Re: serious performance regression in .41

[christos%astron.com@localhost (Christos Zoulas)]

In article <881BAE49-9D0E-474E-9BC2-16230F304F66%eis.cs.tu-bs.de@localhost>,
J. Hannken-Illjes <hannken%eis.cs.tu-bs.de@localhost> wrote:
>On 23 May 2014, at 13:42, Christos Zoulas <christos%astron.com@localhost> 
>wrote:
>
>> In article <09108BB8-536E-48E2-906E-CDF6E0962F3E%eis.cs.tu-bs.de@localhost>,
>> J. Hannken-Illjes <hannken%eis.cs.tu-bs.de@localhost> wrote:
>>> 
>>> Does the attached diff help?
>> 
>> No, I don't think it does.
>
>Christos, please try it.  Of the locks involved locking the vnode is the
>one that is much more expensive and intrusive as the others.

I will try it. That does not fix the unmount problem.
It takes minutes to shutdown now (approximately 20 seconds per filesystem).

>What raid level are you using?

I am using RAID 1.

>Are the file systems mounted with "-o log"?

Yes.

>Null mounts?

No.

christos