Messages in this thread | | | Date | Thu, 14 Nov 2013 10:56:32 -0500 | From | Rik van Riel <> | Subject | Re: [patch 0/8] mm: thrash detection-based file cache sizing v5 |
| |
On 10/21/2013 05:26 AM, Vlastimil Babka wrote: > On 10/10/2013 11:46 PM, Johannes Weiner wrote: >> Hi everyone, >> >> here is an update to the cache sizing patches for 3.13. >> >> Changes in this revision >> >> o Drop frequency synchronization between refaulted and demoted pages >> and just straight up activate refaulting pages whose access >> frequency indicates they could stay in memory. This was suggested >> by Rik van Riel a looong time ago but misinterpretation of test >> results during early stages of development took me a while to >> overcome. It's still the same overall concept, but a little simpler >> and with even faster cache adaptation. Yay! > > Oh, I liked the previous approach with direct competition between the > refaulted and demoted page :) Doesn't the new approach favor the > refaulted page too much? No wonder it leads to faster cache adaptation, > but could it also cause degradations for workloads that don't benefit > from it? Were there any tests for performance regressions on workloads > that were not the target of the patchset?
This is a good question, and one that is probably best settled through experimentation.
Even with the first scheme (fault refaulted page to the inactive list), those pages only need 2 accesses to be promoted to the active list.
That is because a refault tends to immediately be followed by an access (after all, the attempted access causes the page to get loaded back into memory).
| |