Scribd
Upload
221 views8 pages

Query Parallelism

There are two main forms of query parallelism: interquery parallelism which involves executing different queries or transactions in parallel to improve system throughput, and intraquery parallelism which involves parallelizing the execution of a single query to speed up long-running queries. Intraquery parallelism can be achieved through intraoperation parallelism by parallelizing individual operations like sorting, intraoperation parallelism by executing different operations simultaneously, and pipeline parallelism by processing the output of one operation as input to the next without waiting.

Uploaded by

brittain markale
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
221 views8 pages

Query Parallelism

There are two main forms of query parallelism: interquery parallelism which involves executing different queries or transactions in parallel to improve system throughput, and intraquery parallelism which involves parallelizing the execution of a single query to speed up long-running queries. Intraquery parallelism can be achieved through intraoperation parallelism by parallelizing individual operations like sorting, intraoperation parallelism by executing different operations simultaneously, and pipeline parallelism by processing the output of one operation as input to the next without waiting.

Uploaded by

brittain markale
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 8

Query Parallelism

• In parallel database system to improve the


performance of the system, parallelism is used.
• It is achieved through query parallelism
• The transaction throughput is increased
execution of one or more queries
Forms of Query Parallelism
Interquery Parallelism

• “Parallelism among queries’"


• Different queries or transactions
are executed in parallel with one
another
• Main aim: scaling up transaction
processing systems
Intraquery Parallelism
• “Parallelism within query’
• Execution of a single query’
in parallel on multiple processors
and disks
• Main aim: speeding up
long-running queries
Intraquery Parallelism

Execution of a single query can be parallelized in


two ways:
Intraoperation parallelism Interoperation parallelism
 
Each individual operation in a query is parallelized Different operations in expressions are executed in
parallel
 

Example: parallel sort, parallel search Example: Simultaneous sorting or searching query
 

A single operation sorting is parallelized The operations sorting and searching are parallelized
 
Intraoperation parallelism
• “Partitioned parallelism”
• Get all machines working to
compute a given operation
(scan, sort, join)
• Parallelism due to the
data being partitioned
• The degree of
parallelism
is increased based on
the large number of
records in a table
conti…
Within a same query or transaction, different
operations are concurrently executing
Pipeline Parallelism Independent Parallelism
 
Output record of one operation A are consumed by a Multiple operations in a query that do not depend on one
second operation B without completing the first operation another are executed in parallel
A e.g. indexed nested loop join.

Like an assembly line, multiple operations are executing  


   
 
Does not provide high degree of parallelism. It is useful
Only useful for small number of processors with a lower degree of parallelism
   
Pipelined + Independent Parallelism

Inter-operator parallelism. Each operator may run concurrently on a different site (exploits pipelining)

A natural join of 4 relations r1,r2,r3 and r4.


P1 = temp 1 = r1xr2; P2 = temp2 = temp1xr3; P3
=result/output = temp2xr4

You might also like