Re: [Qemu-devel] [PATCH v5 0/8] Add metadata overlap checks

[Eric Blake <eblake@redhat.com>]

[-- Attachment #1: Type: text/plain, Size: 1704 bytes --]

On 09/19/2013 09:07 AM, Max Reitz wrote:
> Hi,
> 
> I've done some benchmarks regarding this series now. In particular, I've
> created a 7G image, installed Arch Linux to a partition in the first 2G
> and created an empty ext4 partition for benchmarking in the remaining 5G.

Thank you for doing this!

> 
> Basically, I didn't get any results which indicate a performance hit.

> 
> All in all, I don't see any significant performance difference when
> benchmarking on a tmpfs (which should maximize the overhead of
> "constant" and "cached") and the data from my HDD benchmarks is probably
> stastically unusable. The only comparison which they would have been
> useful for are the comparison of "all" to "cached", but since "all" will
> not be the default (and anyone explicitly using this option is in fact
> responsible for slow I/O himself)) they aren't actually that important
> anyway.

That's good news.  Remember, my question about whether we needed the
ability for command-line tuning was conditional on whether the tuning
would make a difference - but if you aren't seeing a difference with
your benchmark, then we might as well unconditionally enable the
checking, and not worry about the complexity of exposing additional
tuning.  Simpler is better if it makes no difference in end.

[Of course, if you WANT to write the patches for making it configurable,
I won't stop you; but now that you answered my question about
performance, and the answer is the desirable "no measurable impact", I
don't know that I would ever plan on using such tuning]

-- 
Eric Blake   eblake redhat com    +1-919-301-3266
Libvirt virtualization library http://libvirt.org


[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 621 bytes --]