On Tue, Nov 19, 2024 at 08:03:06PM -0800, Reinette Chatre wrote: > Hi Tony, > > On 11/13/24 4:17 PM, Tony Luck wrote: > > The "mba_MBps" mount option provides an alternate method to > > control memory bandwidth. Instead of specifying allowable > > bandwidth as a percentage of maximum possible, the user > > provides a MiB/s limit value. > > > > Historically the limit was enforced by a feedback loop from > > "Historically the limit was enforced" no history needed since > this is still the case at the time of this patch. > > > the measure local bandwidth to adjust the memory bandwidth > > allocation controls. > > I am not sure what is meant by "a feedback loop from the measure > local bandwidth" (that was copy&pasted to next patch). Dropped the whole of the "Historically" paragraph. > > > > > In preparation to allow the user to pick the memory bandwidth > > monitoring event used as input to the feedback loop, provide > > a file in each ctrl_mon group directory that shows the event > > In the documentation the custom is to use CTRL_MON. Fixed here (and in several other places in the series). > > currently in use. > > Much better changelog. I think it will help to add a snippet that > mentions the file is only visible to user space if resctrl > was mounted with mba_MBps, and thus only visible when mba_sc is > enabled, and thus reinforcing that this maintains the contract > that rdtgrp->mba_mbps_event is only accessed when mba_sc is enabled. Added text to commit message about this file only being visible when the "mba_MBps" mount option is in use. > > > > Suggested-by: Reinette Chatre <reinette.chatre@xxxxxxxxx> > > Signed-off-by: Tony Luck <tony.luck@xxxxxxxxx> > > --- > > Reinette -Tony
