1.. SPDX-License-Identifier: GPL-2.0 2 3==================== 4The /proc Filesystem 5==================== 6 7===================== ======================================= ================ 8/proc/sys Terrehon Bowden <terrehon@pacbell.net>, October 7 1999 9 Bodo Bauer <bb@ricochet.net> 102.4.x update Jorge Nerin <comandante@zaralinux.com> November 14 2000 11move /proc/sys Shen Feng <shen@cn.fujitsu.com> April 1 2009 12fixes/update part 1.1 Stefani Seibold <stefani@seibold.net> June 9 2009 13===================== ======================================= ================ 14 15 16 17.. Table of Contents 18 19 0 Preface 20 0.1 Introduction/Credits 21 0.2 Legal Stuff 22 23 1 Collecting System Information 24 1.1 Process-Specific Subdirectories 25 1.2 Kernel data 26 1.3 IDE devices in /proc/ide 27 1.4 Networking info in /proc/net 28 1.5 SCSI info 29 1.6 Parallel port info in /proc/parport 30 1.7 TTY info in /proc/tty 31 1.8 Miscellaneous kernel statistics in /proc/stat 32 1.9 Ext4 file system parameters 33 34 2 Modifying System Parameters 35 36 3 Per-Process Parameters 37 3.1 /proc/<pid>/oom_adj & /proc/<pid>/oom_score_adj - Adjust the oom-killer 38 score 39 3.2 /proc/<pid>/oom_score - Display current oom-killer score 40 3.3 /proc/<pid>/io - Display the IO accounting fields 41 3.4 /proc/<pid>/coredump_filter - Core dump filtering settings 42 3.5 /proc/<pid>/mountinfo - Information about mounts 43 3.6 /proc/<pid>/comm & /proc/<pid>/task/<tid>/comm 44 3.7 /proc/<pid>/task/<tid>/children - Information about task children 45 3.8 /proc/<pid>/fdinfo/<fd> - Information about opened file 46 3.9 /proc/<pid>/map_files - Information about memory mapped files 47 3.10 /proc/<pid>/timerslack_ns - Task timerslack value 48 3.11 /proc/<pid>/patch_state - Livepatch patch operation state 49 3.12 /proc/<pid>/arch_status - Task architecture specific information 50 51 4 Configuring procfs 52 4.1 Mount options 53 54Preface 55======= 56 570.1 Introduction/Credits 58------------------------ 59 60This documentation is part of a soon (or so we hope) to be released book on 61the SuSE Linux distribution. As there is no complete documentation for the 62/proc file system and we've used many freely available sources to write these 63chapters, it seems only fair to give the work back to the Linux community. 64This work is based on the 2.2.* kernel version and the upcoming 2.4.*. I'm 65afraid it's still far from complete, but we hope it will be useful. As far as 66we know, it is the first 'all-in-one' document about the /proc file system. It 67is focused on the Intel x86 hardware, so if you are looking for PPC, ARM, 68SPARC, AXP, etc., features, you probably won't find what you are looking for. 69It also only covers IPv4 networking, not IPv6 nor other protocols - sorry. But 70additions and patches are welcome and will be added to this document if you 71mail them to Bodo. 72 73We'd like to thank Alan Cox, Rik van Riel, and Alexey Kuznetsov and a lot of 74other people for help compiling this documentation. We'd also like to extend a 75special thank you to Andi Kleen for documentation, which we relied on heavily 76to create this document, as well as the additional information he provided. 77Thanks to everybody else who contributed source or docs to the Linux kernel 78and helped create a great piece of software... :) 79 80If you have any comments, corrections or additions, please don't hesitate to 81contact Bodo Bauer at bb@ricochet.net. We'll be happy to add them to this 82document. 83 84The latest version of this document is available online at 85http://tldp.org/LDP/Linux-Filesystem-Hierarchy/html/proc.html 86 87If the above direction does not works for you, you could try the kernel 88mailing list at linux-kernel@vger.kernel.org and/or try to reach me at 89comandante@zaralinux.com. 90 910.2 Legal Stuff 92--------------- 93 94We don't guarantee the correctness of this document, and if you come to us 95complaining about how you screwed up your system because of incorrect 96documentation, we won't feel responsible... 97 98Chapter 1: Collecting System Information 99======================================== 100 101In This Chapter 102--------------- 103* Investigating the properties of the pseudo file system /proc and its 104 ability to provide information on the running Linux system 105* Examining /proc's structure 106* Uncovering various information about the kernel and the processes running 107 on the system 108 109------------------------------------------------------------------------------ 110 111The proc file system acts as an interface to internal data structures in the 112kernel. It can be used to obtain information about the system and to change 113certain kernel parameters at runtime (sysctl). 114 115First, we'll take a look at the read-only parts of /proc. In Chapter 2, we 116show you how you can use /proc/sys to change settings. 117 1181.1 Process-Specific Subdirectories 119----------------------------------- 120 121The directory /proc contains (among other things) one subdirectory for each 122process running on the system, which is named after the process ID (PID). 123 124The link self points to the process reading the file system. Each process 125subdirectory has the entries listed in Table 1-1. 126 127Note that an open a file descriptor to /proc/<pid> or to any of its 128contained files or subdirectories does not prevent <pid> being reused 129for some other process in the event that <pid> exits. Operations on 130open /proc/<pid> file descriptors corresponding to dead processes 131never act on any new process that the kernel may, through chance, have 132also assigned the process ID <pid>. Instead, operations on these FDs 133usually fail with ESRCH. 134 135.. table:: Table 1-1: Process specific entries in /proc 136 137 ============= =============================================================== 138 File Content 139 ============= =============================================================== 140 clear_refs Clears page referenced bits shown in smaps output 141 cmdline Command line arguments 142 cpu Current and last cpu in which it was executed (2.4)(smp) 143 cwd Link to the current working directory 144 environ Values of environment variables 145 exe Link to the executable of this process 146 fd Directory, which contains all file descriptors 147 maps Memory maps to executables and library files (2.4) 148 mem Memory held by this process 149 root Link to the root directory of this process 150 stat Process status 151 statm Process memory status information 152 status Process status in human readable form 153 wchan Present with CONFIG_KALLSYMS=y: it shows the kernel function 154 symbol the task is blocked in - or "0" if not blocked. 