Copyright (c) 2006, Sun Microsystems, Inc. All Rights Reserved
The contents of this file are subject to the terms of the Common Development and Distribution License (the "License"). You may not use this file except in compliance with the License.
You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE or http://www.opensolaris.org/os/licensing. See the License for the specific language governing permissions and limitations under the License.
When distributing Covered Code, include this CDDL HEADER in each file and include the License file at usr/src/OPENSOLARIS.LICENSE. If applicable, add the following below this CDDL HEADER, with the fields enclosed by brackets "[]" replaced with your own identifying information: Portions Copyright [yyyy] [name of copyright owner]
/usr/bin/pmap [-rslF] [-A address_range] [pid | core]...
/usr/bin/pmap -L [-rslF] [-A address_range] [pid] ...
/usr/bin/pmap -x [-aslF] [-A address_range] [pid | core]...
/usr/bin/pmap -S [-alF] [-A address_range] [pid | core]...
The pmap utility prints information about the address space of a process.
The following options are supported: -a
Prints anonymous and swap reservations for shared mappings.
Specifies the subrange of address space to display. address_range is specified in one of the following forms: start_addr
A single address limits the output to the segment (or the page if the -L option is present) containing that address. If the specified address corresponds to the starting address of a segment, the output always includes the whole segment even when the -L option is specified.
An address followed by comma without the end address limits the output to all segments (or pages if the -L option is present) starting from the one containing the specified address.
An address range specified by the start address and end addresses limits the output to all segments (or pages if the -L option is present) starting from the segment or page containing the start address through the segment or page containing the end address.
An address range started with comma without the start address limits the output to all segments (or pages if the -L option is present) starting from the first one present until the segment (or page if the -L option is present) containing the specified address.
Force. Grabs the target process even if another process has control. See USAGE.
Shows unresolved dynamic linker map names.
Prints lgroup containing physical memory that backs virtual memory.
Prints the process's reserved addresses.
Prints HAT page size information.
Displays swap reservation information per mapping. See USAGE for more information.
Displays additional information per mapping. See USAGE for more information.
The pmap utility prints information about the address space of a process. Process Mappings
/usr/bin/pmap [ -rslF ] [-A address_range] [ pid | core ] ...By default, pmap displays all of the mappings in the virtual address order they are mapped into the process. The mapping size, flags, and mapped object name are shown. The -A option can be used to limit the output to a specified address range. The specified addresses are rounded up or down to a segment boundary and the output includes the segments bounded by those addresses.
/usr/bin/pmap -L [ -rslF ] [-A address_range] pid ...The -L option can be used to determine the lgroup containing the physical memory backing the specified virtual memory. When used with the -A option, the specified addresses are rounded up or down to a page boundary and the output is limited to the page or pages bounded by those addresses. This can be used in conjunction with plgrp(1) to discover whether the home lgroup of a thread of interest is the same as where the memory is located and whether there should be memory locality for the thread. The lgrpinfo(1) command can also be useful with this pmap option. It displays the lgroup hierarchy, contents, and characteristics which gives more information about the lgroups that the memory is distributed across and their relationship to each other and any other lgroups of interest. In addition, the thread and memory placement can be changed by using plgrp(1), pmadvise(1), or madv.so.1(1).
/usr/bin/pmap -x [ -aslF ] [-A address_range] [ pid | core ] ...The -x option displays additional information per mapping. The size of each mapping, the amount of resident physical memory (RSS), the amount of anonymous memory, and the amount of memory locked is shown with this option. This does not include anonymous memory taken by kernel address space due to this process.
/usr/bin/pmap -S [ -alF ] [-A address_range] [ pid | core ] ...The -S option displays swap reservation information per mapping.
Caution should be exercised when using the -F flag. Imposing two controlling processes on one victim process can lead to chaos. Safety is assured only if the primary controlling process, typically a debugger, has stopped the victim process and the primary controlling process is doing nothing at the moment of application of the proc tool in question.
One line of output is printed for each mapping within the process, unless the --s or --L option is specified. With -s option, one line is printed for a contiguous mapping of each hardware translation page size. With -L option one line is printed for a contiguous mapping belonging to the same lgroup. With both -L and -s options, one line is printed for a contiguous mapping of each hardware translation page size belonging to the same lgroup. The column headings are shown in parentheses below. Virtual Address (Address)
The first column of output represents the starting virtual address of each mapping. Virtual addresses are displayed in ascending order.
