|
Server : Apache/2.2.2 (Fedora) System : Linux App1.pathumtani.go.th 2.6.20-1.2320.fc5smp #1 SMP Tue Jun 12 19:40:16 EDT 2007 i686 User : apache ( 48) PHP Version : 5.2.9 Disable Function : NONE Directory : /proc/self/root/usr/share/doc/postgresql-8.1.9/html/ |
Upload File : |
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
<HTML
><HEAD
><TITLE
>Partitioning</TITLE
><META
NAME="GENERATOR"
CONTENT="Modular DocBook HTML Stylesheet Version 1.79"><LINK
REV="MADE"
HREF="mailto:pgsql-docs@postgresql.org"><LINK
REL="HOME"
TITLE="PostgreSQL 8.1.9 Documentation"
HREF="index.html"><LINK
REL="UP"
TITLE="Data Definition"
HREF="ddl.html"><LINK
REL="PREVIOUS"
TITLE="Inheritance"
HREF="ddl-inherit.html"><LINK
REL="NEXT"
TITLE="Other Database Objects"
HREF="ddl-others.html"><LINK
REL="STYLESHEET"
TYPE="text/css"
HREF="stylesheet.css"><META
HTTP-EQUIV="Content-Type"
CONTENT="text/html; charset=ISO-8859-1"><META
NAME="creation"
CONTENT="2007-04-20T04:40:08"></HEAD
><BODY
CLASS="SECT1"
><DIV
CLASS="NAVHEADER"
><TABLE
SUMMARY="Header navigation table"
WIDTH="100%"
BORDER="0"
CELLPADDING="0"
CELLSPACING="0"
><TR
><TH
COLSPAN="5"
ALIGN="center"
VALIGN="bottom"
>PostgreSQL 8.1.9 Documentation</TH
></TR
><TR
><TD
WIDTH="10%"
ALIGN="left"
VALIGN="top"
><A
HREF="ddl-inherit.html"
ACCESSKEY="P"
>Prev</A
></TD
><TD
WIDTH="10%"
ALIGN="left"
VALIGN="top"
><A
HREF="ddl.html"
>Fast Backward</A
></TD
><TD
WIDTH="60%"
ALIGN="center"
VALIGN="bottom"
>Chapter 5. Data Definition</TD
><TD
WIDTH="10%"
ALIGN="right"
VALIGN="top"
><A
HREF="ddl.html"
>Fast Forward</A
></TD
><TD
WIDTH="10%"
ALIGN="right"
VALIGN="top"
><A
HREF="ddl-others.html"
ACCESSKEY="N"
>Next</A
></TD
></TR
></TABLE
><HR
ALIGN="LEFT"
WIDTH="100%"></DIV
><DIV
CLASS="SECT1"
><H1
CLASS="SECT1"
><A
NAME="DDL-PARTITIONING"
>5.9. Partitioning</A
></H1
><A
NAME="AEN2635"
></A
><A
NAME="AEN2637"
></A
><P
> <SPAN
CLASS="PRODUCTNAME"
>PostgreSQL</SPAN
> supports basic table
partitioning. This section describes why and how you can implement
partitioning as part of your database design.
</P
><DIV
CLASS="SECT2"
><H2
CLASS="SECT2"
><A
NAME="DDL-PARTITIONING-OVERVIEW"
>5.9.1. Overview</A
></H2
><P
> Partitioning refers to splitting what is logically one large table
into smaller physical pieces.
Partitioning can provide several benefits:
<P
></P
></P><UL
><LI
><P
> Query performance can be improved dramatically for certain kinds
of queries.
</P
></LI
><LI
><P
> Update performance can be improved too, since each piece of the table
has indexes smaller than an index on the entire data set would be.
When an index no longer fits easily
in memory, both read and write operations on the index take
progressively more disk accesses.
</P
></LI
><LI
><P
> Bulk deletes may be accomplished by simply removing one of the
partitions, if that requirement is planned into the partitioning design.
