lsmemopt : Suivi des affinités mémoire

Détails: Catégorie parente: HMC; Catégorie : Commandes; Mis à jour : 26 janvier 2015; Affichages : 134

La commande 'lsmemopt' permet de suivre l'état des affectations mémoire d'un système ou d'une LPAR afin de valider les bonnes affinités.

Lacommande retourne un 'score', chiffre entre 0 et 100, où 0 représente une très mauvaise affinités et 100 une affinité parfaite.

Suivant les systèmes, le score de 100 ne peut pas toujours être atteint.

Une partition sans ressources mémoire et CPU n'obtient pas de score et la valeur 'Non' est alors affiché.

# lsmemopt -m Chassis11 -o currscore -r lpar

lpar_name=pai111,lpar_id=1,curr_lpar_score=100
lpar_name=pai211,lpar_id=2,curr_lpar_score=none
lpar_name=prasxsa50,lpar_id=3,curr_lpar_score=none
lpar_name=praoxin50,lpar_id=4,curr_lpar_score=none
lpar_name=prasxsa01,lpar_id=5,curr_lpar_score=none
lpar_name=prasxsa52,lpar_id=6,curr_lpar_score=none
lpar_name=prawxas24,lpar_id=7,curr_lpar_score=none
lpar_name=prawxor24,lpar_id=8,curr_lpar_score=none

# lsmemopt -m CHASSIS12 -o calcscore -r lpar
lpar_name=pa12,lpar_id=1,curr_lpar_score=50,predicted_lpar_score=90
lpar_name=pa212,lpar_id=2,curr_lpar_score=50,predicted_lpar_score=90
lpar_name=patf12,lpar_id=4,curr_lpar_score=100,predicted_lpar_score=90

lsmemopt - list memory optimization information

Synopsis
Description
Options
Examples
Environment
Bugs
Author
See Also

lsmemopt -m managed-system [-r {sys | lpar}]
[-o {currscore | calcscore}]
[-p partition-names | --id partition-IDs]
[-x partition-names | --xid partition-IDs]
[--filter "filter-data"]
[-F [attribute-names] [--header]] [--help]

lsmemopt lists information, including status and progress information, about the most recent memory optimization operation that was started on the managed-system.
lsmemopt also lists affinity scores for the managed-system and for partitions in the managed-system. An affinity score is a measure of how good the processor-memory affinity is on the managed system or for a partition. The score is a number between 0 and 100, with 0 representing the worst affinity and 100 representing perfect affinity. Depending on the system configuration, scores of 100 might not be attainable. A partition with no processor and memory resources does not have an affinity score, and none will be displayed for its score.

lsmemopt can list current affinity scores, and can calculate and list potential affinity scores which could be attained after running a Dynamic Platform Optimization operation. Note that potential affinity scores may differ slightly from the actual affinity scores that are attained after running the Dynamic Platform Optimization operation.

-m The name of the managed system for which to list memory optimization information. The name may either be the user-defined name for the managed system, or be in the form tttt-mmm*sssssss, where tttt is the machine type, mmm is the model, and sssssss is the serial number of the managed system. The tttt-mmm*sssssss form must be used if there are multiple managed systems with the same user-defined name.

-r The type of resources for which to list affinity scores. Valid values are sys to list the affinity score for the managed system, and lpar to list affinity scores for partitions.
If this option is omitted when listing affinity scores, the affinity score for the managed system will be listed.

This option is only valid when listing affinity scores.

-o The operation to perform. Valid values are currscore to list current affinity scores, and calcscore to calculate and list potential affinity scores.
If this option is omitted, information about the most recent memory optimization operation that was started on the managed system is listed.

-p The name of one or more potential partitions to optimize. This list of partitions is used to calculate the potential affinity scores that could be attained if a Dynamic Platform Optimization operation were run to optimize this list of partitions.
Multiple partition names must be comma separated.

You can either use this option to specify the names of the potential partitions to optimize, or use the --id option to specify the IDs of the partitions. The -p and the --id options are mutually exclusive.

If neither this option nor the --id option is used to specify a list of potential partiitions to optimize, the list of potential partitions to optimize defaults to all partitions that are not specified in the list of potential partitions to exclude from the optimization.

This option is only valid when -o calcscore is specified.

--id The ID of one or more potential partitions to optimize. This list of partitions is used to calculate the potential affinity scores that could be attained if a Dynamic Platform Optimization operation were run to optimize this list of partitions.
A range of partition IDs may be specified. A range is specified by specifying the beginning partition ID, a dash, and the ending partition ID. Both the beginning and ending partition IDs are included in the range. For example, the range 1-5 includes partitions IDs 1, 2, 3, 4, and 5.

The list of partition IDs specified with this option must be comma separated and can include one or more partition IDs, one or more ranges of partition IDs, or both.

