HP9000 Containers and PSET

[DiDa-THINK]

Hello,

I need to create an HP9000 System containers to support an old HPUX 11iv1 server.

The itanium server is a rx2800 i4 with 16 Cores and 64Gb of RAM.

I need to present only two CPU from the itanium system to the container.

This is the Container :

 # srp -status
NAME TYPE STATE SUBTYPE ROOTPATH
unxs8004 hp9000sys stopped none /var/hpsrp/unxs8004
 

I need only 2 CPU in the container with the help of PSET

 # srp -replace unxs8004 -s prm

Enter the requested values when prompted, then press return.
Enter "?" for help at prompt. Press control-c to exit.

PRM group name to associate with this container: [unxs8004]
PRM group type (FSS, PSET): [FSS] PSET
PRM PSET group cores: [1] 2
PRM group memory shares: [10]
PRM group memory cap (press return for no cap): []
PRM group shared memory (press return for no dedicated memory): []

The following template variables have been set to the values shown:

        prm_cores       =  2
        prm_group_type  =  PSET


Press return or enter "yes" to make the selected modifications with these
values.  Do you wish to continue? [yes] yes
replace prm rules succeeded

 I check the configuration file 

 # /usr/bin/prmconfig -s
Configuration file check complete. No errors found.
 

 I execute the prmconfig command :

 # /usr/bin/prmconfig -ie

PRM configured from file: /etc/prmconf
File last modified: Mon Mar 21 08:47:31 2016

PRM CPU scheduler state: Enabled

CPU CPU LCPU
PRM Group PRMID Entitlement Max Attr
__________________________________________________________________
OTHERS 1 87.50%
unxs8004 196608 12.50% OFF

PRM memory manager state: Enabled (polling interval: 10 seconds)
PRM memory manager logging state: Disabled

Memory Memory
PRM Group PRMID Entitlement Max
____________________________________________________________
OTHERS 1 66.67%
unxs8004 196608 33.33%

PRM User Initial Group Alternate Group(s)
________________________________________________________________________________
adm (NONE)
bin (NONE)
cimsrvr (NONE)
daemon (NONE)
hpdb (NONE)
hpsmh (NONE)
iwww (NONE)
lp (NONE)
nobody (NONE)
nuucp (NONE)
opc_op (NONE)
owww (NONE)
root (PRM_SYS)
sfmdb (NONE)
smbnull (NONE)
srp (NONE)
sshd (NONE)
sys (NONE)
tftp (NONE)
uucp (NONE)
www (NONE)

PRM application manager state: Enabled (polling interval: 30 seconds)
PRM application manager logging state: Disabled

Disk manager state: Disabled

Compartment Default PRM Group
__________________________________
unxs8004 unxs8004

Unix group Default PRM Group
________________________________________________
adm (NONE)
bin (NONE)
cimsrvr (NONE)
daemon (NONE)
lp (NONE)
mail (NONE)
nogroup (NONE)
nuucp (NONE)
opcgrp (NONE)
other (NONE)
root (NONE)
smbnull (NONE)
sys (NONE)
tty (NONE)
users (NONE)

This is the end of the configuration file

# cat /etc/prmconf

.......

.......

# PRM Unix group records cannot contain the PRMID 0 group PRM_SYS.
#
# #!PRM_MEM:{PRMID|GROUP}:SHARES:[MAX]:::[[IMPORT]:[EXPORT]:]
OTHERS:1:20::
#!PRM_MEM:1:20::::