<TT
CLASS="COMMAND"
>DROP TABLE</TT
> is far faster than a bulk <TT
CLASS="COMMAND"
>DELETE</TT
>,
to say nothing of the ensuing <TT
CLASS="COMMAND"
>VACUUM</TT
> overhead.
</P
></LI
><LI
><P
> Seldom-used data can be migrated to cheaper and slower storage media.
</P
></LI
></UL
><P>
The benefits will normally be worthwhile only when a table would
otherwise be very large. The exact point at which a table will
benefit from partitioning depends on the application, although a
rule of thumb is that the size of the table should exceed the physical
memory of the database server.
</P
><P
> Currently, <SPAN
CLASS="PRODUCTNAME"
>PostgreSQL</SPAN
> supports partitioning
via table inheritance. Each partition must be created as a child
table of a single parent table. The parent table itself is normally
empty; it exists just to represent the entire data set. You should be
familiar with inheritance (see <A
HREF="ddl-inherit.html"
>Section 5.8</A
>) before
attempting to implement partitioning.
</P
><P
> The following forms of partitioning can be implemented in
<SPAN
CLASS="PRODUCTNAME"
>PostgreSQL</SPAN
>:
<P
></P
></P><DIV
CLASS="VARIABLELIST"
><DL
><DT
>Range Partitioning</DT
><DD
><P
> The table is partitioned into <SPAN
CLASS="QUOTE"
>"ranges"</SPAN
> defined
by a key column or set of columns, with no overlap between
the ranges of values assigned to different partitions. For
example one might partition by date ranges, or by ranges of
identifiers for particular business objects.
</P
></DD
><DT
>List Partitioning</DT
><DD
><P
> The table is partitioned by explicitly listing which key values
appear in each partition.
</P
></DD
></DL
></DIV
><P>
Hash partitioning is not currently supported.
</P
></DIV
><DIV
CLASS="SECT2"
><H2
CLASS="SECT2"
><A
NAME="DDL-PARTITIONING-IMPLEMENTATION"
>5.9.2. Implementing Partitioning</A
></H2
><P
> To set up a partitioned table, do the following:
<P
></P
></P><OL
COMPACT="COMPACT"
TYPE="1"
><LI
><P
> Create the <SPAN
CLASS="QUOTE"
>"master"</SPAN
> table, from which all of the
partitions will inherit.
</P
><P
> This table will contain no data. Do not define any check
constraints on this table, unless you intend them to
be applied equally to all partitions. There is no point
in defining any indexes or unique constraints on it, either.
</P
></LI
><LI
><P
> Create several <SPAN
CLASS="QUOTE"
>"child"</SPAN
> tables that each inherit from
the master table. Normally, these tables will not add any columns
to the set inherited from the master.
</P
><P
> We will refer to the child tables as partitions, though they
are in every way normal <SPAN
CLASS="PRODUCTNAME"
>PostgreSQL</SPAN
> tables.
</P
></LI
><LI
><P
> Add table constraints to the partition tables to define the
allowed key values in each partition.
</P
><P
> Typical examples would be:
</P><PRE
CLASS="PROGRAMLISTING"
>CHECK ( x = 1 )
CHECK ( county IN ( 'Oxfordshire', 'Buckinghamshire', 'Warwickshire' ))
CHECK ( outletID >= 100 AND outletID < 200 )</PRE
><P>
Ensure that the constraints guarantee that there is no overlap
between the key values permitted in different partitions. A common
mistake is to set up range constraints like this:
</P><PRE
CLASS="PROGRAMLISTING"
>CHECK ( outletID BETWEEN 100 AND 200 )
CHECK ( outletID BETWEEN 200 AND 300 )</PRE
><P>
This is wrong since it is not clear which partition the key value
200 belongs in.
</P
><P
> Note that there is no difference in
syntax between range and list partitioning; those terms are
descriptive only.
</P
></LI
><LI
><P
> For each partition, create an index on the key column(s),
as well as any other indexes you might want. (The key index is
not strictly necessary, but in most scenarios it is helpful.
