<div dir="ltr"><div class="gmail_extra"><div class="gmail_quote">On Thu, Dec 4, 2014 at 7:42 PM, Dietmar Maurer <span dir="ltr"><<a href="mailto:dietmar@proxmox.com" target="_blank">dietmar@proxmox.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><span class="">> > Hi Dietmar, hi Alexandre,<br>
> > I did manage to reproduce the issue without hardware dependency and<br>
> without<br>
> > LVM to reduce any possible influence from other components.<br>
><br>
> IMHO this is a DRBD problem. So I think you should report that to the DRBD list<br>
> instead.<br>
><br>
> I did and I have mentioned that.<br>
<br>
</span>You already reported a reproducible test case?<br>
<br>
</blockquote></div><br>No, but he didn't want this.<br>He said:<br>*******************************************************************<br>Misbehaving upper layer results in potentially divergent blocks on the DRBD peers. Or would result in potentially divergent blocks on a local software RAID 1.<br>...<br>Anyways.<br>Point being: Either have those upper layers stop modifying buffers<br>while they are in-flight (keyword: "stable pages").<br>Kernel upgrade within the VMs may do it. Changing something in the<br>"virtual IO path configuration" may do it. Or not.<br><br>Or live with the results, which are<br>potentially not identical blocks on the DRBD peers.<br>*******************************************************************<br><br>Stanislav</div></div>