or more byte arrays on a heap space of a said JVM, wherein each said layer applies one or more changes to the data via one of a plurality of byte buffers, wherein each said byte buffer is accessible to the JVM and the said application server instance and includes a pointer to the data,

a response is generated by the said application server using the data, and gathered from the one or more byte arrays using scatter/gather input/output (I/O), and

the response is received from a plurality of threads by a sender queue and transferred therefrom using a said muxer to a different said application server instance over a plurality of parallel channels associated with the said muxer.

10. The method of claim 9, wherein the method further comprises

providing a user space, which includes the one or more JVMs and the one or more application server instances;

wherein

the JVM pins the portion of the heap space where the data is stored.

11. The method of claim 9, wherein the one or more high performance computing hardware systems are in

a cluster that communicates over an InfiniBand network.

12. The method of claim 9, wherein the one or more high performance computing hardware systems are in

a cluster that communicates over an InfiniBand network;

and

wherein the plurality of parallel channels include one or more replication channels created from a template by copying attributes from the template and overwriting port information in the attributes.

13. The method of claim 9, wherein the one or a plurality of application server instances include

a primary application server that operates to receive a request associated with a session from a client, wherein the primary application server maintains session information associated with the session and responds to the client based on the session information;

and

a secondary application, selected from the replication group of clustered servers, that operates to receive and maintain serialized session information from the primary application server, wherein the secondary application server operates to update the serialized session information based on one or more session updates received from the primary application server; and

wherein the secondary application server operates to generate deserialized session information based on the updated serialized session information and responds to the client based on the deserialized session information, only when the primary application server fails.

14. The method of claim 9, wherein the system is deployed as one of a full, half, and quarter rack configurations, that provides an application server grid, storage area network, and InfiniBand network.

15. The method of claim 14, wherein the application server grid includes WebLogic Server, JRockit or Hotspot JVM, Oracle Linux or Solaris, and Oracle VM.

16. The method of claim 15, wherein each of the full, half, and quarter rack configurations includes one or more compute nodes, InfiniBand switch gateway, and storage nodes or units that communicate with one another via an InfiniBand network.

17. A non-transitory computer-readable storage medium including instructions stored thereon which, when executed by a computer, cause the computer to perform the steps comprising:

providing one or more high performance computing hardware systems, each including one or a plurality of processors, a high performance memory, and a networking component; and

providing thereon a middleware environment that includes one or a plurality of application server instances, and one or more Java virtual machines (JVMs), wherein each of said application server instances includes at least one muxer;

wherein when a request is received by a said application server instance that includes a plurality of layers to process the request

data associated with the request is stored in one or more byte arrays on a heap space of a said JVM, wherein each said layer applies one or more changes to the data via one of a plurality of byte buffers, wherein each said byte buffer is accessible to the JVM and the said application server instance and includes a pointer to the data,

a response is generated by the said application server using the data, and gathered from the one or more byte arrays using scatter/gather input/output (I/O), and

the response is received from a plurality of threads by a sender queue and transferred therefrom using a said muxer to a different said application server instance over a plurality of parallel channels associated with the said muxer.