vmstat Command

Purpose

Reports virtual memory statistics.

Syntax

vmstat [ -f ] [ -i ] [ -s ] [ -I[-W]] [ -t ] [ -v ] [ -h ] [ -w ] [ -l ] [-c] [ -@ wparname | ALL] [{ -p | -P } physicalvolume | ALL] ALL] [-S power] [physicalvolume] [interval] [count]

Note: Do not use the wparname parameter and the -i flag together inside workload partitions.

Description

The vmstat command reports statistics about kernel threads, virtual memory, disks, hypervisor pages, traps, and processor activity. Reports that are generated by the vmstat command can be used to balance system load activity. These system-wide statistics (among all processors) are calculated as averages for values that are expressed as percentages, and as sums otherwise. The vmstat command might return inconsistent statistics because the statistics are not read atomically.

If you run the vmstat command without flags, the report contains a summary of the virtual memory activity since system startup. If you specify the -f flag, the vmstat command reports the number of forks since system startup. The physicalvolume parameter specifies the name of the physical volume.

The interval parameter specifies the amount of time in seconds between each report. If you do not specify the interval parameter, the vmstat command generates a single report that contains statistics for the time since system startup and then exits. You can specify the count parameter only with the interval parameter. If you specify the count parameter, its value determines the number of reports that are generated and the number of seconds apart. If you specify the interval parameter without the count parameter, reports are continuously generated. Do not specify a value of zero to the count parameter.

The kernel maintains statistics for kernel threads, paging, and interrupt activity, which the vmstat command accesses by using the perfstat kernel extension. The disk input/output statistics are maintained by device drivers. For disks, the average transfer rate is determined by using the active time and number of times information is being transferred. The percent active time is computed from the amount of time the drive is busy during the report.

The vmstat command reports the number of physical processors consumed (pc), and the percentage of entitlement consumed (ec), in Micro-Partitioning® environments. These metrics display on the Micro-Partitioning environments.

The report that is generated by the vmstat command contains a system configuration row and column headings. If the -@ flag is specified, the report consists of system configuration and WPAR configuration. The system configuration row has the following values:

lcpu: Indicates the number of logical processors.
mem: Indicates the amount of memory.
tmem: Indicates the true memory size of the LPAR.
Note: This flag is available only when -c option is provided and Active Memory Expansion is enabled.
ent: Indicates the entitled capacity. Displays only when the partition is running with shared processor.
drives: Indicates the number of disks. Displays only when physical volume name is monitored.
WPARs: Indicates the number of active workload partitions. It is displayed only when the -@ flag is specified.
memlim: Indicates the limit of the memory resource of the workload partition. The limit is in megabytes (MB). This information is displayed only for the WPAR with enforced memory resource limit.
cpulim: Indicates the limit of processor resource of the workload partition in processor units. This information is displayed only for the WPAR with enforced processor resource limit.
rset: Indicates the type of the rset registry that is associated with a WPAR. The type can be regular or exclusive. This information is displayed only for the WPARs that are associated with a rset registry.
mmode: Indicates memory mode. This metric is displayed automatically in a system with Active Memory Sharing enabled. This metric is also displayed when -c option is used.
mpsz: Size of the memory pool in gigabytes. This metric is displayed only in shared-memory mode.

The column headings and their descriptions follow:

WPAR: Information about workload partitions. It displays only when the-@ flag is specified.

WPAR

Workload partition name.

Notes:

The system WPAR name indicates system-wide statistics. The global WPAR name indicates the statistics belong to Global only.
When the vmstat command is started with the -@ ALL option and the WPAR specific information is not available for a metric, then an en dash sign (-) is displayed instead of a value.
When the vmstat command is started with the -@ wparname or started inside a WPAR, if the WPAR information is not available for a metric, then that metric is marked with the at sign (@), and the system-wide value is displayed for that metric.
If a metric is not supported, then a en dash sign (-) is displayed instead of a value.

kthr: Information about kernel thread states.

r: Average number of runnable kernel threads over the sampling interval. Runnable threads consist of the threads that are ready but still waiting to run, and the threads that are already running.
b: Average number of kernel threads that are placed in the Virtual Memory Manager (VMM) wait queue (awaiting resource, awaiting input/output) over the sampling interval.

