aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorRobert Haas <rhaas@postgresql.org>2024-04-19 15:50:02 -0400
committerRobert Haas <rhaas@postgresql.org>2024-04-19 15:50:02 -0400
commitfa7036dd6644d13233b475874a94754a5903e35a (patch)
tree86cca01af92ff6fb8aeabe41bd5b885d520e3558
parentcd64dc42d1e1b03e57e6ba3d316e4f9dec52a78d (diff)
downloadpostgresql-fa7036dd6644d13233b475874a94754a5903e35a.tar.gz
postgresql-fa7036dd6644d13233b475874a94754a5903e35a.zip
Use tempdir_short instead of tempdir.
After cd64dc42d1e1b03e57e6ba3d316e4f9dec52a78d, a significant percentage of the buildfarm got unhappy, because pg_basebackup chokes if it tries to create a tarfile with symlink more than 99 characters in length. To try to fix that problem, use tempdir_short instead of tempdir, as we do in pg_verifybackup's 003_corruption.pl. There's a more complicated workaround for the same issue in pg_basebackup's 010_pg_basebackup.pl, but I'm not clear whether there's any reason to do it that way here. For now, let's try this, to at least get the buildfarm green again. A better long-term fix would be to figure out how to generate tar files containing long symlinks, but that will have to wait for another time.
-rw-r--r--src/bin/pg_combinebackup/t/002_compare_backups.pl2
1 files changed, 1 insertions, 1 deletions
diff --git a/src/bin/pg_combinebackup/t/002_compare_backups.pl b/src/bin/pg_combinebackup/t/002_compare_backups.pl
index 1d9764eeaca..7d582ead223 100644
--- a/src/bin/pg_combinebackup/t/002_compare_backups.pl
+++ b/src/bin/pg_combinebackup/t/002_compare_backups.pl
@@ -7,7 +7,7 @@ use PostgreSQL::Test::Cluster;
use PostgreSQL::Test::Utils;
use Test::More;
-my $tempdir = PostgreSQL::Test::Utils::tempdir;
+my $tempdir = PostgreSQL::Test::Utils::tempdir_short();
# Set up a new database instance.
my $primary = PostgreSQL::Test::Cluster->new('primary');