1 .. SPDX-License-Identifier: GPL-2.0 1 .. SPDX-License-Identifier: GPL-2.0
2 2
3 ==================== 3 ====================
4 The /proc Filesystem 4 The /proc Filesystem
5 ==================== 5 ====================
6 6
7 ===================== ======================= 7 ===================== ======================================= ================
8 /proc/sys Terrehon Bowden <terreho 8 /proc/sys Terrehon Bowden <terrehon@pacbell.net>, October 7 1999
9 Bodo Bauer <bb@ricochet. 9 Bodo Bauer <bb@ricochet.net>
10 2.4.x update Jorge Nerin <comandante@ 10 2.4.x update Jorge Nerin <comandante@zaralinux.com> November 14 2000
11 move /proc/sys Shen Feng <shen@cn.fujit 11 move /proc/sys Shen Feng <shen@cn.fujitsu.com> April 1 2009
12 fixes/update part 1.1 Stefani Seibold <stefani 12 fixes/update part 1.1 Stefani Seibold <stefani@seibold.net> June 9 2009
13 ===================== ======================= 13 ===================== ======================================= ================
14 14
15 15
16 16
17 .. Table of Contents 17 .. Table of Contents
18 18
19 0 Preface 19 0 Preface
20 0.1 Introduction/Credits 20 0.1 Introduction/Credits
21 0.2 Legal Stuff 21 0.2 Legal Stuff
22 22
23 1 Collecting System Information 23 1 Collecting System Information
24 1.1 Process-Specific Subdirectories 24 1.1 Process-Specific Subdirectories
25 1.2 Kernel data 25 1.2 Kernel data
26 1.3 IDE devices in /proc/ide 26 1.3 IDE devices in /proc/ide
27 1.4 Networking info in /proc/net 27 1.4 Networking info in /proc/net
28 1.5 SCSI info 28 1.5 SCSI info
29 1.6 Parallel port info in /proc/parport 29 1.6 Parallel port info in /proc/parport
30 1.7 TTY info in /proc/tty 30 1.7 TTY info in /proc/tty
31 1.8 Miscellaneous kernel statistics in /pr 31 1.8 Miscellaneous kernel statistics in /proc/stat
32 1.9 Ext4 file system parameters 32 1.9 Ext4 file system parameters
33 33
34 2 Modifying System Parameters 34 2 Modifying System Parameters
35 35
36 3 Per-Process Parameters 36 3 Per-Process Parameters
37 3.1 /proc/<pid>/oom_adj & /proc/<pid>/oom_ 37 3.1 /proc/<pid>/oom_adj & /proc/<pid>/oom_score_adj - Adjust the oom-killer
38 38 score
39 3.2 /proc/<pid>/oom_score - Display curren 39 3.2 /proc/<pid>/oom_score - Display current oom-killer score
40 3.3 /proc/<pid>/io - Display the IO accoun 40 3.3 /proc/<pid>/io - Display the IO accounting fields
41 3.4 /proc/<pid>/coredump_filter - Core dum 41 3.4 /proc/<pid>/coredump_filter - Core dump filtering settings
42 3.5 /proc/<pid>/mountinfo - Information ab 42 3.5 /proc/<pid>/mountinfo - Information about mounts
43 3.6 /proc/<pid>/comm & /proc/<pid>/task/< 43 3.6 /proc/<pid>/comm & /proc/<pid>/task/<tid>/comm
44 3.7 /proc/<pid>/task/<tid>/children - Info 44 3.7 /proc/<pid>/task/<tid>/children - Information about task children
45 3.8 /proc/<pid>/fdinfo/<fd> - Information 45 3.8 /proc/<pid>/fdinfo/<fd> - Information about opened file
46 3.9 /proc/<pid>/map_files - Information ab 46 3.9 /proc/<pid>/map_files - Information about memory mapped files
47 3.10 /proc/<pid>/timerslack_ns - Task timer 47 3.10 /proc/<pid>/timerslack_ns - Task timerslack value
48 3.11 /proc/<pid>/patch_state - Livepatch pa 48 3.11 /proc/<pid>/patch_state - Livepatch patch operation state
49 3.12 /proc/<pid>/arch_status - Task archite 49 3.12 /proc/<pid>/arch_status - Task architecture specific information
50 3.13 /proc/<pid>/fd - List of symlinks to o 50 3.13 /proc/<pid>/fd - List of symlinks to open files
51 51
52 4 Configuring procfs 52 4 Configuring procfs
53 4.1 Mount options 53 4.1 Mount options
54 54
55 5 Filesystem behavior 55 5 Filesystem behavior
56 56
57 Preface 57 Preface
58 ======= 58 =======
59 59
60 0.1 Introduction/Credits 60 0.1 Introduction/Credits
61 ------------------------ 61 ------------------------
62 62
63 This documentation is part of a soon (or so 63 This documentation is part of a soon (or so we hope) to be released book on
64 the SuSE Linux distribution. As there is no 64 the SuSE Linux distribution. As there is no complete documentation for the
65 /proc file system and we've used many freely 65 /proc file system and we've used many freely available sources to write these
66 chapters, it seems only fair to give the wor 66 chapters, it seems only fair to give the work back to the Linux community.
67 This work is based on the 2.2.* kernel versi 67 This work is based on the 2.2.* kernel version and the upcoming 2.4.*. I'm
68 afraid it's still far from complete, but we h 68 afraid it's still far from complete, but we hope it will be useful. As far as
69 we know, it is the first 'all-in-one' document 69 we know, it is the first 'all-in-one' document about the /proc file system. It
70 is focused on the Intel x86 hardware, so if 70 is focused on the Intel x86 hardware, so if you are looking for PPC, ARM,
71 SPARC, AXP, etc., features, you probably won' 71 SPARC, AXP, etc., features, you probably won't find what you are looking for.
72 It also only covers IPv4 networking, not IPv6 72 It also only covers IPv4 networking, not IPv6 nor other protocols - sorry. But
73 additions and patches are welcome and will b 73 additions and patches are welcome and will be added to this document if you
74 mail them to Bodo. 74 mail them to Bodo.
75 75
76 We'd like to thank Alan Cox, Rik van Riel, a 76 We'd like to thank Alan Cox, Rik van Riel, and Alexey Kuznetsov and a lot of
77 other people for help compiling this documenta 77 other people for help compiling this documentation. We'd also like to extend a
78 special thank you to Andi Kleen for documenta 78 special thank you to Andi Kleen for documentation, which we relied on heavily
79 to create this document, as well as the add 79 to create this document, as well as the additional information he provided.
80 Thanks to everybody else who contributed so 80 Thanks to everybody else who contributed source or docs to the Linux kernel
81 and helped create a great piece of software... 81 and helped create a great piece of software... :)
82 82
83 If you have any comments, corrections or add 83 If you have any comments, corrections or additions, please don't hesitate to
84 contact Bodo Bauer at bb@ricochet.net. We' 84 contact Bodo Bauer at bb@ricochet.net. We'll be happy to add them to this
85 document. 85 document.
86 86
87 The latest version of this document 87 The latest version of this document is available online at
88 https://www.kernel.org/doc/html/latest/filesys 88 https://www.kernel.org/doc/html/latest/filesystems/proc.html
89 89
90 If the above direction does not works for 90 If the above direction does not works for you, you could try the kernel
91 mailing list at linux-kernel@vger.kernel.or 91 mailing list at linux-kernel@vger.kernel.org and/or try to reach me at
92 comandante@zaralinux.com. 92 comandante@zaralinux.com.
93 93
94 0.2 Legal Stuff 94 0.2 Legal Stuff
95 --------------- 95 ---------------
96 96
97 We don't guarantee the correctness of this 97 We don't guarantee the correctness of this document, and if you come to us
98 complaining about how you screwed up your 98 complaining about how you screwed up your system because of incorrect
99 documentation, we won't feel responsible... 99 documentation, we won't feel responsible...
100 100
101 Chapter 1: Collecting System Information 101 Chapter 1: Collecting System Information
102 ======================================== 102 ========================================
103 103
104 In This Chapter 104 In This Chapter
105 --------------- 105 ---------------
106 * Investigating the properties of the pse 106 * Investigating the properties of the pseudo file system /proc and its
107 ability to provide information on the runnin 107 ability to provide information on the running Linux system
108 * Examining /proc's structure 108 * Examining /proc's structure
109 * Uncovering various information about the 109 * Uncovering various information about the kernel and the processes running
110 on the system 110 on the system
111 111
112 ---------------------------------------------- 112 ------------------------------------------------------------------------------
113 113
114 The proc file system acts as an interface to 114 The proc file system acts as an interface to internal data structures in the
115 kernel. It can be used to obtain informatio 115 kernel. It can be used to obtain information about the system and to change
116 certain kernel parameters at runtime (sysctl). 116 certain kernel parameters at runtime (sysctl).
117 117
118 First, we'll take a look at the read-only 118 First, we'll take a look at the read-only parts of /proc. In Chapter 2, we
119 show you how you can use /proc/sys to change s 119 show you how you can use /proc/sys to change settings.
120 120
121 1.1 Process-Specific Subdirectories 121 1.1 Process-Specific Subdirectories
122 ----------------------------------- 122 -----------------------------------
123 123
124 The directory /proc contains (among other t 124 The directory /proc contains (among other things) one subdirectory for each
125 process running on the system, which is named 125 process running on the system, which is named after the process ID (PID).
126 126
127 The link 'self' points to the process readi 127 The link 'self' points to the process reading the file system. Each process
128 subdirectory has the entries listed in Table 1 128 subdirectory has the entries listed in Table 1-1.
129 129
130 Note that an open file descriptor to /proc/<pi 130 Note that an open file descriptor to /proc/<pid> or to any of its
131 contained files or subdirectories does not pre 131 contained files or subdirectories does not prevent <pid> being reused
132 for some other process in the event that <pid> 132 for some other process in the event that <pid> exits. Operations on
133 open /proc/<pid> file descriptors correspondin 133 open /proc/<pid> file descriptors corresponding to dead processes
134 never act on any new process that the kernel m 134 never act on any new process that the kernel may, through chance, have
135 also assigned the process ID <pid>. Instead, o 135 also assigned the process ID <pid>. Instead, operations on these FDs
136 usually fail with ESRCH. 136 usually fail with ESRCH.
137 137
138 .. table:: Table 1-1: Process specific entries 138 .. table:: Table 1-1: Process specific entries in /proc
139 139
140 ============= ============================== 140 ============= ===============================================================
141 File Content 141 File Content
142 ============= ============================== 142 ============= ===============================================================
143 clear_refs Clears page referenced bits sh 143 clear_refs Clears page referenced bits shown in smaps output
144 cmdline Command line arguments 144 cmdline Command line arguments
145 cpu Current and last cpu in which 145 cpu Current and last cpu in which it was executed (2.4)(smp)
146 cwd Link to the current working di 146 cwd Link to the current working directory
147 environ Values of environment variable 147 environ Values of environment variables
148 exe Link to the executable of this 148 exe Link to the executable of this process
149 fd Directory, which contains all 149 fd Directory, which contains all file descriptors
150 maps Memory maps to executables and 150 maps Memory maps to executables and library files (2.4)
151 mem Memory held by this process 151 mem Memory held by this process
152 root Link to the root directory of 152 root Link to the root directory of this process
153 stat Process status 153 stat Process status
154 statm Process memory status informat 154 statm Process memory status information
155 status Process status in human readab 155 status Process status in human readable form
156 wchan Present with CONFIG_KALLSYMS=y 156 wchan Present with CONFIG_KALLSYMS=y: it shows the kernel function
157 symbol the task is blocked in 157 symbol the task is blocked in - or "0" if not blocked.
158 pagemap Page table 158 pagemap Page table
159 stack Report full stack trace, enabl 159 stack Report full stack trace, enable via CONFIG_STACKTRACE
160 smaps An extension based on maps, sh 160 smaps An extension based on maps, showing the memory consumption of
161 each mapping and flags associa 161 each mapping and flags associated with it
162 smaps_rollup Accumulated smaps stats for al 162 smaps_rollup Accumulated smaps stats for all mappings of the process. This
163 can be derived from smaps, but 163 can be derived from smaps, but is faster and more convenient
164 numa_maps An extension based on maps, sh 164 numa_maps An extension based on maps, showing the memory locality and
165 binding policy as well as mem 165 binding policy as well as mem usage (in pages) of each mapping.
166 ============= ============================== 166 ============= ===============================================================
167 167
168 For example, to get the status information of 168 For example, to get the status information of a process, all you have to do is
169 read the file /proc/PID/status:: 169 read the file /proc/PID/status::
170 170
171 >cat /proc/self/status 171 >cat /proc/self/status
172 Name: cat 172 Name: cat
173 State: R (running) 173 State: R (running)
174 Tgid: 5452 174 Tgid: 5452
175 Pid: 5452 175 Pid: 5452
176 PPid: 743 176 PPid: 743
177 TracerPid: 0 177 TracerPid: 0 (2.4)
178 Uid: 501 501 501 501 178 Uid: 501 501 501 501
179 Gid: 100 100 100 100 179 Gid: 100 100 100 100
180 FDSize: 256 180 FDSize: 256
181 Groups: 100 14 16 181 Groups: 100 14 16
182 Kthread: 0 182 Kthread: 0
183 VmPeak: 5004 kB 183 VmPeak: 5004 kB
184 VmSize: 5004 kB 184 VmSize: 5004 kB
185 VmLck: 0 kB 185 VmLck: 0 kB
186 VmHWM: 476 kB 186 VmHWM: 476 kB
187 VmRSS: 476 kB 187 VmRSS: 476 kB
188 RssAnon: 352 kB 188 RssAnon: 352 kB
189 RssFile: 120 kB 189 RssFile: 120 kB
190 RssShmem: 4 kB 190 RssShmem: 4 kB
191 VmData: 156 kB 191 VmData: 156 kB
192 VmStk: 88 kB 192 VmStk: 88 kB
193 VmExe: 68 kB 193 VmExe: 68 kB
194 VmLib: 1412 kB 194 VmLib: 1412 kB
195 VmPTE: 20 kb 195 VmPTE: 20 kb
196 VmSwap: 0 kB 196 VmSwap: 0 kB
197 HugetlbPages: 0 kB 197 HugetlbPages: 0 kB
198 CoreDumping: 0 198 CoreDumping: 0
199 THP_enabled: 1 199 THP_enabled: 1
200 Threads: 1 200 Threads: 1
201 SigQ: 0/28578 201 SigQ: 0/28578
202 SigPnd: 0000000000000000 202 SigPnd: 0000000000000000
203 ShdPnd: 0000000000000000 203 ShdPnd: 0000000000000000
204 SigBlk: 0000000000000000 204 SigBlk: 0000000000000000
205 SigIgn: 0000000000000000 205 SigIgn: 0000000000000000
206 SigCgt: 0000000000000000 206 SigCgt: 0000000000000000
207 CapInh: 00000000fffffeff 207 CapInh: 00000000fffffeff
208 CapPrm: 0000000000000000 208 CapPrm: 0000000000000000
209 CapEff: 0000000000000000 209 CapEff: 0000000000000000
210 CapBnd: ffffffffffffffff 210 CapBnd: ffffffffffffffff
211 CapAmb: 0000000000000000 211 CapAmb: 0000000000000000
212 NoNewPrivs: 0 212 NoNewPrivs: 0
213 Seccomp: 0 213 Seccomp: 0
214 Speculation_Store_Bypass: thread vulne 214 Speculation_Store_Bypass: thread vulnerable
215 SpeculationIndirectBranch: conditional 215 SpeculationIndirectBranch: conditional enabled
216 voluntary_ctxt_switches: 0 216 voluntary_ctxt_switches: 0
217 nonvoluntary_ctxt_switches: 1 217 nonvoluntary_ctxt_switches: 1
218 218
219 This shows you nearly the same information you 219 This shows you nearly the same information you would get if you viewed it with
220 the ps command. In fact, ps uses the pr 220 the ps command. In fact, ps uses the proc file system to obtain its
221 information. But you get a more detailed vie 221 information. But you get a more detailed view of the process by reading the
222 file /proc/PID/status. It fields are described 222 file /proc/PID/status. It fields are described in table 1-2.
223 223
224 The statm file contains more detailed in 224 The statm file contains more detailed information about the process
225 memory usage. Its seven fields are explained i 225 memory usage. Its seven fields are explained in Table 1-3. The stat file
226 contains detailed information about the proces 226 contains detailed information about the process itself. Its fields are
227 explained in Table 1-4. 227 explained in Table 1-4.
228 228
229 (for SMP CONFIG users) 229 (for SMP CONFIG users)
230 230
231 For making accounting scalable, RSS related in 231 For making accounting scalable, RSS related information are handled in an
232 asynchronous manner and the value may not be v 232 asynchronous manner and the value may not be very precise. To see a precise
233 snapshot of a moment, you can see /proc/<pid>/ 233 snapshot of a moment, you can see /proc/<pid>/smaps file and scan page table.
234 It's slow but very precise. 234 It's slow but very precise.
235 235
236 .. table:: Table 1-2: Contents of the status f 236 .. table:: Table 1-2: Contents of the status fields (as of 4.19)
237 237
238 ========================== ================= 238 ========================== ===================================================
239 Field Content 239 Field Content
240 ========================== ================= 240 ========================== ===================================================
241 Name filename of the e 241 Name filename of the executable
242 Umask file mode creatio 242 Umask file mode creation mask
243 State state (R is runni 243 State state (R is running, S is sleeping, D is sleeping
244 in an uninterrupt 244 in an uninterruptible wait, Z is zombie,
245 T is traced or st 245 T is traced or stopped)
246 Tgid thread group ID 246 Tgid thread group ID
247 Ngid NUMA group ID (0 247 Ngid NUMA group ID (0 if none)
248 Pid process id 248 Pid process id
249 PPid process id of the 249 PPid process id of the parent process
250 TracerPid PID of process tr 250 TracerPid PID of process tracing this process (0 if not, or
251 the tracer is out 251 the tracer is outside of the current pid namespace)
252 Uid Real, effective, 252 Uid Real, effective, saved set, and file system UIDs
253 Gid Real, effective, 253 Gid Real, effective, saved set, and file system GIDs
254 FDSize number of file de 254 FDSize number of file descriptor slots currently allocated
255 Groups supplementary gro 255 Groups supplementary group list
256 NStgid descendant namesp 256 NStgid descendant namespace thread group ID hierarchy
257 NSpid descendant namesp 257 NSpid descendant namespace process ID hierarchy
258 NSpgid descendant namesp 258 NSpgid descendant namespace process group ID hierarchy
259 NSsid descendant namesp 259 NSsid descendant namespace session ID hierarchy
260 Kthread kernel thread fla 260 Kthread kernel thread flag, 1 is yes, 0 is no
261 VmPeak peak virtual memo 261 VmPeak peak virtual memory size
262 VmSize total program siz 262 VmSize total program size
263 VmLck locked memory siz 263 VmLck locked memory size
264 VmPin pinned memory siz 264 VmPin pinned memory size
265 VmHWM peak resident set 265 VmHWM peak resident set size ("high water mark")
266 VmRSS size of memory po 266 VmRSS size of memory portions. It contains the three
267 following parts 267 following parts
268 (VmRSS = RssAnon 268 (VmRSS = RssAnon + RssFile + RssShmem)
269 RssAnon size of resident 269 RssAnon size of resident anonymous memory
270 RssFile size of resident 270 RssFile size of resident file mappings
271 RssShmem size of resident 271 RssShmem size of resident shmem memory (includes SysV shm,
272 mapping of tmpfs 272 mapping of tmpfs and shared anonymous mappings)
273 VmData size of private d 273 VmData size of private data segments
274 VmStk size of stack seg 274 VmStk size of stack segments
275 VmExe size of text segm 275 VmExe size of text segment
276 VmLib size of shared li 276 VmLib size of shared library code
277 VmPTE size of page tabl 277 VmPTE size of page table entries
278 VmSwap amount of swap us 278 VmSwap amount of swap used by anonymous private data
279 (shmem swap usage 279 (shmem swap usage is not included)
280 HugetlbPages size of hugetlb m 280 HugetlbPages size of hugetlb memory portions
281 CoreDumping process's memory 281 CoreDumping process's memory is currently being dumped
282 (killing the proc 282 (killing the process may lead to a corrupted core)
