Does ZFS or UFS classify FS Metatada I/O requests with specific BIO_META like flag?

[Bob Friesenhahn]

On Wed, 6 Apr 2016, Leo Prasath Arulraj wrote:
>
> I want to know if the FreeBSD filesystem UFS and ZFS set any such flag.
> From a skim through the source code, it does not seem so because the bio
> structure itself does not have any such flag in the first place :
> http://fxr.watson.org/fxr/source/sys/bio.h?v=FREEBSD10#L143,144
>
> I approciate any help regarding this.

Zfs would have no use for any such thing since it does everything in 
terms of transaction groups (delimited by a disk cache sync of data 
for involved disks, followed by a TXG write, followed by a disk cache 
sync).  Only synchronous writes get any priority, but they are 
prioritized by writing to a separate synchronous write log (as well as 
async/sync data targeted for the current transaction group) so that 
the request is not lost if the transaction group is otherwise lost.

Bob
-- 
Bob Friesenhahn
bfriesen at simple.dallas.tx.us, http://www.simplesystems.org/users/bfriesen/
GraphicsMagick Maintainer,    http://www.GraphicsMagick.org/