Avoid depending on post-UPDATE row order in float4/float8 tests. While heapam reproduces the insertion order of rows well, updates can move rows to varying places depending on autovacuum activity. In most regression tests we've guarded against getting variable results due to that, but float4.sql and float8.sql had escaped notice so far because they update tables that are too small for autovacuum to pay attention to.
With increasing interest in non-heap table AMs, it seems worth allowing for update behaviors that are not like heapam's. Hence, add ORDER BY to stabilize the results in case the updates put the rows in a different order. (We'll continue to assume that a seqscan will reproduce original insertion order, though. Removing that assumption would require vastly-more-invasive test changes.) Author: Pavel Borisov <pashkin.e...@gmail.com> Reviewed-by: Tom Lane <t...@sss.pgh.pa.us> Discussion: https://postgr.es/m/calt9zeexhanbobvqzquwpmkubapf5-fbo3fdeyg3s2tuwqz...@mail.gmail.com Branch ------ master Details ------- https://git.postgresql.org/pg/commitdiff/da83b1ea10c2b7937d4c9e922465321749c6785b Modified Files -------------- src/test/regress/expected/float4-misrounded-input.out | 8 ++++---- src/test/regress/expected/float4.out | 8 ++++---- src/test/regress/expected/float8.out | 8 ++++---- src/test/regress/sql/float4.sql | 2 +- src/test/regress/sql/float8.sql | 2 +- 5 files changed, 14 insertions(+), 14 deletions(-)