If you intend the key values to be unique then you should
always create a unique or primary-key constraint for each
partition.)
</P
></LI
><LI
><P
> Optionally, define a rule or trigger to redirect modifications
of the master table to the appropriate partition.
</P
></LI
><LI
><P
> Ensure that the <A
HREF="runtime-config-query.html#GUC-CONSTRAINT-EXCLUSION"
>constraint_exclusion</A
>
configuration
parameter is enabled in <TT
CLASS="FILENAME"
>postgresql.conf</TT
>. Without
this, queries will not be optimized as desired.
</P
></LI
></OL
><P>
</P
><P
> For example, suppose we are constructing a database for a large
ice cream company. The company measures peak temperatures every
day as well as ice cream sales in each region. Conceptually,
we want a table like this:
</P><PRE
CLASS="PROGRAMLISTING"
>CREATE TABLE measurement (
city_id int not null,
logdate date not null,
peaktemp int,
unitsales int
);</PRE
><P>
We know that most queries will access just the last week's, month's or
quarter's data, since the main use of this table will be to prepare
online reports for management.
To reduce the amount of old data that needs to be stored, we
decide to only keep the most recent 3 years worth of data. At the
beginning of each month we will remove the oldest month's data.
</P
><P
> In this situation we can use partitioning to help us meet all of our
different requirements for the measurements table. Following the
steps outlined above, partitioning can be set up as follows:
</P
><P
> <P
></P
></P><OL
COMPACT="COMPACT"
TYPE="1"
><LI
><P
> The master table is the <TT
CLASS="STRUCTNAME"
>measurement</TT
> table, declared
exactly as above.
</P
></LI
><LI
><P
> Next we create one partition for each active month:
</P><PRE
CLASS="PROGRAMLISTING"
>CREATE TABLE measurement_yy04mm02 ( ) INHERITS (measurement);
CREATE TABLE measurement_yy04mm03 ( ) INHERITS (measurement);
...
CREATE TABLE measurement_yy05mm11 ( ) INHERITS (measurement);
CREATE TABLE measurement_yy05mm12 ( ) INHERITS (measurement);
CREATE TABLE measurement_yy06mm01 ( ) INHERITS (measurement);</PRE
><P>
Each of the partitions are complete tables in their own right,
but they inherit their definition from the
<TT
CLASS="STRUCTNAME"
>measurement</TT
> table.
</P
><P
> This solves one of our problems: deleting old data. Each
month, all we will need to do is perform a <TT
CLASS="COMMAND"
>DROP
TABLE</TT
> on the oldest child table and create a new
child table for the new month's data.
</P
></LI
><LI
><P
> We must add non-overlapping table constraints, so that our
table creation script becomes:
</P><PRE
CLASS="PROGRAMLISTING"
>CREATE TABLE measurement_yy04mm02 (
CHECK ( logdate >= DATE '2004-02-01' AND logdate < DATE '2004-03-01' )
) INHERITS (measurement);
CREATE TABLE measurement_yy04mm03 (
CHECK ( logdate >= DATE '2004-03-01' AND logdate < DATE '2004-04-01' )
) INHERITS (measurement);
...
CREATE TABLE measurement_yy05mm11 (
CHECK ( logdate >= DATE '2005-11-01' AND logdate < DATE '2005-12-01' )
) INHERITS (measurement);
CREATE TABLE measurement_yy05mm12 (
CHECK ( logdate >= DATE '2005-12-01' AND logdate < DATE '2006-01-01' )
) INHERITS (measurement);
CREATE TABLE measurement_yy06mm01 (
CHECK ( logdate >= DATE '2006-01-01' AND logdate < DATE '2006-02-01' )
) INHERITS (measurement);</PRE
><P>
</P
></LI
><LI
><P
> We probably need indexes on the key columns too:
</P><PRE
CLASS="PROGRAMLISTING"
>CREATE INDEX measurement_yy04mm02_logdate ON measurement_yy04mm02 (logdate);
CREATE INDEX measurement_yy04mm03_logdate ON measurement_yy04mm03 (logdate);
...
