1PQOS(8)                     System Manager's Manual                    PQOS(8)
2
3
4

NAME

6       pqos,  pqos-msr,  pqos-os - Intel(R) Resource Director Technology moni‐
7       toring and control tool
8

SYNOPSIS

10       pqos [OPTIONS]...
11

DESCRIPTION

13       Intel(R) Resource Director Technology is designed to monitor and manage
14       cpu  resources  and  improve  performance  of  applications and virtual
15       machines.
16
17       Intel(R) Resource Director Technology includes monitoring  and  control
18       technologies.  Monitoring  technologies  include  CMT (Cache Monitoring
19       Technology), which monitors occupancy of  last  level  cache,  and  MBM
20       (Memory Bandwidth Monitoring).  Control technologies include CAT (Cache
21       Allocation Technology), CDP (Code Data Prioritization) and MBA  (Memory
22       Bandwidth Allocation).
23
24       pqos  supports  CMT and MBM on a per core or hardware thread basis. MBM
25       supports two types of events reporting local and  remote  memory  band‐
26       width.
27       pqos-msr and pqos-os are simple pqos wrapper scripts that automatically
28       select the MSR or OS/Kernel library interface to program the  technolo‐
29       gies.
30       Please see the -I option below for more information.
31
32       For  hardware  information  please  refer  to  the  README  located on:
33       https://github.com/01org/intel-cmt-cat/blob/master/README
34

