Re: [PATCH] mm: vmstat: Use zeroed stats for unpopulated zones

[Sandipan Das <sandipan@linux.ibm.com>]

On 07/05/20 4:37 pm, Vlastimil Babka wrote:
> On 5/7/20 11:08 AM, Sandipan Das wrote:
>>>>
>>>> This is certainly an improvement. Thanks! The question whether we can
>>>> identify where bogus numbers came from would be interesting as well.
>>>> Maybe those are not worth fixing but it would be great to understand
>>>> them at least. I have to say that the explanation via boot_pageset is
>>>> not really clear to me.
>>>>
>>>
>>> The documentation update will definitely help. Thanks for that.
> 
> Thanks both, will send a proper patch.
> 
>>> I did collect some stack traces on a ppc64 guest for calls to zone_statistics()
>>> in case of zones that are using the boot_pageset and most of them originate
>>> from kmem_cache_init() with eventual calls to allocate_slab().
>>>
>>> [    0.000000] [c00000000282b690] [c000000000402d98] zone_statistics+0x138/0x1d0                                                                                                
>>> [    0.000000] [c00000000282b740] [c000000000401190] rmqueue_pcplist+0xf0/0x120                                                                                                 
>>> [    0.000000] [c00000000282b7d0] [c00000000040b178] get_page_from_freelist+0x2f8/0x2100                                                                                        
>>> [    0.000000] [c00000000282bb30] [c000000000401ae0] __alloc_pages_nodemask+0x1a0/0x2d0                                                                                         
>>> [    0.000000] [c00000000282bbc0] [c00000000044b040] alloc_slab_page+0x70/0x580                                                                                                 
>>> [    0.000000] [c00000000282bc20] [c00000000044b5f8] allocate_slab+0xa8/0x610                                                                                                   
>>> ...
>>>
>>> In the remaining cases, the sources are ftrace_init() and early_trace_init().
>>>
>>
>> Forgot to add that this happens during the period between zone_pcp_init() and setup_zone_pageset().
> 
> If you can identify a good moment during the boot when the boot_pageset stops
> being used, maybe we could just reset its stats to zero once at that point and
> be done with it.
> 

I think that would be in setup_per_cpu_pageset(). After the pagesets for the populated
zone have been allocated.

- Sandipan