CREATE INDEX measurement_yy05mm11_logdate ON measurement_yy05mm11 (logdate);
CREATE INDEX measurement_yy05mm12_logdate ON measurement_yy05mm12 (logdate);
CREATE INDEX measurement_yy06mm01_logdate ON measurement_yy06mm01 (logdate);</PRE
><P>
We choose not to add further indexes at this time.
</P
></LI
><LI
><P
> If data will be added only to the latest partition, we can
set up a very simple rule to insert data. We must
redefine this each month so that it always points to the
current partition.
</P><PRE
CLASS="PROGRAMLISTING"
>CREATE OR REPLACE RULE measurement_current_partition AS
ON INSERT TO measurement
DO INSTEAD
INSERT INTO measurement_yy06mm01 VALUES ( NEW.city_id,
NEW.logdate,
NEW.peaktemp,
NEW.unitsales );</PRE
><P>
We might want to insert data and have the server automatically
locate the partition into which the row should be added. We
could do this with a more complex set of rules as shown below.
</P><PRE
CLASS="PROGRAMLISTING"
>CREATE RULE measurement_insert_yy04mm02 AS
ON INSERT TO measurement WHERE
( logdate >= DATE '2004-02-01' AND logdate < DATE '2004-03-01' )
DO INSTEAD
INSERT INTO measurement_yy04mm02 VALUES ( NEW.city_id,
NEW.logdate,
NEW.peaktemp,
NEW.unitsales );
...
CREATE RULE measurement_insert_yy05mm12 AS
ON INSERT TO measurement WHERE
( logdate >= DATE '2005-12-01' AND logdate < DATE '2006-01-01' )
DO INSTEAD
INSERT INTO measurement_yy05mm12 VALUES ( NEW.city_id,
NEW.logdate,
NEW.peaktemp,
NEW.unitsales );
CREATE RULE measurement_insert_yy06mm01 AS
ON INSERT TO measurement WHERE
( logdate >= DATE '2006-01-01' AND logdate < DATE '2006-02-01' )
DO INSTEAD
INSERT INTO measurement_yy06mm01 VALUES ( NEW.city_id,
NEW.logdate,
NEW.peaktemp,
NEW.unitsales );</PRE
><P>
Note that the <TT
CLASS="LITERAL"
>WHERE</TT
> clause in each rule
exactly matches the the <TT
CLASS="LITERAL"
>CHECK</TT
>
constraint for its partition.
</P
></LI
></OL
><P>
</P
><P
> As we can see, a complex partitioning scheme could require a
substantial amount of DDL. In the above example we would be
creating a new partition each month, so it may be wise to write a
script that generates the required DDL automatically.
</P
><P
> The following caveats apply:
<P
></P
></P><UL
><LI
><P
> There is currently no way to verify that all of the
<TT
CLASS="LITERAL"
>CHECK</TT
> constraints are mutually
exclusive. Care is required by the database designer.
</P
></LI
><LI
><P
> There is currently no simple way to specify that rows must not be
inserted into the master table. A <TT
CLASS="LITERAL"
>CHECK (false)</TT
>
constraint on the master table would be inherited by all child
tables, so that cannot be used for this purpose. One possibility is
to set up an <TT
CLASS="LITERAL"
>ON INSERT</TT
> trigger on the master table that
always raises an error. (Alternatively, such a trigger could be
used to redirect the data into the proper child table, instead of
using a set of rules as suggested above.)
</P
></LI
></UL
><P>
</P
><P
> Partitioning can also be arranged using a <TT
CLASS="LITERAL"
>UNION ALL</TT
>
view:
</P><PRE
CLASS="PROGRAMLISTING"
>CREATE VIEW measurement AS
SELECT * FROM measurement_yy04mm02
UNION ALL SELECT * FROM measurement_yy04mm03
...