The virtual size in kilobytes of each mapping.
The amount of physical memory in kilobytes that is resident for each mapping, including that which is shared with other address spaces.
The number of pages, counted by using the system page size, of anonymous memory associated with the specified mapping. Anonymous memory shared with other address spaces is not included, unless the -a option is specified. Anonymous memory is reported for the process heap, stack, for 'copy on write' pages with mappings mapped with MAP_PRIVATE (see mmap(2)).
The number of pages locked within the mapping. Typical examples are memory locked with mlock() and System V shared memory created with SHM_SHARE_MMU.
The virtual memory permissions are shown for each mapping. Valid permissions are: r:
The mapping can be read by the process.
The mapping can be written by the process.
Instructions that reside within the mapping can be executed by the process.
The mapping is shared such that changes made in the observed address space are committed to the mapped file, and are visible from all other processes sharing the mapping.
Swap space is not reserved for this mapping. Mappings created with MAP_NORESERVE and System V ISM shared memory mappings do not reserve swap space.
The data for the mapping is not present in the core file (only applicable when applied to a core file). See coreadm(8) for information on configuring core file content.
The lgroup containing the physical memory that backs the specified mapping.
A descriptive name for each mapping. The following major types of names are displayed for mappings:
A mapped file: For mappings between a process and a file, the pmap command attempts to resolve the file name for each mapping. If the file name cannot be resolved, pmap displays the major and minor number of the device containing the file, and the file system inode number of the file.
Anonymous memory: Memory not relating to any named object or file within the file system is reported as [ anon ]. The pmap command displays common names for certain known anonymous memory mappings:
[ heap ]
The mapping is the process heap.
The mapping is the main stack.
The mapping is the stack for thread n.
The mapping is used as the alternate signal stack for thread n.
System V Shared Memory: Mappings created using System V shared memory system calls are reported with the names shown below:
shmid=n:
The mapping is a System V shared memory mapping. The shared memory identifier that the mapping was created with is reported.
The mapping is an "Intimate Shared Memory" variant of System V shared memory. ISM mappings are created with the SHM_SHARE_MMU flag set, in accordance with shmat(2) (see shmop(2)).
The mapping is a pageable variant of ISM. Pageable ISM is created with the SHM_PAGEABLE flag set in accordance with shmat(2) (see shmop(2)).
Other: Mappings of other objects, including devices such as frame buffers. No mapping name is shown for other mapped objects.
The page size in kilobytes that is used for hardware address translation for this mapping. See memcntl(2) for further information.
The amount of swap space in kilobytes that is reserved for this mapping. That is, swap space that is deducted from the total available pool of reservable swap space that is displayed with the command swap -s. See swap(8).
Example 1 Displaying Process Mappings
By default, pmap prints one line for each mapping within the address space of the target process. The following example displays the address space of a typical bourne shell:
example$ pmap 102905 102905: sh 00010000 192K r-x-- /usr/bin/ksh 00040000 8K rwx-- /usr/bin/ksh 00042000 40K rwx-- [ heap ] FF180000 664K r-x-- /usr/lib/libc.so.1 FF236000 24K rwx-- /usr/lib/libc.so.1 FF23C000 8K rwx-- /usr/lib/libc.so.1 FF250000 8K rwx-- [ anon ] FF260000 16K r-x-- /usr/lib/en_US.ISO8859-1.so.2 FF272000 16K rwx-- /usr/lib/en_US.ISO8859-1.so.2 FF280000 560K r-x-- /usr/lib/libnsl.so.1 FF31C000 32K rwx-- /usr/lib/libnsl.so.1 FF324000 32K rwx-- /usr/lib/libnsl.so.1 FF340000 16K r-x-- /usr/lib/libc_psr.so.1 FF350000 16K r-x-- /usr/lib/libmp.so.2 FF364000 8K rwx-- /usr/lib/libmp.so.2 FF380000 40K r-x-- /usr/lib/libsocket.so.1 FF39A000 8K rwx-- /usr/lib/libsocket.so.1 FF3A0000 8K r-x-- /usr/lib/libdl.so.1 FF3B0000 8K rwx-- [ anon ] FF3C0000 152K r-x-- /usr/lib/ld.so.1 FF3F6000 8K rwx-- /usr/lib/ld.so.1 FFBFC000 16K rw--- [ stack ] total 1880K
Example 2 Displaying Memory Allocation and Mapping Types
The -x option can be used to provide information about the memory allocation and mapping types per mapping. The amount of resident, non-shared anonymous, and locked memory is shown for each mapping:
example$ pmap -x 102908 102908: sh Address Kbytes RSS Anon Locked Mode Mapped File 00010000 88 88 - - r-x-- sh 00036000 8 8 8 - rwx-- sh 00038000 16 16 16 - rwx-- [ heap ] FF260000 16 16 - - r-x-- en_US.ISO8859-1.so.2 FF272000 16 16 - - rwx-- en_US.ISO8859-1.so.2 FF280000 664 624 - - r-x-- libc.so.1 FF336000 32 32 8 - rwx-- libc.so.1 FF360000 16 16 - - r-x-- libc_psr.so.1 FF380000 24 24 - - r-x-- libgen.so.1 FF396000 8 8 - - rwx-- libgen.so.1 FF3A0000 8 8 - - r-x-- libdl.so.1 FF3B0000 8 8 8 - rwx-- [ anon ] FF3C0000 152 152 - - r-x-- ld.so.1 FF3F6000 8 8 8 - rwx-- ld.so.1 FFBFE000 8 8 8 - rw--- [ stack ] -------- ----- ----- ----- ------ total Kb 1072 1032 56 -
The amount of incremental memory used by each additional instance of a process can be estimated by using the resident and anonymous memory counts of each mapping.
