On Wed, 26 Jun 2019, Bill Maidment wrote:

> Hi friends
> I have run into a problem in SL7.6 copying a large KVM guest lvm snapshot 
> file using cp --sparse=always
> I get flooded with the following message:
>
> XFS: cp(12985) possible memory allocation deadlock size 131088 in 
> kmem_realloc (mode:0x250)
>
> The copy ends eventually, but it takes much longer than I expected.
> Has anyone else come across this? Googling doesn't throw much light on this.

Did you come across this article in your searches:
   https://urldefense.proofpoint.com/v2/url?u=https-3A__blog.codecentric.de_en_2017_04_xfs-2Dpossible-2Dmemory-2Dallocation-2Ddeadlock-2Dkmem-5Falloc_&d=DwIFAg&c=gRgGjJ3BkIsb5y6s49QqsA&r=gd8BzeSQcySVxr0gDWSEbN-P-pgDXkdyCtaMqdCgPPdW1cyL5RIpaIYrCn8C5x2A&m=cY2WwCEYQwykF9FwZEUoviVd7ExZGdSBVlskQqqV0HQ&s=00g_RB_wGAclo8TAu-uQQgMdMiSqF_rO2I9lEVRbF2k&e= 

However their deadlock is in kmem_alloc instead, and there is no
mention of LVM.  It's a nice analysis - it might shed some light on
the problem.

cheers, etc.
-- 
Denice Deatrich, TRIUMF/Science/ATLAS		Ph: +1 604 222 7665
<*> This moment's fortune cookie:
"What the scientists have in their briefcases is terrifying."
-- Nikita Khrushchev