UNION ALL SELECT * FROM measurement_yy05mm11
UNION ALL SELECT * FROM measurement_yy05mm12
UNION ALL SELECT * FROM measurement_yy06mm01;</PRE
><P>
However, constraint exclusion is currently not supported for
partitioned tables defined in this manner. Also, the need to
recreate the view adds an extra step to adding and dropping
individual partitions of the dataset.
</P
></DIV
><DIV
CLASS="SECT2"
><H2
CLASS="SECT2"
><A
NAME="DDL-PARTITIONING-CONSTRAINT-EXCLUSION"
>5.9.3. Partitioning and Constraint Exclusion</A
></H2
><A
NAME="AEN2740"
></A
><P
> <I
CLASS="FIRSTTERM"
>Constraint exclusion</I
> is a query optimization technique
that improves performance for partitioned tables defined in the
fashion described above. As an example:
</P><PRE
CLASS="PROGRAMLISTING"
>SET constraint_exclusion = on;
SELECT count(*) FROM measurement WHERE logdate >= DATE '2006-01-01';</PRE
><P>
Without constraint exclusion, the above query would scan each of
the partitions of the <TT
CLASS="STRUCTNAME"
>measurement</TT
> table. With constraint
exclusion enabled, the planner will examine the constraints of each
partition and try to prove that the partition need not
be scanned because it could not contain any rows meeting the query's
<TT
CLASS="LITERAL"
>WHERE</TT
> clause. When the planner can prove this, it
excludes the partition from the query plan.
</P
><P
> You can use the <TT
CLASS="COMMAND"
>EXPLAIN</TT
> command to show the difference
between a plan with <TT
CLASS="VARNAME"
>constraint_exclusion</TT
> on and a plan
with it off. A typical default plan for this type of table setup is:
</P><PRE
CLASS="PROGRAMLISTING"
>SET constraint_exclusion = off;
EXPLAIN SELECT count(*) FROM measurement WHERE logdate >= DATE '2006-01-01';
QUERY PLAN
-----------------------------------------------------------------------------------------------
Aggregate (cost=158.66..158.68 rows=1 width=0)
-> Append (cost=0.00..151.88 rows=2715 width=0)
-> Seq Scan on measurement (cost=0.00..30.38 rows=543 width=0)
Filter: (logdate >= '2006-01-01'::date)
-> Seq Scan on measurement_yy04mm02 measurement (cost=0.00..30.38 rows=543 width=0)
Filter: (logdate >= '2006-01-01'::date)
-> Seq Scan on measurement_yy04mm03 measurement (cost=0.00..30.38 rows=543 width=0)
Filter: (logdate >= '2006-01-01'::date)
...
-> Seq Scan on measurement_yy05mm12 measurement (cost=0.00..30.38 rows=543 width=0)
Filter: (logdate >= '2006-01-01'::date)
-> Seq Scan on measurement_yy06mm01 measurement (cost=0.00..30.38 rows=543 width=0)
Filter: (logdate >= '2006-01-01'::date)</PRE
><P>
Some or all of the partitions might use index scans instead of
full-table sequential scans, but the point here is that there
is no need to scan the older partitions at all to answer this query.
When we enable constraint exclusion, we get a significantly
reduced plan that will deliver the same answer:
</P><PRE
CLASS="PROGRAMLISTING"
>SET constraint_exclusion = on;
EXPLAIN SELECT count(*) FROM measurement WHERE logdate >= DATE '2006-01-01';
QUERY PLAN
-----------------------------------------------------------------------------------------------
Aggregate (cost=63.47..63.48 rows=1 width=0)
-> Append (cost=0.00..60.75 rows=1086 width=0)
-> Seq Scan on measurement (cost=0.00..30.38 rows=543 width=0)
Filter: (logdate >= '2006-01-01'::date)
-> Seq Scan on measurement_yy06mm01 measurement (cost=0.00..30.38 rows=543 width=0)
Filter: (logdate >= '2006-01-01'::date)</PRE
><P>
</P
><P
> Note that constraint exclusion is driven only by <TT
CLASS="LITERAL"
>CHECK</TT
>
constraints, not by the presence of indexes. Therefore it isn't
necessary to define indexes on the key columns. Whether an index
needs to be created for a given partition depends on whether you
expect that queries that scan the partition will generally scan
a large part of the partition or just a small part. An index will
be helpful in the latter case but not the former.