In the above example, the bourne shell has a resident memory size of 1032Kbytes. However, a large amount of the physical memory used by the shell is shared with other instances of shell. Another identical instance of the shell shares physical memory with the other shell where possible, and allocate anonymous memory for any non-shared portion. In the above example, each additional bourne shell uses approximately 56Kbytes of additional physical memory.
A more complex example shows the output format for a process containing different mapping types. In this example, the mappings are as follows:
0001000: Executable text, mapped from 'maps' program 0002000: Executable data, mapped from 'maps' program 0002200: Program heap 0300000: A mapped file, mapped MAP_SHARED 0400000: A mapped file, mapped MAP_PRIVATE 0500000: A mapped file, mapped MAP_PRIVATE | MAP_NORESERVE 0600000: Anonymous memory, created by mapping /dev/zero 0700000: Anonymous memory, created by mapping /dev/zero with MAP_NORESERVE 0800000: A DISM shared memory mapping, created with SHM_PAGEABLE with 8MB locked via mlock(3C) 0900000: A DISM shared memory mapping, created with SHM_PAGEABLE, with 4MB of its pages touched. 0A00000: A DISM shared memory mapping, created with SHM_PAGEABLE, with none of its pages touched. 0B00000: An ISM shared memory mapping, created with SHM_SHARE_MMU
example$ pmap -x 15492 15492: ./maps Address Kbytes RSS Anon Locked Mode Mapped File 00010000 8 8 - - r-x-- maps 00020000 8 8 8 - rwx-- maps 00022000 20344 16248 16248 - rwx-- [ heap ] 03000000 1024 1024 - - rw-s- dev:0,2 ino:4628487 04000000 1024 1024 512 - rw--- dev:0,2 ino:4628487 05000000 1024 1024 512 - rw--R dev:0,2 ino:4628487 06000000 1024 1024 1024 - rw--- [ anon ] 07000000 512 512 512 - rw--R [ anon ] 08000000 8192 8192 - 8192 rwxs- [ dism shmid=0x5] 09000000 8192 4096 - - rwxs- [ dism shmid=0x4] 0A000000 8192 8192 - 8192 rwxsR [ ism shmid=0x2 ] 0B000000 8192 8192 - 8192 rwxsR [ ism shmid=0x3 ] FF280000 680 672 - - r-x-- libc.so.1 FF33A000 32 32 32 - rwx-- libc.so.1 FF390000 8 8 - - r-x-- libc_psr.so.1 FF3A0000 8 8 - - r-x-- libdl.so.1 FF3B0000 8 8 8 - rwx-- [ anon ] FF3C0000 152 152 - - r-x-- ld.so.1 FF3F6000 8 8 8 - rwx-- ld.so.1 FFBFA000 24 24 24 - rwx-- [ stack ] -------- ------- ------- ------- ------- total Kb 50464 42264 18888 16384
Example 3 Displaying Page Size Information
The -s option can be used to display the hardware translation page sizes for each portion of the address space. (See memcntl(2) for further information on illumos multiple page size support).
In the example below, we can see that the majority of the mappings are using an 8K-Byte page size, while the heap is using a 4M-Byte page size.
