Re: Stalls in qemu with host running 6.1 (everything stuck at mmap_read_lock())

[Vlastimil Babka <vbabka@suse.cz>]

On 1/12/23 11:31, Maxim Levitsky wrote:
> On Thu, 2023-01-12 at 07:07 +0100, Jiri Slaby wrote:
>> 
>> I have rebooted to a fresh kernel which 1) have lockdep enabled, and 2) 
>> I have debuginfo for. So next time this happens, I can print held locks 
>> and dump a kcore (kdump is set up).
>> 
>> regards,
> 
> It is also possible that I noticed something like that on 6.1:
> 
> For me it happens when my system (also no swap, 96G out which 48 are permanetly reserved as 1G hugepages,
> and this happens with VMs which don't use this hugepage reserve) 
> is somewhat low on memory and qemu tries to lock all memory (I use -overcommit mem-lock=on)
> 
> Like it usually happens when I start 32 GB VM while having lot of stuff open in background, but
> still not nearly close to 16GB.
> As a workaround I lowered the reserved area to 32G.
> 
> I also see indication that things like htop or even opening a new shell hang quite hard.
> 
> What almost instantly helps is 'echo 3 | sudo tee /proc/sys/vm/drop_caches'
> e.g that makes the VM start booting, and unlocks everything.

Note it's possible that temporary+recoverable things like that have a
different cause caused by compaction caught in a loop, as discussed here:

https://lore.kernel.org/all/a032e3bf-8470-095a-2262-791f5678e590@suse.cz/

> Best regards,
> 	Maxim Levitsky
>