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.
Showing
Please register or sign in to comment