155 pagemap Page table 156 stack Report full stack trace, enable via CONFIG_STACKTRACE 157 smaps An extension based on maps, showing the memory consumption of 158 each mapping and flags associated with it 159 smaps_rollup Accumulated smaps stats for all mappings of the process. This 160 can be derived from smaps, but is faster and more convenient 161 numa_maps An extension based on maps, showing the memory locality and 162 binding policy as well as mem usage (in pages) of each mapping. 163 ============= =============================================================== 164 165For example, to get the status information of a process, all you have to do is 166read the file /proc/PID/status:: 167 168 >cat /proc/self/status 169 Name: cat 170 State: R (running) 171 Tgid: 5452 172 Pid: 5452 173 PPid: 743 174 TracerPid: 0 (2.4) 175 Uid: 501 501 501 501 176 Gid: 100 100 100 100 177 FDSize: 256 178 Groups: 100 14 16 179 VmPeak: 5004 kB 180 VmSize: 5004 kB 181 VmLck: 0 kB 182 VmHWM: 476 kB 183 VmRSS: 476 kB 184 RssAnon: 352 kB 185 RssFile: 120 kB 186 RssShmem: 4 kB 187 VmData: 156 kB 188 VmStk: 88 kB 189 VmExe: 68 kB 190 VmLib: 1412 kB 191 VmPTE: 20 kb 192 VmSwap: 0 kB 193 HugetlbPages: 0 kB 194 CoreDumping: 0 195 THP_enabled: 1 196 Threads: 1 197 SigQ: 0/28578 198 SigPnd: 0000000000000000 199 ShdPnd: 0000000000000000 200 SigBlk: 0000000000000000 201 SigIgn: 0000000000000000 202 SigCgt: 0000000000000000 203 CapInh: 00000000fffffeff 204 CapPrm: 0000000000000000 205 CapEff: 0000000000000000 206 CapBnd: ffffffffffffffff 207 CapAmb: 0000000000000000 208 NoNewPrivs: 0 209 Seccomp: 0 210 Speculation_Store_Bypass: thread vulnerable 211 voluntary_ctxt_switches: 0 212 nonvoluntary_ctxt_switches: 1 213 214This shows you nearly the same information you would get if you viewed it with 215the ps command. In fact, ps uses the proc file system to obtain its 216information. But you get a more detailed view of the process by reading the 217file /proc/PID/status. It fields are described in table 1-2. 218 219The statm file contains more detailed information about the process 220memory usage. Its seven fields are explained in Table 1-3. The stat file 221contains details information about the process itself. Its fields are 222explained in Table 1-4. 223 224(for SMP CONFIG users) 225 226For making accounting scalable, RSS related information are handled in an 227asynchronous manner and the value may not be very precise. To see a precise 228snapshot of a moment, you can see /proc/<pid>/smaps file and scan page table. 229It's slow but very precise. 230 231.. table:: Table 1-2: Contents of the status files (as of 4.19) 232 233 ========================== =================================================== 234 Field Content 235 ========================== =================================================== 236 Name filename of the executable 237 Umask file mode creation mask 238 State state (R is running, S is sleeping, D is sleeping 239 in an uninterruptible wait, Z is zombie, 240 T is traced or stopped) 241 Tgid thread group ID 242 Ngid NUMA group ID (0 if none) 243 Pid process id 244 PPid process id of the parent process 245 TracerPid PID of process tracing this process (0 if not) 246 Uid Real, effective, saved set, and file system UIDs 247 Gid Real, effective, saved set, and file system GIDs 248 FDSize number of file descriptor slots currently allocated 249 Groups supplementary group list 250 NStgid descendant namespace thread group ID hierarchy 251 NSpid descendant namespace process ID hierarchy 252 NSpgid descendant namespace process group ID hierarchy 253 NSsid descendant namespace session ID hierarchy 254 VmPeak peak virtual memory size 255 VmSize total program size 256 VmLck locked memory size 257 VmPin pinned memory size 258 VmHWM peak resident set size ("high water mark") 259 VmRSS size of memory portions. It contains the three 260 following parts 261 (VmRSS = RssAnon + RssFile + RssShmem) 262 RssAnon size of resident anonymous memory 263 RssFile size of resident file mappings 264 RssShmem size of resident shmem memory (includes SysV shm, 265 mapping of tmpfs and shared anonymous mappings) 266 VmData size of private data segments 267 VmStk size of stack segments 268 VmExe size of text segment 269 VmLib size of shared library code 270 VmPTE size of page table entries 271 VmSwap amount of swap used by anonymous private data 272 (shmem swap usage is not included) 273 HugetlbPages size of hugetlb memory portions 274 CoreDumping process's memory is currently being dumped 275 (killing the process may lead to a corrupted core) 276 THP_enabled process is allowed to use THP (returns 0 when 277 PR_SET_THP_DISABLE is set on the process 278 Threads number of threads 279 SigQ number of signals queued/max. number for queue 280 SigPnd bitmap of pending signals for the thread 281 ShdPnd bitmap of shared pending signals for the process 282 SigBlk bitmap of blocked signals 283 SigIgn bitmap of ignored signals 284 SigCgt bitmap of caught signals 285 CapInh bitmap of inheritable capabilities 286 CapPrm bitmap of permitted capabilities 287 CapEff bitmap of effective capabilities 288 CapBnd bitmap of capabilities bounding set 289 CapAmb bitmap of ambient capabilities 290 NoNewPrivs no_new_privs, like prctl(PR_GET_NO_NEW_PRIV, ...) 291 Seccomp seccomp mode, like prctl(PR_GET_SECCOMP, ...) 292 Speculation_Store_Bypass speculative store bypass mitigation status 293 Cpus_allowed mask of CPUs on which this process may run 294 Cpus_allowed_list Same as previous, but in "list format" 295 Mems_allowed mask of memory nodes allowed to this process 296 Mems_allowed_list Same as previous, but in "list format" 297 voluntary_ctxt_switches number of voluntary context switches 298 nonvoluntary_ctxt_switches number of non voluntary context switches 299 ========================== =================================================== 300 301 302.. table:: Table 1-3: Contents of the statm files (as of 2.6.8-rc3) 303 304 ======== =============================== ============================== 305 Field Content 306 ======== =============================== ============================== 307 size total program size (pages) (same as VmSize in status) 308 resident size of memory portions (pages) (same as VmRSS in status) 309 shared number of pages that are shared (i.e. backed by a file, same 310 as RssFile+RssShmem in status) 311 trs number of pages that are 'code' (not including libs; broken, 312 includes data segment) 313 lrs number of pages of library (always 0 on 2.6) 314 drs number of pages of data/stack (including libs; broken, 315 includes library text) 316 dt number of dirty pages (always 0 on 2.6) 317 ======== =============================== ============================== 318 319 320.. table:: Table 1-4: Contents of the stat files (as of 2.6.30-rc7) 321 322 ============= =============================================================== 323 Field Content 324 ============= =============================================================== 325 pid process id 326 tcomm filename of the executable 327 state state (R is running, S is sleeping, D is sleeping in an 328 uninterruptible wait, Z is zombie, T is traced or stopped) 329 ppid process id of the parent process 330 pgrp pgrp of the process 331 sid session id 332 tty_nr tty the process uses 333 tty_pgrp pgrp of the tty 334 flags task flags 335 min_flt number of minor faults 336 cmin_flt number of minor faults with child's 337 maj_flt number of major faults 338 cmaj_flt number of major faults with child's 339 utime user mode jiffies 340 stime kernel mode jiffies 341 cutime user mode jiffies with child's 342 cstime kernel mode jiffies with child's 343 priority priority level 344 nice nice level 345 num_threads number of threads 346 it_real_value (obsolete, always 0) 347 start_time time the process started after system boot 348 vsize virtual memory size 349 rss resident set memory size 350 rsslim current limit in bytes on the rss 351 start_code address above which program text can run 352 end_code address below which program text can run 353 start_stack address of the start of the main process stack 354 esp current value of ESP 355 eip current value of EIP 356 pending bitmap of pending signals 357 blocked bitmap of blocked signals 358 sigign bitmap of ignored signals 359 sigcatch bitmap of caught signals 360 0 (place holder, used to be the wchan address, 361 use /proc/PID/wchan instead) 362 0 (place holder) 363 0 (place holder) 364 exit_signal signal to send to parent thread on exit 365 task_cpu which CPU the task is scheduled on 366 rt_priority realtime priority 367 policy scheduling policy (man sched_setscheduler) 368 blkio_ticks time spent waiting for block IO 369 gtime guest time of the task in jiffies 370 cgtime guest time of the task children in jiffies 371 start_data address above which program data+bss is placed 372 end_data address below which program data+bss is placed 373 start_brk address above which program heap can be expanded with brk() 374 arg_start address above which program command line is placed 375 arg_end address below which program command line is placed 376 env_start address above which program environment is placed 377 env_end address below which program environment is placed 378 exit_code the thread's exit_code in the form reported by the waitpid 379 system call 380 ============= =============================================================== 381 382The /proc/PID/maps file contains the currently mapped memory regions and 383their access permissions. 384 385The format is:: 386 387 address perms offset dev inode pathname 388 389 08048000-08049000 r-xp 00000000 03:00 8312 /opt/test 390 08049000-0804a000 rw-p 00001000 03:00 8312 /opt/test 391 0804a000-0806b000 rw-p 00000000 00:00 0 [heap] 392 a7cb1000-a7cb2000 ---p 00000000 00:00 0 393 a7cb2000-a7eb2000 rw-p 00000000 00:00 0 394 a7eb2000-a7eb3000 ---p 00000000 00:00 0 395 a7eb3000-a7ed5000 rw-p 00000000 00:00 0 396 a7ed5000-a8008000 r-xp 00000000 03:00 4222 /lib/libc.so.6 397 a8008000-a800a000 r--p 00133000 03:00 4222 /lib/libc.so.6 398 a800a000-a800b000 rw-p 00135000 03:00 4222 /lib/libc.so.6 399 a800b000-a800e000 rw-p 00000000 00:00 0 400 a800e000-a8022000 r-xp 00000000 03:00 14462 /lib/libpthread.so.0 401 a8022000-a8023000 r--p 00013000 03:00 14462 /lib/libpthread.so.0 402 a8023000-a8024000 rw-p 00014000 03:00 14462 /lib/libpthread.so.0 403 a8024000-a8027000 rw-p 00000000 00:00 0 404 a8027000-a8043000 r-xp 00000000 03:00 8317 /lib/ld-linux.so.2 405 a8043000-a8044000 r--p 0001b000 03:00 8317 /lib/ld-linux.so.2 406 a8044000-a8045000 rw-p 0001c000 03:00 8317 /lib/ld-linux.so.2 407 aff35000-aff4a000 rw-p 00000000 00:00 0 [stack] 408 ffffe000-fffff000 r-xp 00000000 00:00 0 [vdso] 409 410where "address" is the address space in the process that it occupies, "perms" 411is a set of permissions:: 412 413 r = read 414 w = write 415 x = execute 416 s = shared 417 p = private (copy on write) 418 419"offset" is the offset into the mapping, "dev" is the device (major:minor), and 420"inode" is the inode on that device. 0 indicates that no inode is associated 421with the memory region, as the case would be with BSS (uninitialized data). 422The "pathname" shows the name associated file for this mapping. If the mapping 423is not associated with a file: 424 425 ======= ==================================== 426 [heap] the heap of the program 427 [stack] the stack of the main process 428 [vdso] the "virtual dynamic shared object", 429 the kernel system call handler 430 ======= ==================================== 431 432 or if empty, the mapping is anonymous. 433 434The /proc/PID/smaps is an extension based on maps, showing the memory 435consumption for each of the process's mappings. For each mapping (aka Virtual 436Memory Area, or VMA) there is a series of lines such as the following:: 437 438 08048000-080bc000 r-xp 00000000 03:02 13130 /bin/bash 439 440 Size: 1084 kB 441 KernelPageSize: 4 kB 442 MMUPageSize: 4 kB 443 Rss: 892 kB 444 Pss: 374 kB 445 Shared_Clean: 892 kB 446 Shared_Dirty: 0 kB 447 Private_Clean: 0 kB 448 Private_Dirty: 0 kB 449 Referenced: 892 kB 450 Anonymous: 0 kB 451 LazyFree: 0 kB 452 AnonHugePages: 0 kB 453 ShmemPmdMapped: 0 kB 454 Shared_Hugetlb: 0 kB 455 Private_Hugetlb: 0 kB 456 Swap: 0 kB 457 SwapPss: 0 kB 458 KernelPageSize: 4 kB 459 MMUPageSize: 4 kB 460 Locked: 0 kB 461 THPeligible: 0 462 VmFlags: rd ex mr mw me dw 463 464The first of these lines shows the same information as is displayed for the 465mapping in /proc/PID/maps. Following lines show the size of the mapping 466(size); the size of each page allocated when backing a VMA (KernelPageSize), 467which is usually the same as the size in the page table entries; the page size 468used by the MMU when backing a VMA (in most cases, the same as KernelPageSize); 469the amount of the mapping that is currently resident in RAM (RSS); the 470process' proportional share of this mapping (PSS); and the number of clean and 471dirty shared and private pages in the mapping. 472 473The "proportional set size" (PSS) of a process is the count of pages it has 474in memory, where each page is divided by the number of processes sharing it. 475So if a process has 1000 pages all to itself, and 1000 shared with one other 476process, its PSS will be 1500. 477 478Note that even a page which is part of a MAP_SHARED mapping, but has only 479a single pte mapped, i.e. is currently used by only one process, is accounted 480as private and not as shared. 481 482"Referenced" indicates the amount of memory currently marked as referenced or 483accessed. 