> Coalesce before initiating writeout? I don't see why NFS should be special
> in this regard, or why it should not leave a page locked until IO has
> completed, like other filesystems. Could you please explain?
It does that for reads.
For writes, however, I see no point in keeping the page lock beyond what is
required in order to safely copy data from userland. To do so would give
disastrous performances if somebody was trying to write < page-sized records.
I belive this is true for all filesystems.
For some reason or another, the buffer stuff needs to re-take the page lock
when it actually performs the physical commit to disk. NFS doesn't need to do
this in order to perform an RPC call, so we don't...
Cheers,
Trond
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/