283 THP_enabled process is allowe 283 THP_enabled process is allowed to use THP (returns 0 when
284 PR_SET_THP_DISABL 284 PR_SET_THP_DISABLE is set on the process
285 Threads number of threads 285 Threads number of threads
286 SigQ number of signals 286 SigQ number of signals queued/max. number for queue
287 SigPnd bitmap of pending 287 SigPnd bitmap of pending signals for the thread
288 ShdPnd bitmap of shared 288 ShdPnd bitmap of shared pending signals for the process
289 SigBlk bitmap of blocked 289 SigBlk bitmap of blocked signals
290 SigIgn bitmap of ignored 290 SigIgn bitmap of ignored signals
291 SigCgt bitmap of caught 291 SigCgt bitmap of caught signals
292 CapInh bitmap of inherit 292 CapInh bitmap of inheritable capabilities
293 CapPrm bitmap of permitt 293 CapPrm bitmap of permitted capabilities
294 CapEff bitmap of effecti 294 CapEff bitmap of effective capabilities
295 CapBnd bitmap of capabil 295 CapBnd bitmap of capabilities bounding set
296 CapAmb bitmap of ambient 296 CapAmb bitmap of ambient capabilities
297 NoNewPrivs no_new_privs, lik 297 NoNewPrivs no_new_privs, like prctl(PR_GET_NO_NEW_PRIV, ...)
298 Seccomp seccomp mode, lik 298 Seccomp seccomp mode, like prctl(PR_GET_SECCOMP, ...)
299 Speculation_Store_Bypass speculative store 299 Speculation_Store_Bypass speculative store bypass mitigation status
300 SpeculationIndirectBranch indirect branch s 300 SpeculationIndirectBranch indirect branch speculation mode
301 Cpus_allowed mask of CPUs on w 301 Cpus_allowed mask of CPUs on which this process may run
302 Cpus_allowed_list Same as previous, 302 Cpus_allowed_list Same as previous, but in "list format"
303 Mems_allowed mask of memory no 303 Mems_allowed mask of memory nodes allowed to this process
304 Mems_allowed_list Same as previous, 304 Mems_allowed_list Same as previous, but in "list format"
305 voluntary_ctxt_switches number of volunta 305 voluntary_ctxt_switches number of voluntary context switches
306 nonvoluntary_ctxt_switches number of non vol 306 nonvoluntary_ctxt_switches number of non voluntary context switches
307 ========================== ================= 307 ========================== ===================================================
308 308
309 309
310 .. table:: Table 1-3: Contents of the statm fi 310 .. table:: Table 1-3: Contents of the statm fields (as of 2.6.8-rc3)
311 311
312 ======== =============================== 312 ======== =============================== ==============================
313 Field Content 313 Field Content
314 ======== =============================== 314 ======== =============================== ==============================
315 size total program size (pages) 315 size total program size (pages) (same as VmSize in status)
316 resident size of memory portions (pages) 316 resident size of memory portions (pages) (same as VmRSS in status)
317 shared number of pages that are shared 317 shared number of pages that are shared (i.e. backed by a file, same
318 318 as RssFile+RssShmem in status)
319 trs number of pages that are 'code' 319 trs number of pages that are 'code' (not including libs; broken,
320 320 includes data segment)
321 lrs number of pages of library 321 lrs number of pages of library (always 0 on 2.6)
322 drs number of pages of data/stack 322 drs number of pages of data/stack (including libs; broken,
323 323 includes library text)
324 dt number of dirty pages 324 dt number of dirty pages (always 0 on 2.6)
325 ======== =============================== 325 ======== =============================== ==============================
326 326
327 327
328 .. table:: Table 1-4: Contents of the stat fie 328 .. table:: Table 1-4: Contents of the stat fields (as of 2.6.30-rc7)
329 329
330 ============= ============================== 330 ============= ===============================================================
331 Field Content 331 Field Content
332 ============= ============================== 332 ============= ===============================================================
333 pid process id 333 pid process id
334 tcomm filename of the executable 334 tcomm filename of the executable
335 state state (R is running, S is slee 335 state state (R is running, S is sleeping, D is sleeping in an
336 uninterruptible wait, Z is zom 336 uninterruptible wait, Z is zombie, T is traced or stopped)
337 ppid process id of the parent proce 337 ppid process id of the parent process
338 pgrp pgrp of the process 338 pgrp pgrp of the process
339 sid session id 339 sid session id
340 tty_nr tty the process uses 340 tty_nr tty the process uses
341 tty_pgrp pgrp of the tty 341 tty_pgrp pgrp of the tty
342 flags task flags 342 flags task flags
343 min_flt number of minor faults 343 min_flt number of minor faults
344 cmin_flt number of minor faults with ch 344 cmin_flt number of minor faults with child's
345 maj_flt number of major faults 345 maj_flt number of major faults
346 cmaj_flt number of major faults with ch 346 cmaj_flt number of major faults with child's
347 utime user mode jiffies 347 utime user mode jiffies
348 stime kernel mode jiffies 348 stime kernel mode jiffies
349 cutime user mode jiffies with child's 349 cutime user mode jiffies with child's
350 cstime kernel mode jiffies with child 350 cstime kernel mode jiffies with child's
351 priority priority level 351 priority priority level
352 nice nice level 352 nice nice level
353 num_threads number of threads 353 num_threads number of threads
354 it_real_value (obsolete, always 0) 354 it_real_value (obsolete, always 0)
355 start_time time the process started after 355 start_time time the process started after system boot
356 vsize virtual memory size 356 vsize virtual memory size
357 rss resident set memory size 357 rss resident set memory size
358 rsslim current limit in bytes on the 358 rsslim current limit in bytes on the rss
359 start_code address above which program te 359 start_code address above which program text can run
360 end_code address below which program te 360 end_code address below which program text can run
361 start_stack address of the start of the ma 361 start_stack address of the start of the main process stack
362 esp current value of ESP 362 esp current value of ESP
363 eip current value of EIP 363 eip current value of EIP
364 pending bitmap of pending signals 364 pending bitmap of pending signals
365 blocked bitmap of blocked signals 365 blocked bitmap of blocked signals
366 sigign bitmap of ignored signals 366 sigign bitmap of ignored signals
367 sigcatch bitmap of caught signals 367 sigcatch bitmap of caught signals
368 0 (place holder, used to be the 368 0 (place holder, used to be the wchan address,
369 use /proc/PID/wchan instead) 369 use /proc/PID/wchan instead)
370 0 (place holder) 370 0 (place holder)
371 0 (place holder) 371 0 (place holder)
372 exit_signal signal to send to parent threa 372 exit_signal signal to send to parent thread on exit
373 task_cpu which CPU the task is schedule 373 task_cpu which CPU the task is scheduled on
374 rt_priority realtime priority 374 rt_priority realtime priority
375 policy scheduling policy (man sched_s 375 policy scheduling policy (man sched_setscheduler)
376 blkio_ticks time spent waiting for block I 376 blkio_ticks time spent waiting for block IO
377 gtime guest time of the task in jiff 377 gtime guest time of the task in jiffies
378 cgtime guest time of the task childre 378 cgtime guest time of the task children in jiffies
379 start_data address above which program da 379 start_data address above which program data+bss is placed
380 end_data address below which program da 380 end_data address below which program data+bss is placed
381 start_brk address above which program he 381 start_brk address above which program heap can be expanded with brk()
382 arg_start address above which program co 382 arg_start address above which program command line is placed
383 arg_end address below which program co 383 arg_end address below which program command line is placed
384 env_start address above which program en 384 env_start address above which program environment is placed
385 env_end address below which program en 385 env_end address below which program environment is placed
386 exit_code the thread's exit_code in the 386 exit_code the thread's exit_code in the form reported by the waitpid
387 system call 387 system call
388 ============= ============================== 388 ============= ===============================================================
389 389
390 The /proc/PID/maps file contains the currently 390 The /proc/PID/maps file contains the currently mapped memory regions and
391 their access permissions. 391 their access permissions.
392 392
393 The format is:: 393 The format is::
394 394
395 address perms offset dev inod 395 address perms offset dev inode pathname
396 396
397 08048000-08049000 r-xp 00000000 03:00 8312 397 08048000-08049000 r-xp 00000000 03:00 8312 /opt/test
398 08049000-0804a000 rw-p 00001000 03:00 8312 398 08049000-0804a000 rw-p 00001000 03:00 8312 /opt/test
399 0804a000-0806b000 rw-p 00000000 00:00 0 399 0804a000-0806b000 rw-p 00000000 00:00 0 [heap]
400 a7cb1000-a7cb2000 ---p 00000000 00:00 0 400 a7cb1000-a7cb2000 ---p 00000000 00:00 0
401 a7cb2000-a7eb2000 rw-p 00000000 00:00 0 401 a7cb2000-a7eb2000 rw-p 00000000 00:00 0
402 a7eb2000-a7eb3000 ---p 00000000 00:00 0 402 a7eb2000-a7eb3000 ---p 00000000 00:00 0
403 a7eb3000-a7ed5000 rw-p 00000000 00:00 0 403 a7eb3000-a7ed5000 rw-p 00000000 00:00 0
404 a7ed5000-a8008000 r-xp 00000000 03:00 4222 404 a7ed5000-a8008000 r-xp 00000000 03:00 4222 /lib/libc.so.6
405 a8008000-a800a000 r--p 00133000 03:00 4222 405 a8008000-a800a000 r--p 00133000 03:00 4222 /lib/libc.so.6
406 a800a000-a800b000 rw-p 00135000 03:00 4222 406 a800a000-a800b000 rw-p 00135000 03:00 4222 /lib/libc.so.6
407 a800b000-a800e000 rw-p 00000000 00:00 0 407 a800b000-a800e000 rw-p 00000000 00:00 0
408 a800e000-a8022000 r-xp 00000000 03:00 1446 408 a800e000-a8022000 r-xp 00000000 03:00 14462 /lib/libpthread.so.0
409 a8022000-a8023000 r--p 00013000 03:00 1446 409 a8022000-a8023000 r--p 00013000 03:00 14462 /lib/libpthread.so.0
410 a8023000-a8024000 rw-p 00014000 03:00 1446 410 a8023000-a8024000 rw-p 00014000 03:00 14462 /lib/libpthread.so.0
411 a8024000-a8027000 rw-p 00000000 00:00 0 411 a8024000-a8027000 rw-p 00000000 00:00 0
412 a8027000-a8043000 r-xp 00000000 03:00 8317 412 a8027000-a8043000 r-xp 00000000 03:00 8317 /lib/ld-linux.so.2
413 a8043000-a8044000 r--p 0001b000 03:00 8317 413 a8043000-a8044000 r--p 0001b000 03:00 8317 /lib/ld-linux.so.2
414 a8044000-a8045000 rw-p 0001c000 03:00 8317 414 a8044000-a8045000 rw-p 0001c000 03:00 8317 /lib/ld-linux.so.2
415 aff35000-aff4a000 rw-p 00000000 00:00 0 415 aff35000-aff4a000 rw-p 00000000 00:00 0 [stack]
416 ffffe000-fffff000 r-xp 00000000 00:00 0 416 ffffe000-fffff000 r-xp 00000000 00:00 0 [vdso]
417 417
418 where "address" is the address space in the pr 418 where "address" is the address space in the process that it occupies, "perms"
419 is a set of permissions:: 419 is a set of permissions::
420 420
421 r = read 421 r = read
422 w = write 422 w = write
423 x = execute 423 x = execute
424 s = shared 424 s = shared
425 p = private (copy on write) 425 p = private (copy on write)
426 426
427 "offset" is the offset into the mapping, "dev" 427 "offset" is the offset into the mapping, "dev" is the device (major:minor), and
428 "inode" is the inode on that device. 0 indic 428 "inode" is the inode on that device. 0 indicates that no inode is associated
429 with the memory region, as the case would be w 429 with the memory region, as the case would be with BSS (uninitialized data).
430 The "pathname" shows the name associated file 430 The "pathname" shows the name associated file for this mapping. If the mapping
431 is not associated with a file: 431 is not associated with a file:
432 432
433 =================== ================== 433 =================== ===========================================
434 [heap] the heap of the pr 434 [heap] the heap of the program
435 [stack] the stack of the m 435 [stack] the stack of the main process
436 [vdso] the "virtual dynam 436 [vdso] the "virtual dynamic shared object",
437 the kernel system 437 the kernel system call handler
438 [anon:<name>] a private anonymou 438 [anon:<name>] a private anonymous mapping that has been
439 named by userspace 439 named by userspace
440 [anon_shmem:<name>] an anonymous share 440 [anon_shmem:<name>] an anonymous shared memory mapping that has
441 been named by user 441 been named by userspace
442 =================== ================== 442 =================== ===========================================
443 443
444 or if empty, the mapping is anonymous. 444 or if empty, the mapping is anonymous.
445 445
446 Starting with 6.11 kernel, /proc/PID/maps prov 446 Starting with 6.11 kernel, /proc/PID/maps provides an alternative
447 ioctl()-based API that gives ability to flexib 447 ioctl()-based API that gives ability to flexibly and efficiently query and
448 filter individual VMAs. This interface is bina 448 filter individual VMAs. This interface is binary and is meant for more
449 efficient and easy programmatic use. `struct p 449 efficient and easy programmatic use. `struct procmap_query`, defined in
450 linux/fs.h UAPI header, serves as an input/out 450 linux/fs.h UAPI header, serves as an input/output argument to the
451 `PROCMAP_QUERY` ioctl() command. See comments 451 `PROCMAP_QUERY` ioctl() command. See comments in linus/fs.h UAPI header for
452 details on query semantics, supported flags, d 452 details on query semantics, supported flags, data returned, and general API
453 usage information. 453 usage information.
454 454
455 The /proc/PID/smaps is an extension based on m 455 The /proc/PID/smaps is an extension based on maps, showing the memory
456 consumption for each of the process's mappings 456 consumption for each of the process's mappings. For each mapping (aka Virtual
457 Memory Area, or VMA) there is a series of line 457 Memory Area, or VMA) there is a series of lines such as the following::
458 458
459 08048000-080bc000 r-xp 00000000 03:02 1313 459 08048000-080bc000 r-xp 00000000 03:02 13130 /bin/bash
460 460
461 Size: 1084 kB 461 Size: 1084 kB
462 KernelPageSize: 4 kB 462 KernelPageSize: 4 kB
463 MMUPageSize: 4 kB 463 MMUPageSize: 4 kB
464 Rss: 892 kB 464 Rss: 892 kB
465 Pss: 374 kB 465 Pss: 374 kB
466 Pss_Dirty: 0 kB 466 Pss_Dirty: 0 kB
467 Shared_Clean: 892 kB 467 Shared_Clean: 892 kB
468 Shared_Dirty: 0 kB 468 Shared_Dirty: 0 kB
469 Private_Clean: 0 kB 469 Private_Clean: 0 kB
470 Private_Dirty: 0 kB 470 Private_Dirty: 0 kB
471 Referenced: 892 kB 471 Referenced: 892 kB
472 Anonymous: 0 kB 472 Anonymous: 0 kB
473 KSM: 0 kB 473 KSM: 0 kB
474 LazyFree: 0 kB 474 LazyFree: 0 kB
475 AnonHugePages: 0 kB 475 AnonHugePages: 0 kB
476 ShmemPmdMapped: 0 kB 476 ShmemPmdMapped: 0 kB
477 Shared_Hugetlb: 0 kB 477 Shared_Hugetlb: 0 kB
478 Private_Hugetlb: 0 kB 478 Private_Hugetlb: 0 kB
479 Swap: 0 kB 479 Swap: 0 kB
480 SwapPss: 0 kB 480 SwapPss: 0 kB
481 KernelPageSize: 4 kB 481 KernelPageSize: 4 kB
482 MMUPageSize: 4 kB 482 MMUPageSize: 4 kB
483 Locked: 0 kB 483 Locked: 0 kB
484 THPeligible: 0 484 THPeligible: 0
485 VmFlags: rd ex mr mw me dw 485 VmFlags: rd ex mr mw me dw
486 486
487 The first of these lines shows the same inform 487 The first of these lines shows the same information as is displayed for the
488 mapping in /proc/PID/maps. Following lines sh 488 mapping in /proc/PID/maps. Following lines show the size of the mapping
489 (size); the size of each page allocated when b 489 (size); the size of each page allocated when backing a VMA (KernelPageSize),
490 which is usually the same as the size in the p 490 which is usually the same as the size in the page table entries; the page size
491 used by the MMU when backing a VMA (in most ca 491 used by the MMU when backing a VMA (in most cases, the same as KernelPageSize);
492 the amount of the mapping that is currently re 492 the amount of the mapping that is currently resident in RAM (RSS); the
493 process' proportional share of this mapping (P 493 process' proportional share of this mapping (PSS); and the number of clean and
494 dirty shared and private pages in the mapping. 494 dirty shared and private pages in the mapping.
495 495
496 The "proportional set size" (PSS) of a process 496 The "proportional set size" (PSS) of a process is the count of pages it has
497 in memory, where each page is divided by the n 497 in memory, where each page is divided by the number of processes sharing it.
498 So if a process has 1000 pages all to itself, 498 So if a process has 1000 pages all to itself, and 1000 shared with one other
499 process, its PSS will be 1500. "Pss_Dirty" is 499 process, its PSS will be 1500. "Pss_Dirty" is the portion of PSS which
500 consists of dirty pages. ("Pss_Clean" is not 500 consists of dirty pages. ("Pss_Clean" is not included, but it can be
501 calculated by subtracting "Pss_Dirty" from "Ps 501 calculated by subtracting "Pss_Dirty" from "Pss".)
502 502
503 Note that even a page which is part of a MAP_S 503 Note that even a page which is part of a MAP_SHARED mapping, but has only
504 a single pte mapped, i.e. is currently used b 504 a single pte mapped, i.e. is currently used by only one process, is accounted
505 as private and not as shared. 505 as private and not as shared.
506 506
507 "Referenced" indicates the amount of memory cu 507 "Referenced" indicates the amount of memory currently marked as referenced or
508 accessed. 508 accessed.
509 509
510 "Anonymous" shows the amount of memory that do 510 "Anonymous" shows the amount of memory that does not belong to any file. Even
511 a mapping associated with a file may contain a 511 a mapping associated with a file may contain anonymous pages: when MAP_PRIVATE
512 and a page is modified, the file page is repla 512 and a page is modified, the file page is replaced by a private anonymous copy.
513 513
514 "KSM" reports how many of the pages are KSM pa 514 "KSM" reports how many of the pages are KSM pages. Note that KSM-placed zeropages
515 are not included, only actual KSM pages. 515 are not included, only actual KSM pages.
516 516
517 "LazyFree" shows the amount of memory which is 517 "LazyFree" shows the amount of memory which is marked by madvise(MADV_FREE).
518 The memory isn't freed immediately with madvis 518 The memory isn't freed immediately with madvise(). It's freed in memory
519 pressure if the memory is clean. Please note t 519 pressure if the memory is clean. Please note that the printed value might
520 be lower than the real value due to optimizati 520 be lower than the real value due to optimizations used in the current
521 implementation. If this is not desirable pleas 521 implementation. If this is not desirable please file a bug report.
522 522
523 "AnonHugePages" shows the amount of memory bac 523 "AnonHugePages" shows the amount of memory backed by transparent hugepage.
524 524
525 "ShmemPmdMapped" shows the amount of shared (s 525 "ShmemPmdMapped" shows the amount of shared (shmem/tmpfs) memory backed by
526 huge pages. 526 huge pages.
527 527
528 "Shared_Hugetlb" and "Private_Hugetlb" show th 528 "Shared_Hugetlb" and "Private_Hugetlb" show the amounts of memory backed by
529 hugetlbfs page which is *not* counted in "RSS" 529 hugetlbfs page which is *not* counted in "RSS" or "PSS" field for historical
530 reasons. And these are not included in {Shared 530 reasons. And these are not included in {Shared,Private}_{Clean,Dirty} field.
531 531
532 "Swap" shows how much would-be-anonymous memor 532 "Swap" shows how much would-be-anonymous memory is also used, but out on swap.
533 533
534 For shmem mappings, "Swap" includes also the s 534 For shmem mappings, "Swap" includes also the size of the mapped (and not
535 replaced by copy-on-write) part of the underly 535 replaced by copy-on-write) part of the underlying shmem object out on swap.
536 "SwapPss" shows proportional swap share of thi 536 "SwapPss" shows proportional swap share of this mapping. Unlike "Swap", this
537 does not take into account swapped out page of 537 does not take into account swapped out page of underlying shmem objects.
538 "Locked" indicates whether the mapping is lock 538 "Locked" indicates whether the mapping is locked in memory or not.
539 539
540 "THPeligible" indicates whether the mapping is 540 "THPeligible" indicates whether the mapping is eligible for allocating
541 naturally aligned THP pages of any currently e 541 naturally aligned THP pages of any currently enabled size. 1 if true, 0
542 otherwise. 542 otherwise.
543 543
544 "VmFlags" field deserves a separate descriptio 544 "VmFlags" field deserves a separate description. This member represents the
545 kernel flags associated with the particular vi 545 kernel flags associated with the particular virtual memory area in two letter
546 encoded manner. The codes are the following: 546 encoded manner. The codes are the following:
547 547
548 == ==================================== 548 == =======================================
549 rd readable 549 rd readable
550 wr writeable 550 wr writeable
551 ex executable 551 ex executable
552 sh shared 552 sh shared
553 mr may read 553 mr may read
554 mw may write 554 mw may write
555 me may execute 555 me may execute
556 ms may share 556 ms may share
557 gd stack segment growns down 557 gd stack segment growns down
558 pf pure PFN range 558 pf pure PFN range
559 dw disabled write to the mapped file 559 dw disabled write to the mapped file
560 lo pages are locked in memory 560 lo pages are locked in memory
561 io memory mapped I/O area 561 io memory mapped I/O area
562 sr sequential read advise provided 562 sr sequential read advise provided
563 rr random read advise provided 563 rr random read advise provided
564 dc do not copy area on fork 564 dc do not copy area on fork
565 de do not expand area on remapping 565 de do not expand area on remapping
566 ac area is accountable 566 ac area is accountable
567 nr swap space is not reserved for the a 567 nr swap space is not reserved for the area
568 ht area uses huge tlb pages 568 ht area uses huge tlb pages
569 sf synchronous page fault 569 sf synchronous page fault
570 ar architecture specific flag 570 ar architecture specific flag
571 wf wipe on fork 571 wf wipe on fork
572 dd do not include area into core dump 572 dd do not include area into core dump
573 sd soft dirty flag 573 sd soft dirty flag
574 mm mixed map area 574 mm mixed map area
575 hg huge page advise flag 575 hg huge page advise flag
576 nh no huge page advise flag 576 nh no huge page advise flag
577 mg mergeable advise flag 577 mg mergeable advise flag
578 bt arm64 BTI guarded page 578 bt arm64 BTI guarded page
579 mt arm64 MTE allocation tags are enable 579 mt arm64 MTE allocation tags are enabled
580 um userfaultfd missing tracking 580 um userfaultfd missing tracking
581 uw userfaultfd wr-protect tracking 581 uw userfaultfd wr-protect tracking
582 ss shadow stack page 582 ss shadow stack page
583 sl sealed 583 sl sealed
584 == ==================================== 584 == =======================================
585 585
586 Note that there is no guarantee that every fla 586 Note that there is no guarantee that every flag and associated mnemonic will
587 be present in all further kernel releases. Thi 587 be present in all further kernel releases. Things get changed, the flags may
588 be vanished or the reverse -- new added. Inter 588 be vanished or the reverse -- new added. Interpretation of their meaning
589 might change in future as well. So each consum 589 might change in future as well. So each consumer of these flags has to
590 follow each specific kernel version for the ex 590 follow each specific kernel version for the exact semantic.
591 591
592 This file is only present if the CONFIG_MMU ke 592 This file is only present if the CONFIG_MMU kernel configuration option is
593 enabled. 593 enabled.
594 594
595 Note: reading /proc/PID/maps or /proc/PID/smap 595 Note: reading /proc/PID/maps or /proc/PID/smaps is inherently racy (consistent
596 output can be achieved only in the single read 596 output can be achieved only in the single read call).
597 597
598 This typically manifests when doing partial re 598 This typically manifests when doing partial reads of these files while the
599 memory map is being modified. Despite the rac 599 memory map is being modified. Despite the races, we do provide the following
600 guarantees: 600 guarantees:
601 601
602 1) The mapped addresses never go backwards, wh 602 1) The mapped addresses never go backwards, which implies no two
603 regions will ever overlap. 603 regions will ever overlap.