#
# begin prmloadconf generated user records
#
root::::(PRM_SYS)
daemon::::(NONE)
bin::::(NONE)
sys::::(NONE)
adm::::(NONE)
uucp::::(NONE)
lp::::(NONE)
nuucp::::(NONE)
hpdb::::(NONE)
nobody::::(NONE)
www::::(NONE)
cimsrvr::::(NONE)
smbnull::::(NONE)
opc_op::::(NONE)
sfmdb::::(NONE)
sshd::::(NONE)
iwww::::(NONE)
owww::::(NONE)
hpsmh::::(NONE)
tftp::::(NONE)
srp::::(NONE)
#
# begin prmloadconf generated unix group records
#
#!UXGRP:root:(NONE)
#!UXGRP:other:(NONE)
#!UXGRP:bin:(NONE)
#!UXGRP:sys:(NONE)
#!UXGRP:adm:(NONE)
#!UXGRP:daemon:(NONE)
#!UXGRP:mail:(NONE)
#!UXGRP:lp:(NONE)
#!UXGRP:tty:(NONE)
#!UXGRP:nuucp:(NONE)
#!UXGRP:users:(NONE)
#!UXGRP:nogroup:(NONE)
#!UXGRP:cimsrvr:(NONE)
#!UXGRP:smbnull:(NONE)
#!UXGRP:opcgrp:(NONE)
##!UXGRP:OTHERS:(NONE)
#
# prmloadconf execution completed Thu May 9 08:14:58 2013
#
#@tag-start compartment="unxs8004" template="hp9000sys" service="prm" id="1";
unxs8004:PSET:::2::LCPU=OFF
#!PRM_MEM:unxs8004:10::::
#!SCOMP:unxs8004:unxs8004
#@tag-end;

I excute this command on the Itanium server : prmlist -p, and it seem thats the configuration is good ...

# prmlist -p

PRM configured from file: /etc/prmconf
File last modified: Mon Mar 21 08:47:31 2016

CPU CPU LCPU
PRM Group PRMID Entitlement Max Attr
__________________________________________________________________
OTHERS 1 87.50%
unxs8004 196608 12.50% OFF (2 cores - 2, 4)

Memory Memory
PRM Group PRMID Entitlement Max
____________________________________________________________
OTHERS 1 66.67%
unxs8004 196608 33.33%

PRM User Initial Group Alternate Group(s)
________________________________________________________________________________
adm (NONE)
bin (NONE)
cimsrvr (NONE)
daemon (NONE)
hpdb (NONE)
hpsmh (NONE)
iwww (NONE)
lp (NONE)
nobody (NONE)
nuucp (NONE)
opc_op (NONE)
owww (NONE)
root (PRM_SYS)
sfmdb (NONE)
smbnull (NONE)
srp (NONE)
sshd (NONE)
sys (NONE)
tftp (NONE)
uucp (NONE)
www (NONE)

Unix group Default PRM Group
________________________________________________
adm (NONE)
bin (NONE)
cimsrvr (NONE)
daemon (NONE)
lp (NONE)
mail (NONE)
nogroup (NONE)
nuucp (NONE)
opcgrp (NONE)
other (NONE)
root (NONE)
smbnull (NONE)
sys (NONE)
tty (NONE)
users (NONE)

I start the container:

# srp -start unxs8004

I go inside the container:

# srp_su unxs8004

I check the number of CPU inside the container with the top command:

# top

System: unxs8004 Mon Mar 21 08:59:32 2016
Load averages: 0.01, 0.01, 0.00
19 processes: 11 sleeping, 8 running
Cpu states:
CPU LOAD USER NICE SYS IDLE BLOCK SWAIT INTR SSYS
0 0.01 0.0% 0.0% 0.0% 100.0% 0.0% 0.0% 0.0% 0.0%
2 0.00 0.0% 0.0% 0.0% 100.0% 0.0% 0.0% 0.0% 0.0%
4 0.00 0.0% 0.0% 0.0% 100.0% 0.0% 0.0% 0.0% 0.0%
6 0.02 0.0% 0.0% 0.0% 100.0% 0.0% 0.0% 0.0% 0.0%
8 0.01 0.0% 0.0% 0.0% 100.0% 0.0% 0.0% 0.0% 0.0%
10 0.01 0.0% 0.0% 0.0% 100.0% 0.0% 0.0% 0.0% 0.0%
12 0.01 0.0% 0.0% 0.0% 100.0% 0.0% 0.0% 0.0% 0.0%
14 0.01 0.0% 0.0% 0.0% 100.0% 0.0% 0.0% 0.0% 0.0%
16 0.01 0.0% 0.0% 0.0% 100.0% 0.0% 0.0% 0.0% 0.0%
18 0.01 0.0% 0.0% 0.0% 100.0% 0.0% 0.0% 0.0% 0.0%
20 0.01 0.0% 0.0% 0.0% 100.0% 0.0% 0.0% 0.0% 0.0%
22 0.01 0.0% 0.0% 0.0% 100.0% 0.0% 0.0% 0.0% 0.0%
24 0.01 0.0% 0.0% 0.0% 100.0% 0.0% 0.0% 0.0% 0.0%
26 0.01 0.0% 0.0% 0.0% 100.0% 0.0% 0.0% 0.0% 0.0%
28 0.03 0.0% 0.0% 0.0% 100.0% 0.0% 0.0% 0.0% 0.0%
30 0.02 0.0% 0.0% 0.0% 100.0% 0.0% 0.0% 0.0% 0.0%
--- ---- ----- ----- ----- ----- ----- ----- ----- -----
avg 0.01 0.0% 0.0% 0.0% 100.0% 0.0% 0.0% 0.0% 0.0%

