pgsql: Fix some libpq_pipeline test problems - Mailing list pgsql-committers

From Alvaro Herrera
Subject pgsql: Fix some libpq_pipeline test problems
Date
Msg-id E1lRfNx-0002vz-PX@gemulon.postgresql.org
Whole thread Raw
List pgsql-committers
Fix some libpq_pipeline test problems

Test pipeline_abort was not checking that it got the rows it expected in
one mode; make it do so.  This doesn't fix the actual problem (no idea
what that is, yet) but at least it should make it more obvious rather
than being visible only as a difference in the trace output.

While at it, fix other infelicities in the test:

* I reversed the order of result vs. expected in like().

* The output traces from -t are being put in the log dir, which means
the buildfarm script uselessly captures them.  Put them in a separate
dir tmp_check/traces instead, to avoid cluttering the buildfarm results.

* Test pipelined_insert was using too large a row count.  Reduce that a
tad and add a filler column to make each insert a little bulkier, while
still keeping enough that a buffer is filled and we have to switch mode.

Branch
------
master

Details
-------
https://git.postgresql.org/pg/commitdiff/db973ffb3ca43e65a0bf15175a35184a53bf977d

Modified Files
--------------
src/test/modules/libpq_pipeline/libpq_pipeline.c   | 33 +++++++++++++++-------
.../modules/libpq_pipeline/t/001_libpq_pipeline.pl |  8 ++++--
.../libpq_pipeline/traces/pipeline_abort.trace     |  8 +++---
3 files changed, 32 insertions(+), 17 deletions(-)


pgsql-committers by date:

Previous
From: Joe Conway
Date:
Subject: pgsql: Fix has_column_privilege function corner case
Next
From: Tom Lane
Date:
Subject: pgsql: Improve style of some replication-related error messages.