604 2) If there is something at a given vaddr duri 604 2) If there is something at a given vaddr during the entirety of the
605 life of the smaps/maps walk, there will be 605 life of the smaps/maps walk, there will be some output for it.
606 606
607 The /proc/PID/smaps_rollup file includes the s 607 The /proc/PID/smaps_rollup file includes the same fields as /proc/PID/smaps,
608 but their values are the sums of the correspon 608 but their values are the sums of the corresponding values for all mappings of
609 the process. Additionally, it contains these 609 the process. Additionally, it contains these fields:
610 610
611 - Pss_Anon 611 - Pss_Anon
612 - Pss_File 612 - Pss_File
613 - Pss_Shmem 613 - Pss_Shmem
614 614
615 They represent the proportional shares of anon 615 They represent the proportional shares of anonymous, file, and shmem pages, as
616 described for smaps above. These fields are o 616 described for smaps above. These fields are omitted in smaps since each
617 mapping identifies the type (anon, file, or sh 617 mapping identifies the type (anon, file, or shmem) of all pages it contains.
618 Thus all information in smaps_rollup can be de 618 Thus all information in smaps_rollup can be derived from smaps, but at a
619 significantly higher cost. 619 significantly higher cost.
620 620
621 The /proc/PID/clear_refs is used to reset the 621 The /proc/PID/clear_refs is used to reset the PG_Referenced and ACCESSED/YOUNG
622 bits on both physical and virtual pages associ 622 bits on both physical and virtual pages associated with a process, and the
623 soft-dirty bit on pte (see Documentation/admin 623 soft-dirty bit on pte (see Documentation/admin-guide/mm/soft-dirty.rst
624 for details). 624 for details).
625 To clear the bits for all the pages associated 625 To clear the bits for all the pages associated with the process::
626 626
627 > echo 1 > /proc/PID/clear_refs 627 > echo 1 > /proc/PID/clear_refs
628 628
629 To clear the bits for the anonymous pages asso 629 To clear the bits for the anonymous pages associated with the process::
630 630
631 > echo 2 > /proc/PID/clear_refs 631 > echo 2 > /proc/PID/clear_refs
632 632
633 To clear the bits for the file mapped pages as 633 To clear the bits for the file mapped pages associated with the process::
634 634
635 > echo 3 > /proc/PID/clear_refs 635 > echo 3 > /proc/PID/clear_refs
636 636
637 To clear the soft-dirty bit:: 637 To clear the soft-dirty bit::
638 638
639 > echo 4 > /proc/PID/clear_refs 639 > echo 4 > /proc/PID/clear_refs
640 640
641 To reset the peak resident set size ("high wat 641 To reset the peak resident set size ("high water mark") to the process's
642 current value:: 642 current value::
643 643
644 > echo 5 > /proc/PID/clear_refs 644 > echo 5 > /proc/PID/clear_refs
645 645
646 Any other value written to /proc/PID/clear_ref 646 Any other value written to /proc/PID/clear_refs will have no effect.
647 647
648 The /proc/pid/pagemap gives the PFN, which can 648 The /proc/pid/pagemap gives the PFN, which can be used to find the pageflags
649 using /proc/kpageflags and number of times a p 649 using /proc/kpageflags and number of times a page is mapped using
650 /proc/kpagecount. For detailed explanation, se 650 /proc/kpagecount. For detailed explanation, see
651 Documentation/admin-guide/mm/pagemap.rst. 651 Documentation/admin-guide/mm/pagemap.rst.
652 652
653 The /proc/pid/numa_maps is an extension based 653 The /proc/pid/numa_maps is an extension based on maps, showing the memory
654 locality and binding policy, as well as the me 654 locality and binding policy, as well as the memory usage (in pages) of
655 each mapping. The output follows a general for 655 each mapping. The output follows a general format where mapping details get
656 summarized separated by blank spaces, one mapp 656 summarized separated by blank spaces, one mapping per each file line::
657 657
658 address policy mapping details 658 address policy mapping details
659 659
660 00400000 default file=/usr/local/bin/app m 660 00400000 default file=/usr/local/bin/app mapped=1 active=0 N3=1 kernelpagesize_kB=4
661 00600000 default file=/usr/local/bin/app a 661 00600000 default file=/usr/local/bin/app anon=1 dirty=1 N3=1 kernelpagesize_kB=4
662 3206000000 default file=/lib64/ld-2.12.so 662 3206000000 default file=/lib64/ld-2.12.so mapped=26 mapmax=6 N0=24 N3=2 kernelpagesize_kB=4
663 320621f000 default file=/lib64/ld-2.12.so 663 320621f000 default file=/lib64/ld-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4
664 3206220000 default file=/lib64/ld-2.12.so 664 3206220000 default file=/lib64/ld-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4
665 3206221000 default anon=1 dirty=1 N3=1 ker 665 3206221000 default anon=1 dirty=1 N3=1 kernelpagesize_kB=4
666 3206800000 default file=/lib64/libc-2.12.s 666 3206800000 default file=/lib64/libc-2.12.so mapped=59 mapmax=21 active=55 N0=41 N3=18 kernelpagesize_kB=4
667 320698b000 default file=/lib64/libc-2.12.s 667 320698b000 default file=/lib64/libc-2.12.so
668 3206b8a000 default file=/lib64/libc-2.12.s 668 3206b8a000 default file=/lib64/libc-2.12.so anon=2 dirty=2 N3=2 kernelpagesize_kB=4
669 3206b8e000 default file=/lib64/libc-2.12.s 669 3206b8e000 default file=/lib64/libc-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4
670 3206b8f000 default anon=3 dirty=3 active=1 670 3206b8f000 default anon=3 dirty=3 active=1 N3=3 kernelpagesize_kB=4
671 7f4dc10a2000 default anon=3 dirty=3 N3=3 k 671 7f4dc10a2000 default anon=3 dirty=3 N3=3 kernelpagesize_kB=4
672 7f4dc10b4000 default anon=2 dirty=2 active 672 7f4dc10b4000 default anon=2 dirty=2 active=1 N3=2 kernelpagesize_kB=4
673 7f4dc1200000 default file=/anon_hugepage\0 673 7f4dc1200000 default file=/anon_hugepage\040(deleted) huge anon=1 dirty=1 N3=1 kernelpagesize_kB=2048
674 7fff335f0000 default stack anon=3 dirty=3 674 7fff335f0000 default stack anon=3 dirty=3 N3=3 kernelpagesize_kB=4
675 7fff3369d000 default mapped=1 mapmax=35 ac 675 7fff3369d000 default mapped=1 mapmax=35 active=0 N3=1 kernelpagesize_kB=4
676 676
677 Where: 677 Where:
678 678
679 "address" is the starting address for the mapp 679 "address" is the starting address for the mapping;
680 680
681 "policy" reports the NUMA memory policy set fo 681 "policy" reports the NUMA memory policy set for the mapping (see Documentation/admin-guide/mm/numa_memory_policy.rst);
682 682
683 "mapping details" summarizes mapping data such 683 "mapping details" summarizes mapping data such as mapping type, page usage counters,
684 node locality page counters (N0 == node0, N1 = 684 node locality page counters (N0 == node0, N1 == node1, ...) and the kernel page
685 size, in KB, that is backing the mapping up. 685 size, in KB, that is backing the mapping up.
686 686
687 1.2 Kernel data 687 1.2 Kernel data
688 --------------- 688 ---------------
689 689
690 Similar to the process entries, the kernel d 690 Similar to the process entries, the kernel data files give information about
691 the running kernel. The files used to obtain t 691 the running kernel. The files used to obtain this information are contained in
692 /proc and are listed in Table 1-5. Not all 692 /proc and are listed in Table 1-5. Not all of these will be present in your
693 system. It depends on the kernel configurati 693 system. It depends on the kernel configuration and the loaded modules, which
694 files are there, and which are missing. 694 files are there, and which are missing.
695 695
696 .. table:: Table 1-5: Kernel info in /proc 696 .. table:: Table 1-5: Kernel info in /proc
697 697
698 ============ ================================ 698 ============ ===============================================================
699 File Content 699 File Content
700 ============ ================================ 700 ============ ===============================================================
701 allocinfo Memory allocations profiling inf 701 allocinfo Memory allocations profiling information
702 apm Advanced power management info 702 apm Advanced power management info
703 bootconfig Kernel command line obtained fro 703 bootconfig Kernel command line obtained from boot config,
704 and, if there were kernel parame 704 and, if there were kernel parameters from the
705 boot loader, a "# Parameters fro 705 boot loader, a "# Parameters from bootloader:"
706 line followed by a line containi 706 line followed by a line containing those
707 parameters prefixed by "# ". 707 parameters prefixed by "# ". (5.5)
708 buddyinfo Kernel memory allocator informat 708 buddyinfo Kernel memory allocator information (see text) (2.5)
709 bus Directory containing bus specifi 709 bus Directory containing bus specific information
710 cmdline Kernel command line, both from b 710 cmdline Kernel command line, both from bootloader and embedded
711 in the kernel image 711 in the kernel image
712 cpuinfo Info about the CPU 712 cpuinfo Info about the CPU
713 devices Available devices (block and cha 713 devices Available devices (block and character)
714 dma Used DMS channels 714 dma Used DMS channels
715 filesystems Supported filesystems 715 filesystems Supported filesystems
716 driver Various drivers grouped here, cu 716 driver Various drivers grouped here, currently rtc (2.4)
717 execdomains Execdomains, related to security 717 execdomains Execdomains, related to security (2.4)
718 fb Frame Buffer devices 718 fb Frame Buffer devices (2.4)
719 fs File system parameters, currentl 719 fs File system parameters, currently nfs/exports (2.4)
720 ide Directory containing info about 720 ide Directory containing info about the IDE subsystem
721 interrupts Interrupt usage 721 interrupts Interrupt usage
722 iomem Memory map 722 iomem Memory map (2.4)
723 ioports I/O port usage 723 ioports I/O port usage
724 irq Masks for irq to cpu affinity 724 irq Masks for irq to cpu affinity (2.4)(smp?)
725 isapnp ISA PnP (Plug&Play) Info 725 isapnp ISA PnP (Plug&Play) Info (2.4)
726 kcore Kernel core image (can be ELF or 726 kcore Kernel core image (can be ELF or A.OUT(deprecated in 2.4))
727 kmsg Kernel messages 727 kmsg Kernel messages
728 ksyms Kernel symbol table 728 ksyms Kernel symbol table
729 loadavg Load average of last 1, 5 & 15 m 729 loadavg Load average of last 1, 5 & 15 minutes;
730 number of processes currently 730 number of processes currently runnable (running or on ready queue);
731 total number of processes in s 731 total number of processes in system;
732 last pid created. 732 last pid created.
733 All fields are separated by on 733 All fields are separated by one space except "number of
734 processes currently runnable" 734 processes currently runnable" and "total number of processes
735 in system", which are separate 735 in system", which are separated by a slash ('/'). Example:
736 0.61 0.61 0.55 3/828 22084 736 0.61 0.61 0.55 3/828 22084
737 locks Kernel locks 737 locks Kernel locks
738 meminfo Memory info 738 meminfo Memory info
739 misc Miscellaneous 739 misc Miscellaneous
740 modules List of loaded modules 740 modules List of loaded modules
741 mounts Mounted filesystems 741 mounts Mounted filesystems
742 net Networking info (see text) 742 net Networking info (see text)
743 pagetypeinfo Additional page allocator inform 743 pagetypeinfo Additional page allocator information (see text) (2.5)
744 partitions Table of partitions known to the 744 partitions Table of partitions known to the system
745 pci Deprecated info of PCI bus (new 745 pci Deprecated info of PCI bus (new way -> /proc/bus/pci/,
746 decoupled by lspci 746 decoupled by lspci (2.4)
747 rtc Real time clock 747 rtc Real time clock
748 scsi SCSI info (see text) 748 scsi SCSI info (see text)
749 slabinfo Slab pool info 749 slabinfo Slab pool info
750 softirqs softirq usage 750 softirqs softirq usage
751 stat Overall statistics 751 stat Overall statistics
752 swaps Swap space utilization 752 swaps Swap space utilization
753 sys See chapter 2 753 sys See chapter 2
754 sysvipc Info of SysVIPC Resources (msg, 754 sysvipc Info of SysVIPC Resources (msg, sem, shm) (2.4)
755 tty Info of tty drivers 755 tty Info of tty drivers
756 uptime Wall clock since boot, combined 756 uptime Wall clock since boot, combined idle time of all cpus
757 version Kernel version 757 version Kernel version
758 video bttv info of video resources 758 video bttv info of video resources (2.4)
759 vmallocinfo Show vmalloced areas 759 vmallocinfo Show vmalloced areas
760 ============ ================================ 760 ============ ===============================================================
761 761
762 You can, for example, check which interrup 762 You can, for example, check which interrupts are currently in use and what
763 they are used for by looking in the file /proc 763 they are used for by looking in the file /proc/interrupts::
764 764
765 > cat /proc/interrupts 765 > cat /proc/interrupts
766 CPU0 766 CPU0
767 0: 8728810 XT-PIC timer 767 0: 8728810 XT-PIC timer
768 1: 895 XT-PIC keyboard 768 1: 895 XT-PIC keyboard
769 2: 0 XT-PIC cascade 769 2: 0 XT-PIC cascade
770 3: 531695 XT-PIC aha152x 770 3: 531695 XT-PIC aha152x
771 4: 2014133 XT-PIC serial 771 4: 2014133 XT-PIC serial
772 5: 44401 XT-PIC pcnet_cs 772 5: 44401 XT-PIC pcnet_cs
773 8: 2 XT-PIC rtc 773 8: 2 XT-PIC rtc
774 11: 8 XT-PIC i82365 774 11: 8 XT-PIC i82365
775 12: 182918 XT-PIC PS/2 Mouse 775 12: 182918 XT-PIC PS/2 Mouse
776 13: 1 XT-PIC fpu 776 13: 1 XT-PIC fpu
777 14: 1232265 XT-PIC ide0 777 14: 1232265 XT-PIC ide0
778 15: 7 XT-PIC ide1 778 15: 7 XT-PIC ide1
779 NMI: 0 779 NMI: 0
780 780
781 In 2.4.* a couple of lines where added to this 781 In 2.4.* a couple of lines where added to this file LOC & ERR (this time is the
782 output of a SMP machine):: 782 output of a SMP machine)::
783 783
784 > cat /proc/interrupts 784 > cat /proc/interrupts
785 785
786 CPU0 CPU1 786 CPU0 CPU1
787 0: 1243498 1214548 IO-APIC-edge 787 0: 1243498 1214548 IO-APIC-edge timer
788 1: 8949 8958 IO-APIC-edge 788 1: 8949 8958 IO-APIC-edge keyboard
789 2: 0 0 XT-PIC 789 2: 0 0 XT-PIC cascade
790 5: 11286 10161 IO-APIC-edge 790 5: 11286 10161 IO-APIC-edge soundblaster
791 8: 1 0 IO-APIC-edge 791 8: 1 0 IO-APIC-edge rtc
792 9: 27422 27407 IO-APIC-edge 792 9: 27422 27407 IO-APIC-edge 3c503
793 12: 113645 113873 IO-APIC-edge 793 12: 113645 113873 IO-APIC-edge PS/2 Mouse
794 13: 0 0 XT-PIC 794 13: 0 0 XT-PIC fpu
795 14: 22491 24012 IO-APIC-edge 795 14: 22491 24012 IO-APIC-edge ide0
796 15: 2183 2415 IO-APIC-edge 796 15: 2183 2415 IO-APIC-edge ide1
797 17: 30564 30414 IO-APIC-level 797 17: 30564 30414 IO-APIC-level eth0
798 18: 177 164 IO-APIC-level 798 18: 177 164 IO-APIC-level bttv
799 NMI: 2457961 2457959 799 NMI: 2457961 2457959
800 LOC: 2457882 2457881 800 LOC: 2457882 2457881
801 ERR: 2155 801 ERR: 2155
802 802
803 NMI is incremented in this case because every 803 NMI is incremented in this case because every timer interrupt generates a NMI
804 (Non Maskable Interrupt) which is used by the 804 (Non Maskable Interrupt) which is used by the NMI Watchdog to detect lockups.
805 805
806 LOC is the local interrupt counter of the inte 806 LOC is the local interrupt counter of the internal APIC of every CPU.
807 807
808 ERR is incremented in the case of errors in th 808 ERR is incremented in the case of errors in the IO-APIC bus (the bus that
809 connects the CPUs in a SMP system. This means 809 connects the CPUs in a SMP system. This means that an error has been detected,
810 the IO-APIC automatically retry the transmissi 810 the IO-APIC automatically retry the transmission, so it should not be a big
811 problem, but you should read the SMP-FAQ. 811 problem, but you should read the SMP-FAQ.
812 812
813 In 2.6.2* /proc/interrupts was expanded again. 813 In 2.6.2* /proc/interrupts was expanded again. This time the goal was for
814 /proc/interrupts to display every IRQ vector i 814 /proc/interrupts to display every IRQ vector in use by the system, not
815 just those considered 'most important'. The n 815 just those considered 'most important'. The new vectors are:
816 816
817 THR 817 THR
818 interrupt raised when a machine check thresh 818 interrupt raised when a machine check threshold counter
819 (typically counting ECC corrected errors of 819 (typically counting ECC corrected errors of memory or cache) exceeds
820 a configurable threshold. Only available on 820 a configurable threshold. Only available on some systems.
821 821
822 TRM 822 TRM
823 a thermal event interrupt occurs when a temp 823 a thermal event interrupt occurs when a temperature threshold
824 has been exceeded for the CPU. This interru 824 has been exceeded for the CPU. This interrupt may also be generated
825 when the temperature drops back to normal. 825 when the temperature drops back to normal.
826 826
827 SPU 827 SPU
828 a spurious interrupt is some interrupt that 828 a spurious interrupt is some interrupt that was raised then lowered
829 by some IO device before it could be fully p 829 by some IO device before it could be fully processed by the APIC. Hence
830 the APIC sees the interrupt but does not kno 830 the APIC sees the interrupt but does not know what device it came from.
831 For this case the APIC will generate the int 831 For this case the APIC will generate the interrupt with a IRQ vector
832 of 0xff. This might also be generated by chi 832 of 0xff. This might also be generated by chipset bugs.
833 833
834 RES, CAL, TLB 834 RES, CAL, TLB
835 rescheduling, call and TLB flush interrupts 835 rescheduling, call and TLB flush interrupts are
836 sent from one CPU to another per the needs o 836 sent from one CPU to another per the needs of the OS. Typically,
837 their statistics are used by kernel develope 837 their statistics are used by kernel developers and interested users to
838 determine the occurrence of interrupts of th 838 determine the occurrence of interrupts of the given type.
839 839
840 The above IRQ vectors are displayed only when 840 The above IRQ vectors are displayed only when relevant. For example,
841 the threshold vector does not exist on x86_64 841 the threshold vector does not exist on x86_64 platforms. Others are
842 suppressed when the system is a uniprocessor. 842 suppressed when the system is a uniprocessor. As of this writing, only
843 i386 and x86_64 platforms support the new IRQ 843 i386 and x86_64 platforms support the new IRQ vector displays.
844 844
845 Of some interest is the introduction of the /p 845 Of some interest is the introduction of the /proc/irq directory to 2.4.
846 It could be used to set IRQ to CPU affinity. T 846 It could be used to set IRQ to CPU affinity. This means that you can "hook" an
847 IRQ to only one CPU, or to exclude a CPU of ha 847 IRQ to only one CPU, or to exclude a CPU of handling IRQs. The contents of the
848 irq subdir is one subdir for each IRQ, and two 848 irq subdir is one subdir for each IRQ, and two files; default_smp_affinity and
849 prof_cpu_mask. 849 prof_cpu_mask.
850 850
851 For example:: 851 For example::
852 852
853 > ls /proc/irq/ 853 > ls /proc/irq/
854 0 10 12 14 16 18 2 4 6 8 prof_cpu_ 854 0 10 12 14 16 18 2 4 6 8 prof_cpu_mask
855 1 11 13 15 17 19 3 5 7 9 default_s 855 1 11 13 15 17 19 3 5 7 9 default_smp_affinity
856 > ls /proc/irq/0/ 856 > ls /proc/irq/0/
857 smp_affinity 857 smp_affinity
858 858
859 smp_affinity is a bitmask, in which you can sp 859 smp_affinity is a bitmask, in which you can specify which CPUs can handle the
860 IRQ. You can set it by doing:: 860 IRQ. You can set it by doing::
861 861
862 > echo 1 > /proc/irq/10/smp_affinity 862 > echo 1 > /proc/irq/10/smp_affinity
863 863
864 This means that only the first CPU will handle 864 This means that only the first CPU will handle the IRQ, but you can also echo
865 5 which means that only the first and third CP 865 5 which means that only the first and third CPU can handle the IRQ.
866 866
867 The contents of each smp_affinity file is the 867 The contents of each smp_affinity file is the same by default::
868 868
869 > cat /proc/irq/0/smp_affinity 869 > cat /proc/irq/0/smp_affinity
870 ffffffff 870 ffffffff
871 871
872 There is an alternate interface, smp_affinity_ 872 There is an alternate interface, smp_affinity_list which allows specifying
873 a CPU range instead of a bitmask:: 873 a CPU range instead of a bitmask::
874 874
875 > cat /proc/irq/0/smp_affinity_list 875 > cat /proc/irq/0/smp_affinity_list
876 1024-1031 876 1024-1031
877 877
878 The default_smp_affinity mask applies to all n 878 The default_smp_affinity mask applies to all non-active IRQs, which are the
879 IRQs which have not yet been allocated/activat 879 IRQs which have not yet been allocated/activated, and hence which lack a
880 /proc/irq/[0-9]* directory. 880 /proc/irq/[0-9]* directory.
881 881
882 The node file on an SMP system shows the node 882 The node file on an SMP system shows the node to which the device using the IRQ
883 reports itself as being attached. This hardwar 883 reports itself as being attached. This hardware locality information does not
884 include information about any possible driver 884 include information about any possible driver locality preference.
