When the optimizer determines that parallel query is the fastest execution
strategy for a particular query, it will create a query plan which includes
- a Gather node. Here is a simple example:
+ a Gather or Gather Merge
+ node. Here is a simple example:
EXPLAIN SELECT * FROM pgbench_accounts WHERE filler LIKE '%x%';
- In all cases, the Gather node will have exactly one
+ In all cases, the Gather or
+ Gather Merge node will have exactly one
child plan, which is the portion of the plan that will be executed in
- parallel. If the Gather node is at the very top of the plan
- tree, then the entire query will execute in parallel. If it is somewhere
- else in the plan tree, then only the portion of the plan below it will run
- in parallel. In the example above, the query accesses only one table, so
- there is only one plan node other than the Gather node itself;
- since that plan node is a child of the Gather node, it will
- run in parallel.
+ parallel. If the Gather or Gather Merge node is
+ at the very top of the plan tree, then the entire query will execute in
+ parallel. If it is somewhere else in the plan tree, then only the portion
+ of the plan below it will run in parallel. In the example above, the
+ query accesses only one table, so there is only one plan node other than
+ the Gather node itself; since that plan node is a child of the
+ Gather node, it will run in parallel.
during query execution, the process which is implementing the user's
session will request a number of background
worker processes equal to the number
- of workers chosen by the planner. The total number of background
- workers that can exist at any one time is limited by both
+ of workers chosen by the planner. The number of background workers that
+ the planner will consider using is limited to at most
+ . The total number
+ of background workers that can exist at any one time is limited by both
and
- , so it is possible for a
+ . Therefore, it is possible for a
parallel query to run with fewer workers than planned, or even with
no workers at all. The optimal plan may depend on the number of workers
that are available, so this can result in poor query performance. If this
- occurrence is frequent, considering increasing
+ occurrence is frequent, consider increasing
max_worker_processes and max_parallel_workers
so that more workers can be run simultaneously or alternatively reducing
- <xref linkend="guc-max-parallel-workers-per-gather"> so that the planner
+ <varname>max_parallel_workers_per_gather> so that the planner
requests fewer workers.
Every background worker process which is successfully started for a given
- parallel query will execute the portion of the plan below
- the Gather node. The leader will also execute that portion
- of the plan, but it has an additional responsibility: it must also read
- all of the tuples generated by the workers. When the parallel portion of
- the plan generates only a small number of tuples, the leader will often
- behave very much like an additional worker, speeding up query execution.
- Conversely, when the parallel portion of the plan generates a large number
- of tuples, the leader may be almost entirely occupied with reading the
- tuples generated by the workers and performing any further processing
- steps which are required by plan nodes above the level of the
- Gather node. In such cases, the leader will do very
- little of the work of executing the parallel portion of the plan.
+ parallel query will execute the parallel portion of the plan. The leader
+ will also execute that portion of the plan, but it has an additional
+ responsibility: it must also read all of the tuples generated by the
+ workers. When the parallel portion of the plan generates only a small
+ number of tuples, the leader will often behave very much like an additional
+ worker, speeding up query execution. Conversely, when the parallel portion
+ of the plan generates a large number of tuples, the leader may be almost
+ entirely occupied with reading the tuples generated by the workers and
+ performing any further processing steps which are required by plan nodes
+ above the level of the Gather node or
+ Gather Merge node. In such cases, the leader will
+ do very little of the work of executing the parallel portion of the plan.
+
+ When the node at the top of the parallel portion of the plan is
+ Gather Merge rather than Gather, it indicates that
+ each process executing the parallel portion of the plan is producing
+ tuples in sorted order, and that the leader is performing an
+ order-preserving merge. In contrast, Gather reads tuples
+ from the workers in whatever order is convenient, destroying any sort
+ order that may have existed.
+
send such a message, this can only occur when using a client that
does not rely on libpq. If this is a frequent
occurrence, it may be a good idea to set
- in sessions
- where it is likely, so as to avoid generating query plans that may
- be suboptimal when run serially.
+ to zero in
+ sessions where it is likely, so as to avoid generating query plans
+ that may be suboptimal when run serially.
so that each process which executes the plan will generate only a
subset of the output rows in such a way that each required output row
is guaranteed to be generated by exactly one of the cooperating processes.
+ Generally, this means that the scan on the driving table of the query
+ must be a parallel-aware scan.
- Only the scan types listed above may be used for a scan on the driving
- table within a parallel plan. Other scan types, such as parallel scans of
- non-btree indexes, may be supported in the future.
+ Other scan types, such as scans of non-btree indexes, may support
+ parallel scans in the future.
the query performs an aggregation step, producing a partial result for
each group of which that process is aware. This is reflected in the plan
as a Partial Aggregate node. Second, the partial results are
- transferred to the leader via the Gather node. Finally, the
- leader re-aggregates the results across all workers in order to produce
- the final result. This is reflected in the plan as a
- Finalize Aggregate node.
+ transferred to the leader via Gather or Gather
+ Merge. Finally, the leader re-aggregates the results across all
+ workers in order to produce the final result. This is reflected in the
+ plan as a Finalize Aggregate node.
operation is one which cannot be performed in a parallel worker, but which
can be performed in the leader while parallel query is in use. Therefore,
parallel restricted operations can never occur below a Gather
- node, but can occur elsewhere in a plan which contains a
- Gather node. A parallel unsafe operation is one which cannot
+ or Gather Merge node, but can occur elsewhere in a plan which
+ contains such a node. A parallel unsafe operation is one which cannot
be performed while parallel query is in use, not even in the leader.
When a query contains anything which is parallel unsafe, parallel query
is completely disabled for that query.
- Access to an InitPlan or SubPlan.
+ Access to an InitPlan or correlated SubPlan.
parallel-restricted functions or aggregates involved in the query in
order to obtain a superior plan. So, for example, if a WHERE
clause applied to a particular table is parallel restricted, the query
- planner will not consider placing the scan of that table below a
- Gather node. In some cases, it would be
+ planner will not consider performing a scan of that table in the parallel
+ portion of a plan. In some cases, it would be
possible (and perhaps even efficient) to include the scan of that table in
the parallel portion of the query and defer the evaluation of the
WHERE clause so that it happens above the Gather
projects / postgresql.git / commitdiff