Skip to content

Commit

Permalink
rdtset: Update rdtset manpage to support SMBA feature
Browse files Browse the repository at this point in the history
Signed-off-by: Babu Moger <[email protected]>
  • Loading branch information
babumoger committed Feb 16, 2023
1 parent 99afb97 commit d58e53b
Showing 1 changed file with 10 additions and 3 deletions.
13 changes: 10 additions & 3 deletions rdtset/rdtset.8
Original file line number Diff line number Diff line change
Expand Up @@ -43,9 +43,10 @@ architecture-and-technology/resource-director-technology.html
.br
or https://github.com/intel/intel-cmt-cat/wiki
.PP
The rdtset tool provides support to set up the CAT (Cache Allocation Technology) and MBA (Memory
Bandwidth Allocation) capabilities for a task and set its CPU affinity. For MBA, rdtset offers two modes of operation, fixed MBA rate
or closed-loop one monitoring local memory B/W usage and adjust MBA accordingly.
The rdtset tool provides support to set up the CAT (Cache Allocation Technology), MBA (Memory
Bandwidth Allocation) and SMBA (Slow Memory Bandwidth Allocation) capabilities for a task and
set its CPU affinity. For MBA, rdtset offers two modes of operation, fixed MBA rate or
closed-loop one monitoring local memory B/W usage and adjust MBA accordingly.
For OS interface, it uses MBA CTRL via libpqos (OS support available in Linux kernel 4.18 or later).
For MSRs, the tool adjusts MBA configuration by itself based on local memory B/W.
Intel(R) RDT/AMD PQoS allocation operations of the utility are done via libpqos library. Class of service 0 (CLOS0)
Expand Down Expand Up @@ -88,6 +89,8 @@ Accepted values for features:
.br
.B m, mba for MBA
.br
.B s, smba for SMBA
.br
.B b, mba_max for max allowable local memory bandwidth

For example:
Expand Down Expand Up @@ -116,6 +119,10 @@ data and code cache-ways are non-overlapping
.br
CPUs 0-2 can utilize up to 70% of available memory bandwidth

.B \-t\ 'smba=64;cpu=0-2'
.br
CPUs 0-2 can utilize up to 64 units of available slow memory bandwidth

.B \-t\ 'mba=50;l3=0xf;cpu=1'
.br
CPU 1 uses four L3 (mask 0xf) cache-ways and can utilize up to 50% of available memory bandwidth
Expand Down

0 comments on commit d58e53b

Please sign in to comment.