885 885
886 prof_cpu_mask specifies which CPUs are to be p 886 prof_cpu_mask specifies which CPUs are to be profiled by the system wide
887 profiler. Default value is ffffffff (all CPUs 887 profiler. Default value is ffffffff (all CPUs if there are only 32 of them).
888 888
889 The way IRQs are routed is handled by the IO-A 889 The way IRQs are routed is handled by the IO-APIC, and it's Round Robin
890 between all the CPUs which are allowed to hand 890 between all the CPUs which are allowed to handle it. As usual the kernel has
891 more info than you and does a better job than 891 more info than you and does a better job than you, so the defaults are the
892 best choice for almost everyone. [Note this a 892 best choice for almost everyone. [Note this applies only to those IO-APIC's
893 that support "Round Robin" interrupt distribut 893 that support "Round Robin" interrupt distribution.]
894 894
895 There are three more important subdirectori 895 There are three more important subdirectories in /proc: net, scsi, and sys.
896 The general rule is that the contents, o 896 The general rule is that the contents, or even the existence of these
897 directories, depend on your kernel configurat 897 directories, depend on your kernel configuration. If SCSI is not enabled, the
898 directory scsi may not exist. The same is t 898 directory scsi may not exist. The same is true with the net, which is there
899 only when networking support is present in the 899 only when networking support is present in the running kernel.
900 900
901 The slabinfo file gives information about 901 The slabinfo file gives information about memory usage at the slab level.
902 Linux uses slab pools for memory management 902 Linux uses slab pools for memory management above page level in version 2.2.
903 Commonly used objects have their own slab 903 Commonly used objects have their own slab pool (such as network buffers,
904 directory cache, and so on). 904 directory cache, and so on).
905 905
906 :: 906 ::
907 907
908 > cat /proc/buddyinfo 908 > cat /proc/buddyinfo
909 909
910 Node 0, zone DMA 0 4 5 910 Node 0, zone DMA 0 4 5 4 4 3 ...
911 Node 0, zone Normal 1 0 0 911 Node 0, zone Normal 1 0 0 1 101 8 ...
912 Node 0, zone HighMem 2 0 0 912 Node 0, zone HighMem 2 0 0 1 1 0 ...
913 913
914 External fragmentation is a problem under some 914 External fragmentation is a problem under some workloads, and buddyinfo is a
915 useful tool for helping diagnose these problem 915 useful tool for helping diagnose these problems. Buddyinfo will give you a
916 clue as to how big an area you can safely allo 916 clue as to how big an area you can safely allocate, or why a previous
917 allocation failed. 917 allocation failed.
918 918
919 Each column represents the number of pages of 919 Each column represents the number of pages of a certain order which are
920 available. In this case, there are 0 chunks o 920 available. In this case, there are 0 chunks of 2^0*PAGE_SIZE available in
921 ZONE_DMA, 4 chunks of 2^1*PAGE_SIZE in ZONE_DM 921 ZONE_DMA, 4 chunks of 2^1*PAGE_SIZE in ZONE_DMA, 101 chunks of 2^4*PAGE_SIZE
922 available in ZONE_NORMAL, etc... 922 available in ZONE_NORMAL, etc...
923 923
924 More information relevant to external fragment 924 More information relevant to external fragmentation can be found in
925 pagetypeinfo:: 925 pagetypeinfo::
926 926
927 > cat /proc/pagetypeinfo 927 > cat /proc/pagetypeinfo
928 Page block order: 9 928 Page block order: 9
929 Pages per block: 512 929 Pages per block: 512
930 930
931 Free pages count per migrate type at order 931 Free pages count per migrate type at order 0 1 2 3 4 5 6 7 8 9 10
932 Node 0, zone DMA, type Unmovabl 932 Node 0, zone DMA, type Unmovable 0 0 0 1 1 1 1 1 1 1 0
933 Node 0, zone DMA, type Reclaimabl 933 Node 0, zone DMA, type Reclaimable 0 0 0 0 0 0 0 0 0 0 0
934 Node 0, zone DMA, type Movabl 934 Node 0, zone DMA, type Movable 1 1 2 1 2 1 1 0 1 0 2
935 Node 0, zone DMA, type Reserv 935 Node 0, zone DMA, type Reserve 0 0 0 0 0 0 0 0 0 1 0
936 Node 0, zone DMA, type Isolat 936 Node 0, zone DMA, type Isolate 0 0 0 0 0 0 0 0 0 0 0
937 Node 0, zone DMA32, type Unmovabl 937 Node 0, zone DMA32, type Unmovable 103 54 77 1 1 1 11 8 7 1 9
938 Node 0, zone DMA32, type Reclaimabl 938 Node 0, zone DMA32, type Reclaimable 0 0 2 1 0 0 0 0 1 0 0
939 Node 0, zone DMA32, type Movabl 939 Node 0, zone DMA32, type Movable 169 152 113 91 77 54 39 13 6 1 452
940 Node 0, zone DMA32, type Reserv 940 Node 0, zone DMA32, type Reserve 1 2 2 2 2 0 1 1 1 1 0
941 Node 0, zone DMA32, type Isolat 941 Node 0, zone DMA32, type Isolate 0 0 0 0 0 0 0 0 0 0 0
942 942
943 Number of blocks type Unmovable Recla 943 Number of blocks type Unmovable Reclaimable Movable Reserve Isolate
944 Node 0, zone DMA 2 944 Node 0, zone DMA 2 0 5 1 0
945 Node 0, zone DMA32 41 945 Node 0, zone DMA32 41 6 967 2 0
946 946
947 Fragmentation avoidance in the kernel works by 947 Fragmentation avoidance in the kernel works by grouping pages of different
948 migrate types into the same contiguous regions 948 migrate types into the same contiguous regions of memory called page blocks.
949 A page block is typically the size of the defa 949 A page block is typically the size of the default hugepage size, e.g. 2MB on
950 X86-64. By keeping pages grouped based on thei 950 X86-64. By keeping pages grouped based on their ability to move, the kernel
951 can reclaim pages within a page block to satis 951 can reclaim pages within a page block to satisfy a high-order allocation.
952 952
953 The pagetypinfo begins with information on the 953 The pagetypinfo begins with information on the size of a page block. It
954 then gives the same type of information as bud 954 then gives the same type of information as buddyinfo except broken down
955 by migrate-type and finishes with details on h 955 by migrate-type and finishes with details on how many page blocks of each
956 type exist. 956 type exist.
957 957
958 If min_free_kbytes has been tuned correctly (r 958 If min_free_kbytes has been tuned correctly (recommendations made by hugeadm
959 from libhugetlbfs https://github.com/libhugetl 959 from libhugetlbfs https://github.com/libhugetlbfs/libhugetlbfs/), one can
960 make an estimate of the likely number of huge 960 make an estimate of the likely number of huge pages that can be allocated
961 at a given point in time. All the "Movable" bl 961 at a given point in time. All the "Movable" blocks should be allocatable
962 unless memory has been mlock()'d. Some of the 962 unless memory has been mlock()'d. Some of the Reclaimable blocks should
963 also be allocatable although a lot of filesyst 963 also be allocatable although a lot of filesystem metadata may have to be
964 reclaimed to achieve this. 964 reclaimed to achieve this.
965 965
966 966
967 allocinfo 967 allocinfo
968 ~~~~~~~~~ 968 ~~~~~~~~~
969 969
970 Provides information about memory allocations 970 Provides information about memory allocations at all locations in the code
971 base. Each allocation in the code is identifie 971 base. Each allocation in the code is identified by its source file, line
972 number, module (if originates from a loadable 972 number, module (if originates from a loadable module) and the function calling
973 the allocation. The number of bytes allocated 973 the allocation. The number of bytes allocated and number of calls at each
974 location are reported. The first line indicate 974 location are reported. The first line indicates the version of the file, the
975 second line is the header listing fields in th 975 second line is the header listing fields in the file.
976 976
977 Example output. 977 Example output.
978 978
979 :: 979 ::
980 980
981 > tail -n +3 /proc/allocinfo | sort -rn 981 > tail -n +3 /proc/allocinfo | sort -rn
982 127664128 31168 mm/page_ext.c:270 func:a 982 127664128 31168 mm/page_ext.c:270 func:alloc_page_ext
983 56373248 4737 mm/slub.c:2259 func:allo 983 56373248 4737 mm/slub.c:2259 func:alloc_slab_page
984 14880768 3633 mm/readahead.c:247 func: 984 14880768 3633 mm/readahead.c:247 func:page_cache_ra_unbounded
985 14417920 3520 mm/mm_init.c:2530 func:a 985 14417920 3520 mm/mm_init.c:2530 func:alloc_large_system_hash
986 13377536 234 block/blk-mq.c:3421 func 986 13377536 234 block/blk-mq.c:3421 func:blk_mq_alloc_rqs
987 11718656 2861 mm/filemap.c:1919 func:_ 987 11718656 2861 mm/filemap.c:1919 func:__filemap_get_folio
988 9192960 2800 kernel/fork.c:307 func:a 988 9192960 2800 kernel/fork.c:307 func:alloc_thread_stack_node
989 4206592 4 net/netfilter/nf_conntra 989 4206592 4 net/netfilter/nf_conntrack_core.c:2567 func:nf_ct_alloc_hashtable
990 4136960 1010 drivers/staging/ctagmod/ 990 4136960 1010 drivers/staging/ctagmod/ctagmod.c:20 [ctagmod] func:ctagmod_start
991 3940352 962 mm/memory.c:4214 func:al 991 3940352 962 mm/memory.c:4214 func:alloc_anon_folio
992 2894464 22613 fs/kernfs/dir.c:615 func 992 2894464 22613 fs/kernfs/dir.c:615 func:__kernfs_new_node
993 ... 993 ...
994 994
995 995
996 meminfo 996 meminfo
997 ~~~~~~~ 997 ~~~~~~~
998 998
999 Provides information about distribution and ut 999 Provides information about distribution and utilization of memory. This
1000 varies by architecture and compile options. 1000 varies by architecture and compile options. Some of the counters reported
1001 here overlap. The memory reported by the non 1001 here overlap. The memory reported by the non overlapping counters may not
1002 add up to the overall memory usage and the di 1002 add up to the overall memory usage and the difference for some workloads
1003 can be substantial. In many cases there are 1003 can be substantial. In many cases there are other means to find out
1004 additional memory using subsystem specific in 1004 additional memory using subsystem specific interfaces, for instance
1005 /proc/net/sockstat for TCP memory allocations 1005 /proc/net/sockstat for TCP memory allocations.
1006 1006
1007 Example output. You may not have all of these 1007 Example output. You may not have all of these fields.
1008 1008
1009 :: 1009 ::
1010 1010
1011 > cat /proc/meminfo 1011 > cat /proc/meminfo
1012 1012
1013 MemTotal: 32858820 kB 1013 MemTotal: 32858820 kB
1014 MemFree: 21001236 kB 1014 MemFree: 21001236 kB
1015 MemAvailable: 27214312 kB 1015 MemAvailable: 27214312 kB
1016 Buffers: 581092 kB 1016 Buffers: 581092 kB
1017 Cached: 5587612 kB 1017 Cached: 5587612 kB
1018 SwapCached: 0 kB 1018 SwapCached: 0 kB
1019 Active: 3237152 kB 1019 Active: 3237152 kB
1020 Inactive: 7586256 kB 1020 Inactive: 7586256 kB
1021 Active(anon): 94064 kB 1021 Active(anon): 94064 kB
1022 Inactive(anon): 4570616 kB 1022 Inactive(anon): 4570616 kB
1023 Active(file): 3143088 kB 1023 Active(file): 3143088 kB
1024 Inactive(file): 3015640 kB 1024 Inactive(file): 3015640 kB
1025 Unevictable: 0 kB 1025 Unevictable: 0 kB
1026 Mlocked: 0 kB 1026 Mlocked: 0 kB
1027 SwapTotal: 0 kB 1027 SwapTotal: 0 kB
1028 SwapFree: 0 kB 1028 SwapFree: 0 kB
1029 Zswap: 1904 kB 1029 Zswap: 1904 kB
1030 Zswapped: 7792 kB 1030 Zswapped: 7792 kB
1031 Dirty: 12 kB 1031 Dirty: 12 kB
1032 Writeback: 0 kB 1032 Writeback: 0 kB
1033 AnonPages: 4654780 kB 1033 AnonPages: 4654780 kB
1034 Mapped: 266244 kB 1034 Mapped: 266244 kB
1035 Shmem: 9976 kB 1035 Shmem: 9976 kB
1036 KReclaimable: 517708 kB 1036 KReclaimable: 517708 kB
1037 Slab: 660044 kB 1037 Slab: 660044 kB
1038 SReclaimable: 517708 kB 1038 SReclaimable: 517708 kB
1039 SUnreclaim: 142336 kB 1039 SUnreclaim: 142336 kB
1040 KernelStack: 11168 kB 1040 KernelStack: 11168 kB
1041 PageTables: 20540 kB 1041 PageTables: 20540 kB
1042 SecPageTables: 0 kB 1042 SecPageTables: 0 kB
1043 NFS_Unstable: 0 kB 1043 NFS_Unstable: 0 kB
1044 Bounce: 0 kB 1044 Bounce: 0 kB
1045 WritebackTmp: 0 kB 1045 WritebackTmp: 0 kB
1046 CommitLimit: 16429408 kB 1046 CommitLimit: 16429408 kB
1047 Committed_AS: 7715148 kB 1047 Committed_AS: 7715148 kB
1048 VmallocTotal: 34359738367 kB 1048 VmallocTotal: 34359738367 kB
1049 VmallocUsed: 40444 kB 1049 VmallocUsed: 40444 kB
1050 VmallocChunk: 0 kB 1050 VmallocChunk: 0 kB
1051 Percpu: 29312 kB 1051 Percpu: 29312 kB
1052 EarlyMemtestBad: 0 kB 1052 EarlyMemtestBad: 0 kB
1053 HardwareCorrupted: 0 kB 1053 HardwareCorrupted: 0 kB
1054 AnonHugePages: 4149248 kB 1054 AnonHugePages: 4149248 kB
1055 ShmemHugePages: 0 kB 1055 ShmemHugePages: 0 kB
1056 ShmemPmdMapped: 0 kB 1056 ShmemPmdMapped: 0 kB
1057 FileHugePages: 0 kB 1057 FileHugePages: 0 kB
1058 FilePmdMapped: 0 kB 1058 FilePmdMapped: 0 kB
1059 CmaTotal: 0 kB 1059 CmaTotal: 0 kB
1060 CmaFree: 0 kB 1060 CmaFree: 0 kB
1061 HugePages_Total: 0 1061 HugePages_Total: 0
1062 HugePages_Free: 0 1062 HugePages_Free: 0
1063 HugePages_Rsvd: 0 1063 HugePages_Rsvd: 0
1064 HugePages_Surp: 0 1064 HugePages_Surp: 0
1065 Hugepagesize: 2048 kB 1065 Hugepagesize: 2048 kB
1066 Hugetlb: 0 kB 1066 Hugetlb: 0 kB
1067 DirectMap4k: 401152 kB 1067 DirectMap4k: 401152 kB
1068 DirectMap2M: 10008576 kB 1068 DirectMap2M: 10008576 kB
1069 DirectMap1G: 24117248 kB 1069 DirectMap1G: 24117248 kB
1070 1070
1071 MemTotal 1071 MemTotal
1072 Total usable RAM (i.e. physical 1072 Total usable RAM (i.e. physical RAM minus a few reserved
1073 bits and the kernel binary code 1073 bits and the kernel binary code)
1074 MemFree 1074 MemFree
1075 Total free RAM. On highmem syst 1075 Total free RAM. On highmem systems, the sum of LowFree+HighFree
1076 MemAvailable 1076 MemAvailable
1077 An estimate of how much memory 1077 An estimate of how much memory is available for starting new
1078 applications, without swapping. 1078 applications, without swapping. Calculated from MemFree,
1079 SReclaimable, the size of the f 1079 SReclaimable, the size of the file LRU lists, and the low
1080 watermarks in each zone. 1080 watermarks in each zone.
1081 The estimate takes into account 1081 The estimate takes into account that the system needs some
1082 page cache to function well, an 1082 page cache to function well, and that not all reclaimable
1083 slab will be reclaimable, due t 1083 slab will be reclaimable, due to items being in use. The
1084 impact of those factors will va 1084 impact of those factors will vary from system to system.
1085 Buffers 1085 Buffers
1086 Relatively temporary storage fo 1086 Relatively temporary storage for raw disk blocks
1087 shouldn't get tremendously larg 1087 shouldn't get tremendously large (20MB or so)
1088 Cached 1088 Cached
1089 In-memory cache for files read 1089 In-memory cache for files read from the disk (the
1090 pagecache) as well as tmpfs & s 1090 pagecache) as well as tmpfs & shmem.
1091 Doesn't include SwapCached. 1091 Doesn't include SwapCached.
1092 SwapCached 1092 SwapCached
1093 Memory that once was swapped ou 1093 Memory that once was swapped out, is swapped back in but
1094 still also is in the swapfile ( 1094 still also is in the swapfile (if memory is needed it
1095 doesn't need to be swapped out 1095 doesn't need to be swapped out AGAIN because it is already
1096 in the swapfile. This saves I/O 1096 in the swapfile. This saves I/O)
1097 Active 1097 Active
1098 Memory that has been used more 1098 Memory that has been used more recently and usually not
1099 reclaimed unless absolutely nec 1099 reclaimed unless absolutely necessary.
1100 Inactive 1100 Inactive
1101 Memory which has been less rece 1101 Memory which has been less recently used. It is more
1102 eligible to be reclaimed for ot 1102 eligible to be reclaimed for other purposes
1103 Unevictable 1103 Unevictable
1104 Memory allocated for userspace 1104 Memory allocated for userspace which cannot be reclaimed, such
1105 as mlocked pages, ramfs backing 1105 as mlocked pages, ramfs backing pages, secret memfd pages etc.
1106 Mlocked 1106 Mlocked
1107 Memory locked with mlock(). 1107 Memory locked with mlock().
1108 HighTotal, HighFree 1108 HighTotal, HighFree
1109 Highmem is all memory above ~86 1109 Highmem is all memory above ~860MB of physical memory.
1110 Highmem areas are for use by us 1110 Highmem areas are for use by userspace programs, or
1111 for the pagecache. The kernel 1111 for the pagecache. The kernel must use tricks to access
1112 this memory, making it slower t 1112 this memory, making it slower to access than lowmem.
1113 LowTotal, LowFree 1113 LowTotal, LowFree
1114 Lowmem is memory which can be u 1114 Lowmem is memory which can be used for everything that
1115 highmem can be used for, but it 1115 highmem can be used for, but it is also available for the
1116 kernel's use for its own data s 1116 kernel's use for its own data structures. Among many
1117 other things, it is where every 1117 other things, it is where everything from the Slab is
1118 allocated. Bad things happen w 1118 allocated. Bad things happen when you're out of lowmem.
1119 SwapTotal 1119 SwapTotal
1120 total amount of swap space avai 1120 total amount of swap space available
1121 SwapFree 1121 SwapFree
1122 Memory which has been evicted f 1122 Memory which has been evicted from RAM, and is temporarily
1123 on the disk 1123 on the disk
1124 Zswap 1124 Zswap
1125 Memory consumed by the zswap ba 1125 Memory consumed by the zswap backend (compressed size)
1126 Zswapped 1126 Zswapped
1127 Amount of anonymous memory stor 1127 Amount of anonymous memory stored in zswap (original size)
1128 Dirty 1128 Dirty
1129 Memory which is waiting to get 1129 Memory which is waiting to get written back to the disk
1130 Writeback 1130 Writeback
1131 Memory which is actively being 1131 Memory which is actively being written back to the disk
1132 AnonPages 1132 AnonPages
1133 Non-file backed pages mapped in 1133 Non-file backed pages mapped into userspace page tables
1134 Mapped 1134 Mapped
1135 files which have been mmapped, 1135 files which have been mmapped, such as libraries
1136 Shmem 1136 Shmem
1137 Total memory used by shared mem 1137 Total memory used by shared memory (shmem) and tmpfs
1138 KReclaimable 1138 KReclaimable
1139 Kernel allocations that the ker 1139 Kernel allocations that the kernel will attempt to reclaim
1140 under memory pressure. Includes 1140 under memory pressure. Includes SReclaimable (below), and other
1141 direct allocations with a shrin 1141 direct allocations with a shrinker.
1142 Slab 1142 Slab
1143 in-kernel data structures cache 1143 in-kernel data structures cache
1144 SReclaimable 1144 SReclaimable
1145 Part of Slab, that might be rec 1145 Part of Slab, that might be reclaimed, such as caches
1146 SUnreclaim 1146 SUnreclaim
1147 Part of Slab, that cannot be re 1147 Part of Slab, that cannot be reclaimed on memory pressure
1148 KernelStack 1148 KernelStack
1149 Memory consumed by the kernel s 1149 Memory consumed by the kernel stacks of all tasks
1150 PageTables 1150 PageTables
1151 Memory consumed by userspace pa 1151 Memory consumed by userspace page tables
1152 SecPageTables 1152 SecPageTables
1153 Memory consumed by secondary pa 1153 Memory consumed by secondary page tables, this currently includes
1154 KVM mmu and IOMMU allocations o 1154 KVM mmu and IOMMU allocations on x86 and arm64.
1155 NFS_Unstable 1155 NFS_Unstable
1156 Always zero. Previous counted p 1156 Always zero. Previous counted pages which had been written to
1157 the server, but has not been co 1157 the server, but has not been committed to stable storage.
1158 Bounce 1158 Bounce
1159 Memory used for block device "b 1159 Memory used for block device "bounce buffers"
1160 WritebackTmp 1160 WritebackTmp
1161 Memory used by FUSE for tempora 1161 Memory used by FUSE for temporary writeback buffers
1162 CommitLimit 1162 CommitLimit
1163 Based on the overcommit ratio ( 1163 Based on the overcommit ratio ('vm.overcommit_ratio'),
1164 this is the total amount of me 1164 this is the total amount of memory currently available to
1165 be allocated on the system. Thi 1165 be allocated on the system. This limit is only adhered to
1166 if strict overcommit accounting 1166 if strict overcommit accounting is enabled (mode 2 in
1167 'vm.overcommit_memory'). 1167 'vm.overcommit_memory').