Memory: 47212K (27696K) real, 83828K (49300K) virtual, 3889776K free Page# 1/1

CPU TTY PID USERNAME PRI NI SIZE RES STATE TIME %WCPU %CPU COMMAND
22 ? 25640 root 158 20 684K 180K sleep 0:00 3.51 0.49 sh
2 ? 25598 root 154 20 812K 232K sleep 0:00 0.52 0.25 prngd
8 ? 25641 root 178 20 1144K 544K run 0:00 1.54 0.15 top
2 ? 25560 root 154 20 964K 328K sleep 0:00 0.23 0.14 pwgrd
2 ? 25568 root 154 20 1472K 436K sleep 0:00 0.19 0.11 swagentd
2 ? 25515 root 154 20 936K 276K sleep 0:00 0.06 0.04 inetd
2 ? 25442 root 152 20 2284K 636K run 0:00 0.04 0.03 ldapclientd

I see 16 CPUs on the HP9000 Containers...

Why ?,  I configured PSET with only 2 Cores ....

Can you help me ?

Thanks.

David

[Arunabha Banerjee]

As per HPE PRM Guide:

Group/CPU record syntax:

GROUP:PSET:::[CORES]:[CORE_LIST][:PSET_ATTR]

Consider the following example group/CPU records:
management:PSET:::2:3,4

These group/CPU records define:
A management PSET PRM group with two cores assigned. The specific cores assigned are Core 3 and Core 4.

Your current settings:
unxs8004:PSET:::2::LCPU=OFF

Change it to => unxs8004:PSET:::2:2,4:LCPU=OFF

To add or modify a group/CPU record, follow these steps:
1. Open the desired configuration file in a text editor.
2. Add or modify a line specifying the group name, PRMID, HIER or PSET keyword, and CPU allocations. Use the syntax shown above:
3. Save the file and exit your editor.
4. Load the configuration using one of the following commands:
To initialize, moving user processes to the owners’ initial groups and moving applications to their assigned groups, use the command:
#prmconfig -i [-fconfigfile] {-s | -c}
To keep the existing assignments of users, processes, and groups, use the command:
#prmconfig -k [-fconfigfile] {-s | -c}
Use the -f configfile option to specify a file other than the default /etc/prmconf. The -s option displays warnings regarding the configuration file. (The -c option displays a subset of the -s warnings.)
5. Enable PRM’s CPU manager if it is not already enabled:
#prmconfig -e CPU
Alternatively, enable all PRM resource managers using prmconfig -e without any additional arguments:
#prmconfig -e

After the above steps please share the output: prmlist -g -s

More Info:

CORES: Is the number of cores assigned to the PSET PRM group. (A core is the actual data-processing engine within a processor. A single processor might have multiple cores. A core might support multiple execution threads.) The range for this field is from 0 to MAX_CORE-1. The number of cores must agree with the number of cores in CORE_LIST, if CORE_LIST is specified. If it is not specified, PRM chooses which cores to use. However, PRM does not guarantee to choose an optimal set of cores.

CORE_LIST: Is the comma-delimited list of core IDs for the cores to be assigned to the PSET PRM group. You cannot specify core ID 0 in CORE_LIST. The number of cores specified in the CORES field must match the number of cores listed in CORE_LIST.

