2019-03-29 21:15:42 +00:00
|
|
|
-- etldoc: layer_housenumber[shape=record fillcolor=lightpink, style="rounded,filled",
|
2016-12-04 01:52:52 +00:00
|
|
|
-- etldoc: label="layer_housenumber | <z14_> z14+" ] ;
|
2016-11-10 00:11:11 +00:00
|
|
|
|
2016-10-25 17:16:18 +00:00
|
|
|
CREATE OR REPLACE FUNCTION layer_housenumber(bbox geometry, zoom_level integer)
|
2020-06-08 16:19:55 +00:00
|
|
|
RETURNS TABLE
|
|
|
|
(
|
|
|
|
osm_id bigint,
|
|
|
|
geometry geometry,
|
|
|
|
housenumber text
|
|
|
|
)
|
|
|
|
AS
|
Parallel capability to layer functions (#728)
This PR allows queries to be parallelized on recent versions of Postgres. The `PARALLEL SAFE` modifier has been added to the layer functions and a PLPGSQL function to convert strings into number has been replaced.
`PARALLEL SAFE` is a modifier for `CREATE FUNCTION` available since Postgres 9.6, so this change does not break current OpenMapTiles supported database version. More details about this topic [here](https://www.postgresql.org/docs/current/parallel-safety.html) and at the reference documentation for [`CREATE FUNCTION`](https://www.postgresql.org/docs/current/sql-createfunction.html).
### Testing procedure
The procedure to test this was:
* Imported `spain.pbf` in a clean environment
* Dumped the OpenMapTiles database from the Postgres Docker image
* Created a clean Postgres 12 database using the default Docker image
* Installed `postgis` 3 from the default Debian package and `osml10n` 2.5.8 from the repository (`make`, etc.)
* Restored the dump
* Lowered the postgres planner parameters for triggering parallel plans:
```sql
set parallel_setup_cost = 5;
set parallel_tuple_cost = 0.005;
```
* Manually added the `PARALLEL SAFE` modifier to each function involved in layer queries (not on updates or inserting functions).
* For each layer, run a testing query to confirm parallel workers were created, something like this:
```sql
explain analyze
select * from layer_aerodrome_label(tilebbox(8,128,95),10,null)
union all
select * from layer_aerodrome_label(tilebbox(8,128,97),10,null);
```
* After all the layers were processed and confirmed to start parallel executions, a more complete example was run. This example just retrieves the geometries for all the layers from the same tile but without using any MVT related function.
<details><summary>Testing query</summary>
```sql
-- Using the function layer_landuse
explain analyze
select geometry from layer_water(tilebbox(14,8020,6178),14)
union all
select geometry from layer_waterway(tilebbox(14,8020,6178),14)
union all
select geometry from layer_landcover(tilebbox(14,8020,6178),14)
union all
select geometry from layer_landuse(tilebbox(14,8020,6178),14)
union all
select geometry from layer_mountain_peak(tilebbox(14,8020,6178),14)
union all
select geometry from layer_park(tilebbox(14,8020,6178),14)
union all
select geometry from layer_boundary(tilebbox(14,8020,6178),14)
union all
select geometry from layer_aeroway(tilebbox(14,8020,6178),14)
union all
select geometry from layer_transportation(tilebbox(14,8020,6178),14)
union all
select geometry from layer_building(tilebbox(14,8020,6178),14)
union all
select geometry from layer_water_name(tilebbox(14,8020,6178),14)
union all
select geometry from layer_transportation_name(tilebbox(14,8020,6178),14)
union all
select geometry from layer_place(tilebbox(14,8020,6178),14)
union all
select geometry from layer_housenumber(tilebbox(14,8020,6178),14)
union all
select geometry from layer_poi(tilebbox(14,8020,6178),14)
union all
select geometry from layer_aerodrome_label(tilebbox(14,8020,6178),14);
```
</details>
You can inspect the execution plan and results on [this page](https://explain.dalibo.com/plan/3z). Also [attaching](https://github.com/openmaptiles/openmaptiles/files/3951822/explain-tile-simple.tar.gz) the query and JSON output for future reference. The website gives a ton of details, but you may want to search for nodes mentioning `workers` or `parallel` like in this area referring to `osm_border` or `osm_aeroway_linestring` entities
![image](https://user-images.githubusercontent.com/188264/70647153-9cac9300-1c48-11ea-96ea-ac7a1e2f4a79.png)
### Next steps
Since the execution plan is not showing a parallel append at the top level, meaning it's not running each layer individually, I want to continue experimenting with parameters and queries to see if it's possible to even parallelize more the request.
I will post my finding here, even no change in the code should happen.
cc. @nyurik
Co-authored-by: Yuri Astrakhan <yuriastrakhan@gmail.com>
2020-02-01 00:36:02 +00:00
|
|
|
$$
|
2020-06-08 16:19:55 +00:00
|
|
|
SELECT
|
|
|
|
-- etldoc: osm_housenumber_point -> layer_housenumber:z14_
|
|
|
|
osm_id,
|
|
|
|
geometry,
|
2023-09-13 09:09:41 +00:00
|
|
|
display_housenumber(housenumber)
|
2023-01-17 08:34:27 +00:00
|
|
|
FROM (
|
|
|
|
SELECT
|
|
|
|
osm_id,
|
|
|
|
geometry,
|
|
|
|
housenumber,
|
|
|
|
row_number() OVER(PARTITION BY concat(street, block_number, housenumber) ORDER BY has_name ASC) as rn
|
|
|
|
FROM osm_housenumber_point
|
|
|
|
WHERE 1=1
|
|
|
|
AND zoom_level >= 14
|
|
|
|
AND geometry && bbox
|
|
|
|
) t
|
|
|
|
WHERE rn = 1;
|
|
|
|
|
2020-06-17 16:15:26 +00:00
|
|
|
$$ LANGUAGE SQL STABLE
|
|
|
|
-- STRICT
|
2020-06-08 16:19:55 +00:00
|
|
|
PARALLEL SAFE;
|