484 485"Anonymous" shows the amount of memory that does not belong to any file. Even 486a mapping associated with a file may contain anonymous pages: when MAP_PRIVATE 487and a page is modified, the file page is replaced by a private anonymous copy. 488 489"LazyFree" shows the amount of memory which is marked by madvise(MADV_FREE). 490The memory isn't freed immediately with madvise(). It's freed in memory 491pressure if the memory is clean. Please note that the printed value might 492be lower than the real value due to optimizations used in the current 493implementation. If this is not desirable please file a bug report. 494 495"AnonHugePages" shows the ammount of memory backed by transparent hugepage. 496 497"ShmemPmdMapped" shows the ammount of shared (shmem/tmpfs) memory backed by 498huge pages. 499 500"Shared_Hugetlb" and "Private_Hugetlb" show the ammounts of memory backed by 501hugetlbfs page which is *not* counted in "RSS" or "PSS" field for historical 502reasons. And these are not included in {Shared,Private}_{Clean,Dirty} field. 503 504"Swap" shows how much would-be-anonymous memory is also used, but out on swap. 505 506For shmem mappings, "Swap" includes also the size of the mapped (and not 507replaced by copy-on-write) part of the underlying shmem object out on swap. 508"SwapPss" shows proportional swap share of this mapping. Unlike "Swap", this 509does not take into account swapped out page of underlying shmem objects. 510"Locked" indicates whether the mapping is locked in memory or not. 511"THPeligible" indicates whether the mapping is eligible for allocating THP 512pages - 1 if true, 0 otherwise. It just shows the current status. 513 514"VmFlags" field deserves a separate description. This member represents the 515kernel flags associated with the particular virtual memory area in two letter 516encoded manner. The codes are the following: 517 518 == ======================================= 519 rd readable 520 wr writeable 521 ex executable 522 sh shared 523 mr may read 524 mw may write 525 me may execute 526 ms may share 527 gd stack segment growns down 528 pf pure PFN range 529 dw disabled write to the mapped file 530 lo pages are locked in memory 531 io memory mapped I/O area 532 sr sequential read advise provided 533 rr random read advise provided 534 dc do not copy area on fork 535 de do not expand area on remapping 536 ac area is accountable 537 nr swap space is not reserved for the area 538 ht area uses huge tlb pages 539 ar architecture specific flag 540 dd do not include area into core dump 541 sd soft dirty flag 542 mm mixed map area 543 hg huge page advise flag 544 nh no huge page advise flag 545 mg mergable advise flag 546 bt - arm64 BTI guarded page 547 == ======================================= 548 549Note that there is no guarantee that every flag and associated mnemonic will 550be present in all further kernel releases. Things get changed, the flags may 551be vanished or the reverse -- new added. Interpretation of their meaning 552might change in future as well. So each consumer of these flags has to 553follow each specific kernel version for the exact semantic. 554 555This file is only present if the CONFIG_MMU kernel configuration option is 556enabled. 557 558Note: reading /proc/PID/maps or /proc/PID/smaps is inherently racy (consistent 559output can be achieved only in the single read call). 560 561This typically manifests when doing partial reads of these files while the 562memory map is being modified. Despite the races, we do provide the following 563guarantees: 564 5651) The mapped addresses never go backwards, which implies no two 566 regions will ever overlap. 5672) If there is something at a given vaddr during the entirety of the 568 life of the smaps/maps walk, there will be some output for it. 569 570The /proc/PID/smaps_rollup file includes the same fields as /proc/PID/smaps, 571but their values are the sums of the corresponding values for all mappings of 572the process. Additionally, it contains these fields: 573 574- Pss_Anon 575- Pss_File 576- Pss_Shmem 577 578They represent the proportional shares of anonymous, file, and shmem pages, as 579described for smaps above. These fields are omitted in smaps since each 580mapping identifies the type (anon, file, or shmem) of all pages it contains. 581Thus all information in smaps_rollup can be derived from smaps, but at a 582significantly higher cost. 583 584The /proc/PID/clear_refs is used to reset the PG_Referenced and ACCESSED/YOUNG 585bits on both physical and virtual pages associated with a process, and the 586soft-dirty bit on pte (see Documentation/admin-guide/mm/soft-dirty.rst 587for details). 588To clear the bits for all the pages associated with the process:: 589 590 > echo 1 > /proc/PID/clear_refs 591 592To clear the bits for the anonymous pages associated with the process:: 593 594 > echo 2 > /proc/PID/clear_refs 595 596To clear the bits for the file mapped pages associated with the process:: 597 598 > echo 3 > /proc/PID/clear_refs 599 600To clear the soft-dirty bit:: 601 602 > echo 4 > /proc/PID/clear_refs 603 604To reset the peak resident set size ("high water mark") to the process's 605current value:: 606 607 > echo 5 > /proc/PID/clear_refs 608 609Any other value written to /proc/PID/clear_refs will have no effect. 610 611The /proc/pid/pagemap gives the PFN, which can be used to find the pageflags 612using /proc/kpageflags and number of times a page is mapped using 613/proc/kpagecount. For detailed explanation, see 614Documentation/admin-guide/mm/pagemap.rst. 615 616The /proc/pid/numa_maps is an extension based on maps, showing the memory 617locality and binding policy, as well as the memory usage (in pages) of 618each mapping. The output follows a general format where mapping details get 619summarized separated by blank spaces, one mapping per each file line:: 620 621 address policy mapping details 622 623 00400000 default file=/usr/local/bin/app mapped=1 active=0 N3=1 kernelpagesize_kB=4 624 00600000 default file=/usr/local/bin/app anon=1 dirty=1 N3=1 kernelpagesize_kB=4 625 3206000000 default file=/lib64/ld-2.12.so mapped=26 mapmax=6 N0=24 N3=2 kernelpagesize_kB=4 626 320621f000 default file=/lib64/ld-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4 627 3206220000 default file=/lib64/ld-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4 628 3206221000 default anon=1 dirty=1 N3=1 kernelpagesize_kB=4 629 3206800000 default file=/lib64/libc-2.12.so mapped=59 mapmax=21 active=55 N0=41 N3=18 kernelpagesize_kB=4 630 320698b000 default file=/lib64/libc-2.12.so 631 3206b8a000 default file=/lib64/libc-2.12.so anon=2 dirty=2 N3=2 kernelpagesize_kB=4 632 3206b8e000 default file=/lib64/libc-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4 633 3206b8f000 default anon=3 dirty=3 active=1 N3=3 kernelpagesize_kB=4 634 7f4dc10a2000 default anon=3 dirty=3 N3=3 kernelpagesize_kB=4 635 7f4dc10b4000 default anon=2 dirty=2 active=1 N3=2 kernelpagesize_kB=4 