1168 1168
1169 The CommitLimit is calculated w 1169 The CommitLimit is calculated with the following formula::
1170 1170
1171 CommitLimit = ([total RAM pag 1171 CommitLimit = ([total RAM pages] - [total huge TLB pages]) *
1172 overcommit_rat 1172 overcommit_ratio / 100 + [total swap pages]
1173 1173
1174 For example, on a system with 1 1174 For example, on a system with 1G of physical RAM and 7G
1175 of swap with a `vm.overcommit_r 1175 of swap with a `vm.overcommit_ratio` of 30 it would
1176 yield a CommitLimit of 7.3G. 1176 yield a CommitLimit of 7.3G.
1177 1177
1178 For more details, see the memor 1178 For more details, see the memory overcommit documentation
1179 in mm/overcommit-accounting. 1179 in mm/overcommit-accounting.
1180 Committed_AS 1180 Committed_AS
1181 The amount of memory presently 1181 The amount of memory presently allocated on the system.
1182 The committed memory is a sum o 1182 The committed memory is a sum of all of the memory which
1183 has been allocated by processes 1183 has been allocated by processes, even if it has not been
1184 "used" by them as of yet. A pro 1184 "used" by them as of yet. A process which malloc()'s 1G
1185 of memory, but only touches 300 1185 of memory, but only touches 300M of it will show up as
1186 using 1G. This 1G is memory whi 1186 using 1G. This 1G is memory which has been "committed" to
1187 by the VM and can be used at an 1187 by the VM and can be used at any time by the allocating
1188 application. With strict overco 1188 application. With strict overcommit enabled on the system
1189 (mode 2 in 'vm.overcommit_memor 1189 (mode 2 in 'vm.overcommit_memory'), allocations which would
1190 exceed the CommitLimit (detaile 1190 exceed the CommitLimit (detailed above) will not be permitted.
1191 This is useful if one needs to 1191 This is useful if one needs to guarantee that processes will
1192 not fail due to lack of memory 1192 not fail due to lack of memory once that memory has been
1193 successfully allocated. 1193 successfully allocated.
1194 VmallocTotal 1194 VmallocTotal
1195 total size of vmalloc virtual a 1195 total size of vmalloc virtual address space
1196 VmallocUsed 1196 VmallocUsed
1197 amount of vmalloc area which is 1197 amount of vmalloc area which is used
1198 VmallocChunk 1198 VmallocChunk
1199 largest contiguous block of vma 1199 largest contiguous block of vmalloc area which is free
1200 Percpu 1200 Percpu
1201 Memory allocated to the percpu 1201 Memory allocated to the percpu allocator used to back percpu
1202 allocations. This stat excludes 1202 allocations. This stat excludes the cost of metadata.
1203 EarlyMemtestBad 1203 EarlyMemtestBad
1204 The amount of RAM/memory in kB, 1204 The amount of RAM/memory in kB, that was identified as corrupted
1205 by early memtest. If memtest wa 1205 by early memtest. If memtest was not run, this field will not
1206 be displayed at all. Size is ne 1206 be displayed at all. Size is never rounded down to 0 kB.
1207 That means if 0 kB is reported, 1207 That means if 0 kB is reported, you can safely assume
1208 there was at least one pass of 1208 there was at least one pass of memtest and none of the passes
1209 found a single faulty byte of R 1209 found a single faulty byte of RAM.
1210 HardwareCorrupted 1210 HardwareCorrupted
1211 The amount of RAM/memory in KB, 1211 The amount of RAM/memory in KB, the kernel identifies as
1212 corrupted. 1212 corrupted.
1213 AnonHugePages 1213 AnonHugePages
1214 Non-file backed huge pages mapp 1214 Non-file backed huge pages mapped into userspace page tables
1215 ShmemHugePages 1215 ShmemHugePages
1216 Memory used by shared memory (s 1216 Memory used by shared memory (shmem) and tmpfs allocated
1217 with huge pages 1217 with huge pages
1218 ShmemPmdMapped 1218 ShmemPmdMapped
1219 Shared memory mapped into users 1219 Shared memory mapped into userspace with huge pages
1220 FileHugePages 1220 FileHugePages
1221 Memory used for filesystem data 1221 Memory used for filesystem data (page cache) allocated
1222 with huge pages 1222 with huge pages
1223 FilePmdMapped 1223 FilePmdMapped
1224 Page cache mapped into userspac 1224 Page cache mapped into userspace with huge pages
1225 CmaTotal 1225 CmaTotal
1226 Memory reserved for the Contigu 1226 Memory reserved for the Contiguous Memory Allocator (CMA)
1227 CmaFree 1227 CmaFree
1228 Free remaining memory in the CM 1228 Free remaining memory in the CMA reserves
1229 HugePages_Total, HugePages_Free, HugePages_Rs 1229 HugePages_Total, HugePages_Free, HugePages_Rsvd, HugePages_Surp, Hugepagesize, Hugetlb
1230 See Documentation/admin-guide/m 1230 See Documentation/admin-guide/mm/hugetlbpage.rst.
1231 DirectMap4k, DirectMap2M, DirectMap1G 1231 DirectMap4k, DirectMap2M, DirectMap1G
1232 Breakdown of page table sizes u 1232 Breakdown of page table sizes used in the kernel's
1233 identity mapping of RAM 1233 identity mapping of RAM
1234 1234
1235 vmallocinfo 1235 vmallocinfo
1236 ~~~~~~~~~~~ 1236 ~~~~~~~~~~~
1237 1237
1238 Provides information about vmalloced/vmaped a 1238 Provides information about vmalloced/vmaped areas. One line per area,
1239 containing the virtual address range of the a 1239 containing the virtual address range of the area, size in bytes,
1240 caller information of the creator, and option 1240 caller information of the creator, and optional information depending
1241 on the kind of area: 1241 on the kind of area:
1242 1242
1243 ========== ================================ 1243 ========== ===================================================
1244 pages=nr number of pages 1244 pages=nr number of pages
1245 phys=addr if a physical address was specif 1245 phys=addr if a physical address was specified
1246 ioremap I/O mapping (ioremap() and frien 1246 ioremap I/O mapping (ioremap() and friends)
1247 vmalloc vmalloc() area 1247 vmalloc vmalloc() area
1248 vmap vmap()ed pages 1248 vmap vmap()ed pages
1249 user VM_USERMAP area 1249 user VM_USERMAP area
1250 vpages buffer for pages pointers was vm 1250 vpages buffer for pages pointers was vmalloced (huge area)
1251 N<node>=nr (Only on NUMA kernels) 1251 N<node>=nr (Only on NUMA kernels)
1252 Number of pages allocated on mem 1252 Number of pages allocated on memory node <node>
1253 ========== ================================ 1253 ========== ===================================================
1254 1254
1255 :: 1255 ::
1256 1256
1257 > cat /proc/vmallocinfo 1257 > cat /proc/vmallocinfo
1258 0xffffc20000000000-0xffffc20000201000 210 1258 0xffffc20000000000-0xffffc20000201000 2101248 alloc_large_system_hash+0x204 ...
1259 /0x2c0 pages=512 vmalloc N0=128 N1=128 N2 1259 /0x2c0 pages=512 vmalloc N0=128 N1=128 N2=128 N3=128
1260 0xffffc20000201000-0xffffc20000302000 105 1260 0xffffc20000201000-0xffffc20000302000 1052672 alloc_large_system_hash+0x204 ...
1261 /0x2c0 pages=256 vmalloc N0=64 N1=64 N2=6 1261 /0x2c0 pages=256 vmalloc N0=64 N1=64 N2=64 N3=64
1262 0xffffc20000302000-0xffffc20000304000 1262 0xffffc20000302000-0xffffc20000304000 8192 acpi_tb_verify_table+0x21/0x4f...
1263 phys=7fee8000 ioremap 1263 phys=7fee8000 ioremap
1264 0xffffc20000304000-0xffffc20000307000 1 1264 0xffffc20000304000-0xffffc20000307000 12288 acpi_tb_verify_table+0x21/0x4f...
1265 phys=7fee7000 ioremap 1265 phys=7fee7000 ioremap
1266 0xffffc2000031d000-0xffffc2000031f000 1266 0xffffc2000031d000-0xffffc2000031f000 8192 init_vdso_vars+0x112/0x210
1267 0xffffc2000031f000-0xffffc2000032b000 4 1267 0xffffc2000031f000-0xffffc2000032b000 49152 cramfs_uncompress_init+0x2e ...
1268 /0x80 pages=11 vmalloc N0=3 N1=3 N2=2 N3= 1268 /0x80 pages=11 vmalloc N0=3 N1=3 N2=2 N3=3
1269 0xffffc2000033a000-0xffffc2000033d000 1 1269 0xffffc2000033a000-0xffffc2000033d000 12288 sys_swapon+0x640/0xac0 ...
1270 pages=2 vmalloc N1=2 1270 pages=2 vmalloc N1=2
1271 0xffffc20000347000-0xffffc2000034c000 2 1271 0xffffc20000347000-0xffffc2000034c000 20480 xt_alloc_table_info+0xfe ...
1272 /0x130 [x_tables] pages=4 vmalloc N0=4 1272 /0x130 [x_tables] pages=4 vmalloc N0=4
1273 0xffffffffa0000000-0xffffffffa000f000 6 1273 0xffffffffa0000000-0xffffffffa000f000 61440 sys_init_module+0xc27/0x1d00 ...
1274 pages=14 vmalloc N2=14 1274 pages=14 vmalloc N2=14
1275 0xffffffffa000f000-0xffffffffa0014000 2 1275 0xffffffffa000f000-0xffffffffa0014000 20480 sys_init_module+0xc27/0x1d00 ...
1276 pages=4 vmalloc N1=4 1276 pages=4 vmalloc N1=4
1277 0xffffffffa0014000-0xffffffffa0017000 1 1277 0xffffffffa0014000-0xffffffffa0017000 12288 sys_init_module+0xc27/0x1d00 ...
1278 pages=2 vmalloc N1=2 1278 pages=2 vmalloc N1=2
1279 0xffffffffa0017000-0xffffffffa0022000 4 1279 0xffffffffa0017000-0xffffffffa0022000 45056 sys_init_module+0xc27/0x1d00 ...
1280 pages=10 vmalloc N0=10 1280 pages=10 vmalloc N0=10
1281 1281
1282 1282
1283 softirqs 1283 softirqs
1284 ~~~~~~~~ 1284 ~~~~~~~~
1285 1285
1286 Provides counts of softirq handlers serviced 1286 Provides counts of softirq handlers serviced since boot time, for each CPU.
1287 1287
1288 :: 1288 ::
1289 1289
1290 > cat /proc/softirqs 1290 > cat /proc/softirqs
1291 CPU0 CPU1 CPU2 1291 CPU0 CPU1 CPU2 CPU3
1292 HI: 0 0 0 1292 HI: 0 0 0 0
1293 TIMER: 27166 27120 27097 1293 TIMER: 27166 27120 27097 27034
1294 NET_TX: 0 0 0 1294 NET_TX: 0 0 0 17
1295 NET_RX: 42 0 0 1295 NET_RX: 42 0 0 39
1296 BLOCK: 0 0 107 1296 BLOCK: 0 0 107 1121
1297 TASKLET: 0 0 0 1297 TASKLET: 0 0 0 290
1298 SCHED: 27035 26983 26971 1298 SCHED: 27035 26983 26971 26746
1299 HRTIMER: 0 0 0 1299 HRTIMER: 0 0 0 0
1300 RCU: 1678 1769 2178 1300 RCU: 1678 1769 2178 2250
1301 1301
1302 1.3 Networking info in /proc/net 1302 1.3 Networking info in /proc/net
1303 -------------------------------- 1303 --------------------------------
1304 1304
1305 The subdirectory /proc/net follows the us 1305 The subdirectory /proc/net follows the usual pattern. Table 1-8 shows the
1306 additional values you get for IP version 1306 additional values you get for IP version 6 if you configure the kernel to
1307 support this. Table 1-9 lists the files and t 1307 support this. Table 1-9 lists the files and their meaning.
1308 1308
1309 1309
1310 .. table:: Table 1-8: IPv6 info in /proc/net 1310 .. table:: Table 1-8: IPv6 info in /proc/net
1311 1311
1312 ========== ================================= 1312 ========== =====================================================
1313 File Content 1313 File Content
1314 ========== ================================= 1314 ========== =====================================================
1315 udp6 UDP sockets (IPv6) 1315 udp6 UDP sockets (IPv6)
1316 tcp6 TCP sockets (IPv6) 1316 tcp6 TCP sockets (IPv6)
1317 raw6 Raw device statistics (IPv6) 1317 raw6 Raw device statistics (IPv6)
1318 igmp6 IP multicast addresses, which thi 1318 igmp6 IP multicast addresses, which this host joined (IPv6)
1319 if_inet6 List of IPv6 interface addresses 1319 if_inet6 List of IPv6 interface addresses
1320 ipv6_route Kernel routing table for IPv6 1320 ipv6_route Kernel routing table for IPv6
1321 rt6_stats Global IPv6 routing tables statis 1321 rt6_stats Global IPv6 routing tables statistics
1322 sockstat6 Socket statistics (IPv6) 1322 sockstat6 Socket statistics (IPv6)
1323 snmp6 Snmp data (IPv6) 1323 snmp6 Snmp data (IPv6)
1324 ========== ================================= 1324 ========== =====================================================
1325 1325
1326 .. table:: Table 1-9: Network info in /proc/n 1326 .. table:: Table 1-9: Network info in /proc/net
1327 1327
1328 ============= ============================== 1328 ============= ================================================================
1329 File Content 1329 File Content
1330 ============= ============================== 1330 ============= ================================================================
1331 arp Kernel ARP table 1331 arp Kernel ARP table
1332 dev network devices with statistic 1332 dev network devices with statistics
1333 dev_mcast the Layer2 multicast groups a 1333 dev_mcast the Layer2 multicast groups a device is listening too
1334 (interface index, label, numbe 1334 (interface index, label, number of references, number of bound
1335 addresses). 1335 addresses).
1336 dev_stat network device status 1336 dev_stat network device status
1337 ip_fwchains Firewall chain linkage 1337 ip_fwchains Firewall chain linkage
1338 ip_fwnames Firewall chain names 1338 ip_fwnames Firewall chain names
1339 ip_masq Directory containing the masqu 1339 ip_masq Directory containing the masquerading tables
1340 ip_masquerade Major masquerading table 1340 ip_masquerade Major masquerading table
1341 netstat Network statistics 1341 netstat Network statistics
1342 raw raw device statistics 1342 raw raw device statistics
1343 route Kernel routing table 1343 route Kernel routing table
1344 rpc Directory containing rpc info 1344 rpc Directory containing rpc info
1345 rt_cache Routing cache 1345 rt_cache Routing cache
1346 snmp SNMP data 1346 snmp SNMP data
1347 sockstat Socket statistics 1347 sockstat Socket statistics
1348 softnet_stat Per-CPU incoming packets queue 1348 softnet_stat Per-CPU incoming packets queues statistics of online CPUs
1349 tcp TCP sockets 1349 tcp TCP sockets
1350 udp UDP sockets 1350 udp UDP sockets
1351 unix UNIX domain sockets 1351 unix UNIX domain sockets
1352 wireless Wireless interface data (Wavel 1352 wireless Wireless interface data (Wavelan etc)
1353 igmp IP multicast addresses, which 1353 igmp IP multicast addresses, which this host joined
1354 psched Global packet scheduler parame 1354 psched Global packet scheduler parameters.
1355 netlink List of PF_NETLINK sockets 1355 netlink List of PF_NETLINK sockets
1356 ip_mr_vifs List of multicast virtual inte 1356 ip_mr_vifs List of multicast virtual interfaces
1357 ip_mr_cache List of multicast routing cach 1357 ip_mr_cache List of multicast routing cache
1358 ============= ============================== 1358 ============= ================================================================
1359 1359
1360 You can use this information to see which 1360 You can use this information to see which network devices are available in
1361 your system and how much traffic was routed o 1361 your system and how much traffic was routed over those devices::
1362 1362
1363 > cat /proc/net/dev 1363 > cat /proc/net/dev
1364 Inter-|Receive 1364 Inter-|Receive |[...
1365 face |bytes packets errs drop fifo fram 1365 face |bytes packets errs drop fifo frame compressed multicast|[...
1366 lo: 908188 5596 0 0 0 1366 lo: 908188 5596 0 0 0 0 0 0 [...
1367 ppp0:15475140 20721 410 0 0 41 1367 ppp0:15475140 20721 410 0 0 410 0 0 [...
1368 eth0: 614530 7085 0 0 0 1368 eth0: 614530 7085 0 0 0 0 0 1 [...
1369 1369
1370 ...] Transmit 1370 ...] Transmit
1371 ...] bytes packets errs drop fifo colls 1371 ...] bytes packets errs drop fifo colls carrier compressed
1372 ...] 908188 5596 0 0 0 0 1372 ...] 908188 5596 0 0 0 0 0 0
1373 ...] 1375103 17405 0 0 0 0 1373 ...] 1375103 17405 0 0 0 0 0 0
1374 ...] 1703981 5535 0 0 0 3 1374 ...] 1703981 5535 0 0 0 3 0 0
1375 1375
1376 In addition, each Channel Bond interface has 1376 In addition, each Channel Bond interface has its own directory. For
1377 example, the bond0 device will have a directo 1377 example, the bond0 device will have a directory called /proc/net/bond0/.
1378 It will contain information that is specific 1378 It will contain information that is specific to that bond, such as the
1379 current slaves of the bond, the link status o 1379 current slaves of the bond, the link status of the slaves, and how
1380 many times the slaves link has failed. 1380 many times the slaves link has failed.
1381 1381
1382 1.4 SCSI info 1382 1.4 SCSI info
1383 ------------- 1383 -------------
1384 1384
1385 If you have a SCSI or ATA host adapter in you 1385 If you have a SCSI or ATA host adapter in your system, you'll find a
1386 subdirectory named after the driver for this 1386 subdirectory named after the driver for this adapter in /proc/scsi.
1387 You'll also see a list of all recognized SCSI 1387 You'll also see a list of all recognized SCSI devices in /proc/scsi::
1388 1388
1389 >cat /proc/scsi/scsi 1389 >cat /proc/scsi/scsi
1390 Attached devices: 1390 Attached devices:
1391 Host: scsi0 Channel: 00 Id: 00 Lun: 00 1391 Host: scsi0 Channel: 00 Id: 00 Lun: 00
1392 Vendor: IBM Model: DGHS09U 1392 Vendor: IBM Model: DGHS09U Rev: 03E0
1393 Type: Direct-Access 1393 Type: Direct-Access ANSI SCSI revision: 03
1394 Host: scsi0 Channel: 00 Id: 06 Lun: 00 1394 Host: scsi0 Channel: 00 Id: 06 Lun: 00
1395 Vendor: PIONEER Model: CD-ROM DR-U06S 1395 Vendor: PIONEER Model: CD-ROM DR-U06S Rev: 1.04
1396 Type: CD-ROM 1396 Type: CD-ROM ANSI SCSI revision: 02
1397 1397
1398 1398
1399 The directory named after the driver has o 1399 The directory named after the driver has one file for each adapter found in
1400 the system. These files contain informatio 1400 the system. These files contain information about the controller, including
1401 the used IRQ and the IO address range. T 1401 the used IRQ and the IO address range. The amount of information shown is
1402 dependent on the adapter you use. The exampl 1402 dependent on the adapter you use. The example shows the output for an Adaptec
1403 AHA-2940 SCSI adapter:: 1403 AHA-2940 SCSI adapter::
1404 1404
1405 > cat /proc/scsi/aic7xxx/0 1405 > cat /proc/scsi/aic7xxx/0
1406 1406
1407 Adaptec AIC7xxx driver version: 5.1.19/3.2. 1407 Adaptec AIC7xxx driver version: 5.1.19/3.2.4
1408 Compile Options: 1408 Compile Options:
1409 TCQ Enabled By Default : Disabled 1409 TCQ Enabled By Default : Disabled
1410 AIC7XXX_PROC_STATS : Disabled 1410 AIC7XXX_PROC_STATS : Disabled
1411 AIC7XXX_RESET_DELAY : 5 1411 AIC7XXX_RESET_DELAY : 5
1412 Adapter Configuration: 1412 Adapter Configuration:
1413 SCSI Adapter: Adaptec AHA-294X U 1413 SCSI Adapter: Adaptec AHA-294X Ultra SCSI host adapter
1414 Ultra Wide Contr 1414 Ultra Wide Controller
1415 PCI MMAPed I/O Base: 0xeb001000 1415 PCI MMAPed I/O Base: 0xeb001000
1416 Adapter SEEPROM Config: SEEPROM found and 1416 Adapter SEEPROM Config: SEEPROM found and used.
1417 Adaptec SCSI BIOS: Enabled 1417 Adaptec SCSI BIOS: Enabled
1418 IRQ: 10 1418 IRQ: 10
1419 SCBs: Active 0, Max Acti 1419 SCBs: Active 0, Max Active 2,
1420 Allocated 15, HW 1 1420 Allocated 15, HW 16, Page 255
1421 Interrupts: 160328 1421 Interrupts: 160328
1422 BIOS Control Word: 0x18b6 1422 BIOS Control Word: 0x18b6
1423 Adapter Control Word: 0x005b 1423 Adapter Control Word: 0x005b
1424 Extended Translation: Enabled 1424 Extended Translation: Enabled
1425 Disconnect Enable Flags: 0xffff 1425 Disconnect Enable Flags: 0xffff
1426 Ultra Enable Flags: 0x0001 1426 Ultra Enable Flags: 0x0001
1427 Tag Queue Enable Flags: 0x0000 1427 Tag Queue Enable Flags: 0x0000
1428 Ordered Queue Tag Flags: 0x0000 1428 Ordered Queue Tag Flags: 0x0000
1429 Default Tag Queue Depth: 8 1429 Default Tag Queue Depth: 8
1430 Tagged Queue By Device array for aic7xx 1430 Tagged Queue By Device array for aic7xxx host instance 0:
1431 {255,255,255,255,255,255,255,255,255, 1431 {255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255}
1432 Actual queue depth per device for aic7x 1432 Actual queue depth per device for aic7xxx host instance 0:
1433 {1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1} 1433 {1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1}
1434 Statistics: 1434 Statistics:
1435 (scsi0:0:0:0) 1435 (scsi0:0:0:0)
1436 Device using Wide/Sync transfers at 40.0 1436 Device using Wide/Sync transfers at 40.0 MByte/sec, offset 8
1437 Transinfo settings: current(12/8/1/0), go 1437 Transinfo settings: current(12/8/1/0), goal(12/8/1/0), user(12/15/1/0)
1438 Total transfers 160151 (74577 reads and 8 1438 Total transfers 160151 (74577 reads and 85574 writes)
1439 (scsi0:0:6:0) 1439 (scsi0:0:6:0)
1440 Device using Narrow/Sync transfers at 5.0 1440 Device using Narrow/Sync transfers at 5.0 MByte/sec, offset 15
1441 Transinfo settings: current(50/15/0/0), g 1441 Transinfo settings: current(50/15/0/0), goal(50/15/0/0), user(50/15/0/0)
1442 Total transfers 0 (0 reads and 0 writes) 1442 Total transfers 0 (0 reads and 0 writes)
1443 1443
1444 1444
1445 1.5 Parallel port info in /proc/parport 1445 1.5 Parallel port info in /proc/parport
1446 --------------------------------------- 1446 ---------------------------------------
1447 1447
1448 The directory /proc/parport contains inform 1448 The directory /proc/parport contains information about the parallel ports of
1449 your system. It has one subdirectory for 1449 your system. It has one subdirectory for each port, named after the port
1450 number (0,1,2,...). 1450 number (0,1,2,...).
