Searched refs:cachelines (Results 1 – 10 of 10) sorted by relevance
23 multi-CPU system these may be on cachelines that keep bouncing40 and on a multi-CPU system these may be on cachelines that keep
1185 unsigned int bytes, cachelines; in max_recycle_threshold_store() local1195 cachelines = bytes / cqm_l3_scale; in max_recycle_threshold_store()1200 if (__intel_cqm_threshold > cachelines) in max_recycle_threshold_store()1201 __intel_cqm_threshold = cachelines; in max_recycle_threshold_store()
34 and on a multi-CPU system these may be on cachelines that keep
17 Write-Through caching only fetches cachelines from memory on a
172 Write-Through caching only fetches cachelines from memory on a
287 objects are aligned on cachelines.
36 even stores into cachelines of common dentries). This is known as "rcu-walk"
407 dirty only the log item cachelines. Normally I wouldn't be concerned about one408 vs two dirty cachelines except for the fact I've seen upwards of 80,000 log
1039 https://lkml.org/lkml/2004/5/20/49 (split vars into cachelines)
2793 Basically, whilst both cachelines will be updated on CPU 2 eventually, there's