636 7f4dc1200000 default file=/anon_hugepage\040(deleted) huge anon=1 dirty=1 N3=1 kernelpagesize_kB=2048 637 7fff335f0000 default stack anon=3 dirty=3 N3=3 kernelpagesize_kB=4 638 7fff3369d000 default mapped=1 mapmax=35 active=0 N3=1 kernelpagesize_kB=4 639 640Where: 641 642"address" is the starting address for the mapping; 643 644"policy" reports the NUMA memory policy set for the mapping (see Documentation/admin-guide/mm/numa_memory_policy.rst); 645 646"mapping details" summarizes mapping data such as mapping type, page usage counters, 647node locality page counters (N0 == node0, N1 == node1, ...) and the kernel page 648size, in KB, that is backing the mapping up. 649 6501.2 Kernel data 651--------------- 652 653Similar to the process entries, the kernel data files give information about 654the running kernel. The files used to obtain this information are contained in 655/proc and are listed in Table 1-5. Not all of these will be present in your 656system. It depends on the kernel configuration and the loaded modules, which 657files are there, and which are missing. 658 659.. table:: Table 1-5: Kernel info in /proc 660 661 ============ =============================================================== 662 File Content 663 ============ =============================================================== 664 apm Advanced power management info 665 buddyinfo Kernel memory allocator information (see text) (2.5) 666 bus Directory containing bus specific information 667 cmdline Kernel command line 668 cpuinfo Info about the CPU 669 devices Available devices (block and character) 670 dma Used DMS channels 671 filesystems Supported filesystems 672 driver Various drivers grouped here, currently rtc (2.4) 673 execdomains Execdomains, related to security (2.4) 674 fb Frame Buffer devices (2.4) 675 fs File system parameters, currently nfs/exports (2.4) 676 ide Directory containing info about the IDE subsystem 677 interrupts Interrupt usage 678 iomem Memory map (2.4) 679 ioports I/O port usage 680 irq Masks for irq to cpu affinity (2.4)(smp?) 681 isapnp ISA PnP (Plug&Play) Info (2.4) 682 kcore Kernel core image (can be ELF or A.OUT(deprecated in 2.4)) 683 kmsg Kernel messages 684 ksyms Kernel symbol table 685 loadavg Load average of last 1, 5 & 15 minutes 686 locks Kernel locks 687 meminfo Memory info 688 misc Miscellaneous 689 modules List of loaded modules 690 mounts Mounted filesystems 691 net Networking info (see text) 692 pagetypeinfo Additional page allocator information (see text) (2.5) 693 partitions Table of partitions known to the system 694 pci Deprecated info of PCI bus (new way -> /proc/bus/pci/, 695 decoupled by lspci (2.4) 696 rtc Real time clock 697 scsi SCSI info (see text) 698 slabinfo Slab pool info 699 softirqs softirq usage 700 stat Overall statistics 701 swaps Swap space utilization 702 sys See chapter 2 703 sysvipc Info of SysVIPC Resources (msg, sem, shm) (2.4) 704 tty Info of tty drivers 705 uptime Wall clock since boot, combined idle time of all cpus 706 version Kernel version 707 video bttv info of video resources (2.4) 708 vmallocinfo Show vmalloced areas 709 ============ =============================================================== 710 711You can, for example, check which interrupts are currently in use and what 712they are used for by looking in the file /proc/interrupts:: 713 714 > cat /proc/interrupts 715 CPU0 716 0: 8728810 XT-PIC timer 717 1: 895 XT-PIC keyboard 718 2: 0 XT-PIC cascade 719 3: 531695 XT-PIC aha152x 720 4: 2014133 XT-PIC serial 721 5: 44401 XT-PIC pcnet_cs 722 8: 2 XT-PIC rtc 723 11: 8 XT-PIC i82365 724 12: 182918 XT-PIC PS/2 Mouse 725 13: 1 XT-PIC fpu 726 14: 1232265 XT-PIC ide0 727 15: 7 XT-PIC ide1 728 NMI: 0 729 730In 2.4.* a couple of lines where added to this file LOC & ERR (this time is the 731output of a SMP machine):: 732 733 > cat /proc/interrupts 734 735 CPU0 CPU1 736 0: 1243498 1214548 IO-APIC-edge timer 737 1: 8949 8958 IO-APIC-edge keyboard 738 2: 0 0 XT-PIC cascade 739 5: 11286 10161 IO-APIC-edge soundblaster 740 8: 1 0 IO-APIC-edge rtc 741 9: 27422 27407 IO-APIC-edge 3c503 742 12: 113645 113873 IO-APIC-edge PS/2 Mouse 743 13: 0 0 XT-PIC fpu 744 14: 22491 24012 IO-APIC-edge ide0 745 15: 2183 2415 IO-APIC-edge ide1 746 17: 30564 30414 IO-APIC-level eth0 747 18: 177 164 IO-APIC-level bttv 748 NMI: 2457961 2457959 749 LOC: 2457882 2457881 750 ERR: 2155 751 752NMI is incremented in this case because every timer interrupt generates a NMI 753(Non Maskable Interrupt) which is used by the NMI Watchdog to detect lockups. 754 755LOC is the local interrupt counter of the internal APIC of every CPU. 756 757ERR is incremented in the case of errors in the IO-APIC bus (the bus that 758connects the CPUs in a SMP system. This means that an error has been detected, 759the IO-APIC automatically retry the transmission, so it should not be a big 760problem, but you should read the SMP-FAQ. 761 762In 2.6.2* /proc/interrupts was expanded again. This time the goal was for 763/proc/interrupts to display every IRQ vector in use by the system, not 764just those considered 'most important'. The new vectors are: 765 766THR 767 interrupt raised when a machine check threshold counter 768 (typically counting ECC corrected errors of memory or cache) exceeds 769 a configurable threshold. Only available on some systems. 770 771TRM 772 a thermal event interrupt occurs when a temperature threshold 773 has been exceeded for the CPU. This interrupt may also be generated 774 when the temperature drops back to normal. 775 776SPU 777 a spurious interrupt is some interrupt that was raised then lowered 778 by some IO device before it could be fully processed by the APIC. Hence 779 the APIC sees the interrupt but does not know what device it came from. 780 For this case the APIC will generate the interrupt with a IRQ vector 781 of 0xff. This might also be generated by chipset bugs. 782 783RES, CAL, TLB] 784 rescheduling, call and TLB flush interrupts are 785 sent from one CPU to another per the needs of the OS. Typically, 786 their statistics are used by kernel developers and interested users to 787 determine the occurrence of interrupts of the given type. 788 789The above IRQ vectors are displayed only when relevant. For example, 790the threshold vector does not exist on x86_64 platforms. Others are 791suppressed when the system is a uniprocessor. As of this writing, only 792i386 and x86_64 platforms support the new IRQ vector displays. 793 794Of some interest is the introduction of the /proc/irq directory to 2.4. 