Remove some obsolete smgrcloseall() calls.

Before the advent of PROCSIGNAL_BARRIER_SMGRRELEASE, we didn't have a
comprehensive way to deal with Windows file handles that get in the way
of unlinking directories.  We had smgrcloseall() calls in a few places
to try to mitigate.

It's still a good idea for bgwriter and checkpointer to do that once per
checkpoint so they don't accumulate unbounded SMgrRelation objects, but
there is no longer any reason to close them at other random places such
as the error path, and the explanation as given in the comments is now
obsolete.

Author: Thomas Munro
Reviewed-by: Heikki Linnakangas, Robert Haas
Discussion: https://www.postgresql.org/message-id/CA%2BhUKGJ8NTvqLHz6dqbQnt2c8XCki4r2QvXjBQcXpVwxTY_pvA@mail.gmail.com
This commit is contained in:
Heikki Linnakangas 2024-01-31 11:40:29 +02:00
parent 0fda392138
commit 6a8ffe812d
3 changed files with 0 additions and 21 deletions

View File

@ -197,13 +197,6 @@ BackgroundWriterMain(void)
*/
pg_usleep(1000000L);
/*
* Close all open files after any error. This is helpful on Windows,
* where holding deleted files open causes various strange errors.
* It's not clear we need it elsewhere, but shouldn't hurt.
*/
smgrcloseall();
/* Report wait end here, when there is no further possibility of wait */
pgstat_report_wait_end();
}

View File

@ -301,13 +301,6 @@ CheckpointerMain(void)
* fast as we can.
*/
pg_usleep(1000000L);
/*
* Close all open files after any error. This is helpful on Windows,
* where holding deleted files open causes various strange errors.
* It's not clear we need it elsewhere, but shouldn't hurt.
*/
smgrcloseall();
}
/* We can now handle ereport(ERROR) */

View File

@ -186,13 +186,6 @@ WalWriterMain(void)
* fast as we can.
*/
pg_usleep(1000000L);
/*
* Close all open files after any error. This is helpful on Windows,
* where holding deleted files open causes various strange errors.
* It's not clear we need it elsewhere, but shouldn't hurt.
*/
smgrcloseall();
}
/* We can now handle ereport(ERROR) */