Clean up EXPLAIN's handling of per-worker details.

Previously, it was possible for EXPLAIN ANALYZE of a parallel query
to produce several different "Workers" fields for a single plan node,
because different portions of explain.c independently generated
per-worker data and wrapped that output in separate fields.  This
is pretty bogus, especially for the structured output formats: even
if it's not technically illegal, most programs would have a hard time
dealing with such data.

To improve matters, add infrastructure that allows redirecting
per-worker values into a side data structure, and then collect that
data into a single "Workers" field after we've finished running all
the relevant code for a given plan node.

There are a few visible side-effects:

* In text format, instead of something like

  Sort Method: external merge  Disk: 4920kB
  Worker 0:  Sort Method: external merge  Disk: 5880kB
  Worker 1:  Sort Method: external merge  Disk: 5920kB
  Buffers: shared hit=682 read=10188, temp read=1415 written=2101
  Worker 0:  actual time=130.058..130.324 rows=1324 loops=1
    Buffers: shared hit=337 read=3489, temp read=505 written=739
  Worker 1:  actual time=130.273..130.512 rows=1297 loops=1
    Buffers: shared hit=345 read=3507, temp read=505 written=744

you get

  Sort Method: external merge  Disk: 4920kB
  Buffers: shared hit=682 read=10188, temp read=1415 written=2101
  Worker 0:  actual time=130.058..130.324 rows=1324 loops=1
    Sort Method: external merge  Disk: 5880kB
    Buffers: shared hit=337 read=3489, temp read=505 written=739
  Worker 1:  actual time=130.273..130.512 rows=1297 loops=1
    Sort Method: external merge  Disk: 5920kB
    Buffers: shared hit=345 read=3507, temp read=505 written=744

* When JIT is enabled, any relevant per-worker JIT stats are attached
to the child node of the Gather or Gather Merge node, which is where
the other per-worker output has always been.  Previously, that info
was attached directly to a Gather node, or missed entirely for Gather
Merge.

* A query's summary JIT data no longer includes a bogus
"Worker Number: -1" field.

A notable code-level change is that indenting for lines of text-format
output should now be handled by calling "ExplainIndentText(es)",
instead of hard-wiring how much space to emit.  This seems a good deal
cleaner anyway.

This patch also adds a new "explain.sql" regression test script that's
dedicated to testing EXPLAIN.  There is more that can be done in that
line, certainly, but for now it just adds some coverage of the XML and
YAML output formats, which had been completely untested.

Although this is surely a bug fix, it's not clear that people would
be happy with rearranging EXPLAIN output in a minor release, so apply
to HEAD only.

Maciek Sakrejda and Tom Lane, based on an idea of Andres Freund's;
reviewed by Georgios Kokolatos

Discussion: https://postgr.es/m/CAOtHd0AvAA8CLB9Xz0wnxu1U=zJCKrr1r4QwwXi_kcQsHDVU=Q@mail.gmail.com

src/include/commands/explain.h

@@ -25,6 +25,15 @@ typedef enum ExplainFormat
 	EXPLAIN_FORMAT_YAML
 } ExplainFormat;
 
+typedef struct ExplainWorkersState
+{
+	int			num_workers;	/* # of worker processes the plan used */
+	bool	   *worker_inited;	/* per-worker state-initialized flags */
+	StringInfoData *worker_str; /* per-worker transient output buffers */
+	int		   *worker_state_save;	/* per-worker grouping state save areas */
+	StringInfo	prev_str;		/* saved output buffer while redirecting */
+} ExplainWorkersState;
+
 typedef struct ExplainState
 {
 	StringInfo	str;			/* output buffer */
@@ -47,6 +56,8 @@ typedef struct ExplainState
 	List	   *deparse_cxt;	/* context list for deparsing expressions */
 	Bitmapset  *printed_subplans;	/* ids of SubPlans we've printed */
 	bool		hide_workers;	/* set if we find an invisible Gather */
+	/* state related to the current plan node */
+	ExplainWorkersState *workers_state; /* needed if parallel plan */
 } ExplainState;
 