795It could be used to set IRQ to CPU affinity, this means that you can "hook" an 796IRQ to only one CPU, or to exclude a CPU of handling IRQs. The contents of the 797irq subdir is one subdir for each IRQ, and two files; default_smp_affinity and 798prof_cpu_mask. 799 800For example:: 801 802 > ls /proc/irq/ 803 0 10 12 14 16 18 2 4 6 8 prof_cpu_mask 804 1 11 13 15 17 19 3 5 7 9 default_smp_affinity 805 > ls /proc/irq/0/ 806 smp_affinity 807 808smp_affinity is a bitmask, in which you can specify which CPUs can handle the 809IRQ, you can set it by doing:: 810 811 > echo 1 > /proc/irq/10/smp_affinity 812 813This means that only the first CPU will handle the IRQ, but you can also echo 8145 which means that only the first and third CPU can handle the IRQ. 815 816The contents of each smp_affinity file is the same by default:: 817 818 > cat /proc/irq/0/smp_affinity 819 ffffffff 820 821There is an alternate interface, smp_affinity_list which allows specifying 822a cpu range instead of a bitmask:: 823 824 > cat /proc/irq/0/smp_affinity_list 825 1024-1031 826 827The default_smp_affinity mask applies to all non-active IRQs, which are the 828IRQs which have not yet been allocated/activated, and hence which lack a 829/proc/irq/[0-9]* directory. 830 831The node file on an SMP system shows the node to which the device using the IRQ 832reports itself as being attached. This hardware locality information does not 833include information about any possible driver locality preference. 834 835prof_cpu_mask specifies which CPUs are to be profiled by the system wide 836profiler. Default value is ffffffff (all cpus if there are only 32 of them). 837 838The way IRQs are routed is handled by the IO-APIC, and it's Round Robin 839between all the CPUs which are allowed to handle it. As usual the kernel has 840more info than you and does a better job than you, so the defaults are the 841best choice for almost everyone. [Note this applies only to those IO-APIC's 842that support "Round Robin" interrupt distribution.] 843 844There are three more important subdirectories in /proc: net, scsi, and sys. 845The general rule is that the contents, or even the existence of these 846directories, depend on your kernel configuration. If SCSI is not enabled, the 847directory scsi may not exist. The same is true with the net, which is there 848only when networking support is present in the running kernel. 849 850The slabinfo file gives information about memory usage at the slab level. 851Linux uses slab pools for memory management above page level in version 2.2. 852Commonly used objects have their own slab pool (such as network buffers, 853directory cache, and so on). 854 855:: 856 857 > cat /proc/buddyinfo 858 859 Node 0, zone DMA 0 4 5 4 4 3 ... 860 Node 0, zone Normal 1 0 0 1 101 8 ... 861 Node 0, zone HighMem 2 0 0 1 1 0 ... 862 863External fragmentation is a problem under some workloads, and buddyinfo is a 864useful tool for helping diagnose these problems. Buddyinfo will give you a 865clue as to how big an area you can safely allocate, or why a previous 866allocation failed. 867 868Each column represents the number of pages of a certain order which are 869available. In this case, there are 0 chunks of 2^0*PAGE_SIZE available in 870ZONE_DMA, 4 chunks of 2^1*PAGE_SIZE in ZONE_DMA, 101 chunks of 2^4*PAGE_SIZE 871available in ZONE_NORMAL, etc... 872 873More information relevant to external fragmentation can be found in 874pagetypeinfo:: 875 876 > cat /proc/pagetypeinfo 877 Page block order: 9 878 Pages per block: 512 879 880 Free pages count per migrate type at order 0 1 2 3 4 5 6 7 8 9 10 881 Node 0, zone DMA, type Unmovable 0 0 0 1 1 1 1 1 1 1 0 882 Node 0, zone DMA, type Reclaimable 0 0 0 0 0 0 0 0 0 0 0 883 Node 0, zone DMA, type Movable 1 1 2 1 2 1 1 0 1 0 2 884 Node 0, zone DMA, type Reserve 0 0 0 0 0 0 0 0 0 1 0 885 Node 0, zone DMA, type Isolate 0 0 0 0 0 0 0 0 0 0 0 886 Node 0, zone DMA32, type Unmovable 103 54 77 1 1 1 11 8 7 1 9 887 Node 0, zone DMA32, type Reclaimable 0 0 2 1 0 0 0 0 1 0 0 888 Node 0, zone DMA32, type Movable 169 152 113 91 77 54 39 13 6 1 452 889 Node 0, zone DMA32, type Reserve 1 2 2 2 2 0 1 1 1 1 0 890 Node 0, zone DMA32, type Isolate 0 0 0 0 0 0 0 0 0 0 0 891 892 Number of blocks type Unmovable Reclaimable Movable Reserve Isolate 893 Node 0, zone DMA 2 0 5 1 0 894 Node 0, zone DMA32 41 6 967 2 0 895 896Fragmentation avoidance in the kernel works by grouping pages of different 897migrate types into the same contiguous regions of memory called page blocks. 898A page block is typically the size of the default hugepage size e.g. 2MB on 899X86-64. By keeping pages grouped based on their ability to move, the kernel 900can reclaim pages within a page block to satisfy a high-order allocation. 901 902The pagetypinfo begins with information on the size of a page block. It 903then gives the same type of information as buddyinfo except broken down 904by migrate-type and finishes with details on how many page blocks of each 905type exist. 906 907If min_free_kbytes has been tuned correctly (recommendations made by hugeadm 908from libhugetlbfs https://github.com/libhugetlbfs/libhugetlbfs/), one can 909make an estimate of the likely number of huge pages that can be allocated 910at a given point in time. All the "Movable" blocks should be allocatable 911unless memory has been mlock()'d. Some of the Reclaimable blocks should 912also be allocatable although a lot of filesystem metadata may have to be 913reclaimed to achieve this. 914 915 916meminfo 917~~~~~~~ 918 919Provides information about distribution and utilization of memory. This 920varies by architecture and compile options. The following is from a 92116GB PIII, which has highmem enabled. You may not have all of these fields. 922 923:: 924 925 > cat /proc/meminfo 926 927 MemTotal: 16344972 kB 928 MemFree: 13634064 kB 929 MemAvailable: 14836172 kB 930 Buffers: 3656 kB 931 Cached: 1195708 kB 932 SwapCached: 0 kB 933 Active: 891636 kB 934 Inactive: 1077224 kB 935 HighTotal: 15597528 kB 936 HighFree: 13629632 kB 937 LowTotal: 747444 kB 938 LowFree: 4432 kB 939 SwapTotal: 0 kB 940 SwapFree: 0 kB 941 Dirty: 968 kB 942 Writeback: 0 kB 943 AnonPages: 861800 kB 944 Mapped: 280372 kB 945 Shmem: 644 kB 946 KReclaimable: 168048 kB 947 Slab: 284364 kB 948 SReclaimable: 159856 kB 949 SUnreclaim: 124508 kB 950 PageTables: 24448 kB 951 NFS_Unstable: 0 kB 952 Bounce: 0 kB 953 WritebackTmp: 0 kB 954 CommitLimit: 7669796 kB 955 Committed_AS: 100056 kB 956 VmallocTotal: 112216 kB 957 VmallocUsed: 428 kB 958 VmallocChunk: 111088 kB 959 Percpu: 62080 kB 960 HardwareCorrupted: 0 kB 961 AnonHugePages: 49152 kB 962 ShmemHugePages: 0 kB 963 ShmemPmdMapped: 0 kB 964 965MemTotal 966 Total usable ram (i.e. physical ram minus a few reserved 967 bits and the kernel binary code) 968MemFree 969 The sum of LowFree+HighFree 970MemAvailable 971 An estimate of how much memory is available for starting new 972 applications, without swapping. Calculated from MemFree, 973 SReclaimable, the size of the file LRU lists, and the low 974 watermarks in each zone. 975 The estimate takes into account that the system needs some 976 page cache to function well, and that not all reclaimable 977 slab will be reclaimable, due to items being in use. The 978 impact of those factors will vary from system to system. 