Memory: Information about the usage of virtual and real memory. Virtual pages are considered active if they are accessed. A page is 4096 bytes.

avm: Active virtual pages.
fre: Size of the free list.
Note: A large portion of real memory is used as a cache for file system data. It is not unusual for the size of the free list to remain small.

Page: Information about page faults and paging activity. This information is averaged over the interval and given in units per second.

re: Pager input/output list.
pi: Pages that are paged in from paging space.
po: Pages paged out to paging space.
fr: Pages freed (page replacement).
sr: Pages that are scanned by page-replacement algorithm.
cy: Clock cycles by page-replacement algorithm.

Faults: Trap and interrupt rate averages per second over the sampling interval.

in: Device interrupts.
sy: System calls.
cs: Kernel thread context switches.

CPU: Breakdown of percentage usage of processor time.

us: User time.
If the current physical processor consumption of the uncapped partitions exceeds the entitled capacity, the percentage becomes relative to the number of physical processor consumed (pc).
sy: System time.
If the current physical processor consumption of the uncapped partitions exceeds the entitled capacity, the percentage becomes relative to the number of physical processor consumed (pc).
id: Processor idle time.
If the current physical processor consumption of the uncapped partitions exceeds the entitled capacity, the percentage becomes relative to the number of physical processor consumed (pc).
wa: Processor idle time during which the system had outstanding disk/NFS I/O request.
If the current physical processor consumption of the uncapped partitions exceeds the entitled capacity, the percentage becomes relative to the number of physical processor consumed (pc).
pc: Number of physical processors used. Displayed only if the partition is running with shared processor.
ec: The percentage of entitled capacity that is consumed. Displayed only if the partition is running with shared processor. Because the time base over which this data is computed can vary, the entitled capacity percentage can sometimes exceed 100%. This excess is noticeable only with small sampling intervals.
rc: The percentage of processor resource that is used. This information is displayed only for the WPARs with enforced processor resource limit.

Disk: Provides the number of transfers per second to the specified physical volumes that occurred in the sample interval. The physicalvolume parameter can be used to specify one to four names. Transfer statistics are given for each specified drive in the order specified. This count represents requests to the physical device. It does not imply an amount of data that was read or written. Several logical requests can be combined into one physical request. If the physicalvolume parameter is used, the physical volume names are printed at the beginning of command execution.

If the -I flag is specified, an I/O oriented view is presented with the following column changes.

kthr

The p column is displayed in addition to the r and b columns.

p

Average number of threads waiting for I/O messages from raw devices. Raw devices are the devices that are directly attached to the system.

If the -W flag is specified along with the -I flag, an additional w column is also displayed along with the r, b, and p flags.

w

Number of threads per second of time that are waiting for the file system direct I/O event to occur. These events include the following types:

Asynchronous I/O (AIO)
Buffer cache subsystem
Concurrent I/O (CIO)
File system direct I/O
NFS subsystem
A thread is waiting for an action from the virtual memory manager (VMM) waiting list.

page

New fi and fo columns are displayed instead of the re and cy columns.

fi: File page-ins per second.
fo: File page-outs per second.

If the -c flag is specified, Active Memory Expansion view is presented with the following column changes.

memory

The columns csz, cfr, and dxm are displayed besides columns avm and fre.

csz: Current compressed pool size, in 4K page units.
cfr: Free pages available in compressed pool, in 4K page units.
dxm: Deficit in Expanded Memory Size, in 4K page units.

page

New columns ci and co are displayed instead of re and cy columns.

ci: Number of page-ins per second from compressed pool.
co: Number of page-outs per second to compressed pool.

