Re: [PATCH V3 3/4] x86/resctrl: Enable per-thread MBA

2020-05-16 Thread Reinette Chatre
.ts...@intel.com; ravi.v.shan...@intel.com; mi...@redhat.com; >> Moger, Babu ; h...@zytor.com; x...@kernel.org; >> linux-kernel@vger.kernel.org; Reinette Chatre >> Subject: [PATCH V3 3/4] x86/resctrl: Enable per-thread MBA >> >> From: Fenghua Yu >&

RE: [PATCH V3 3/4] x86/resctrl: Enable per-thread MBA

2020-05-14 Thread Babu Moger
u ; h...@zytor.com; x...@kernel.org; > linux-kernel@vger.kernel.org; Reinette Chatre > Subject: [PATCH V3 3/4] x86/resctrl: Enable per-thread MBA > > From: Fenghua Yu > > Current Memory Bandwidth Allocation (MBA) hardware has a limitation: > all threads on th

[PATCH V3 3/4] x86/resctrl: Enable per-thread MBA

2020-05-06 Thread Reinette Chatre
From: Fenghua Yu Current Memory Bandwidth Allocation (MBA) hardware has a limitation: all threads on the same core must have the same delay value. If there are different delay values across threads on one core, the original MBA implementation allocates the max delay value to the core and an