979Buffers 980 Relatively temporary storage for raw disk blocks 981 shouldn't get tremendously large (20MB or so) 982Cached 983 in-memory cache for files read from the disk (the 984 pagecache). Doesn't include SwapCached 985SwapCached 986 Memory that once was swapped out, is swapped back in but 987 still also is in the swapfile (if memory is needed it 988 doesn't need to be swapped out AGAIN because it is already 989 in the swapfile. This saves I/O) 990Active 991 Memory that has been used more recently and usually not 992 reclaimed unless absolutely necessary. 993Inactive 994 Memory which has been less recently used. It is more 995 eligible to be reclaimed for other purposes 996HighTotal, HighFree 997 Highmem is all memory above ~860MB of physical memory 998 Highmem areas are for use by userspace programs, or 999 for the pagecache. The kernel must use tricks to access 1000 this memory, making it slower to access than lowmem. 1001LowTotal, LowFree 1002 Lowmem is memory which can be used for everything that 1003 highmem can be used for, but it is also available for the 1004 kernel's use for its own data structures. Among many 1005 other things, it is where everything from the Slab is 1006 allocated. Bad things happen when you're out of lowmem. 1007SwapTotal 1008 total amount of swap space available 1009SwapFree 1010 Memory which has been evicted from RAM, and is temporarily 1011 on the disk 1012Dirty 1013 Memory which is waiting to get written back to the disk 1014Writeback 1015 Memory which is actively being written back to the disk 1016AnonPages 1017 Non-file backed pages mapped into userspace page tables 1018HardwareCorrupted 1019 The amount of RAM/memory in KB, the kernel identifies as 1020 corrupted. 1021AnonHugePages 1022 Non-file backed huge pages mapped into userspace page tables 1023Mapped 1024 files which have been mmaped, such as libraries 1025Shmem 1026 Total memory used by shared memory (shmem) and tmpfs 1027ShmemHugePages 1028 Memory used by shared memory (shmem) and tmpfs allocated 1029 with huge pages 1030ShmemPmdMapped 1031 Shared memory mapped into userspace with huge pages 1032KReclaimable 1033 Kernel allocations that the kernel will attempt to reclaim 1034 under memory pressure. Includes SReclaimable (below), and other 1035 direct allocations with a shrinker. 1036Slab 1037 in-kernel data structures cache 1038SReclaimable 1039 Part of Slab, that might be reclaimed, such as caches 1040SUnreclaim 1041 Part of Slab, that cannot be reclaimed on memory pressure 1042PageTables 1043 amount of memory dedicated to the lowest level of page 1044 tables. 1045NFS_Unstable 1046 Always zero. Previous counted pages which had been written to 1047 the server, but has not been committed to stable storage. 1048Bounce 1049 Memory used for block device "bounce buffers" 1050WritebackTmp 1051 Memory used by FUSE for temporary writeback buffers 1052CommitLimit 1053 Based on the overcommit ratio ('vm.overcommit_ratio'), 1054 this is the total amount of memory currently available to 1055 be allocated on the system. This limit is only adhered to 1056 if strict overcommit accounting is enabled (mode 2 in 1057 'vm.overcommit_memory'). 1058 1059 The CommitLimit is calculated with the following formula:: 1060 1061 CommitLimit = ([total RAM pages] - [total huge TLB pages]) * 1062 overcommit_ratio / 100 + [total swap pages] 1063 1064 For example, on a system with 1G of physical RAM and 7G 1065 of swap with a `vm.overcommit_ratio` of 30 it would 1066 yield a CommitLimit of 7.3G. 1067 1068 For more details, see the memory overcommit documentation 1069 in vm/overcommit-accounting. 1070Committed_AS 1071 The amount of memory presently allocated on the system. 1072 The committed memory is a sum of all of the memory which 1073 has been allocated by processes, even if it has not been 1074 "used" by them as of yet. A process which malloc()'s 1G 1075 of memory, but only touches 300M of it will show up as 1076 using 1G. This 1G is memory which has been "committed" to 1077 by the VM and can be used at any time by the allocating 1078 application. With strict overcommit enabled on the system 1079 (mode 2 in 'vm.overcommit_memory'),allocations which would 1080 exceed the CommitLimit (detailed above) will not be permitted. 1081 This is useful if one needs to guarantee that processes will 1082 not fail due to lack of memory once that memory has been 1083 successfully allocated. 1084VmallocTotal 1085 total size of vmalloc memory area 1086VmallocUsed 1087 amount of vmalloc area which is used 1088VmallocChunk 1089 largest contiguous block of vmalloc area which is free 1090Percpu 1091 Memory allocated to the percpu allocator used to back percpu 1092 allocations. This stat excludes the cost of metadata. 1093 1094vmallocinfo 1095~~~~~~~~~~~ 1096 1097Provides information about vmalloced/vmaped areas. One line per area, 1098containing the virtual address range of the area, size in bytes, 1099caller information of the creator, and optional information depending 1100on the kind of area : 1101 1102 ========== =================================================== 1103 pages=nr number of pages 1104 phys=addr if a physical address was specified 1105 ioremap I/O mapping (ioremap() and friends) 1106 vmalloc vmalloc() area 1107 vmap vmap()ed pages 1108 user VM_USERMAP area 1109 vpages buffer for pages pointers was vmalloced (huge area) 1110 N<node>=nr (Only on NUMA kernels) 1111 Number of pages allocated on memory node <node> 1112 ========== =================================================== 1113 1114:: 1115 1116 > cat /proc/vmallocinfo 1117 0xffffc20000000000-0xffffc20000201000 2101248 alloc_large_system_hash+0x204 ... 1118 /0x2c0 pages=512 vmalloc N0=128 N1=128 N2=128 N3=128 1119 0xffffc20000201000-0xffffc20000302000 1052672 alloc_large_system_hash+0x204 ... 1120 /0x2c0 pages=256 vmalloc N0=64 N1=64 N2=64 N3=64 1121 0xffffc20000302000-0xffffc20000304000 8192 acpi_tb_verify_table+0x21/0x4f... 1122 phys=7fee8000 ioremap 1123 0xffffc20000304000-0xffffc20000307000 12288 acpi_tb_verify_table+0x21/0x4f... 1124 phys=7fee7000 ioremap 1125 0xffffc2000031d000-0xffffc2000031f000 8192 init_vdso_vars+0x112/0x210 1126 0xffffc2000031f000-0xffffc2000032b000 49152 cramfs_uncompress_init+0x2e ... 1127 /0x80 pages=11 vmalloc N0=3 N1=3 N2=2 N3=3 1128 0xffffc2000033a000-0xffffc2000033d000 12288 sys_swapon+0x640/0xac0 ... 1129 pages=2 vmalloc N1=2 1130 0xffffc20000347000-0xffffc2000034c000 20480 xt_alloc_table_info+0xfe ... 1131 /0x130 [x_tables] pages=4 vmalloc N0=4 1132 0xffffffffa0000000-0xffffffffa000f000 61440 sys_init_module+0xc27/0x1d00 ... 