If while the vmstat command is running, there is a change in system configuration that affects the output, vmstat prints a warning message about the configuration change. It then continues the output after printing the updated system configuration information and the header.

If the -l flag is specified, an additional "large-page" section is displayed with the following columns:

alp: Indicates the number of large pages currently in use.
flp: Indicates the number of large pages on the large page freelist.

If the -p option is specified, additional lines of VMM statistics are displayed for the specified page sizes. With -I and -t options, the -p option produces an additional line for the specified page size. This line contains the following VMM statistics relevant to the specified page size:

avm
fre
re
fi
fo
pi
po
ci
co
fr
sr
cy

Notes:

The display of the re, fi, fo, and cy options are affected by the -I option.
The display of the re, ci, co, and cy options are affected by the -c option.
If there is no resource control, then the avm and fre options are system-wide. Therefore, with the -@ option set, both the avm and fre options will be marked with the at sign (@).

These VMM statistics are preceded by a psz column and followed by an siz column. The description of these two columns follows:

psz: Page size (for example, 4 KB, 64 KB).
siz: Number of frames of the specified page size that exist on the system.

With the -s option, the -p option produces a separate stanza of output that contains only the statistics relevant to the specified page size. This additional stanza is preceded by a page size header.

The -P option produces the following report for the specified page size:

pgsz: Indicates the page size (for example, 4 KB, 64 KB).
Memory: Indicates the memory statistics for the specified page sizes.
siz: The number of frames of the specified page size that exist on the system.
avm: Active virtual pages applicable to the specified page size.
fre: Size of the free list for the specified page size.
Page: Indicates the relevant page faults and paging activity for the specified page size. The page-related columns re, pi, po, fr, sr, cy, fi, fo, ci, and co are also applicable to this report.

Flags

Note: If the -f (or -s) flag is entered on the command line, then the system accepts the -f (or -s) flag and ignores other flags. If both the -f and -s flags are specified, the system accepts only the first flag and ignore the second flag.

