FreeBSD: Remove BIO_ORDERED flag from BIO_FLUSH

ZFS always waits for the write completion before flushing the cache.
That is why it does not require explicit ordering fences around it,
which are pretty difficult to implement for NVMe, since one has no
internal concept of strict request ordering.

This was already removed from FreeBSD once, but got resurrected
by mistake during OpenZFS merge.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Signed-off-by: Alexander Motin <mav@FreeBSD.org>
Closes #11130
This commit is contained in:
Alexander Motin 2020-10-30 11:50:57 -04:00 committed by GitHub
parent f829227f49
commit e3a6ac8d06
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

View File

@ -1141,7 +1141,6 @@ sendreq:
break;
case ZIO_TYPE_IOCTL:
bp->bio_cmd = BIO_FLUSH;
bp->bio_flags |= BIO_ORDERED;
bp->bio_data = NULL;
bp->bio_offset = cp->provider->mediasize;
bp->bio_length = 0;