1451 1451
1452 These directories contain the four files show 1452 These directories contain the four files shown in Table 1-10.
1453 1453
1454 1454
1455 .. table:: Table 1-10: Files in /proc/parport 1455 .. table:: Table 1-10: Files in /proc/parport
1456 1456
1457 ========= ================================== 1457 ========= ====================================================================
1458 File Content 1458 File Content
1459 ========= ================================== 1459 ========= ====================================================================
1460 autoprobe Any IEEE-1284 device ID informatio 1460 autoprobe Any IEEE-1284 device ID information that has been acquired.
1461 devices list of the device drivers using t 1461 devices list of the device drivers using that port. A + will appear by the
1462 name of the device currently using 1462 name of the device currently using the port (it might not appear
1463 against any). 1463 against any).
1464 hardware Parallel port's base address, IRQ 1464 hardware Parallel port's base address, IRQ line and DMA channel.
1465 irq IRQ that parport is using for that 1465 irq IRQ that parport is using for that port. This is in a separate
1466 file to allow you to alter it by w 1466 file to allow you to alter it by writing a new value in (IRQ
1467 number or none). 1467 number or none).
1468 ========= ================================== 1468 ========= ====================================================================
1469 1469
1470 1.6 TTY info in /proc/tty 1470 1.6 TTY info in /proc/tty
1471 ------------------------- 1471 -------------------------
1472 1472
1473 Information about the available and actual 1473 Information about the available and actually used tty's can be found in the
1474 directory /proc/tty. You'll find entries fo 1474 directory /proc/tty. You'll find entries for drivers and line disciplines in
1475 this directory, as shown in Table 1-11. 1475 this directory, as shown in Table 1-11.
1476 1476
1477 1477
1478 .. table:: Table 1-11: Files in /proc/tty 1478 .. table:: Table 1-11: Files in /proc/tty
1479 1479
1480 ============= ============================== 1480 ============= ==============================================
1481 File Content 1481 File Content
1482 ============= ============================== 1482 ============= ==============================================
1483 drivers list of drivers and their usag 1483 drivers list of drivers and their usage
1484 ldiscs registered line disciplines 1484 ldiscs registered line disciplines
1485 driver/serial usage statistic and status of 1485 driver/serial usage statistic and status of single tty lines
1486 ============= ============================== 1486 ============= ==============================================
1487 1487
1488 To see which tty's are currently in use, 1488 To see which tty's are currently in use, you can simply look into the file
1489 /proc/tty/drivers:: 1489 /proc/tty/drivers::
1490 1490
1491 > cat /proc/tty/drivers 1491 > cat /proc/tty/drivers
1492 pty_slave /dev/pts 136 0- 1492 pty_slave /dev/pts 136 0-255 pty:slave
1493 pty_master /dev/ptm 128 0- 1493 pty_master /dev/ptm 128 0-255 pty:master
1494 pty_slave /dev/ttyp 3 0- 1494 pty_slave /dev/ttyp 3 0-255 pty:slave
1495 pty_master /dev/pty 2 0- 1495 pty_master /dev/pty 2 0-255 pty:master
1496 serial /dev/cua 5 64 1496 serial /dev/cua 5 64-67 serial:callout
1497 serial /dev/ttyS 4 64 1497 serial /dev/ttyS 4 64-67 serial
1498 /dev/tty0 /dev/tty0 4 1498 /dev/tty0 /dev/tty0 4 0 system:vtmaster
1499 /dev/ptmx /dev/ptmx 5 1499 /dev/ptmx /dev/ptmx 5 2 system
1500 /dev/console /dev/console 5 1500 /dev/console /dev/console 5 1 system:console
1501 /dev/tty /dev/tty 5 1501 /dev/tty /dev/tty 5 0 system:/dev/tty
1502 unknown /dev/tty 4 1 1502 unknown /dev/tty 4 1-63 console
1503 1503
1504 1504
1505 1.7 Miscellaneous kernel statistics in /proc/ 1505 1.7 Miscellaneous kernel statistics in /proc/stat
1506 --------------------------------------------- 1506 -------------------------------------------------
1507 1507
1508 Various pieces of information about kerne 1508 Various pieces of information about kernel activity are available in the
1509 /proc/stat file. All of the numbers report 1509 /proc/stat file. All of the numbers reported in this file are aggregates
1510 since the system first booted. For a quick l 1510 since the system first booted. For a quick look, simply cat the file::
1511 1511
1512 > cat /proc/stat 1512 > cat /proc/stat
1513 cpu 237902850 368826709 106375398 18735175 1513 cpu 237902850 368826709 106375398 1873517540 1135548 0 14507935 0 0 0
1514 cpu0 60045249 91891769 26331539 468411416 4 1514 cpu0 60045249 91891769 26331539 468411416 495718 0 5739640 0 0 0
1515 cpu1 59746288 91759249 26609887 468860630 3 1515 cpu1 59746288 91759249 26609887 468860630 312281 0 4384817 0 0 0
1516 cpu2 59489247 92985423 26904446 467808813 1 1516 cpu2 59489247 92985423 26904446 467808813 171668 0 2268998 0 0 0
1517 cpu3 58622065 92190267 26529524 468436680 1 1517 cpu3 58622065 92190267 26529524 468436680 155879 0 2114478 0 0 0
1518 intr 8688370575 8 3373 0 0 0 0 0 0 1 40791 1518 intr 8688370575 8 3373 0 0 0 0 0 0 1 40791 0 0 353317 0 0 0 0 224789828 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 190974333 41958554 123983334 43 0 224593 0 0 0 <more 0's deleted>
1519 ctxt 22848221062 1519 ctxt 22848221062
1520 btime 1605316999 1520 btime 1605316999
1521 processes 746787147 1521 processes 746787147
1522 procs_running 2 1522 procs_running 2
1523 procs_blocked 0 1523 procs_blocked 0
1524 softirq 12121874454 100099120 3938138295 12 1524 softirq 12121874454 100099120 3938138295 127375644 2795979 187870761 0 173808342 3072582055 52608 224184354
1525 1525
1526 The very first "cpu" line aggregates the nu 1526 The very first "cpu" line aggregates the numbers in all of the other "cpuN"
1527 lines. These numbers identify the amount of 1527 lines. These numbers identify the amount of time the CPU has spent performing
1528 different kinds of work. Time units are in U 1528 different kinds of work. Time units are in USER_HZ (typically hundredths of a
1529 second). The meanings of the columns are as 1529 second). The meanings of the columns are as follows, from left to right:
1530 1530
1531 - user: normal processes executing in user mo 1531 - user: normal processes executing in user mode
1532 - nice: niced processes executing in user mod 1532 - nice: niced processes executing in user mode
1533 - system: processes executing in kernel mode 1533 - system: processes executing in kernel mode
1534 - idle: twiddling thumbs 1534 - idle: twiddling thumbs
1535 - iowait: In a word, iowait stands for waitin 1535 - iowait: In a word, iowait stands for waiting for I/O to complete. But there
1536 are several problems: 1536 are several problems:
1537 1537
1538 1. CPU will not wait for I/O to complete, i 1538 1. CPU will not wait for I/O to complete, iowait is the time that a task is
1539 waiting for I/O to complete. When CPU go 1539 waiting for I/O to complete. When CPU goes into idle state for
1540 outstanding task I/O, another task will 1540 outstanding task I/O, another task will be scheduled on this CPU.
1541 2. In a multi-core CPU, the task waiting fo 1541 2. In a multi-core CPU, the task waiting for I/O to complete is not running
1542 on any CPU, so the iowait of each CPU is 1542 on any CPU, so the iowait of each CPU is difficult to calculate.
1543 3. The value of iowait field in /proc/stat 1543 3. The value of iowait field in /proc/stat will decrease in certain
1544 conditions. 1544 conditions.
1545 1545
1546 So, the iowait is not reliable by reading f 1546 So, the iowait is not reliable by reading from /proc/stat.
1547 - irq: servicing interrupts 1547 - irq: servicing interrupts
1548 - softirq: servicing softirqs 1548 - softirq: servicing softirqs
1549 - steal: involuntary wait 1549 - steal: involuntary wait
1550 - guest: running a normal guest 1550 - guest: running a normal guest
1551 - guest_nice: running a niced guest 1551 - guest_nice: running a niced guest
1552 1552
1553 The "intr" line gives counts of interrupts s 1553 The "intr" line gives counts of interrupts serviced since boot time, for each
1554 of the possible system interrupts. The fir 1554 of the possible system interrupts. The first column is the total of all
1555 interrupts serviced including unnumbered a 1555 interrupts serviced including unnumbered architecture specific interrupts;
1556 each subsequent column is the total for tha 1556 each subsequent column is the total for that particular numbered interrupt.
1557 Unnumbered interrupts are not shown, only sum 1557 Unnumbered interrupts are not shown, only summed into the total.
1558 1558
1559 The "ctxt" line gives the total number of con 1559 The "ctxt" line gives the total number of context switches across all CPUs.
1560 1560
1561 The "btime" line gives the time at which the 1561 The "btime" line gives the time at which the system booted, in seconds since
1562 the Unix epoch. 1562 the Unix epoch.
1563 1563
1564 The "processes" line gives the number of pro 1564 The "processes" line gives the number of processes and threads created, which
1565 includes (but is not limited to) those cre 1565 includes (but is not limited to) those created by calls to the fork() and
1566 clone() system calls. 1566 clone() system calls.
1567 1567
1568 The "procs_running" line gives the total numb 1568 The "procs_running" line gives the total number of threads that are
1569 running or ready to run (i.e., the total numb 1569 running or ready to run (i.e., the total number of runnable threads).
1570 1570
1571 The "procs_blocked" line gives the number 1571 The "procs_blocked" line gives the number of processes currently blocked,
1572 waiting for I/O to complete. 1572 waiting for I/O to complete.
1573 1573
1574 The "softirq" line gives counts of softirqs s 1574 The "softirq" line gives counts of softirqs serviced since boot time, for each
1575 of the possible system softirqs. The first co 1575 of the possible system softirqs. The first column is the total of all
1576 softirqs serviced; each subsequent column is 1576 softirqs serviced; each subsequent column is the total for that particular
1577 softirq. 1577 softirq.
1578 1578
1579 1579
1580 1.8 Ext4 file system parameters 1580 1.8 Ext4 file system parameters
1581 ------------------------------- 1581 -------------------------------
1582 1582
1583 Information about mounted ext4 file systems c 1583 Information about mounted ext4 file systems can be found in
1584 /proc/fs/ext4. Each mounted filesystem will 1584 /proc/fs/ext4. Each mounted filesystem will have a directory in
1585 /proc/fs/ext4 based on its device name (i.e., 1585 /proc/fs/ext4 based on its device name (i.e., /proc/fs/ext4/hdc or
1586 /proc/fs/ext4/sda9 or /proc/fs/ext4/dm-0). 1586 /proc/fs/ext4/sda9 or /proc/fs/ext4/dm-0). The files in each per-device
1587 directory are shown in Table 1-12, below. 1587 directory are shown in Table 1-12, below.
1588 1588
1589 .. table:: Table 1-12: Files in /proc/fs/ext4 1589 .. table:: Table 1-12: Files in /proc/fs/ext4/<devname>
1590 1590
1591 ============== ============================ 1591 ============== ==========================================================
1592 File Content 1592 File Content
1593 mb_groups details of multiblock alloca 1593 mb_groups details of multiblock allocator buddy cache of free blocks
1594 ============== ============================ 1594 ============== ==========================================================
1595 1595
1596 1.9 /proc/consoles 1596 1.9 /proc/consoles
1597 ------------------- 1597 -------------------
1598 Shows registered system console lines. 1598 Shows registered system console lines.
1599 1599
1600 To see which character device lines are curre 1600 To see which character device lines are currently used for the system console
1601 /dev/console, you may simply look into the fi 1601 /dev/console, you may simply look into the file /proc/consoles::
1602 1602
1603 > cat /proc/consoles 1603 > cat /proc/consoles
1604 tty0 -WU (ECp) 4:7 1604 tty0 -WU (ECp) 4:7
1605 ttyS0 -W- (Ep) 4:64 1605 ttyS0 -W- (Ep) 4:64
1606 1606
1607 The columns are: 1607 The columns are:
1608 1608
1609 +--------------------+----------------------- 1609 +--------------------+-------------------------------------------------------+
1610 | device | name of the device 1610 | device | name of the device |
1611 +====================+======================= 1611 +====================+=======================================================+
1612 | operations | * R = can do read oper 1612 | operations | * R = can do read operations |
1613 | | * W = can do write ope 1613 | | * W = can do write operations |
1614 | | * U = can do unblank 1614 | | * U = can do unblank |
1615 +--------------------+----------------------- 1615 +--------------------+-------------------------------------------------------+
1616 | flags | * E = it is enabled 1616 | flags | * E = it is enabled |
1617 | | * C = it is preferred 1617 | | * C = it is preferred console |
1618 | | * B = it is primary bo 1618 | | * B = it is primary boot console |
1619 | | * p = it is used for p 1619 | | * p = it is used for printk buffer |
1620 | | * b = it is not a TTY 1620 | | * b = it is not a TTY but a Braille device |
1621 | | * a = it is safe to us 1621 | | * a = it is safe to use when cpu is offline |
1622 +--------------------+----------------------- 1622 +--------------------+-------------------------------------------------------+
1623 | major:minor | major and minor number 1623 | major:minor | major and minor number of the device separated by a |
1624 | | colon 1624 | | colon |
1625 +--------------------+----------------------- 1625 +--------------------+-------------------------------------------------------+
1626 1626
1627 Summary 1627 Summary
1628 ------- 1628 -------
1629 1629
1630 The /proc file system serves information abou 1630 The /proc file system serves information about the running system. It not only
1631 allows access to process data but also allows 1631 allows access to process data but also allows you to request the kernel status
1632 by reading files in the hierarchy. 1632 by reading files in the hierarchy.
1633 1633
1634 The directory structure of /proc reflects t 1634 The directory structure of /proc reflects the types of information and makes
1635 it easy, if not obvious, where to look for sp 1635 it easy, if not obvious, where to look for specific data.
1636 1636
1637 Chapter 2: Modifying System Parameters 1637 Chapter 2: Modifying System Parameters
1638 ====================================== 1638 ======================================
1639 1639
1640 In This Chapter 1640 In This Chapter
1641 --------------- 1641 ---------------
1642 1642
1643 * Modifying kernel parameters by writing into 1643 * Modifying kernel parameters by writing into files found in /proc/sys
1644 * Exploring the files which modify certain pa 1644 * Exploring the files which modify certain parameters
1645 * Review of the /proc/sys file tree 1645 * Review of the /proc/sys file tree
1646 1646
1647 --------------------------------------------- 1647 ------------------------------------------------------------------------------
1648 1648
1649 A very interesting part of /proc is the dire 1649 A very interesting part of /proc is the directory /proc/sys. This is not only
1650 a source of information, it also allows yo 1650 a source of information, it also allows you to change parameters within the
1651 kernel. Be very careful when attempting th 1651 kernel. Be very careful when attempting this. You can optimize your system,
1652 but you can also cause it to crash. Ne 1652 but you can also cause it to crash. Never alter kernel parameters on a
1653 production system. Set up a development m 1653 production system. Set up a development machine and test to make sure that
1654 everything works the way you want it to. Y 1654 everything works the way you want it to. You may have no alternative but to
1655 reboot the machine once an error has been mad 1655 reboot the machine once an error has been made.
1656 1656
1657 To change a value, simply echo the new v 1657 To change a value, simply echo the new value into the file.
1658 You need to be root to do this. You can cre 1658 You need to be root to do this. You can create your own boot script
1659 to perform this every time your system boots. 1659 to perform this every time your system boots.
1660 1660
1661 The files in /proc/sys can be used to fine t 1661 The files in /proc/sys can be used to fine tune and monitor miscellaneous and
1662 general things in the operation of the Linu 1662 general things in the operation of the Linux kernel. Since some of the files
1663 can inadvertently disrupt your system, it 1663 can inadvertently disrupt your system, it is advisable to read both
1664 documentation and source before actually ma 1664 documentation and source before actually making adjustments. In any case, be
1665 very careful when writing to any of thes 1665 very careful when writing to any of these files. The entries in /proc may
1666 change slightly between the 2.1.* and the 2.2 1666 change slightly between the 2.1.* and the 2.2 kernel, so if there is any doubt
1667 review the kernel documentation in the direct 1667 review the kernel documentation in the directory linux/Documentation.
1668 This chapter is heavily based on the docu 1668 This chapter is heavily based on the documentation included in the pre 2.2
1669 kernels, and became part of it in version 2.2 1669 kernels, and became part of it in version 2.2.1 of the Linux kernel.
1670 1670
1671 Please see: Documentation/admin-guide/sysctl/ 1671 Please see: Documentation/admin-guide/sysctl/ directory for descriptions of
1672 these entries. 1672 these entries.
1673 1673
1674 Summary 1674 Summary
1675 ------- 1675 -------
1676 1676
1677 Certain aspects of kernel behavior can be 1677 Certain aspects of kernel behavior can be modified at runtime, without the
1678 need to recompile the kernel, or even to re 1678 need to recompile the kernel, or even to reboot the system. The files in the
1679 /proc/sys tree can not only be read, but al 1679 /proc/sys tree can not only be read, but also modified. You can use the echo
1680 command to write value into these files, ther 1680 command to write value into these files, thereby changing the default settings
1681 of the kernel. 1681 of the kernel.
1682 1682
1683 1683
1684 Chapter 3: Per-process Parameters 1684 Chapter 3: Per-process Parameters
1685 ================================= 1685 =================================
1686 1686
1687 3.1 /proc/<pid>/oom_adj & /proc/<pid>/oom_sco 1687 3.1 /proc/<pid>/oom_adj & /proc/<pid>/oom_score_adj- Adjust the oom-killer score
1688 --------------------------------------------- 1688 --------------------------------------------------------------------------------
1689 1689
1690 These files can be used to adjust the badness 1690 These files can be used to adjust the badness heuristic used to select which
1691 process gets killed in out of memory (oom) co 1691 process gets killed in out of memory (oom) conditions.
1692 1692
1693 The badness heuristic assigns a value to each 1693 The badness heuristic assigns a value to each candidate task ranging from 0
1694 (never kill) to 1000 (always kill) to determi 1694 (never kill) to 1000 (always kill) to determine which process is targeted. The
1695 units are roughly a proportion along that ran 1695 units are roughly a proportion along that range of allowed memory the process
1696 may allocate from based on an estimation of i 1696 may allocate from based on an estimation of its current memory and swap use.
1697 For example, if a task is using all allowed m 1697 For example, if a task is using all allowed memory, its badness score will be
1698 1000. If it is using half of its allowed mem 1698 1000. If it is using half of its allowed memory, its score will be 500.
1699 1699
1700 The amount of "allowed" memory depends on the 1700 The amount of "allowed" memory depends on the context in which the oom killer
1701 was called. If it is due to the memory assig 1701 was called. If it is due to the memory assigned to the allocating task's cpuset
1702 being exhausted, the allowed memory represent 1702 being exhausted, the allowed memory represents the set of mems assigned to that
1703 cpuset. If it is due to a mempolicy's node(s 1703 cpuset. If it is due to a mempolicy's node(s) being exhausted, the allowed
1704 memory represents the set of mempolicy nodes. 1704 memory represents the set of mempolicy nodes. If it is due to a memory
1705 limit (or swap limit) being reached, the allo 1705 limit (or swap limit) being reached, the allowed memory is that configured
1706 limit. Finally, if it is due to the entire s 1706 limit. Finally, if it is due to the entire system being out of memory, the
1707 allowed memory represents all allocatable res 1707 allowed memory represents all allocatable resources.
1708 1708
1709 The value of /proc/<pid>/oom_score_adj is add 1709 The value of /proc/<pid>/oom_score_adj is added to the badness score before it
1710 is used to determine which task to kill. Acc 1710 is used to determine which task to kill. Acceptable values range from -1000
1711 (OOM_SCORE_ADJ_MIN) to +1000 (OOM_SCORE_ADJ_M 1711 (OOM_SCORE_ADJ_MIN) to +1000 (OOM_SCORE_ADJ_MAX). This allows userspace to
1712 polarize the preference for oom killing eithe 1712 polarize the preference for oom killing either by always preferring a certain
1713 task or completely disabling it. The lowest 1713 task or completely disabling it. The lowest possible value, -1000, is
1714 equivalent to disabling oom killing entirely 1714 equivalent to disabling oom killing entirely for that task since it will always
1715 report a badness score of 0. 1715 report a badness score of 0.
1716 1716
1717 Consequently, it is very simple for userspace 1717 Consequently, it is very simple for userspace to define the amount of memory to
1718 consider for each task. Setting a /proc/<pid 1718 consider for each task. Setting a /proc/<pid>/oom_score_adj value of +500, for
1719 example, is roughly equivalent to allowing th 1719 example, is roughly equivalent to allowing the remainder of tasks sharing the
1720 same system, cpuset, mempolicy, or memory con 1720 same system, cpuset, mempolicy, or memory controller resources to use at least
1721 50% more memory. A value of -500, on the oth 1721 50% more memory. A value of -500, on the other hand, would be roughly
1722 equivalent to discounting 50% of the task's a 1722 equivalent to discounting 50% of the task's allowed memory from being considered
1723 as scoring against the task. 1723 as scoring against the task.