PSET_ATTR: Passes attributes for the specified PSET to HP-UX. (For a complete attribute list, see the -t option in the psrset(1M) manpage.) The only attribute currently available is the logical CPU (Hyper-Threading) feature, available starting with HP-UX 11i v3 (B.11.31). Set this attribute as follows:
LCPU=ON Explicitly enables Hyper-Threading
LCPU=OFF Explicitly disables Hyper-Threading
If PSET_ATTR is not specified, a nondefault PSET inherits the Hyper-Threading state the system had before PRM was enabled. (The state from before PRM was enabled is used because PRM may change the Hyper-Threading setting for PSET 0, where FSS PRM groups are created, to optimize workload performance.)

[DiDa-THINK]

Hello

Thanks for your reply ;)

So, i modified the configuration file /etc/prmconf :

# cat /etc/prmconf

#
# #!PRM_MEM:{PRMID|GROUP}:SHARES:[MAX]:::[[IMPORT]:[EXPORT]:]
OTHERS:1:100::
#!PRM_MEM:1:20::::

#
# begin prmloadconf generated user records
#
root::::(PRM_SYS)
daemon::::(NONE)
bin::::(NONE)
sys::::(NONE)
adm::::(NONE)
uucp::::(NONE)
lp::::(NONE)
nuucp::::(NONE)
hpdb::::(NONE)
nobody::::(NONE)
www::::(NONE)
cimsrvr::::(NONE)
smbnull::::(NONE)
opc_op::::(NONE)
sfmdb::::(NONE)
sshd::::(NONE)
iwww::::(NONE)
owww::::(NONE)
hpsmh::::(NONE)
tftp::::(NONE)
srp::::(NONE)
#
# begin prmloadconf generated unix group records
#
#!UXGRP:root:(NONE)
#!UXGRP:other:(NONE)
#!UXGRP:bin:(NONE)
#!UXGRP:sys:(NONE)
#!UXGRP:adm:(NONE)
#!UXGRP:daemon:(NONE)
#!UXGRP:mail:(NONE)
#!UXGRP:lp:(NONE)
#!UXGRP:tty:(NONE)
#!UXGRP:nuucp:(NONE)
#!UXGRP:users:(NONE)
#!UXGRP:nogroup:(NONE)
#!UXGRP:cimsrvr:(NONE)
#!UXGRP:smbnull:(NONE)
#!UXGRP:opcgrp:(NONE)
##!UXGRP:OTHERS:(NONE)
#
# prmloadconf execution completed Thu May 9 08:14:58 2013
#
#@tag-start compartment="unxs8004" template="hp9000sys" service="prm" id="1";
unxs8004:PSET:::2:2,4:LCPU=OFF
#!PRM_MEM:unxs8004:10::::
#!SCOMP:unxs8004:unxs8004
#@tag-end;

To check the configuration file, i prefered to restart the global system (Integrity):

#shutdown -ry 0

After the system restart, i check the configuration of PRM :

# prmlist -p

PRM configured from file: /etc/prmconf
File last modified: Tue Mar 22 09:31:56 2016

CPU CPU LCPU
PRM Group PRMID Entitlement Max Attr
__________________________________________________________________
OTHERS 1 87.50%
unxs8004 65536 12.50% OFF (2 cores - 2, 4)

Memory Memory
PRM Group PRMID Entitlement Max
____________________________________________________________
OTHERS 1 66.67%
unxs8004 65536 33.33%

PRM User Initial Group Alternate Group(s)
________________________________________________________________________________
adm (NONE)
bin (NONE)
cimsrvr (NONE)
daemon (NONE)
hpdb (NONE)
hpsmh (NONE)
iwww (NONE)
lp (NONE)
nobody (NONE)
nuucp (NONE)
opc_op (NONE)
owww (NONE)
root (PRM_SYS)
sfmdb (NONE)
smbnull (NONE)
srp (NONE)
sshd (NONE)
sys (NONE)
tftp (NONE)
uucp (NONE)
www (NONE)

Unix group Default PRM Group
________________________________________________
adm (NONE)
bin (NONE)
cimsrvr (NONE)
daemon (NONE)
lp (NONE)
mail (NONE)
nogroup (NONE)
nuucp (NONE)
opcgrp (NONE)
other (NONE)
root (NONE)
smbnull (NONE)
sys (NONE)
tty (NONE)
users (NONE)

 # prmlist -g -s

PRM configured from file: /etc/prmconf
File last modified: Tue Mar 22 09:31:56 2016

