Re: [PATCH v4 1/3] mm/slub: Introduce two counters for partial objects

2021-03-28 Thread Shu Ming
I am not sure how people are using partial object accounting. I believe it is used as a memory usage hint of slabs. On Mon, Mar 22, 2021 at 6:22 PM Vlastimil Babka wrote: > > On 3/22/21 2:46 AM, Shu Ming wrote: > > More precisely, ss will count partial objects like denty objects with > >

Re: [PATCH v4 1/3] mm/slub: Introduce two counters for partial objects

2021-03-22 Thread Vlastimil Babka
On 3/22/21 2:46 AM, Shu Ming wrote: > More precisely, ss will count partial objects like denty objects with > "/sys/kernel/slab/dentry/partial" whose number can become huge. Uh, that's interesting. Would you know what exactly it uses the value for? I can think of several reasons why it might be

Re: [PATCH v4 1/3] mm/slub: Introduce two counters for partial objects

2021-03-21 Thread Shu Ming
More precisely, ss will count partial objects like denty objects with "/sys/kernel/slab/dentry/partial" whose number can become huge. On Thu, Mar 18, 2021 at 8:56 PM Xunlei Pang wrote: > > > > On 3/18/21 8:18 PM, Vlastimil Babka wrote: > > On 3/17/21 8:54 AM, Xunlei Pang wrote: > >> The node

Re: [PATCH v4 1/3] mm/slub: Introduce two counters for partial objects

2021-03-18 Thread Xunlei Pang
On 3/18/21 8:18 PM, Vlastimil Babka wrote: > On 3/17/21 8:54 AM, Xunlei Pang wrote: >> The node list_lock in count_partial() spends long time iterating >> in case of large amount of partial page lists, which can cause >> thunder herd effect to the list_lock contention. >> >> We have HSF

Re: [PATCH v4 1/3] mm/slub: Introduce two counters for partial objects

2021-03-18 Thread Vlastimil Babka
On 3/17/21 8:54 AM, Xunlei Pang wrote: > The node list_lock in count_partial() spends long time iterating > in case of large amount of partial page lists, which can cause > thunder herd effect to the list_lock contention. > > We have HSF RT(High-speed Service Framework Response-Time) monitors, >

Re: [PATCH v4 1/3] mm/slub: Introduce two counters for partial objects

2021-03-17 Thread Xunlei Pang
On 3/18/21 2:45 AM, Vlastimil Babka wrote: > On 3/17/21 8:54 AM, Xunlei Pang wrote: >> The node list_lock in count_partial() spends long time iterating >> in case of large amount of partial page lists, which can cause >> thunder herd effect to the list_lock contention. >> >> We have HSF

Re: [PATCH v4 1/3] mm/slub: Introduce two counters for partial objects

2021-03-17 Thread Vlastimil Babka
On 3/17/21 8:54 AM, Xunlei Pang wrote: > The node list_lock in count_partial() spends long time iterating > in case of large amount of partial page lists, which can cause > thunder herd effect to the list_lock contention. > > We have HSF RT(High-speed Service Framework Response-Time) monitors, >

[PATCH v4 1/3] mm/slub: Introduce two counters for partial objects

2021-03-17 Thread Xunlei Pang
The node list_lock in count_partial() spends long time iterating in case of large amount of partial page lists, which can cause thunder herd effect to the list_lock contention. We have HSF RT(High-speed Service Framework Response-Time) monitors, the RT figures fluctuated randomly, then we