Notice that non-contiguous regions of resident pages of the same page size are reported as separate mappings. In the example below, the libc.so library is reported as separate mappings, since only some of the libc.so text is resident:
example$ pmap -xs 15492 15492: ./maps Address Kbytes RSS Anon Locked Pgsz Mode Mapped File 00010000 8 8 - - 8K r-x-- maps 00020000 8 8 8 - 8K rwx-- maps 00022000 3960 3960 3960 - 8K rwx-- [ heap ] 00400000 8192 8192 8192 - 4M rwx-- [ heap ] 00C00000 4096 - - - - rwx-- [ heap ] 01000000 4096 4096 4096 - 4M rwx-- [ heap ] 03000000 1024 1024 - - 8K rw-s- dev:0,2 ino:4628487 04000000 512 512 512 - 8K rw--- dev:0,2 ino:4628487 04080000 512 512 - - - rw--- dev:0,2 ino:4628487 05000000 512 512 512 - 8K rw--R dev:0,2 ino:4628487 05080000 512 512 - - - rw--R dev:0,2 ino:4628487 06000000 1024 1024 1024 - 8K rw--- [ anon ] 07000000 512 512 512 - 8K rw--R [ anon ] 08000000 8192 8192 - 8192 - rwxs- [ dism shmid=0x5 ] 09000000 4096 4096 - - 8K rwxs- [ dism shmid=0x4 ] 0A000000 4096 - - - - rwxs- [ dism shmid=0x2 ] 0B000000 8192 8192 - 8192 4M rwxsR [ ism shmid=0x3 ] FF280000 136 136 - - 8K r-x-- libc.so.1 FF2A2000 120 120 - - - r-x-- libc.so.1 FF2C0000 128 128 - - 8K r-x-- libc.so.1 FF2E0000 200 200 - - - r-x-- libc.so.1 FF312000 48 48 - - 8K r-x-- libc.so.1 FF31E000 48 40 - - - r-x-- libc.so.1 FF33A000 32 32 32 - 8K rwx-- libc.so.1 FF390000 8 8 - - 8K r-x-- libc_psr.so.1 FF3A0000 8 8 - - 8K r-x-- libdl.so.1 FF3B0000 8 8 8 - 8K rwx-- [ anon ] FF3C0000 152 152 - - 8K r-x-- ld.so.1 FF3F6000 8 8 8 - 8K rwx-- ld.so.1 FFBFA000 24 24 24 - 8K rwx-- [ stack ] -------- ------- ------- ------- ------- total Kb 50464 42264 18888 16384
Example 4 Displaying Swap Reservations
The -S option can be used to describe the swap reservations for a process. The amount of swap space reserved is displayed for each mapping within the process. Swap reservations are reported as zero for shared mappings, since they are accounted for only once system wide.
example$ pmap -S 15492 15492: ./maps Address Kbytes Swap Mode Mapped File 00010000 8 - r-x-- maps 00020000 8 8 rwx-- maps 00022000 20344 20344 rwx-- [ heap ] 03000000 1024 - rw-s- dev:0,2 ino:4628487 04000000 1024 1024 rw--- dev:0,2 ino:4628487 05000000 1024 512 rw--R dev:0,2 ino:4628487 06000000 1024 1024 rw--- [ anon ] 07000000 512 512 rw--R [ anon ] 08000000 8192 - rwxs- [ dism shmid=0x5] 09000000 8192 - rwxs- [ dism shmid=0x4] 0A000000 8192 - rwxs- [ dism shmid=0x2] 0B000000 8192 - rwxsR [ ism shmid=0x3] FF280000 680 - r-x-- libc.so.1 FF33A000 32 32 rwx-- libc.so.1 FF390000 8 - r-x-- libc_psr.so.1 FF3A0000 8 - r-x-- libdl.so.1 FF3B0000 8 8 rwx-- [ anon ] FF3C0000 152 - r-x-- ld.so.1 FF3F6000 8 8 rwx-- ld.so.1 FFBFA000 24 24 rwx-- [ stack ] -------- ------- ------- total Kb 50464 23496
The swap reservation information can be used to estimate the amount of virtual swap used by each additional process. Each process consumes virtual swap from a global virtual swap pool. Global swap reservations are reported by the 'avail' field of the swap(8) command.