CPU CPU LCPU
PRM Group PRMID Entitlement Max Attr
__________________________________________________________________
OTHERS 1 87.50%
unxs8004 65536 12.50% OFF

Memory Memory
PRM Group PRMID Entitlement Max
____________________________________________________________
OTHERS 1 66.67%
unxs8004 65536 33.33%

Compartment Default PRM Group
__________________________________
unxs8004 unxs8004

Now, i go inside the container and check the number of CPU, with the command top:

# spr_su unxs8004

# top

System: unxs8004 Tue Mar 22 09:52:58 2016
Load averages: 0.00, 0.00, 0.00
19 processes: 11 sleeping, 8 running
Cpu states:
CPU LOAD USER NICE SYS IDLE BLOCK SWAIT INTR SSYS
0 0.00 0.0% 0.0% 0.0% 100.0% 0.0% 0.0% 0.0% 0.0%
2 0.00 0.0% 0.0% 0.0% 100.0% 0.0% 0.0% 0.0% 0.0%
4 0.00 0.0% 0.0% 0.0% 100.0% 0.0% 0.0% 0.0% 0.0%
6 0.00 0.0% 0.0% 0.0% 100.0% 0.0% 0.0% 0.0% 0.0%
8 0.00 0.0% 0.0% 0.0% 100.0% 0.0% 0.0% 0.0% 0.0%
10 0.00 0.0% 0.0% 0.0% 100.0% 0.0% 0.0% 0.0% 0.0%
12 0.00 0.0% 0.0% 0.0% 100.0% 0.0% 0.0% 0.0% 0.0%
14 0.00 0.0% 0.0% 0.0% 100.0% 0.0% 0.0% 0.0% 0.0%
16 0.00 0.0% 0.0% 0.0% 100.0% 0.0% 0.0% 0.0% 0.0%
18 0.00 0.0% 0.0% 0.0% 100.0% 0.0% 0.0% 0.0% 0.0%
20 0.00 0.0% 0.0% 0.0% 100.0% 0.0% 0.0% 0.0% 0.0%
22 0.00 0.0% 0.0% 0.0% 100.0% 0.0% 0.0% 0.0% 0.0%
24 0.00 0.0% 0.0% 0.0% 100.0% 0.0% 0.0% 0.0% 0.0%
26 0.00 0.0% 0.0% 0.0% 100.0% 0.0% 0.0% 0.0% 0.0%
28 0.00 0.0% 0.0% 0.0% 100.0% 0.0% 0.0% 0.0% 0.0%
30 0.00 0.0% 0.0% 0.0% 100.0% 0.0% 0.0% 0.0% 0.0%
--- ---- ----- ----- ----- ----- ----- ----- ----- -----
avg 0.00 0.0% 0.0% 0.0% 100.0% 0.0% 0.0% 0.0% 0.0%

Memory: 517072K (272912K) real, 1054276K (509884K) virtual, 59189884K free Page# 1/1

CPU TTY PID USERNAME PRI NI SIZE RES STATE TIME %WCPU %CPU COMMAND
2 ? 4805 root 158 20 10556K 2412K sleep 0:00 3.48 0.48 sh
4 ? 4806 root 178 20 17288K 7736K run 0:00 4.00 0.20 top
4 ? 4236 root 168 20 14320K 3632K sleep 0:00 0.00 0.00 srp_init
2 ? 4319 root 154 20 12080K 2776K sleep 0:00 0.00 0.00 syslogd
4 ? 4325 root 154 20 15872K 3640K sleep 0:00 0.00 0.00 sshd
4 ? 4335 root 154 20 6440K 640K sleep 0:00 0.00 0.00 rpcbind
2 ? 4359 root 152 20 30288K 5416K run 0:00 0.00 0.00 ldapclientd
4 ? 4379 daemon 152 20 13536K 2360K run 0:00 0.00 0.00 rpc.statd
4 ? 4385 root 152 20 7336K 844K run 0:00 0.00 0.00 rpc.lockd
4 ? 4406 root 152 20 7600K 928K run 0:00 0.00 0.00 nfs4cbd

We can see the 16 CPUs from the Itanium Server .....The PRM configuration with PSET don't work well....

Have you an other idea ?

Thanks a lot.

David