AUTOMATED CLIENT/SERVER OPERATION PARTITIONING

• US 20130138731A1
• Filed: 01/25/2013
• Published: 05/30/2013
• Est. Priority Date: 06/25/2008
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Meijer, Erik, Warren, Matthew J., Hejlsberg, Anders, Kulkami, Dinesh Chandrakant
• Granted Patent: US 9,712,646 B2
• Time in Patent Office: Days
• US Class Current: 709/203
• CPC Class Codes: G06F 16/2455 Query execution
• CPC Class Codes: G06F 16/252 between a Database Management System and a front-end application
• CPC Class Codes: H04L 67/01 Protocols
• CPC Class Codes: H04L 67/02 based on web technology, e.g. hypertext transfer protocol [HTTP]

Abstract

An operation (such as a relational query) may be processed on a processing engine (such as a relational database server) on behalf of a client. A conventional processing involves the delivery of the operation to the processing engine, which executes the entire operation to completion and returns a result data set. It may be more efficient to allocate part of the operation to be performed on the client, but a developer may be unable or unavailable to rewrite the operation in a distributed manner. Instead, the operation may be automatically partitioned into a pre-engine client portion, a processing engine portion, and a client portion, and the instructions of each portion may be automatically allocated respectively to the client, the server, and the client. The partitioning may be adjusted to conserve computing resources, such as bandwidth and storage, and the instructions may be reordered to improve the processing of the operation.

Claims

1. A computer-implemented method of evaluating an operation comprising instructions to be processed by a processing engine for a client, the method comprising:

partitioning the operation into a partitioned operation having three portions comprising;

a pre-engine portion executed by the client,

a processing engine portion executed by the processing engine, and

a post-engine portion executed by the client;

upon identifying a relocatable instruction that;

is initially provided in a first portion of the partitioned operation;

is more efficiently executed in a second portion that is different from the first portion;

with respect to an unrelocatable instruction within the first portion, is located on a first side of the relocatable instruction opposite the second portion; and

can be equivalently executed opposite the first side of the unrelocatable instruction,

moving the relocatable instruction from the first portion to the second portion;

executing the pre-engine portion at the client to produce a pre-engine partially executed operation;

sending the pre-engine partially executed operation to the processing engine;

receiving a processing engine partially executed operation from the processing engine after sending the pre-engine partially executed operation; and

executing the post-engine portion of the computing engine partially executed operation at the client to complete the operation execution.

2. The method of claim 1:

the first portion comprising the processing engine portion; and

the unrelocatable instruction comprising an instruction executable at the processing engine and not executable at the client.

3. The method of claim 2, the unrelocatable instruction comprising:

an instruction utilizing a resource accessible to the processing engine and not accessible to the client.

4. The method of claim 2:

the second portion selected from a client portion set comprising the pre-engine portion and the post-engine portion; and

the relocatable instruction more efficiently executed in the second portion comprising;

an instruction executed at the client faster than executed at the processing engine.

5. The method of claim 2:

the second portion comprising the pre-engine portion; and

the relocatable instruction more efficiently executed in the second portion comprising;

an instruction that, when executed at the client, compacts the pre-engine partially executed operation.

6. The method of claim 2, identifying the relocatable instruction comprising:

identifying an instruction equivalently executable by the client and the processing engine; and

detecting a higher processing load at the processing engine than at the client.

7. The method of claim 1:

the first portion selected from a client portion set comprising the pre-engine portion and the post-engine portion; and

the unrelocatable instruction comprising an instruction executable at the client and not executable at the processing engine.

8. The method of claim 7, the unrelocatable instruction comprising:

an instruction utilizing a resource accessible to the client and not accessible to the processing engine.

9. The method of claim 7:

the second portion comprising the processing engine portion; and

the relocatable instruction more efficiently executed in the second portion comprising;

an instruction executed at the processing engine faster than executed at the client.

10. The method of claim 7:

the second portion comprising the post-engine portion; and

the relocatable instruction more efficiently executed in the second portion comprising;

an instruction that, when executed at the processing engine, compacts the post-engine partially executed operation sent to the client.

