Re: [PATCH] slub: limit number of slabs to scan in count_partial()

[Jianfeng Wang <jianfeng.w.wang@oracle.com>]

On 4/12/24 11:16 AM, Christoph Lameter (Ampere) wrote:
> On Fri, 12 Apr 2024, Jianfeng Wang wrote:
> 
>>>> Can you run some tests showing the difference between the estimation and
>>>> the real count?
>>
>> Yes.
>> On a server with one NUMA node, I create a case that uses many dentry objects.
>> For "dentry", the length of partial slabs is slightly above 250000. Then, I
>> compare my approach of scanning N slabs from the list's head v.s. the original
>> approach of scanning the full list. I do it by getting both results using
>> the new and the original count_partial() and printing them in /proc/slabinfo.
>>
>> N = 10000
>> my_result = 4741651
>> org_result = 4744966
>> diff = (org_result - my_result) / org_result = 0.00069 = 0.069 %
>>
>> Increasing N further to 25000 will only slight improve the accuracy:
>> N = 15000 -> diff =  0.02 %
>> N = 20000 -> diff =  0.01 %
>> N = 25000 -> diff = -0.017 %
>>
>> Based on the measurement, I think the difference between the estimation and
>> the real count is very limited (i.e. less than 0.1% for N = 10000). The
>> benefit is significant: shorter execution time for get_slabinfo(); no more
>> soft lockups or crashes caused by count_partial().
> 
> Wow. That is good. Maybe decrease N to 1000 instead?
> 

Yes, the diff is still limited. Here are some numbers:
N = 5000 -> diff = 0.0019 = 0.19 %
N = 3000 -> diff = 0.0023 = 0.23 %
N = 1000 -> diff = 0.0040 = 0.40 %

So, the estimation is quite accurate.