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 Brian Behlendorf
parent 8a1b26eb54
commit 2dd2e49cc7

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;