Background ---------- The resctrl filesystem supports a mount option that allows users to specify a memory bandwidth limit in MiB/s for each domain of a CTRL_MON group. The underlying implementation uses data collected from the local memory bandwidth monitoring event for the CTRL_MON group and all of its MON subgroups as input to a feedback loop that adjusts the memory bandwidth allocation control percentage up or down to keep the group within the limit set by the user. Problem statement ----------------- Hard coding the local memory bandwidth monitoring event has the following issues: 1) Some systems may support total memory bandwidth monitoring but not local. The user cannot use this mount option on such systems. 2) For large workloads that span NUMA domains using local bandwidth monitoring will not throttle jobs correctly. 3) Users may have a mix of large and small workloads and may want to use different input events per CTRL_MON group. Solution -------- A) Provide a new user interface to choose which event is used for each CTRL_MON group. B) Allow systems that only support total memory bandwidth monitoring to use total bandwidth event. Changes since v9 Link: https://lore.kernel.org/all/20241114001712.80315-1-tony.luck@xxxxxxxxx/ Globally s/ctrl_mon/CTRL_MON/ in commit comments. Patch Change 1 * Moved "Reviewed-by:" tag after Signed-off-by tags * Added comment that I dropped the __init attribute that was in Babu's original patch 2 * More detail in commit comment * Added block comment above definition of mba_mbps_default_event global variable * Fixed bug reported by Reinette that changes to event used for default group persist across unmount/mount. Did this by moving initialization from rdtgroup_setup_default to set_mba_sc() to catch both mount and unmount. 3 * Write commit commemt with problem & fix sections * Add note to commit comment that check for is_mbm_local_enabled() is deleted by this patch. * Delete redundant check of is_mbm_local_enabled() 4 * Write commit commemt with problem & fix sections * Reword legacy comment to avoid "we". 5 * Merged old patch 9 into this patch * Write commit commemt with problem & fix sections 6 * Remove "historical" paragraph from commit comment * Add note that "mba_MBps_event" file is only visible when the "mba_MBps" mount option is in use. 7 * Remove "historical" paragraph from commit comment 8 * No change Signed-off-by: Tony Luck <tony.luck@xxxxxxxxx> Babu Moger (1): x86/resctrl: Introduce resctrl_file_fflags_init() to initialize fflags Tony Luck (7): x86/resctrl: Prepare for per-CTRL_MON group mba_MBps control x86/resctrl: Modify update_mba_bw() to use per CTRL_MON group event x86/resctrl: Compute memory bandwidth for all supported events x86/resctrl: Make mba_sc use total bandwidth if local is not supported x86/resctrl: Add "mba_MBps_event" file to CTRL_MON directories x86/resctrl: Add write option to "mba_MBps_event" file x86/resctrl: Document the new "mba_MBps_event" file Documentation/arch/x86/resctrl.rst | 10 +++ include/linux/resctrl.h | 2 + arch/x86/kernel/cpu/resctrl/internal.h | 9 ++- arch/x86/kernel/cpu/resctrl/core.c | 9 ++- arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 70 +++++++++++++++++ arch/x86/kernel/cpu/resctrl/monitor.c | 94 +++++++++++------------ arch/x86/kernel/cpu/resctrl/rdtgroup.c | 45 +++++++---- 7 files changed, 173 insertions(+), 66 deletions(-) base-commit: adc218676eef25575469234709c2d87185ca223a -- 2.47.0