</P
><P
> The following caveats apply:
<P
></P
></P><UL
><LI
><P
> Constraint exclusion only works when the query's <TT
CLASS="LITERAL"
>WHERE</TT
>
clause contains constants. A parameterized query will not be
optimized, since the planner cannot know what partitions the
parameter value might select at runtime. For the same reason,
<SPAN
CLASS="QUOTE"
>"stable"</SPAN
> functions such as <CODE
CLASS="FUNCTION"
>CURRENT_DATE</CODE
>
must be avoided. Joining the partition key to a column of another
table will not be optimized, either.
</P
></LI
><LI
><P
> Avoid cross-datatype comparisons in the <TT
CLASS="LITERAL"
>CHECK</TT
>
constraints, as the planner will currently fail to prove such
conditions false. For example, the following constraint
will work if <TT
CLASS="VARNAME"
>x</TT
> is an <TT
CLASS="TYPE"
>integer</TT
>
column, but not if <TT
CLASS="VARNAME"
>x</TT
> is a
<TT
CLASS="TYPE"
>bigint</TT
>:
</P><PRE
CLASS="PROGRAMLISTING"
>CHECK ( x = 1 )</PRE
><P>
For a <TT
CLASS="TYPE"
>bigint</TT
> column we must use a constraint like:
</P><PRE
CLASS="PROGRAMLISTING"
>CHECK ( x = 1::bigint )</PRE
><P>
The problem is not limited to the <TT
CLASS="TYPE"
>bigint</TT
> data type
— it can occur whenever the default data type of the
constant does not match the data type of the column to which it
is being compared. Cross-datatype comparisons in the supplied
queries are usually OK, just not in the <TT
CLASS="LITERAL"
>CHECK</TT
> conditions.
</P
></LI
><LI
><P
> <TT
CLASS="COMMAND"
>UPDATE</TT
> and <TT
CLASS="COMMAND"
>DELETE</TT
> commands
against the master table do not currently perform constraint exclusion.
</P
></LI
><LI
><P
> All constraints on all partitions of the master table are considered for
constraint exclusion, so large numbers of partitions are likely to
increase query planning time considerably.
</P
></LI
><LI
><P
> Don't forget that you still need to run <TT
CLASS="COMMAND"
>ANALYZE</TT
>
on each partition individually. A command like
</P><PRE
CLASS="PROGRAMLISTING"
>ANALYZE measurement;</PRE
><P>
will only process the master table.
</P
></LI
></UL
><P>
</P
></DIV
></DIV
><DIV
CLASS="NAVFOOTER"
><HR
ALIGN="LEFT"
WIDTH="100%"><TABLE
SUMMARY="Footer navigation table"
WIDTH="100%"
BORDER="0"
CELLPADDING="0"
CELLSPACING="0"
><TR
><TD
WIDTH="33%"
ALIGN="left"
VALIGN="top"
><A
HREF="ddl-inherit.html"
ACCESSKEY="P"
>Prev</A
></TD
><TD
WIDTH="34%"
ALIGN="center"
VALIGN="top"
><A
HREF="index.html"
ACCESSKEY="H"
>Home</A
></TD
><TD
WIDTH="33%"
ALIGN="right"
VALIGN="top"
><A
HREF="ddl-others.html"
ACCESSKEY="N"
>Next</A
></TD
></TR
><TR
><TD
WIDTH="33%"
ALIGN="left"
VALIGN="top"
>Inheritance</TD
><TD
WIDTH="34%"
ALIGN="center"
VALIGN="top"
><A
HREF="ddl.html"
ACCESSKEY="U"
>Up</A
></TD
><TD
WIDTH="33%"
ALIGN="right"
VALIGN="top"
>Other Database Objects</TD
></TR
></TABLE
></DIV
></BODY
></HTML
>