On Mon, 2014-02-24 at 22:55 +0100, Henrik Goldman wrote:
> > Not sure what you mean here.. Does this mean the filesystem that the
> > FILEIO file is referencing was offline when the -EINVAL error was
> > generated..?
> >
>
> Correct. Physically HDD's were gone but the filesystem was still
> exported using targetcli.
> As said this is just a misconfiguration on my part. However obviously
> a feature would be for targetcli to detect if a filesystem is really
> valid or not.
>
> >
> > Strange, FILEIO does support WRITE_SAME (VAAI BlockZero) emulation and
> > there is no reason why it should be failing..
> >
>
> But this is probably from 3.12 kernel, right? We're still on 3.11.
> However even if VAAI is not supported with 3.11 then likely it should
> not fail.
>
FYI, the WRITE_SAME (VAAI BlockZero) parts have been included since the
v3.8 time frame.
Starting with v3.12 code, COMPARE_AND_WRITE (VAAI AtomicTestAndSet) and
EXTENDED_COPY (VAAI CopyOffload) support was added.
Note this VAAI primitives work independent of each other, and it's
possible to check what is enabled using:
esxcli storage core device vaai status get
--nab
--
To unsubscribe from this list: send the line "unsubscribe target-devel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