OPTIONS

36       pqos options are as follow:
37
38       -h, --help
39              show help
40
41       -v, --verbose
42              verbose mode
43
44       -V, --super-verbose
45              super-verbose mode
46
47       -l FILE, --log-file=FILE
48              log messages into selected log FILE
49
50       -s, --show
51              show the current allocation and monitoring configuration
52
53       -d, --display
54              display supported Intel(R) Resource Director Technology capabil‐
55              ities
56
57       -D, --display-verbose
58              display supported Intel(R) Resource Director Technology capabil‐
59              ities in verbose mode
60
61       -f FILE, --config-file=FILE
62              load commands from selected configuration FILE
63
64       -e CLASSDEF, --alloc-class=CLASSDEF
65              define the allocation classes on all CPU sockets. CLASSDEF  for‐
66              mat is "TYPE:ID=DEFINITION;...".
67              define  classes  for  selected CPU resources. CLASSDEF format is
68              "TYPE[@RESOURCE_ID]:ID=DEFINITION;...".
69              For CAT, TYPE is "llc" for the last level  cache  (aka  l3)  and
70              "l2"  for level 2 cache, ID is a CLOS number and DEFINITION is a
71              bitmask.
72              For MBA, TYPE is "mba", ID is a CLOS number and DEFINITION is  a
73              value between 1 and 100 representing the percentage of available
74              memory bandwidth.
75              For MBA CTRL, TYPE is "mba_max", ID is a CLOS number and DEFINI‐
76              TION  is  a  value  representing  the requested memory bandwidth
77              specified in MBps.
78              RESOURCE_ID is a unique number that can represent  a  socket  or
79              l2/l3 cache identifier. The RESOURCE_ID for each logical CPU can
80              be found using "pqos -s"
81              Note: When L2/L3 CDP is on, ID can be  postfixed  with  'D'  for
82              data or 'C' for code.
83              Note: L2/L3 CDP is available on selected CPUs only.
84              Note:  MBA  CTRL  is  supported  only  by  the  OS interface and
85              requires Linux and kernel version 4.18 or newer.
86              Some examples:
87                     "-e llc:0=0xffff;llc:1=0x00ff"
88                     "-e llc@0-1:2=0xff00;l2:2=0x3f;l2@2:1=0xf"
89                     "-e llc:0d=0xfff;llc:0c=0xfff00"
90                     "-e l2:0d=0xf;l2:0c=0xc"
91                     "-e mba:1=30;mba@1:3=80"
92                     "-e mba_max:1=6000;mba_max@1:3=10000"
93              Note:
94                     "-e l2:2=0x3f" means that COS2 for all L2 cache  clusters
95                     is changed to 0x3f.
96                     "-e l2@2:1=0xf" means that COS1 for L2 cache cluster 2 is
97                     changed to 0xf.
98                     "-e mba:1=30" means that COS1, on all sockets,  can  uti‐
99                     lize up to 30% of available memory bandwidth.
100                     "-e  mba_max:1=6000" means that COS1, on all sockets, can
101                     utilize up to 6000 MBps of memory bandwidth.
102
103       -a CLASS2ID, --alloc-assoc=CLASS2ID
104              associate allocation classes  with  cores.  CLASS2ID  format  is
105              "TYPE:ID=CORE_LIST;..." or "TYPE:ID=TASK_LIST;...".
106              For  CAT,  TYPE is "llc", "core" or "pid" and ID is a class num‐
107              ber. CORE_LIST  is  comma  or  dash  separated  list  of  cores.
108              TASK_LIST is comma or dash separated list of process/task ID's.
109              For example:
110                     "-a  llc:0=0,2,4,6-10;llc:1=1;" associates cores 0, 2, 4,
111                     6, 7, 8, 9, 10 with CAT class 0 and core 1 with class 1.
112                     "-a core:0=0,2,4,6-10;core:1=1;" associates cores  0,  2,
113                     4,  6, 7, 8, 9, 10 with CAT class 0 and core 1 with class
114                     1.
115                     "-I   -a   pid:0=3543,7643,4556;pid:1=7644;"   associates
116                     process  ID 3543, 7643, 4556 with CAT class 0 and process
117                     ID 7644 with class 1.
118              Note:
119                     The -I option must be used for PID association.
120
121       -R [CONFIG[,CONFIG]], --alloc-reset[=CONFIG[,CONFIG]]
122              reset allocation setting (L3 CAT, L2 CAT, MBA)  and  reconfigure
123              L3 CDP. CONFIG is one of the following options:
124              l3cdp-on  sets L3 CDP on
125              l3cdp-off sets L3 CDP off
126              l3cdp-any keeps current L3 CDP setting (default)
127              l2cdp-on  sets L2 CDP on
128              l2cdp-off sets L2 CDP off
129              l2cdp-any keeps current L2 CDP setting (default)
130              mbaCtrl-on     sets MBA CTRL on
131              mbaCtrl-off    sets MBA CTRL off
132              mbaCtrl-any    keeps current MBA CTRL setting (default)
133
134       -m EVTCORES, --mon-core=EVTCORES
135              select  the  cores and events for monitoring, EVTCORES format is
136              "EVENT:CORE_LIST". Valid EVENT settings are:
137              - "llc" for CMT (LLC occupancy)
138              - "mbr" for MBR (remote memory bandwidth)
139              - "mbl" for MBL (local memory bandwidth)
140              - "all" or ""  for all detected event types
141              CORE_LIST is comma or dash separated list of cores.
142              Example "-m all:0,2,4-10;llc:1,3;mbr:11-12".
143              Core statistics can be grouped by enclosing  the  core  list  in
144              square brackets.
145              Example "-m llc:[0-3];all:[4,5,6];mbr:[0-3],7,8".
146
147       -p [EVTPIDS], --mon-pid[=EVTPIDS]
148              select top 10 most active (CPU utilizing) process ids to monitor
149              or select the process ids and events to monitor, EVTPIDS  format
150              is "EVENT:PID_LIST".
151              See  -m option for valid EVENT settings. PID_LIST is comma sepa‐
152              rated list of process ids.
153              Examples:
154                     "-p llc:22,25673"
155                     "-p all:892,4588-4592"
156
157              Process' IDs can be grouped by enclosing them in  square  brack‐
158              ets.
159              Examples:
160                     "-p llc:[22,25673]"
161                     "-p all:892,[4588-4592]"
162
163              Note:
164                     Requires Linux and kernel versions 4.10 and newer.
165                     The -I option must be used for PID monitoring.
166                     It  is  not possible to track both processes and cores at
167                     the same time.
168
169       -T, --mon-top
170              enable top like monitoring output sorted by  highest  LLC  occu‐
171              pancy
172
173       -o FILE, --mon-file FILE
174              select  output  FILE  to store monitored data in, the default is
175              'stdout'
176
177       -u TYPE, --mon-file-type=TYPE
178              select the output format TYPE for monitored data. Supported TYPE
179              settings are: "text" (default), "xml" and "csv".
180
181       -i INTERVAL, --mon-interval=INTERVAL
182              define  monitoring  sampling  INTERVAL  in 100ms units, 1=100ms,
183              default 10=10x100ms=1s
184
185       -t SECONDS, --mon-time=SECONDS
186              define monitoring time in seconds, use 'inf' or  'infinite'  for
187              infinite monitoring. Use CTRL+C to stop monitoring at any time.
188
189       -r, --mon-reset
190              reset monitoring and use all RMID's and cores in the system
191
192       -H, --profile-list
193              list supported allocation profiles
194
195       -c PROFILE, --profile-set=PROFILE
196              select  a  PROFILE from predefined allocation classes, use -H to
197              list available profiles
198
199       -I, --iface-os
200              set the library interface to use the kernel  implementation.  If
201              not  set  the  default  implementation  is  to program the MSR's
202              directly.
203

NOTES

205       CMT, MBM and CAT are configured using Model Specific Registers  (MSRs).
206       The  pqos  software  executes  in user space, and access to the MSRs is
207       obtained through a standard Linux* interface. The msr file interface is
208       protected  and  requires  root privileges.  The msr driver might not be
209       auto-loaded and on some modular kernels  the  driver  may  need  to  be
210       loaded manually:
211
212       For Linux:
213       sudo modprobe msr
214
215       For FreeBSD:
216       sudo kldload cpuctl
217
218       Interface enforcement:
219       If  you require system wide interface enforcement you can do so by set‐
220       ting the "RDT_IFACE" environment variable.
221

SEE ALSO

223       msr(4)
224

AUTHOR

226       pqos was written by Tomasz Kantecki <tomasz.kantecki@intel.com>, Marcel
227       Cornu  <marcel.d.cornu@intel.com>, Aaron Hetherington <aaron.hethering‐
228       ton@intel.com>
229
230       This is free software; see the source for copying conditions.  There is
231       NO  warranty;  not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR
232       PURPOSE.
233
234
235
236                               January 04, 2019                        PQOS(8)
Impressum