From: | Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us> |
---|---|
To: | pgsql-committers(at)postgresql(dot)org |
Subject: | pgsql: Fix regression test parallel-make hazard. |
Date: | 2016-08-13 00:52:27 |
Message-ID: | E1bYNBb-0001op-CS@gemulon.postgresql.org |
Views: | Raw Message | Whole Thread | Download mbox | Resend email |
Thread: | |
Lists: | pgsql-committers |
Fix regression test parallel-make hazard.
Back-patch 9.4-era commit 384f933046dc9e9a2b416f5f7b3be30b93587c63 into
the previous branches. Although that was only advertised as repairing a
problem with missed header-file dependencies, it turns out to also be
important for parallel make safety. The previous coding allowed two
independent make jobs to get launched concurrently in contrib/spi.
Normally this would be OK, because they are building independent targets;
but if --enable-depend is in use, it's unsafe, because one make run might
try to read a .deps file that the other one is in process of rewriting.
This is evidently the cause of buildfarm member francolin's recent failure
in the 9.2 branch. I believe this patch will result in only one subsidiary
make run, making it safe(r).
Report: http://buildfarm.postgresql.org/cgi-bin/show_log.pl?nm=francolin&dt=2016-08-12%2017%3A12%3A52
Branch
------
REL9_1_STABLE
Details
-------
http://git.postgresql.org/pg/commitdiff/99396e63f2bbb265dc68bd541157a62251ffa8a3
Modified Files
--------------
src/test/regress/GNUmakefile | 17 +++++++++++------
1 file changed, 11 insertions(+), 6 deletions(-)
From | Date | Subject | |
---|---|---|---|
Next Message | Tom Lane | 2016-08-13 22:31:30 | pgsql: Add SQL-accessible functions for inspecting index AM properties. |
Previous Message | Tom Lane | 2016-08-12 22:45:32 | pgsql: Doc: clarify that DROP ... CASCADE is recursive. |