diff options
author | Robert Haas <rhaas@postgresql.org> | 2024-04-19 15:50:02 -0400 |
---|---|---|
committer | Robert Haas <rhaas@postgresql.org> | 2024-04-19 15:50:02 -0400 |
commit | fa7036dd6644d13233b475874a94754a5903e35a (patch) | |
tree | 86cca01af92ff6fb8aeabe41bd5b885d520e3558 /src/backend/commands/dbcommands.c | |
parent | cd64dc42d1e1b03e57e6ba3d316e4f9dec52a78d (diff) | |
download | postgresql-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.
Diffstat (limited to 'src/backend/commands/dbcommands.c')
0 files changed, 0 insertions, 0 deletions