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.