You can either use this option to specify the IDs of the potential partitions to optimize, or use the -p option to specify the names of the partitions. The --id and the -p options are mutually exclusive.

If neither this option nor the -p option is used to specify a list of potential partiitions to optimize, the list of potential partitions to optimize defaults to all partitions that are not specified in the list of potential partitions to exclude from the optimization.

This option is only valid when -o calcscore is specified.

-x The name of one or more potential partitions to exclude and protect from an optimization operation. This list of partitions is used to calculate the potential affinity scores that could be attained if a Dynamic Platform Optimization operation were run with this list of partitions to exclude.
Multiple partition names must be comma separated.

You can either use this option to specify the names of the potential partitions to exclude, or use the --xid option to specify the IDs of the partitions. The -x and the --xid options are mutually exclusive.

If neither this option nor the --xid option is used to specify a list of potential partiitions to exclude, the list of potential partitions to exclude defaults to an empty list.

This option is only valid when -o calcscore is specified.

--xid The ID of one or more potential partitions to exclude and protect from an optimization operation. This list of partitions is used to calculate the potential affinity scores that could be attained if a Dynamic Platform Optimization operation were run with this list of partitions to exclude.
A range of partition IDs may be specified. A range is specified by specifying the beginning partition ID, a dash, and the ending partition ID. Both the beginning and ending partition IDs are included in the range. For example, the range 8-11 includes partitions IDs 8, 9, 10, and 11.

The list of partition IDs specified with this option must be comma separated and can include one or more partition IDs, one or more ranges of partition IDs, or both.

You can either use this option to specify the IDs of the potential partitions to exclude, or use the -x option to specify the names of the partitions. The --xid and the -x options are mutually exclusive.

If neither this option nor the -x option is used to specify a list of potential partiitions to exclude, the list of potential partitions to exclude defaults to an empty list.

This option is only valid when -o calcscore is specified.

--filter The filter to apply to the partition affinity scores to list. The filter is used to select which partitions to list. If a filter is not specified, then all partitions will be listed.
The filter data consists of filter name/value pairs, which are in comma separated value (CSV) format. The filter data must be enclosed in double quotes.

The format of the filter data is as follows:

filter-name=value

Note that the filters accept a comma separated list of values, as follows:

filter-name=value,value,...

When a list of values is specified, the filter name/value pair must be enclosed in double quotes. Depending on the shell being used, nested double quote characters may need to be preceded by an escape character, which is usually a ’#146; character.

Multiple values can be specified for each filter.

Valid filter names:
lpar_names | lpar_ids

This option is only valid when listing partition affinity scores.

-F A delimiter separated list of attribute names for the desired attribute values to be displayed. If no attribute names are specified, then values for all of the attributes will be displayed.
When this option is specified, only attribute values will be displayed. No attribute names will be displayed. The attribute values displayed will be separated by the delimiter which was specified with this option.

This option is useful when only attribute values are desired to be displayed, or when the values of only selected attributes are desired to be displayed.

--header Display a header record, which is a delimiter separated list of attribute names for the attribute values that will be displayed. This header record will be the first record displayed. This option is only valid when used with the -F option.

--help Display the help text for this command and exit.

List information about the last memory optimization operation that was started:

lsmemopt -m system1

List just the status of the last memory optimization operation that was started:

lsmemopt -m 8233-E8B*1234321 -F status

List the current system affinity score:

lsmemopt -m sys -o currscore

List the current affinity scores for all partitions in the managed system:

lsmemopt -m sys -o currscore -r lpar

List the current affinity scores for partitions lp2 and lp3 only:

lsmemopt -m sys -o currscore -r lpar --filter ""lpar_names=lp2,lp3""

Calculate and list the potential system affinity score that could be attained if a Dynamic Platform Optimization operation were run to optimize all partitions in the system:

lsmemopt -m sys -o calcscore

Calculate and list the potential partition affinity scores that could be attained if a Dynamic Platform Optimization operation were run to optimize partitions lp1 and lp3:

lsmemopt -m sys -o calcscore -r lpar -p lp1,lp3

Calculate and list the potential system affinity score that could be attained if a Dynamic Platform Optimization operation were run to optimize the partitions with IDs 2, 4, 6 through 9, and 11, while excluding the partition with ID 1:

lsmemopt -m sys -o calcscore --id 2,4,6-9,11 --xid 1

HMCs

lsmemopt : Suivi des affinités mémoire

CONTENTS

-m	The name of the managed system for which to list memory optimization information. The name may either be the user-defined name for the managed system, or be in the form tttt-mmm*sssssss, where tttt is the machine type, mmm is the model, and sssssss is the serial number of the managed system. The tttt-mmm*sssssss form must be used if there are multiple managed systems with the same user-defined name.
-r	The type of resources for which to list affinity scores. Valid values are sys to list the affinity score for the managed system, and lpar to list affinity scores for partitions. If this option is omitted when listing affinity scores, the affinity score for the managed system will be listed. This option is only valid when listing affinity scores.
-o	The operation to perform. Valid values are currscore to list current affinity scores, and calcscore to calculate and list potential affinity scores. If this option is omitted, information about the most recent memory optimization operation that was started on the managed system is listed.
-p	The name of one or more potential partitions to optimize. This list of partitions is used to calculate the potential affinity scores that could be attained if a Dynamic Platform Optimization operation were run to optimize this list of partitions. Multiple partition names must be comma separated. You can either use this option to specify the names of the potential partitions to optimize, or use the --id option to specify the IDs of the partitions. The -p and the --id options are mutually exclusive. If neither this option nor the --id option is used to specify a list of potential partiitions to optimize, the list of potential partitions to optimize defaults to all partitions that are not specified in the list of potential partitions to exclude from the optimization. This option is only valid when -o calcscore is specified.
--id	The ID of one or more potential partitions to optimize. This list of partitions is used to calculate the potential affinity scores that could be attained if a Dynamic Platform Optimization operation were run to optimize this list of partitions. A range of partition IDs may be specified. A range is specified by specifying the beginning partition ID, a dash, and the ending partition ID. Both the beginning and ending partition IDs are included in the range. For example, the range 1-5 includes partitions IDs 1, 2, 3, 4, and 5. The list of partition IDs specified with this option must be comma separated and can include one or more partition IDs, one or more ranges of partition IDs, or both. You can either use this option to specify the IDs of the potential partitions to optimize, or use the -p option to specify the names of the partitions. The --id and the -p options are mutually exclusive. If neither this option nor the -p option is used to specify a list of potential partiitions to optimize, the list of potential partitions to optimize defaults to all partitions that are not specified in the list of potential partitions to exclude from the optimization. This option is only valid when -o calcscore is specified.
-x	The name of one or more potential partitions to exclude and protect from an optimization operation. This list of partitions is used to calculate the potential affinity scores that could be attained if a Dynamic Platform Optimization operation were run with this list of partitions to exclude. Multiple partition names must be comma separated. You can either use this option to specify the names of the potential partitions to exclude, or use the --xid option to specify the IDs of the partitions. The -x and the --xid options are mutually exclusive. If neither this option nor the --xid option is used to specify a list of potential partiitions to exclude, the list of potential partitions to exclude defaults to an empty list. This option is only valid when -o calcscore is specified.
--xid	The ID of one or more potential partitions to exclude and protect from an optimization operation. This list of partitions is used to calculate the potential affinity scores that could be attained if a Dynamic Platform Optimization operation were run with this list of partitions to exclude. A range of partition IDs may be specified. A range is specified by specifying the beginning partition ID, a dash, and the ending partition ID. Both the beginning and ending partition IDs are included in the range. For example, the range 8-11 includes partitions IDs 8, 9, 10, and 11. The list of partition IDs specified with this option must be comma separated and can include one or more partition IDs, one or more ranges of partition IDs, or both. You can either use this option to specify the IDs of the potential partitions to exclude, or use the -x option to specify the names of the partitions. The --xid and the -x options are mutually exclusive. If neither this option nor the -x option is used to specify a list of potential partiitions to exclude, the list of potential partitions to exclude defaults to an empty list. This option is only valid when -o calcscore is specified.
--filter	The filter to apply to the partition affinity scores to list. The filter is used to select which partitions to list. If a filter is not specified, then all partitions will be listed. The filter data consists of filter name/value pairs, which are in comma separated value (CSV) format. The filter data must be enclosed in double quotes. The format of the filter data is as follows: filter-name=value Note that the filters accept a comma separated list of values, as follows: filter-name=value,value,... When a list of values is specified, the filter name/value pair must be enclosed in double quotes. Depending on the shell being used, nested double quote characters may need to be preceded by an escape character, which is usually a ’#146; character. Multiple values can be specified for each filter. Valid filter names: lpar_names \| lpar_ids This option is only valid when listing partition affinity scores.
-F	A delimiter separated list of attribute names for the desired attribute values to be displayed. If no attribute names are specified, then values for all of the attributes will be displayed. When this option is specified, only attribute values will be displayed. No attribute names will be displayed. The attribute values displayed will be separated by the delimiter which was specified with this option. This option is useful when only attribute values are desired to be displayed, or when the values of only selected attributes are desired to be displayed.
--header	Display a header record, which is a delimiter separated list of attribute names for the attribute values that will be displayed. This header record will be the first record displayed. This option is only valid when used with the -F option.
--help	Display the help text for this command and exit.