At 2014-09-25 22:41:18 +0200, wrote:
>  * Also recovery shouldn't be regarded successful if the reset fails -
>  * e.g. because of ENOSPC.


> * Doing this in a separate pass is advantageous for performance reasons
> * because it allows the kernel to perform all the flushes at once.


> Unless I miss something this isn't sufficient. We need to fsync the
> files in the data directory, not just the toplevel directory?

No, of course you're right. So a separate function that does the moral
equivalent of "find $PGDATA -exec fsync_fname …"?

Will resubmit with the additional comments.

-- Abhijit

Sent via pgsql-hackers mailing list (
To make changes to your subscription:

Reply via email to