Fix representation of SORT_TYPE_STILL_IN_PROGRESS.
authorTom Lane <tgl@sss.pgh.pa.us>
Tue, 7 Apr 2020 02:22:13 +0000 (22:22 -0400)
committerTom Lane <tgl@sss.pgh.pa.us>
Tue, 7 Apr 2020 02:22:13 +0000 (22:22 -0400)
commitc7654f6a37792ab9525ff98b710c23b27c7868a5
tree38b482ac8386739b6dd2893564d1ab9443036bf0
parent4c04be9b05ad2ec5acd27c3417bf075c13cab134
Fix representation of SORT_TYPE_STILL_IN_PROGRESS.

It turns out that the code did indeed rely on a zeroed
TuplesortInstrumentation.sortMethod field to indicate
"this worker never did anything", although it seems the
issue only comes up during certain race-condition-y cases.

Hence, rearrange the TuplesortMethod enum to restore
SORT_TYPE_STILL_IN_PROGRESS to having the value zero,
and add some comments reinforcing that that isn't optional.

Also future-proof a loop over the possible values of the enum.
sizeof(bits32) happened to be the correct limit value,
but only by purest coincidence.

Per buildfarm and local investigation.

Discussion: https://postgr.es/m/12222.1586223974@sss.pgh.pa.us
src/backend/commands/explain.c
src/include/utils/tuplesort.h