1724 1724
1725 For backwards compatibility with previous ker 1725 For backwards compatibility with previous kernels, /proc/<pid>/oom_adj may also
1726 be used to tune the badness score. Its accep 1726 be used to tune the badness score. Its acceptable values range from -16
1727 (OOM_ADJUST_MIN) to +15 (OOM_ADJUST_MAX) and 1727 (OOM_ADJUST_MIN) to +15 (OOM_ADJUST_MAX) and a special value of -17
1728 (OOM_DISABLE) to disable oom killing entirely 1728 (OOM_DISABLE) to disable oom killing entirely for that task. Its value is
1729 scaled linearly with /proc/<pid>/oom_score_ad 1729 scaled linearly with /proc/<pid>/oom_score_adj.
1730 1730
1731 The value of /proc/<pid>/oom_score_adj may be 1731 The value of /proc/<pid>/oom_score_adj may be reduced no lower than the last
1732 value set by a CAP_SYS_RESOURCE process. To r 1732 value set by a CAP_SYS_RESOURCE process. To reduce the value any lower
1733 requires CAP_SYS_RESOURCE. 1733 requires CAP_SYS_RESOURCE.
1734 1734
1735 1735
1736 3.2 /proc/<pid>/oom_score - Display current o 1736 3.2 /proc/<pid>/oom_score - Display current oom-killer score
1737 --------------------------------------------- 1737 -------------------------------------------------------------
1738 1738
1739 This file can be used to check the current sc 1739 This file can be used to check the current score used by the oom-killer for
1740 any given <pid>. Use it together with /proc/< 1740 any given <pid>. Use it together with /proc/<pid>/oom_score_adj to tune which
1741 process should be killed in an out-of-memory 1741 process should be killed in an out-of-memory situation.
1742 1742
1743 Please note that the exported value includes 1743 Please note that the exported value includes oom_score_adj so it is
1744 effectively in range [0,2000]. 1744 effectively in range [0,2000].
1745 1745
1746 1746
1747 3.3 /proc/<pid>/io - Display the IO accounti 1747 3.3 /proc/<pid>/io - Display the IO accounting fields
1748 --------------------------------------------- 1748 -------------------------------------------------------
1749 1749
1750 This file contains IO statistics for each run 1750 This file contains IO statistics for each running process.
1751 1751
1752 Example 1752 Example
1753 ~~~~~~~ 1753 ~~~~~~~
1754 1754
1755 :: 1755 ::
1756 1756
1757 test:/tmp # dd if=/dev/zero of=/tmp/test. 1757 test:/tmp # dd if=/dev/zero of=/tmp/test.dat &
1758 [1] 3828 1758 [1] 3828
1759 1759
1760 test:/tmp # cat /proc/3828/io 1760 test:/tmp # cat /proc/3828/io
1761 rchar: 323934931 1761 rchar: 323934931
1762 wchar: 323929600 1762 wchar: 323929600
1763 syscr: 632687 1763 syscr: 632687
1764 syscw: 632675 1764 syscw: 632675
1765 read_bytes: 0 1765 read_bytes: 0
1766 write_bytes: 323932160 1766 write_bytes: 323932160
1767 cancelled_write_bytes: 0 1767 cancelled_write_bytes: 0
1768 1768
1769 1769
1770 Description 1770 Description
1771 ~~~~~~~~~~~ 1771 ~~~~~~~~~~~
1772 1772
1773 rchar 1773 rchar
1774 ^^^^^ 1774 ^^^^^
1775 1775
1776 I/O counter: chars read 1776 I/O counter: chars read
1777 The number of bytes which this task has cause 1777 The number of bytes which this task has caused to be read from storage. This
1778 is simply the sum of bytes which this process 1778 is simply the sum of bytes which this process passed to read() and pread().
1779 It includes things like tty IO and it is unaf 1779 It includes things like tty IO and it is unaffected by whether or not actual
1780 physical disk IO was required (the read might 1780 physical disk IO was required (the read might have been satisfied from
1781 pagecache). 1781 pagecache).
1782 1782
1783 1783
1784 wchar 1784 wchar
1785 ^^^^^ 1785 ^^^^^
1786 1786
1787 I/O counter: chars written 1787 I/O counter: chars written
1788 The number of bytes which this task has cause 1788 The number of bytes which this task has caused, or shall cause to be written
1789 to disk. Similar caveats apply here as with r 1789 to disk. Similar caveats apply here as with rchar.
1790 1790
1791 1791
1792 syscr 1792 syscr
1793 ^^^^^ 1793 ^^^^^
1794 1794
1795 I/O counter: read syscalls 1795 I/O counter: read syscalls
1796 Attempt to count the number of read I/O opera 1796 Attempt to count the number of read I/O operations, i.e. syscalls like read()
1797 and pread(). 1797 and pread().
1798 1798
1799 1799
1800 syscw 1800 syscw
1801 ^^^^^ 1801 ^^^^^
1802 1802
1803 I/O counter: write syscalls 1803 I/O counter: write syscalls
1804 Attempt to count the number of write I/O oper 1804 Attempt to count the number of write I/O operations, i.e. syscalls like
1805 write() and pwrite(). 1805 write() and pwrite().
1806 1806
1807 1807
1808 read_bytes 1808 read_bytes
1809 ^^^^^^^^^^ 1809 ^^^^^^^^^^
1810 1810
1811 I/O counter: bytes read 1811 I/O counter: bytes read
1812 Attempt to count the number of bytes which th 1812 Attempt to count the number of bytes which this process really did cause to
1813 be fetched from the storage layer. Done at th 1813 be fetched from the storage layer. Done at the submit_bio() level, so it is
1814 accurate for block-backed filesystems. <pleas 1814 accurate for block-backed filesystems. <please add status regarding NFS and
1815 CIFS at a later time> 1815 CIFS at a later time>
1816 1816
1817 1817
1818 write_bytes 1818 write_bytes
1819 ^^^^^^^^^^^ 1819 ^^^^^^^^^^^
1820 1820
1821 I/O counter: bytes written 1821 I/O counter: bytes written
1822 Attempt to count the number of bytes which th 1822 Attempt to count the number of bytes which this process caused to be sent to
1823 the storage layer. This is done at page-dirty 1823 the storage layer. This is done at page-dirtying time.
1824 1824
1825 1825
1826 cancelled_write_bytes 1826 cancelled_write_bytes
1827 ^^^^^^^^^^^^^^^^^^^^^ 1827 ^^^^^^^^^^^^^^^^^^^^^
1828 1828
1829 The big inaccuracy here is truncate. If a pro 1829 The big inaccuracy here is truncate. If a process writes 1MB to a file and
1830 then deletes the file, it will in fact perfor 1830 then deletes the file, it will in fact perform no writeout. But it will have
1831 been accounted as having caused 1MB of write. 1831 been accounted as having caused 1MB of write.
1832 In other words: The number of bytes which thi 1832 In other words: The number of bytes which this process caused to not happen,
1833 by truncating pagecache. A task can cause "ne 1833 by truncating pagecache. A task can cause "negative" IO too. If this task
1834 truncates some dirty pagecache, some IO which 1834 truncates some dirty pagecache, some IO which another task has been accounted
1835 for (in its write_bytes) will not be happenin 1835 for (in its write_bytes) will not be happening. We _could_ just subtract that
1836 from the truncating task's write_bytes, but t 1836 from the truncating task's write_bytes, but there is information loss in doing
1837 that. 1837 that.
1838 1838
1839 1839
1840 .. Note:: 1840 .. Note::
1841 1841
1842 At its current implementation state, this 1842 At its current implementation state, this is a bit racy on 32-bit machines:
1843 if process A reads process B's /proc/pid/i 1843 if process A reads process B's /proc/pid/io while process B is updating one
1844 of those 64-bit counters, process A could 1844 of those 64-bit counters, process A could see an intermediate result.
1845 1845
1846 1846
1847 More information about this can be found with 1847 More information about this can be found within the taskstats documentation in
1848 Documentation/accounting. 1848 Documentation/accounting.
1849 1849
1850 3.4 /proc/<pid>/coredump_filter - Core dump f 1850 3.4 /proc/<pid>/coredump_filter - Core dump filtering settings
1851 --------------------------------------------- 1851 ---------------------------------------------------------------
1852 When a process is dumped, all anonymous memor 1852 When a process is dumped, all anonymous memory is written to a core file as
1853 long as the size of the core file isn't limit 1853 long as the size of the core file isn't limited. But sometimes we don't want
1854 to dump some memory segments, for example, hu 1854 to dump some memory segments, for example, huge shared memory or DAX.
1855 Conversely, sometimes we want to save file-ba 1855 Conversely, sometimes we want to save file-backed memory segments into a core
1856 file, not only the individual files. 1856 file, not only the individual files.
1857 1857
1858 /proc/<pid>/coredump_filter allows you to cus 1858 /proc/<pid>/coredump_filter allows you to customize which memory segments
1859 will be dumped when the <pid> process is dump 1859 will be dumped when the <pid> process is dumped. coredump_filter is a bitmask
1860 of memory types. If a bit of the bitmask is s 1860 of memory types. If a bit of the bitmask is set, memory segments of the
1861 corresponding memory type are dumped, otherwi 1861 corresponding memory type are dumped, otherwise they are not dumped.
1862 1862
1863 The following 9 memory types are supported: 1863 The following 9 memory types are supported:
1864 1864
1865 - (bit 0) anonymous private memory 1865 - (bit 0) anonymous private memory
1866 - (bit 1) anonymous shared memory 1866 - (bit 1) anonymous shared memory
1867 - (bit 2) file-backed private memory 1867 - (bit 2) file-backed private memory
1868 - (bit 3) file-backed shared memory 1868 - (bit 3) file-backed shared memory
1869 - (bit 4) ELF header pages in file-backed p 1869 - (bit 4) ELF header pages in file-backed private memory areas (it is
1870 effective only if the bit 2 is cleared) 1870 effective only if the bit 2 is cleared)
1871 - (bit 5) hugetlb private memory 1871 - (bit 5) hugetlb private memory
1872 - (bit 6) hugetlb shared memory 1872 - (bit 6) hugetlb shared memory
1873 - (bit 7) DAX private memory 1873 - (bit 7) DAX private memory
1874 - (bit 8) DAX shared memory 1874 - (bit 8) DAX shared memory
1875 1875
1876 Note that MMIO pages such as frame buffer a 1876 Note that MMIO pages such as frame buffer are never dumped and vDSO pages
1877 are always dumped regardless of the bitmask 1877 are always dumped regardless of the bitmask status.
1878 1878
1879 Note that bits 0-4 don't affect hugetlb or 1879 Note that bits 0-4 don't affect hugetlb or DAX memory. hugetlb memory is
1880 only affected by bit 5-6, and DAX is only a 1880 only affected by bit 5-6, and DAX is only affected by bits 7-8.
1881 1881
1882 The default value of coredump_filter is 0x33; 1882 The default value of coredump_filter is 0x33; this means all anonymous memory
1883 segments, ELF header pages and hugetlb privat 1883 segments, ELF header pages and hugetlb private memory are dumped.
1884 1884
1885 If you don't want to dump all shared memory s 1885 If you don't want to dump all shared memory segments attached to pid 1234,
1886 write 0x31 to the process's proc file:: 1886 write 0x31 to the process's proc file::
1887 1887
1888 $ echo 0x31 > /proc/1234/coredump_filter 1888 $ echo 0x31 > /proc/1234/coredump_filter
1889 1889
1890 When a new process is created, the process in 1890 When a new process is created, the process inherits the bitmask status from its
1891 parent. It is useful to set up coredump_filte 1891 parent. It is useful to set up coredump_filter before the program runs.
1892 For example:: 1892 For example::
1893 1893
1894 $ echo 0x7 > /proc/self/coredump_filter 1894 $ echo 0x7 > /proc/self/coredump_filter
1895 $ ./some_program 1895 $ ./some_program
1896 1896
1897 3.5 /proc/<pid>/mountinfo - Information a 1897 3.5 /proc/<pid>/mountinfo - Information about mounts
1898 --------------------------------------------- 1898 --------------------------------------------------------
1899 1899
1900 This file contains lines of the form:: 1900 This file contains lines of the form::
1901 1901
1902 36 35 98:0 /mnt1 /mnt2 rw,noatime master: 1902 36 35 98:0 /mnt1 /mnt2 rw,noatime master:1 - ext3 /dev/root rw,errors=continue
1903 (1)(2)(3) (4) (5) (6) (n…m 1903 (1)(2)(3) (4) (5) (6) (n…m) (m+1)(m+2) (m+3) (m+4)
1904 1904
1905 (1) mount ID: unique identifier 1905 (1) mount ID: unique identifier of the mount (may be reused after umount)
1906 (2) parent ID: ID of parent (or o 1906 (2) parent ID: ID of parent (or of self for the top of the mount tree)
1907 (3) major:minor: value of st_dev fo 1907 (3) major:minor: value of st_dev for files on filesystem
1908 (4) root: root of the mount 1908 (4) root: root of the mount within the filesystem
1909 (5) mount point: mount point relati 1909 (5) mount point: mount point relative to the process's root
1910 (6) mount options: per mount options 1910 (6) mount options: per mount options
1911 (n…m) optional fields: zero or more fie 1911 (n…m) optional fields: zero or more fields of the form "tag[:value]"
1912 (m+1) separator: marks the end of t 1912 (m+1) separator: marks the end of the optional fields
1913 (m+2) filesystem type: name of filesystem 1913 (m+2) filesystem type: name of filesystem of the form "type[.subtype]"
1914 (m+3) mount source: filesystem specifi 1914 (m+3) mount source: filesystem specific information or "none"
1915 (m+4) super options: per super block op 1915 (m+4) super options: per super block options
1916 1916
1917 Parsers should ignore all unrecognised option 1917 Parsers should ignore all unrecognised optional fields. Currently the
1918 possible optional fields are: 1918 possible optional fields are:
1919 1919
1920 ================ =========================== 1920 ================ ==============================================================
1921 shared:X mount is shared in peer gro 1921 shared:X mount is shared in peer group X
1922 master:X mount is slave to peer grou 1922 master:X mount is slave to peer group X
1923 propagate_from:X mount is slave and receives 1923 propagate_from:X mount is slave and receives propagation from peer group X [#]_
1924 unbindable mount is unbindable 1924 unbindable mount is unbindable
1925 ================ =========================== 1925 ================ ==============================================================
1926 1926
1927 .. [#] X is the closest dominant peer group u 1927 .. [#] X is the closest dominant peer group under the process's root. If
1928 X is the immediate master of the mount 1928 X is the immediate master of the mount, or if there's no dominant peer
1929 group under the same root, then only t 1929 group under the same root, then only the "master:X" field is present
1930 and not the "propagate_from:X" field. 1930 and not the "propagate_from:X" field.
1931 1931
1932 For more information on mount propagation see 1932 For more information on mount propagation see:
1933 1933
1934 Documentation/filesystems/sharedsubtree.rst 1934 Documentation/filesystems/sharedsubtree.rst
1935 1935
1936 1936
1937 3.6 /proc/<pid>/comm & /proc/<pid>/task/ 1937 3.6 /proc/<pid>/comm & /proc/<pid>/task/<tid>/comm
1938 --------------------------------------------- 1938 --------------------------------------------------------
1939 These files provide a method to access a task 1939 These files provide a method to access a task's comm value. It also allows for
1940 a task to set its own or one of its thread si 1940 a task to set its own or one of its thread siblings comm value. The comm value
1941 is limited in size compared to the cmdline va 1941 is limited in size compared to the cmdline value, so writing anything longer
1942 then the kernel's TASK_COMM_LEN (currently 16 1942 then the kernel's TASK_COMM_LEN (currently 16 chars, including the NUL
1943 terminator) will result in a truncated comm v 1943 terminator) will result in a truncated comm value.
1944 1944
1945 1945
1946 3.7 /proc/<pid>/task/<tid>/children - Inf 1946 3.7 /proc/<pid>/task/<tid>/children - Information about task children
1947 --------------------------------------------- 1947 -------------------------------------------------------------------------
1948 This file provides a fast way to retrieve fir 1948 This file provides a fast way to retrieve first level children pids
1949 of a task pointed by <pid>/<tid> pair. The fo 1949 of a task pointed by <pid>/<tid> pair. The format is a space separated
1950 stream of pids. 1950 stream of pids.
1951 1951
1952 Note the "first level" here -- if a child has 1952 Note the "first level" here -- if a child has its own children they will
1953 not be listed here; one needs to read /proc/< 1953 not be listed here; one needs to read /proc/<children-pid>/task/<tid>/children
1954 to obtain the descendants. 1954 to obtain the descendants.
1955 1955
1956 Since this interface is intended to be fast a 1956 Since this interface is intended to be fast and cheap it doesn't
1957 guarantee to provide precise results and some 1957 guarantee to provide precise results and some children might be
1958 skipped, especially if they've exited right a 1958 skipped, especially if they've exited right after we printed their
1959 pids, so one needs to either stop or freeze p 1959 pids, so one needs to either stop or freeze processes being inspected
1960 if precise results are needed. 1960 if precise results are needed.
1961 1961
1962 1962
1963 3.8 /proc/<pid>/fdinfo/<fd> - Information 1963 3.8 /proc/<pid>/fdinfo/<fd> - Information about opened file
1964 --------------------------------------------- 1964 ---------------------------------------------------------------
1965 This file provides information associated wit 1965 This file provides information associated with an opened file. The regular
1966 files have at least four fields -- 'pos', 'fl 1966 files have at least four fields -- 'pos', 'flags', 'mnt_id' and 'ino'.
1967 The 'pos' represents the current offset of th 1967 The 'pos' represents the current offset of the opened file in decimal
1968 form [see lseek(2) for details], 'flags' deno 1968 form [see lseek(2) for details], 'flags' denotes the octal O_xxx mask the
1969 file has been created with [see open(2) for d 1969 file has been created with [see open(2) for details] and 'mnt_id' represents
1970 mount ID of the file system containing the op 1970 mount ID of the file system containing the opened file [see 3.5
1971 /proc/<pid>/mountinfo for details]. 'ino' rep 1971 /proc/<pid>/mountinfo for details]. 'ino' represents the inode number of
1972 the file. 1972 the file.
1973 1973
1974 A typical output is:: 1974 A typical output is::
1975 1975
1976 pos: 0 1976 pos: 0
1977 flags: 0100002 1977 flags: 0100002
1978 mnt_id: 19 1978 mnt_id: 19
1979 ino: 63107 1979 ino: 63107
1980 1980
1981 All locks associated with a file descriptor a 1981 All locks associated with a file descriptor are shown in its fdinfo too::
1982 1982
1983 lock: 1: FLOCK ADVISORY WRITE 359 1983 lock: 1: FLOCK ADVISORY WRITE 359 00:13:11691 0 EOF
1984 1984
1985 The files such as eventfd, fsnotify, signalfd 1985 The files such as eventfd, fsnotify, signalfd, epoll among the regular pos/flags
1986 pair provide additional information particula 1986 pair provide additional information particular to the objects they represent.
1987 1987
1988 Eventfd files 1988 Eventfd files
1989 ~~~~~~~~~~~~~ 1989 ~~~~~~~~~~~~~
1990 1990
1991 :: 1991 ::
1992 1992
1993 pos: 0 1993 pos: 0
1994 flags: 04002 1994 flags: 04002
1995 mnt_id: 9 1995 mnt_id: 9
1996 ino: 63107 1996 ino: 63107
1997 eventfd-count: 5a 1997 eventfd-count: 5a
1998 1998
1999 where 'eventfd-count' is hex value of a count 1999 where 'eventfd-count' is hex value of a counter.
2000 2000
2001 Signalfd files 2001 Signalfd files
2002 ~~~~~~~~~~~~~~ 2002 ~~~~~~~~~~~~~~
2003 2003
2004 :: 2004 ::
2005 2005
2006 pos: 0 2006 pos: 0
2007 flags: 04002 2007 flags: 04002
2008 mnt_id: 9 2008 mnt_id: 9
2009 ino: 63107 2009 ino: 63107
2010 sigmask: 0000000000000200 2010 sigmask: 0000000000000200
2011 2011
2012 where 'sigmask' is hex value of the signal ma 2012 where 'sigmask' is hex value of the signal mask associated
2013 with a file. 2013 with a file.
2014 2014
2015 Epoll files 2015 Epoll files
2016 ~~~~~~~~~~~ 2016 ~~~~~~~~~~~
2017 2017
2018 :: 2018 ::
2019 2019
2020 pos: 0 2020 pos: 0
2021 flags: 02 2021 flags: 02
2022 mnt_id: 9 2022 mnt_id: 9
2023 ino: 63107 2023 ino: 63107
2024 tfd: 5 events: 1d data: 2024 tfd: 5 events: 1d data: ffffffffffffffff pos:0 ino:61af sdev:7
2025 2025
2026 where 'tfd' is a target file descriptor numbe 2026 where 'tfd' is a target file descriptor number in decimal form,
2027 'events' is events mask being watched and the 2027 'events' is events mask being watched and the 'data' is data
2028 associated with a target [see epoll(7) for mo 2028 associated with a target [see epoll(7) for more details].
2029 2029
2030 The 'pos' is current offset of the target fil 2030 The 'pos' is current offset of the target file in decimal form
2031 [see lseek(2)], 'ino' and 'sdev' are inode an 2031 [see lseek(2)], 'ino' and 'sdev' are inode and device numbers
2032 where target file resides, all in hex format. 2032 where target file resides, all in hex format.