Item	Description
-@ wparname	Reports the Virtual Memory activity of a workload partition: The -@ ALL option indicates that the report pertains to the system and global environment, in addition to all of the workload partitions in the system. Note: The values that are system-wide statistics are marked with dash sign (-) against the WPAR section. The -@ wparname flag indicates that the activity is only for that workload partition. In a workload partition, if you specify the -@ flag, system-wide statistics and workload partition statistics are displayed. The system-wide statistics are marked with the at sign (@). Note: Do not use the -@ flag with any combination of the -i flag.
-c	Displays memory compression statistics with the new columns of output, csz, cfr, and dxm under the heading memory, and columns ci and co under the heading page instead of the columns re and cy. Note: This option is available only when Active Memory Expansion is enabled.
-f	Reports the number of forks since system startup.
-i	Displays the number of interrupts that are taken by each device since system startup. Note: The -I, -t, -w, and -l flags are ignored when they are specified with the -i flag.
-I	Displays I/O oriented view with the new columns of output, p under heading `kthr`,and columns fi and fo under heading page instead of the columns re and cy in the page heading.
-l	Displays an extra "large-page" section with the `alp` and `flp` columns.
-p pagesize	Appends the VMM statistics for the specified page size to the regular vmstat output.
-P pagesize	Displays only the VMM statistics, which are relevant for the specified page size.
-s	Writes to standard output the contents of the sum structure, which contains an absolute count of paging events since system initialization. The -s flag can only be used with the -v flag. These events are described as follows: address translation faults Incremented for each occurrence of an address translation page fault. I/O may or may not be required to resolve the page fault. Storage protection page faults (lock misses) are not included in this count.
-s	backtracks Incremented for each page fault that occurs while resolving a previous page fault. (The new page fault must be resolved first and then initial page faults can be backtracked.) CPU context switches Incremented for each processor context switch (dispatch of a new process). decrementer interrupts Incremented on each decrementer interrupt. device interrupts Incremented on each hardware interrupt. executable-filled page faults Incremented for each instruction page fault. extend XPT waits Incremented each time that a process is waited by VMM due to a commit in progress for the segments accessed. free frame waits Incremented each time that a process requests a page frame. The free list is empty, and the process is forced to wait while the free list is replenished. iodones Incremented at the completion of each VMM I/O request. mpc send interrupts Incremented on each mpc send interrupt. mpc receive interrupts Incremented on each mpc receive interrupt. page ins Incremented for each page read in by the virtual memory manager. The count is incremented for page ins from page space and file space. Along with the page-out statistic, this value represents the total amount of real I/O initiated by the virtual memory manager. page outs Incremented for each page that is written out by the virtual memory manager. The count is incremented for page outs to page space and for page outs to file space. Along with the page in statistic, this statistic represents the total amount of real I/O initiated by the virtual memory manager. paging space page ins Incremented for VMM initiated page ins from paging space only. paging space page outs Incremented for VMM initiated page outs to paging space only. pages examined by the clock VMM uses a clock-algorithm to implement a pseudo least recently used (lru) page replacement scheme. Pages are aged by being examined by the clock. This count is incremented for each page examined by the clock. pages freed by the clock Incremented for each page the clock algorithm selects to free from real memory. pending I/O waits Incremented each time that a process is waited by VMM for a page-in I/O to complete.
-s	phantom interrupts Incremented on each phantom interrupt revolutions of the clock hand Incremented for each VMM clock revolution (that is after each complete scan of memory). start I/Os Incremented for each read or write I/O request that is initiated by VMM. syscalls Incremented for each system call. total reclaims Incremented when an address translation fault can be satisfied without initiating a new I/O request. This can occur if the page has been previously requested by VMM, but the I/O has not yet completed; or if the page was pre-fetched by VMM's read-ahead algorithm, but was hidden from the faulting segment; or if the page has been put on the free list and has not yet been reused. traps Not maintained by the operating system. zero-filled page faults Incremented if the page fault is to working storage and can be satisfied by assigning a frame and zero-filling it. When the -c flag is specified along with the -s flag, the following additional metrics are displayed. compressed pool page ins Number of page-ins from Compressed Pool since system boot. compressed pool page outs Number of page-outs to Compressed Pool since system boot.
-s	When used with the -p pagesize option, the -s option appends the sum structure for the specified page size to the system-wide sum structure. This additional stanza is preceded by a page size header (for example, 4K pages). The following details are not be displayed in this pagesize-based stanza as these statistics are not related to page sizes: Processor context switches Device interrupts Software interrupts Decrementer interrupts MPC-sent interrupts MPC-received interrupts Phantom interrupts Traps Syscalls Notes: When the -s flag is used with the -@ ALL option, the system-wide statistics are repeated in the workload partition section. When the -s flag is used with the wparname option, all metrics are reported and the system-wide statistics are marked with the at sign (@). When the -s flag is used with the -l flag, the vmstat command displays the following metric: large-page hi water count Specifies the maximum value of the large-page inuse count.