Example 5 Labeling Stacks in a Multi-threaded Process
example$ pmap 121969 121969: ./stacks 00010000 8K r-x-- /tmp/stacks 00020000 8K rwx-- /tmp/stacks FE8FA000 8K rwx-R [ stack tid=11 ] FE9FA000 8K rwx-R [ stack tid=10 ] FEAFA000 8K rwx-R [ stack tid=9 ] FEBFA000 8K rwx-R [ stack tid=8 ] FECFA000 8K rwx-R [ stack tid=7 ] FEDFA000 8K rwx-R [ stack tid=6 ] FEEFA000 8K rwx-R [ stack tid=5 ] FEFFA000 8K rwx-R [ stack tid=4 ] FF0FA000 8K rwx-R [ stack tid=3 ] FF1FA000 8K rwx-R [ stack tid=2 ] FF200000 64K rw--- [ altstack tid=8 ] FF220000 64K rw--- [ altstack tid=4 ] FF240000 112K rw--- [ anon ] FF260000 16K rw--- [ anon ] FF270000 16K r-x-- /usr/platform/sun4u/lib/libc_psr.so.1 FF280000 672K r-x-- /usr/lib/libc.so.1 FF338000 24K rwx-- /usr/lib/libc.so.1 FF33E000 8K rwx-- /usr/lib/libc.so.1 FF35A000 8K rwxs- [ anon ] FF360000 104K r-x-- /usr/lib/libthread.so.1 FF38A000 8K rwx-- /usr/lib/libthread.so.1 FF38C000 8K rwx-- /usr/lib/libthread.so.1 FF3A0000 8K r-x-- /usr/lib/libdl.so.1 FF3B0000 8K rwx-- [ anon ] FF3C0000 152K r-x-- /usr/lib/ld.so.1 FF3F6000 8K rwx-- /usr/lib/ld.so.1 FFBFA000 24K rwx-- [ stack ] total 1400K
Example 6 Displaying lgroup Memory Allocation
The following example displays lgroup memory allocation by mapping:
example$ pmap -L `pgrep nscd` 100095: /usr/sbin/nscd 00010000 8K r-x-- 2 /usr/sbin/nscd 00012000 48K r-x-- 1 /usr/sbin/nscd 0002E000 8K rwx-- 2 /usr/sbin/nscd 00030000 16K rwx-- 2 [ heap ] 00034000 8K rwx-- 1 [ heap ] . . . FD80A000 24K rwx-- 2 [ anon ] FD820000 8K r-x-- 2 /lib/libmd5.so.1 FD840000 16K r-x-- 1 /lib/libmp.so.2 FD860000 8K r-x-- 2 /usr/lib/straddr.so.2 FD872000 8K rwx-- 1 /usr/lib/straddr.so.2 FD97A000 8K rw--R 1 [ stack tid=24 ] FD990000 8K r-x-- 2 /lib/nss_nis.so.1 FD992000 16K r-x-- 1 /lib/nss_nis.so.1 FD9A6000 8K rwx-- 1 /lib/nss_nis.so.1 FD9C0000 8K rwx-- 2 [ anon ] FD9D0000 8K r-x-- 2 /lib/nss_files.so.1 FD9D2000 16K r-x-- 1 /lib/nss_files.so.1 FD9E6000 8K rwx-- 2 /lib/nss_files.so.1 FDAFA000 8K rw--R 2 [ stack tid=23 ] FDBFA000 8K rw--R 1 [ stack tid=22 ] FDCFA000 8K rw--R 1 [ stack tid=21 ] FDDFA000 8K rw--R 1 [ stack tid=20 ] . . . FEFFA000 8K rw--R 1 [ stack tid=2 ] FF000000 8K rwx-- 2 [ anon ] FF004000 16K rwx-- 1 [ anon ] FF00A000 16K rwx-- 1 [ anon ] . . . FF3EE000 8K rwx-- 2 /lib/ld.so.1 FFBFE000 8K rw--- 2 [ stack ] total 2968K
The following exit values are returned: 0
Successful operation.
An error has occurred.
process files
proc tools supporting files
See attributes(7) for descriptions of the following attributes:
| ATTRIBUTE TYPE ATTRIBUTE VALUE |
| Interface Stability See below. |
The command syntax is Evolving. The -L option and the output formats are Unstable.
ldd (1), lgrpinfo (1), madv.so.1 (1), mdb (1), plgrp (1), pmadvise (1), proc (1), ps (1), memcntl (2), meminfo (2), mmap (2), shmop (2), dlopen (3C), proc (5), attributes (7), coreadm (8), prstat (8), swap (8)