11. The method of claim 7, identifying the relocatable instruction comprising:

identifying an instruction equivalently executable by the client and the processing engine; and

detecting a higher processing load at the client than at the processing engine.

12. The method of claim 1, the partitioning configured to reduce the size of at least one of the pre-engine partially executed operation and the processing engine partially executed operation.

13. The method of claim 1, comprising:

after the partitioning and before executing the pre-engine portion, further adjusting the partitioned operation according to at least one instruction adjusting rule.

14. The method of claim 13, the instruction adjusting rule comprising:

after partitioning the operation between a first instruction in one of a client portion and the processing engine portion and a last instruction in the other of the client portion and the processing engine portion, moving at least one instruction other than the first instruction and the last instruction from one of the client portion and the processing engine portion to the other of the processing engine portion and the client portion.

15. The method of claim 13, the instruction adjusting rule comprising:

upon identifying a compacting instruction that;

compacts a result of the operation,

follows a computationally intensive instruction involving the result, and

can be equivalently executed before the computationally intensive instruction,

moving the compacting instruction in the partitioned operation to precede the computationally intensive instruction.

16. A system for evaluating an operation comprising instructions to be processed by a processing engine for a client, the system comprising:

an operation partitioning component configured to;

partition the operation into a partitioned operation having three portions comprising;

a pre-engine portion executed by the client,

a processing engine portion executed by the processing engine, and

a post-engine portion executed by the client; and

upon identifying a relocatable instruction that;

is initially provided in a first portion of the partitioned operation;

is more efficiently executed in a second portion that is different from the first portion;

with respect to an unrelocatable instruction within the first portion, is located on a first side of the relocatable instruction opposite the second portion; and

can be equivalently executed opposite the first side of the unrelocatable instruction,

move the relocatable instruction from the first portion to the second portion;

a client portion execution component configured to;

execute the pre-engine portion at the client to produce a pre-engine partially executed operation, and

execute the post-engine portion of a processing engine partially executed operation at the client to complete the operation execution; and

a processing engine communications component configured to;

send the pre-engine partially executed operation produced by the client portion execution component to the processing engine, and

receive the processing engine partially executed operation from the processing engine after sending the pre-engine partially executed operation.

17. The system of claim 16:

the first portion comprising the processing engine portion; and

the unrelocatable instruction comprising an instruction executable at the processing engine and not executable at the client.

18. The system of claim 17, the unrelocatable instruction comprising:

an instruction utilizing a resource accessible to the processing engine and not accessible to the client.

19. The system of claim 16:

the first portion selected from a client portion set comprising the pre-engine portion and the post-engine portion; and

the unrelocatable instruction comprising an instruction executable at the client and not executable at the processing engine.

20. A computer-implemented method of evaluating an operation comprising a language-integrated query to be processed by a processing engine comprising a query processor for a client, the method comprising:

transforming the operation into an expression tree;

partitioning the operation into a partitioned operation having three portions comprising;

a pre-engine portion executed by the client,

a processing engine portion executed by the processing engine, and

a post-engine portion executed by the client;

expanding at least one portion of the partitioned query executed by one of the client and the processing engine, and equivalently compacting portions of the partitioned query executed by the other of the client and the processing engine, related to at least one of;

processing capacity of the processing engine,

processing capacity of the client,

computational load of the processing engine,

computational load of the client,

storage capacity of the processing engine,

storage capacity of the client, and

communications capacity between the processing engine and the client;

upon identifying a relocatable instruction that;

is initially provided in a first portion of the partitioned operation;

is more efficiently executed in a second portion that is different from the first portion;

with respect to an unrelocatable instruction within the first portion, is located on a first side of the relocatable instruction opposite the second portion; and

can be equivalently executed opposite the first side of the unrelocatable instruction,

moving the relocatable instruction from the first portion to the second portion;

executing the pre-engine portion at the client to produce a pre-engine partially executed operation;

sending the pre-engine partially executed operation to the processing engine;

receiving a processing engine partially executed operation from the processing engine after sending the pre-engine partially executed operation; and

executing the post-engine portion of the computing engine partially executed operation at the client to complete the operation execution.