-S power	Multiplies the statistics of the processor with a value of 10^power. The default value of the power is 0. The following statistics are scaled: us sy id wa pc ec Notes: Do not use the -S flag with the -f, -s, -i, -v, or -p flags. When the -S flag is specified, the us, sy, id, and wa statistics change. By default, the us, sy, id, and wa statistics are relative to the processor consumption of WPAR. When the -S flag is specified with a value of power that is not equal to zero, these statistics will be relative to system-wide processor consumption. The value of power for -S flag can be only between 0 and 3.
-t	Prints the time-stamp next to each line of output of vmstat. The time-stamp is displayed in the `HH:MM:SS` format. Note: Time stamp is not be printed if -f, -s, or -i flags are specified.
-v	Writes to standard output various statistics maintained by the Virtual Memory Manager. The -v flag can only be used with the -s and the -h flags. If you specify the -v flag, the following statistics are displayed: compressed percentage Percentage of memory used by compressed pages. client filesystem I/Os blocked with no fsbuf Number of client filesystem I/O requests blocked because no fsbuf was available. NFS (Network File System) and VxFS (Veritas) are client filesystems. Fsbuf are pinned memory buffers used to hold I/O requests in the filesystem layer. client pages Number of client pages. compressed pages Number of compressed memory pages. external pager filesystem I/Os blocked with no fsbuf Number of external pager client filesystem I/O requests blocked because no fsbuf was available. JFS2 is an external pager client filesystem. Fsbuf are pinned memory buffers used to hold I/O requests in the filesystem layer. file pages Number of 4 KB pages that are currently used by the file cache. free pages Number of free 4 KB pages. filesystem I/Os blocked with no fsbuf Number of filesystem I/O requests blocked because no fsbuf was available. Fsbuf are pinned memory buffers used to hold I/O requests in the filesystem layer. lruable pages Number of 4 KB pages that are considered for replacement. This number excludes the pages that are used for VMM internal pages, and the pages that are used for the pinned part of the kernel text. maxclient percentage Tuning parameter (managed using vmo) specifying the maximum percentage of memory, which can be used for client pages. maxperm percentage Tuning parameter (managed using vmo) in percentage of real memory. maxpin percentage Tuning parameter (managed using vmo) specifying the percentage of real memory which can be pinned. memory pages Size of real memory in number of 4 KB pages. memory pools Tuning parameter (managed using vmo) specifying the number of memory pools. minperm percentage Tuning parameter (managed using vmo) in percentage of real memory. numclient percentage Percentage of memory that is occupied by client pages.
-v	(Statistics that are displayed by -v, continued): numperm percentage Percentage of memory that is currently used by the file cache. paging space I/Os blocked with no psbuf Number of paging space I/O requests that are blocked because the psbuf space is not available. The psbufs space is pinned memory buffers that are used to hold I/O requests at the virtual memory manager layer. pending disk I/Os blocked with no pbuf Number of pending disk I/O requests blocked because no pbuf was available. Pbufs are pinned memory buffers used to hold I/O requests at the logical volume manager layer pinned pages Number of pinned 4 KB pages. Note: When the kernel locking feature (`vmm_klock_mode` parameter) is enabled, the pinned pages include the kernel locking (klocked) pages. For more information about the kernel locking feature, enter the following command: `vmo -h vmm_klock_mode`. remote pageouts scheduled Number of pageouts scheduled for client file systems. If you specify the -h flag with the -v flag, the following additional metrics are displayed: Time resolving virtualized partition memory page faults The total time that the virtual partition is blocked to wait for the resolution of its memory page fault. The time is measured in seconds, with millisecond granularity. Virtualized partition memory page faults The total number of virtual partition memory page faults that are recorded for the virtualized partition. Number of 4 KB page frames loaned The number of the 4 KB pages of partition's memory loaned to the hypervisor. Percentage of partition memory loaned The percentage of the partition's memory loaned to the hypervisor. Notes: When the -v flag is used with the -@ ALL option, the system-wide statistics are not repeated in the workload partition section. When the -s flag is used with the wparname option, all metrics are reported and the system-wide statistics are marked with the at sign (@). When the -c flag is specified along with the -v flag, the following additional metrics are displayed: Compressed Pool Size Size of Compressed Pool, in 4K page unit. percentage of true memory that is used for compressed pool Percentage of unexpanded memory that is used for compressed pool. free pages in compressed pool (4K pages) Number of free pages in compressed pool, in 4K page unit. target memory expansion factor Target memory expansion factor that is configured for the LPAR. achieved memory expansion factor Current memory expansion factor achieved.
-h	Displays the hypv-page section that includes the hypervisor page information. The hypv-page section contains the following metrics: hpi Number of hypervisor page-in per second. hpit Average time that is spent in milliseconds per hypervisor page-in. pmem Amount of physical memory that is backing the logical memory of partitions. The value is measured in gigabytes. If you specify the -h flag with the -v flag, the following metrics are displayed in addition to the metrics that are displayed using the -v flag: Time resolving virtualized partition memory page faults The total time that the virtual partition is blocked to wait for the resolution of its memory page fault. The time is measured in seconds, with millisecond granularity. Virtualized partition memory page faults The total number of virtual partition memory page faults that are recorded for the virtualized partition. Number of 4 KB page frames loaned The number of the 4 KB pages of the memory that is loaned to the hypervisor in the partition. Percentage of partition memory loaned The percentage of the memory loaned to the hypervisor in the partition.
-w	Displays the report in wide mode.
-W	Displays an extra field w in the kthr section. This option is allowed only with -I flag.

