Home
last modified time | relevance | path

Searched refs:cachelines (Results 1 – 10 of 10) sorted by relevance

/linux-4.1.27/fs/fscache/
DKconfig23 multi-CPU system these may be on cachelines that keep bouncing
40 and on a multi-CPU system these may be on cachelines that keep
/linux-4.1.27/arch/x86/kernel/cpu/
Dperf_event_intel_cqm.c1185 unsigned int bytes, cachelines; in max_recycle_threshold_store() local
1195 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()
/linux-4.1.27/fs/cachefiles/
DKconfig34 and on a multi-CPU system these may be on cachelines that keep
/linux-4.1.27/arch/mn10300/mm/
DKconfig.cache17 Write-Through caching only fetches cachelines from memory on a
/linux-4.1.27/arch/frv/
DKconfig172 Write-Through caching only fetches cachelines from memory on a
/linux-4.1.27/Documentation/ABI/testing/
Dsysfs-kernel-slab287 objects are aligned on cachelines.
/linux-4.1.27/Documentation/filesystems/
Dpath-lookup.txt36 even stores into cachelines of common dentries). This is known as "rcu-walk"
Dxfs-delayed-logging-design.txt407 dirty only the log item cachelines. Normally I wouldn't be concerned about one
408 vs two dirty cachelines except for the fact I've seen upwards of 80,000 log
/linux-4.1.27/Documentation/RCU/
DRTFP.txt1039 https://lkml.org/lkml/2004/5/20/49 (split vars into cachelines)
/linux-4.1.27/Documentation/
Dmemory-barriers.txt2793 Basically, whilst both cachelines will be updated on CPU 2 eventually, there's