 /* Hook for plugins to get control in ExplainOneQuery() */
@@ -84,8 +95,6 @@ extern void ExplainPrintPlan(ExplainState *es, QueryDesc *queryDesc);
 extern void ExplainPrintTriggers(ExplainState *es, QueryDesc *queryDesc);
 
 extern void ExplainPrintJITSummary(ExplainState *es, QueryDesc *queryDesc);
-extern void ExplainPrintJIT(ExplainState *es, int jit_flags,
-							struct JitInstrumentation *jit_instr, int worker_num);
 
 extern void ExplainQueryText(ExplainState *es, QueryDesc *queryDesc);
 

src/test/regress/parallel_schedule

@@ -112,7 +112,7 @@ test: plancache limit plpgsql copy2 temp domain rangefuncs prepare conversion tr
 # ----------
 # Another group of parallel tests
 # ----------
-test: partition_join partition_prune reloptions hash_part indexing partition_aggregate partition_info tuplesort
+test: partition_join partition_prune reloptions hash_part indexing partition_aggregate partition_info tuplesort explain
 
 # event triggers cannot run concurrently with any test that runs DDL
 test: event_trigger

src/test/regress/serial_schedule

@@ -193,6 +193,7 @@ test: indexing
 test: partition_aggregate
 test: partition_info
 test: tuplesort
+test: explain
 test: event_trigger
 test: fast_default
 test: stats

src/test/regress/sql/explain.sql

+--
+-- EXPLAIN
+--
+-- There are many test cases elsewhere that use EXPLAIN as a vehicle for
+-- checking something else (usually planner behavior).  This file is
+-- concerned with testing EXPLAIN in its own right.
+--
+
+-- To produce stable regression test output, it's usually necessary to
+-- ignore details such as exact costs or row counts.  These filter
+-- functions replace changeable output details with fixed strings.
+
+create function explain_filter(text) returns setof text
+language plpgsql as
+$$
+declare
+    ln text;
+begin
+    for ln in execute $1
+    loop
+        -- Replace any numeric word with just 'N'
+        ln := regexp_replace(ln, '\m\d+\M', 'N', 'g');
+        -- In sort output, the above won't match units-suffixed numbers
+        ln := regexp_replace(ln, '\m\d+kB', 'NkB', 'g');
+        -- Text-mode buffers output varies depending on the system state
+        ln := regexp_replace(ln, '^( +Buffers: shared)( hit=N)?( read=N)?', '\1 [read]');
+        return next ln;
+    end loop;
+end;
+$$;
+
+-- To produce valid JSON output, replace numbers with "0" or "0.0" not "N"
+create function explain_filter_to_json(text) returns jsonb
+language plpgsql as
+$$
+declare
+    data text := '';
+    ln text;
+begin
+    for ln in execute $1
+    loop
+        -- Replace any numeric word with just '0'
+        ln := regexp_replace(ln, '\m\d+\M', '0', 'g');
+        data := data || ln;
+    end loop;
+    return data::jsonb;
+end;
+$$;
+
+-- Simple cases
+
+select explain_filter('explain select * from int8_tbl i8');
+select explain_filter('explain (analyze) select * from int8_tbl i8');
+select explain_filter('explain (analyze, verbose) select * from int8_tbl i8');
+select explain_filter('explain (analyze, buffers, format text) select * from int8_tbl i8');
+select explain_filter('explain (analyze, buffers, format json) select * from int8_tbl i8');
+select explain_filter('explain (analyze, buffers, format xml) select * from int8_tbl i8');
+select explain_filter('explain (analyze, buffers, format yaml) select * from int8_tbl i8');
+
+--
+-- Test production of per-worker data
+--
+-- Unfortunately, because we don't know how many worker processes we'll
+-- actually get (maybe none at all), we can't examine the "Workers" output
+-- in any detail.  We can check that it parses correctly as JSON, and then
+-- remove it from the displayed results.
+
+-- Serializable isolation would disable parallel query, so explicitly use an
+-- arbitrary other level.
+begin isolation level repeatable read;
+-- encourage use of parallel plans
+set parallel_setup_cost=0;
+set parallel_tuple_cost=0;
+set min_parallel_table_scan_size=0;
+set max_parallel_workers_per_gather=4;
+
+select jsonb_pretty(
+  explain_filter_to_json('explain (analyze, verbose, buffers, format json)
+                         select * from tenk1 order by tenthous')
+  -- remove "Workers" node of the Seq Scan plan node
+  #- '{0,Plan,Plans,0,Plans,0,Workers}'
+  -- remove "Workers" node of the Sort plan node
+  #- '{0,Plan,Plans,0,Workers}'
+  -- Also remove its sort-type fields, as those aren't 100% stable
+  #- '{0,Plan,Plans,0,Sort Method}'
+  #- '{0,Plan,Plans,0,Sort Space Type}'
+);
+
+rollback;