Notes:

If Active Memory Expansion is enabled, the vmstat reports memory statistics in the expanded view. However, if the environment variable AME_MEMVIEW is set to TRUE, the memory statistics represent the true view.
The AME_MEMVIEW environment variable has no impact on memory statistics reported using the -c option.

Examples

To display a summary of the statistics since boot, enter the following command:
```
vmstat
```
To display five summaries at 2-second intervals, enter the following command:
```
vmstat 2 5
```
To display a summary of the statistics since boot including statistics for logical disks scdisk13 and scdisk14, enter the following command:
```
vmstat scdisk13 scdisk14
```
To display fork statistics, enter the following command:
```
vmstat -f
```
To display the count of various events, enter the following command:
```
vmstat -s
```
To display time-stamp next to each column of output of vmstat, enter the following command:
```
vmstat -t
```
To display the I/O oriented view with an alternative set of columns, enter the following command:
```
vmstat -I
```
To display all the VMM statistics available, enter the following command:
```
vmstat -vs
```
To display the large-page section with the alp and flp columns at 8-second intervals, enter the following command:
```
vmstat -l 8
```
To display the VMM statistics specific to a particular page size (in the example, 4 KB), enter the following command:
```
vmstat -p 4K
```
To display the VMM statistics for all page sizes that are supported on the system, enter the following command:
```
vmstat -p ALL
```
Or enter the following command:
```
vmstat -p all
```
To display only the VMM statistics for a particular page size (in this example, 4 KB), enter the following command:
```
vmstat -P 4K
```
To display only the per-page breakdown of VMM statistics for all supported page sizes, enter the following command:
```
vmstat -P ALL
```
Or enter the following command:
```
vmstat -P all
```
To display a summary of the statistics for all of the workload partitions after boot, enter the following command:
```
vmstat -@ ALL
```
To display all of the VMM statistics available for all of the workload partitions, enter the following command:
```
vmstat –vs -@ ALL
```
To display both WPAR and system-wide VMM statistics from a workload partition, enter the following command:
```
vmstat -@
```
To multiply the processor values with 10 and display the results, enter the following command:
```
vmstat -S 1
```
To display the statistics for the hypervisor page, enter the following command:
```
vmstat –h
```
To display the information about pages that are loaned to the hypervisor, enter the following command:
```
vmstat -vh
```
To display memory compression statistics (in an LPAR with Active Memory Expansion enabled), enter the following command:
```
vmstat -c
```
To display memory compression statistics specific to per-pagesize (in an LPAR with Active Memory Expansion enabled), enter the following command:
```
vmstat –c –P ALL
```
To append memory compression information to the statistics displayed by -soption (in an LPAR with Active Memory Expansion enabled), enter the following command:
```
vmstat –s -c
```
To append memory compression information to the statistics displayed by -voption (in an LPAR with Active Memory Expansion enabled), enter the following command:
```
vmstat –v -c
```

Files

Item	Description
/usr/bin/vmstat	Contains the vmstat command.