psql: Fix assertion failures with pipeline mode A correct cocktail of COPY FROM, SELECT and/or DML queries and \syncpipeline was able to break the logic in charge of discarding results of a pipeline, done in discardAbortedPipelineResults(). Such sequence make the backend generate a FATAL, due to a protocol synchronization loss.
This problem comes down to the fact that we did not consider the case of libpq returning a PGRES_FATAL_ERROR when discarding the results of an aborted pipeline. The discarding code is changed so as this result status is handled as a special case, with the caller of discardAbortedPipelineResults() being responsible for consuming the result. A couple of tests are added to cover the problems reported, bringing an interesting gain in coverage as there were no tests in the tree covering the case of protocol synchronization loss. Issue introduced by 41625ab8ea3d. Reported-by: Alexander Kozhemyakin <a.kozhemya...@postgrespro.ru> Author: Anthonin Bonnefoy <anthonin.bonne...@datadoghq.com> Co-authored-by: Michael Paquier <mich...@paquier.xyz> Discussion: https://postgr.es/m/ebf6ce77-b180-4d6b-8eab-71f641499...@postgrespro.ru Branch ------ master Details ------- https://git.postgresql.org/pg/commitdiff/3631612eae9c2def99151c4f36b1b3771f53cba7 Modified Files -------------- src/bin/psql/common.c | 17 +++++++++++++++++ src/bin/psql/t/001_basic.pl | 41 +++++++++++++++++++++++++++++++++++++++++ 2 files changed, 58 insertions(+)