2033 2033
2034 Fsnotify files 2034 Fsnotify files
2035 ~~~~~~~~~~~~~~ 2035 ~~~~~~~~~~~~~~
2036 For inotify files the format is the following 2036 For inotify files the format is the following::
2037 2037
2038 pos: 0 2038 pos: 0
2039 flags: 02000000 2039 flags: 02000000
2040 mnt_id: 9 2040 mnt_id: 9
2041 ino: 63107 2041 ino: 63107
2042 inotify wd:3 ino:9e7e sdev:800013 mas 2042 inotify wd:3 ino:9e7e sdev:800013 mask:800afce ignored_mask:0 fhandle-bytes:8 fhandle-type:1 f_handle:7e9e0000640d1b6d
2043 2043
2044 where 'wd' is a watch descriptor in decimal f 2044 where 'wd' is a watch descriptor in decimal form, i.e. a target file
2045 descriptor number, 'ino' and 'sdev' are inode 2045 descriptor number, 'ino' and 'sdev' are inode and device where the
2046 target file resides and the 'mask' is the mas 2046 target file resides and the 'mask' is the mask of events, all in hex
2047 form [see inotify(7) for more details]. 2047 form [see inotify(7) for more details].
2048 2048
2049 If the kernel was built with exportfs support 2049 If the kernel was built with exportfs support, the path to the target
2050 file is encoded as a file handle. The file h 2050 file is encoded as a file handle. The file handle is provided by three
2051 fields 'fhandle-bytes', 'fhandle-type' and 'f 2051 fields 'fhandle-bytes', 'fhandle-type' and 'f_handle', all in hex
2052 format. 2052 format.
2053 2053
2054 If the kernel is built without exportfs suppo 2054 If the kernel is built without exportfs support the file handle won't be
2055 printed out. 2055 printed out.
2056 2056
2057 If there is no inotify mark attached yet the 2057 If there is no inotify mark attached yet the 'inotify' line will be omitted.
2058 2058
2059 For fanotify files the format is:: 2059 For fanotify files the format is::
2060 2060
2061 pos: 0 2061 pos: 0
2062 flags: 02 2062 flags: 02
2063 mnt_id: 9 2063 mnt_id: 9
2064 ino: 63107 2064 ino: 63107
2065 fanotify flags:10 event-flags:0 2065 fanotify flags:10 event-flags:0
2066 fanotify mnt_id:12 mflags:40 mask:38 2066 fanotify mnt_id:12 mflags:40 mask:38 ignored_mask:40000003
2067 fanotify ino:4f969 sdev:800013 mflags 2067 fanotify ino:4f969 sdev:800013 mflags:0 mask:3b ignored_mask:40000000 fhandle-bytes:8 fhandle-type:1 f_handle:69f90400c275b5b4
2068 2068
2069 where fanotify 'flags' and 'event-flags' are 2069 where fanotify 'flags' and 'event-flags' are values used in fanotify_init
2070 call, 'mnt_id' is the mount point identifier, 2070 call, 'mnt_id' is the mount point identifier, 'mflags' is the value of
2071 flags associated with mark which are tracked 2071 flags associated with mark which are tracked separately from events
2072 mask. 'ino' and 'sdev' are target inode and d 2072 mask. 'ino' and 'sdev' are target inode and device, 'mask' is the events
2073 mask and 'ignored_mask' is the mask of events 2073 mask and 'ignored_mask' is the mask of events which are to be ignored.
2074 All are in hex format. Incorporation of 'mfla 2074 All are in hex format. Incorporation of 'mflags', 'mask' and 'ignored_mask'
2075 provide information about flags and mask used 2075 provide information about flags and mask used in fanotify_mark
2076 call [see fsnotify manpage for details]. 2076 call [see fsnotify manpage for details].
2077 2077
2078 While the first three lines are mandatory and 2078 While the first three lines are mandatory and always printed, the rest is
2079 optional and may be omitted if no marks creat 2079 optional and may be omitted if no marks created yet.
2080 2080
2081 Timerfd files 2081 Timerfd files
2082 ~~~~~~~~~~~~~ 2082 ~~~~~~~~~~~~~
2083 2083
2084 :: 2084 ::
2085 2085
2086 pos: 0 2086 pos: 0
2087 flags: 02 2087 flags: 02
2088 mnt_id: 9 2088 mnt_id: 9
2089 ino: 63107 2089 ino: 63107
2090 clockid: 0 2090 clockid: 0
2091 ticks: 0 2091 ticks: 0
2092 settime flags: 01 2092 settime flags: 01
2093 it_value: (0, 49406829) 2093 it_value: (0, 49406829)
2094 it_interval: (1, 0) 2094 it_interval: (1, 0)
2095 2095
2096 where 'clockid' is the clock type and 'ticks' 2096 where 'clockid' is the clock type and 'ticks' is the number of the timer expirations
2097 that have occurred [see timerfd_create(2) for 2097 that have occurred [see timerfd_create(2) for details]. 'settime flags' are
2098 flags in octal form been used to setup the ti 2098 flags in octal form been used to setup the timer [see timerfd_settime(2) for
2099 details]. 'it_value' is remaining time until 2099 details]. 'it_value' is remaining time until the timer expiration.
2100 'it_interval' is the interval for the timer. 2100 'it_interval' is the interval for the timer. Note the timer might be set up
2101 with TIMER_ABSTIME option which will be shown 2101 with TIMER_ABSTIME option which will be shown in 'settime flags', but 'it_value'
2102 still exhibits timer's remaining time. 2102 still exhibits timer's remaining time.
2103 2103
2104 DMA Buffer files 2104 DMA Buffer files
2105 ~~~~~~~~~~~~~~~~ 2105 ~~~~~~~~~~~~~~~~
2106 2106
2107 :: 2107 ::
2108 2108
2109 pos: 0 2109 pos: 0
2110 flags: 04002 2110 flags: 04002
2111 mnt_id: 9 2111 mnt_id: 9
2112 ino: 63107 2112 ino: 63107
2113 size: 32768 2113 size: 32768
2114 count: 2 2114 count: 2
2115 exp_name: system-heap 2115 exp_name: system-heap
2116 2116
2117 where 'size' is the size of the DMA buffer in 2117 where 'size' is the size of the DMA buffer in bytes. 'count' is the file count of
2118 the DMA buffer file. 'exp_name' is the name o 2118 the DMA buffer file. 'exp_name' is the name of the DMA buffer exporter.
2119 2119
2120 3.9 /proc/<pid>/map_files - Information a 2120 3.9 /proc/<pid>/map_files - Information about memory mapped files
2121 --------------------------------------------- 2121 ---------------------------------------------------------------------
2122 This directory contains symbolic links which 2122 This directory contains symbolic links which represent memory mapped files
2123 the process is maintaining. Example output:: 2123 the process is maintaining. Example output::
2124 2124
2125 | lr-------- 1 root root 64 Jan 27 11:24 2125 | lr-------- 1 root root 64 Jan 27 11:24 333c600000-333c620000 -> /usr/lib64/ld-2.18.so
2126 | lr-------- 1 root root 64 Jan 27 11:24 2126 | lr-------- 1 root root 64 Jan 27 11:24 333c81f000-333c820000 -> /usr/lib64/ld-2.18.so
2127 | lr-------- 1 root root 64 Jan 27 11:24 2127 | lr-------- 1 root root 64 Jan 27 11:24 333c820000-333c821000 -> /usr/lib64/ld-2.18.so
2128 | ... 2128 | ...
2129 | lr-------- 1 root root 64 Jan 27 11:24 2129 | lr-------- 1 root root 64 Jan 27 11:24 35d0421000-35d0422000 -> /usr/lib64/libselinux.so.1
2130 | lr-------- 1 root root 64 Jan 27 11:24 2130 | lr-------- 1 root root 64 Jan 27 11:24 400000-41a000 -> /usr/bin/ls
2131 2131
2132 The name of a link represents the virtual mem 2132 The name of a link represents the virtual memory bounds of a mapping, i.e.
2133 vm_area_struct::vm_start-vm_area_struct::vm_e 2133 vm_area_struct::vm_start-vm_area_struct::vm_end.
2134 2134
2135 The main purpose of the map_files is to retri 2135 The main purpose of the map_files is to retrieve a set of memory mapped
2136 files in a fast way instead of parsing /proc/ 2136 files in a fast way instead of parsing /proc/<pid>/maps or
2137 /proc/<pid>/smaps, both of which contain many 2137 /proc/<pid>/smaps, both of which contain many more records. At the same
2138 time one can open(2) mappings from the listin 2138 time one can open(2) mappings from the listings of two processes and
2139 comparing their inode numbers to figure out w 2139 comparing their inode numbers to figure out which anonymous memory areas
2140 are actually shared. 2140 are actually shared.
2141 2141
2142 3.10 /proc/<pid>/timerslack_ns - Task time 2142 3.10 /proc/<pid>/timerslack_ns - Task timerslack value
2143 --------------------------------------------- 2143 ---------------------------------------------------------
2144 This file provides the value of the task's ti 2144 This file provides the value of the task's timerslack value in nanoseconds.
2145 This value specifies an amount of time that n 2145 This value specifies an amount of time that normal timers may be deferred
2146 in order to coalesce timers and avoid unneces 2146 in order to coalesce timers and avoid unnecessary wakeups.
2147 2147
2148 This allows a task's interactivity vs power c 2148 This allows a task's interactivity vs power consumption tradeoff to be
2149 adjusted. 2149 adjusted.
2150 2150
2151 Writing 0 to the file will set the task's tim 2151 Writing 0 to the file will set the task's timerslack to the default value.
2152 2152
2153 Valid values are from 0 - ULLONG_MAX 2153 Valid values are from 0 - ULLONG_MAX
2154 2154
2155 An application setting the value must have PT 2155 An application setting the value must have PTRACE_MODE_ATTACH_FSCREDS level
2156 permissions on the task specified to change i 2156 permissions on the task specified to change its timerslack_ns value.
2157 2157
2158 3.11 /proc/<pid>/patch_state - Livepatch p 2158 3.11 /proc/<pid>/patch_state - Livepatch patch operation state
2159 --------------------------------------------- 2159 -----------------------------------------------------------------
2160 When CONFIG_LIVEPATCH is enabled, this file d 2160 When CONFIG_LIVEPATCH is enabled, this file displays the value of the
2161 patch state for the task. 2161 patch state for the task.
2162 2162
2163 A value of '-1' indicates that no patch is in 2163 A value of '-1' indicates that no patch is in transition.
2164 2164
2165 A value of '0' indicates that a patch is in t 2165 A value of '0' indicates that a patch is in transition and the task is
2166 unpatched. If the patch is being enabled, th 2166 unpatched. If the patch is being enabled, then the task hasn't been
2167 patched yet. If the patch is being disabled, 2167 patched yet. If the patch is being disabled, then the task has already
2168 been unpatched. 2168 been unpatched.
2169 2169
2170 A value of '1' indicates that a patch is in t 2170 A value of '1' indicates that a patch is in transition and the task is
2171 patched. If the patch is being enabled, then 2171 patched. If the patch is being enabled, then the task has already been
2172 patched. If the patch is being disabled, the 2172 patched. If the patch is being disabled, then the task hasn't been
2173 unpatched yet. 2173 unpatched yet.
2174 2174
2175 3.12 /proc/<pid>/arch_status - task architect 2175 3.12 /proc/<pid>/arch_status - task architecture specific status
2176 --------------------------------------------- 2176 -------------------------------------------------------------------
2177 When CONFIG_PROC_PID_ARCH_STATUS is enabled, 2177 When CONFIG_PROC_PID_ARCH_STATUS is enabled, this file displays the
2178 architecture specific status of the task. 2178 architecture specific status of the task.
2179 2179
2180 Example 2180 Example
2181 ~~~~~~~ 2181 ~~~~~~~
2182 2182
2183 :: 2183 ::
2184 2184
2185 $ cat /proc/6753/arch_status 2185 $ cat /proc/6753/arch_status
2186 AVX512_elapsed_ms: 8 2186 AVX512_elapsed_ms: 8
2187 2187
2188 Description 2188 Description
2189 ~~~~~~~~~~~ 2189 ~~~~~~~~~~~
2190 2190
2191 x86 specific entries 2191 x86 specific entries
2192 ~~~~~~~~~~~~~~~~~~~~~ 2192 ~~~~~~~~~~~~~~~~~~~~~
2193 2193
2194 AVX512_elapsed_ms 2194 AVX512_elapsed_ms
2195 ^^^^^^^^^^^^^^^^^^ 2195 ^^^^^^^^^^^^^^^^^^
2196 2196
2197 If AVX512 is supported on the machine, this 2197 If AVX512 is supported on the machine, this entry shows the milliseconds
2198 elapsed since the last time AVX512 usage wa 2198 elapsed since the last time AVX512 usage was recorded. The recording
2199 happens on a best effort basis when a task 2199 happens on a best effort basis when a task is scheduled out. This means
2200 that the value depends on two factors: 2200 that the value depends on two factors:
2201 2201
2202 1) The time which the task spent on the C 2202 1) The time which the task spent on the CPU without being scheduled
2203 out. With CPU isolation and a single r 2203 out. With CPU isolation and a single runnable task this can take
2204 several seconds. 2204 several seconds.
2205 2205
2206 2) The time since the task was scheduled 2206 2) The time since the task was scheduled out last. Depending on the
2207 reason for being scheduled out (time s 2207 reason for being scheduled out (time slice exhausted, syscall ...)
2208 this can be arbitrary long time. 2208 this can be arbitrary long time.
2209 2209
2210 As a consequence the value cannot be consid 2210 As a consequence the value cannot be considered precise and authoritative
2211 information. The application which uses thi 2211 information. The application which uses this information has to be aware
2212 of the overall scenario on the system in or 2212 of the overall scenario on the system in order to determine whether a
2213 task is a real AVX512 user or not. Precise 2213 task is a real AVX512 user or not. Precise information can be obtained
2214 with performance counters. 2214 with performance counters.
2215 2215
2216 A special value of '-1' indicates that no A 2216 A special value of '-1' indicates that no AVX512 usage was recorded, thus
2217 the task is unlikely an AVX512 user, but de 2217 the task is unlikely an AVX512 user, but depends on the workload and the
2218 scheduling scenario, it also could be a fal 2218 scheduling scenario, it also could be a false negative mentioned above.
2219 2219
2220 3.13 /proc/<pid>/fd - List of symlinks to ope 2220 3.13 /proc/<pid>/fd - List of symlinks to open files
2221 --------------------------------------------- 2221 -------------------------------------------------------
2222 This directory contains symbolic links which 2222 This directory contains symbolic links which represent open files
2223 the process is maintaining. Example output:: 2223 the process is maintaining. Example output::
2224 2224
2225 lr-x------ 1 root root 64 Sep 20 17:53 0 -> 2225 lr-x------ 1 root root 64 Sep 20 17:53 0 -> /dev/null
2226 l-wx------ 1 root root 64 Sep 20 17:53 1 -> 2226 l-wx------ 1 root root 64 Sep 20 17:53 1 -> /dev/null
2227 lrwx------ 1 root root 64 Sep 20 17:53 10 - 2227 lrwx------ 1 root root 64 Sep 20 17:53 10 -> 'socket:[12539]'
2228 lrwx------ 1 root root 64 Sep 20 17:53 11 - 2228 lrwx------ 1 root root 64 Sep 20 17:53 11 -> 'socket:[12540]'
2229 lrwx------ 1 root root 64 Sep 20 17:53 12 - 2229 lrwx------ 1 root root 64 Sep 20 17:53 12 -> 'socket:[12542]'
2230 2230
2231 The number of open files for the process is s 2231 The number of open files for the process is stored in 'size' member
2232 of stat() output for /proc/<pid>/fd for fast 2232 of stat() output for /proc/<pid>/fd for fast access.
2233 --------------------------------------------- 2233 -------------------------------------------------------
2234 2234
2235 2235
2236 Chapter 4: Configuring procfs 2236 Chapter 4: Configuring procfs
2237 ============================= 2237 =============================
2238 2238
2239 4.1 Mount options 2239 4.1 Mount options
2240 --------------------- 2240 ---------------------
2241 2241
2242 The following mount options are supported: 2242 The following mount options are supported:
2243 2243
2244 ========= ===================== 2244 ========= ========================================================
2245 hidepid= Set /proc/<pid>/ acce 2245 hidepid= Set /proc/<pid>/ access mode.
2246 gid= Set the group authori 2246 gid= Set the group authorized to learn processes information.
2247 subset= Show only the specifi 2247 subset= Show only the specified subset of procfs.
2248 ========= ===================== 2248 ========= ========================================================
2249 2249
2250 hidepid=off or hidepid=0 means classic mode - 2250 hidepid=off or hidepid=0 means classic mode - everybody may access all
2251 /proc/<pid>/ directories (default). 2251 /proc/<pid>/ directories (default).
2252 2252
2253 hidepid=noaccess or hidepid=1 means users may 2253 hidepid=noaccess or hidepid=1 means users may not access any /proc/<pid>/
2254 directories but their own. Sensitive files l 2254 directories but their own. Sensitive files like cmdline, sched*, status are now
2255 protected against other users. This makes it 2255 protected against other users. This makes it impossible to learn whether any
2256 user runs specific program (given the program 2256 user runs specific program (given the program doesn't reveal itself by its
2257 behaviour). As an additional bonus, as /proc 2257 behaviour). As an additional bonus, as /proc/<pid>/cmdline is unaccessible for
2258 other users, poorly written programs passing 2258 other users, poorly written programs passing sensitive information via program
2259 arguments are now protected against local eav 2259 arguments are now protected against local eavesdroppers.
2260 2260
2261 hidepid=invisible or hidepid=2 means hidepid= 2261 hidepid=invisible or hidepid=2 means hidepid=1 plus all /proc/<pid>/ will be
2262 fully invisible to other users. It doesn't m 2262 fully invisible to other users. It doesn't mean that it hides a fact whether a
2263 process with a specific pid value exists (it 2263 process with a specific pid value exists (it can be learned by other means, e.g.
2264 by "kill -0 $PID"), but it hides process' uid 2264 by "kill -0 $PID"), but it hides process' uid and gid, which may be learned by
2265 stat()'ing /proc/<pid>/ otherwise. It greatl 2265 stat()'ing /proc/<pid>/ otherwise. It greatly complicates an intruder's task of
2266 gathering information about running processes 2266 gathering information about running processes, whether some daemon runs with
2267 elevated privileges, whether other user runs 2267 elevated privileges, whether other user runs some sensitive program, whether
2268 other users run any program at all, etc. 2268 other users run any program at all, etc.
2269 2269
2270 hidepid=ptraceable or hidepid=4 means that pr 2270 hidepid=ptraceable or hidepid=4 means that procfs should only contain
2271 /proc/<pid>/ directories that the caller can 2271 /proc/<pid>/ directories that the caller can ptrace.
2272 2272
2273 gid= defines a group authorized to learn proc 2273 gid= defines a group authorized to learn processes information otherwise
2274 prohibited by hidepid=. If you use some daem 2274 prohibited by hidepid=. If you use some daemon like identd which needs to learn
2275 information about processes information, just 2275 information about processes information, just add identd to this group.
2276 2276
2277 subset=pid hides all top level files and dire 2277 subset=pid hides all top level files and directories in the procfs that
2278 are not related to tasks. 2278 are not related to tasks.
2279 2279
2280 Chapter 5: Filesystem behavior 2280 Chapter 5: Filesystem behavior
2281 ============================== 2281 ==============================
2282 2282
2283 Originally, before the advent of pid namespac 2283 Originally, before the advent of pid namespace, procfs was a global file
2284 system. It means that there was only one proc 2284 system. It means that there was only one procfs instance in the system.
2285 2285
2286 When pid namespace was added, a separate proc 2286 When pid namespace was added, a separate procfs instance was mounted in
2287 each pid namespace. So, procfs mount options 2287 each pid namespace. So, procfs mount options are global among all
2288 mountpoints within the same namespace:: 2288 mountpoints within the same namespace::
2289 2289
2290 # grep ^proc /proc/mounts 2290 # grep ^proc /proc/mounts
2291 proc /proc proc rw,relatime,hidepid=2 2291 proc /proc proc rw,relatime,hidepid=2 0 0
2292 2292
2293 # strace -e mount mount -o hidepid=1 2293 # strace -e mount mount -o hidepid=1 -t proc proc /tmp/proc
2294 mount("proc", "/tmp/proc", "proc", 0, 2294 mount("proc", "/tmp/proc", "proc", 0, "hidepid=1") = 0
2295 +++ exited with 0 +++ 2295 +++ exited with 0 +++
2296 2296
2297 # grep ^proc /proc/mounts 2297 # grep ^proc /proc/mounts
2298 proc /proc proc rw,relatime,hidepid=2 2298 proc /proc proc rw,relatime,hidepid=2 0 0
2299 proc /tmp/proc proc rw,relatime,hidep 2299 proc /tmp/proc proc rw,relatime,hidepid=2 0 0
2300 2300
2301 and only after remounting procfs mount option 2301 and only after remounting procfs mount options will change at all
2302 mountpoints:: 2302 mountpoints::
2303 2303
2304 # mount -o remount,hidepid=1 -t proc 2304 # mount -o remount,hidepid=1 -t proc proc /tmp/proc
2305 2305
2306 # grep ^proc /proc/mounts 2306 # grep ^proc /proc/mounts
2307 proc /proc proc rw,relatime,hidepid=1 2307 proc /proc proc rw,relatime,hidepid=1 0 0
2308 proc /tmp/proc proc rw,relatime,hidep 2308 proc /tmp/proc proc rw,relatime,hidepid=1 0 0
2309 2309
2310 This behavior is different from the behavior 2310 This behavior is different from the behavior of other filesystems.
2311 2311
2312 The new procfs behavior is more like other fi 2312 The new procfs behavior is more like other filesystems. Each procfs mount
2313 creates a new procfs instance. Mount options 2313 creates a new procfs instance. Mount options affect own procfs instance.
2314 It means that it became possible to have seve 2314 It means that it became possible to have several procfs instances
2315 displaying tasks with different filtering opt 2315 displaying tasks with different filtering options in one pid namespace::
2316 2316
2317 # mount -o hidepid=invisible -t proc 2317 # mount -o hidepid=invisible -t proc proc /proc
2318 # mount -o hidepid=noaccess -t proc p 2318 # mount -o hidepid=noaccess -t proc proc /tmp/proc
2319 # grep ^proc /proc/mounts 2319 # grep ^proc /proc/mounts
2320 proc /proc proc rw,relatime,hidepid=i 2320 proc /proc proc rw,relatime,hidepid=invisible 0 0
2321 proc /tmp/proc proc rw,relatime,hidep 2321 proc /tmp/proc proc rw,relatime,hidepid=noaccess 0 0
Linux® is a registered trademark of Linus Torvalds in the United States and other countries.
TOMOYO® is a registered trademark of NTT DATA CORPORATION.