1133 pages=14 vmalloc N2=14 1134 0xffffffffa000f000-0xffffffffa0014000 20480 sys_init_module+0xc27/0x1d00 ... 1135 pages=4 vmalloc N1=4 1136 0xffffffffa0014000-0xffffffffa0017000 12288 sys_init_module+0xc27/0x1d00 ... 1137 pages=2 vmalloc N1=2 1138 0xffffffffa0017000-0xffffffffa0022000 45056 sys_init_module+0xc27/0x1d00 ... 1139 pages=10 vmalloc N0=10 1140 1141 1142softirqs 1143~~~~~~~~ 1144 1145Provides counts of softirq handlers serviced since boot time, for each cpu. 1146 1147:: 1148 1149 > cat /proc/softirqs 1150 CPU0 CPU1 CPU2 CPU3 1151 HI: 0 0 0 0 1152 TIMER: 27166 27120 27097 27034 1153 NET_TX: 0 0 0 17 1154 NET_RX: 42 0 0 39 1155 BLOCK: 0 0 107 1121 1156 TASKLET: 0 0 0 290 1157 SCHED: 27035 26983 26971 26746 1158 HRTIMER: 0 0 0 0 1159 RCU: 1678 1769 2178 2250 1160 1161 11621.3 IDE devices in /proc/ide 1163---------------------------- 1164 1165The subdirectory /proc/ide contains information about all IDE devices of which 1166the kernel is aware. There is one subdirectory for each IDE controller, the 1167file drivers and a link for each IDE device, pointing to the device directory 1168in the controller specific subtree. 1169 1170The file drivers contains general information about the drivers used for the 1171IDE devices:: 1172 1173 > cat /proc/ide/drivers 1174 ide-cdrom version 4.53 1175 ide-disk version 1.08 1176 1177More detailed information can be found in the controller specific 1178subdirectories. These are named ide0, ide1 and so on. Each of these 1179directories contains the files shown in table 1-6. 1180 1181 1182.. table:: Table 1-6: IDE controller info in /proc/ide/ide? 1183 1184 ======= ======================================= 1185 File Content 1186 ======= ======================================= 1187 channel IDE channel (0 or 1) 1188 config Configuration (only for PCI/IDE bridge) 1189 mate Mate name 1190 model Type/Chipset of IDE controller 1191 ======= ======================================= 1192 1193Each device connected to a controller has a separate subdirectory in the 1194controllers directory. The files listed in table 1-7 are contained in these 1195directories. 1196 1197 1198.. table:: Table 1-7: IDE device information 1199 1200 ================ ========================================== 1201 File Content 1202 ================ ========================================== 1203 cache The cache 1204 capacity Capacity of the medium (in 512Byte blocks) 1205 driver driver and version 1206 geometry physical and logical geometry 1207 identify device identify block 1208 media media type 1209 model device identifier 1210 settings device setup 1211 smart_thresholds IDE disk management thresholds 1212 smart_values IDE disk management values 1213 ================ ========================================== 1214 1215The most interesting file is ``settings``. This file contains a nice 1216overview of the drive parameters:: 1217 1218 # cat /proc/ide/ide0/hda/settings 1219 name value min max mode 1220 ---- ----- --- --- ---- 1221 bios_cyl 526 0 65535 rw 1222 bios_head 255 0 255 rw 1223 bios_sect 63 0 63 rw 1224 breada_readahead 4 0 127 rw 1225 bswap 0 0 1 r 1226 file_readahead 72 0 2097151 rw 1227 io_32bit 0 0 3 rw 1228 keepsettings 0 0 1 rw 1229 max_kb_per_request 122 1 127 rw 1230 multcount 0 0 8 rw 1231 nice1 1 0 1 rw 1232 nowerr 0 0 1 rw 1233 pio_mode write-only 0 255 w 1234 slow 0 0 1 rw 1235 unmaskirq 0 0 1 rw 1236 using_dma 0 0 1 rw 1237 1238 12391.4 Networking info in /proc/net 1240-------------------------------- 1241 1242The subdirectory /proc/net follows the usual pattern. Table 1-8 shows the 1243additional values you get for IP version 6 if you configure the kernel to 1244support this. Table 1-9 lists the files and their meaning. 1245 1246 1247.. table:: Table 1-8: IPv6 info in /proc/net 1248 1249 ========== ===================================================== 1250 File Content 1251 ========== ===================================================== 1252 udp6 UDP sockets (IPv6) 1253 tcp6 TCP sockets (IPv6) 1254 raw6 Raw device statistics (IPv6) 1255 igmp6 IP multicast addresses, which this host joined (IPv6) 1256 if_inet6 List of IPv6 interface addresses 1257 ipv6_route Kernel routing table for IPv6 1258 rt6_stats Global IPv6 routing tables statistics 1259 sockstat6 Socket statistics (IPv6) 1260 snmp6 Snmp data (IPv6) 1261 ========== ===================================================== 1262 1263.. table:: Table 1-9: Network info in /proc/net 1264 1265 ============= ================================================================ 1266 File Content 1267 ============= ================================================================ 1268 arp Kernel ARP table 1269 dev network devices with statistics 1270 dev_mcast the Layer2 multicast groups a device is listening too 1271 (interface index, label, number of references, number of bound 1272 addresses). 1273 dev_stat network device status 1274 ip_fwchains Firewall chain linkage 1275 ip_fwnames Firewall chain names 1276 ip_masq Directory containing the masquerading tables 1277 ip_masquerade Major masquerading table 1278 netstat Network statistics 1279 raw raw device statistics 1280 route Kernel routing table 1281 rpc Directory containing rpc info 1282 rt_cache Routing cache 1283 snmp SNMP data 1284 sockstat Socket statistics 1285 tcp TCP sockets 1286 udp UDP sockets 1287 unix UNIX domain sockets 1288 wireless Wireless interface data (Wavelan etc) 1289 igmp IP multicast addresses, which this host joined 1290 psched Global packet scheduler parameters. 1291 netlink List of PF_NETLINK sockets 1292 ip_mr_vifs List of multicast virtual interfaces 1293 ip_mr_cache List of multicast routing cache 1294 ============= ================================================================ 1295 1296You can use this information to see which network devices are available in 1297your system and how much traffic was routed over those devices:: 1298 1299 > cat /proc/net/dev 1300 Inter-|Receive |[... 1301 face |bytes packets errs drop fifo frame compressed multicast|[... 1302 lo: 908188 5596 0 0 0 0 0 0 [... 1303 ppp0:15475140 20721 410 0 0 410 0 0 [... 1304 eth0: 614530 7085 0 0 0 0 0 1 [... 1305 1306 ...] Transmit 1307 ...] bytes packets errs drop fifo colls carrier compressed 1308 ...] 908188 5596 0 0 0 0 0 0 1309 ...] 1375103 17405 0 0 0 0 0 0 1310 ...] 1703981 5535 0 0 0 3 0 0 1311 1312In addition, each Channel Bond interface has its own directory. For 1313example, the bond0 device will have a directory called /proc/net/bond0/. 1314It will contain information that is specific to that bond, such as the 1315current slaves of the bond, the link status of the slaves, and how 1316many times the slaves link has failed. 1317 13181.5 SCSI info 1319------------- 1320 1321If you have a SCSI host adapter in your system, you'll find a subdirectory 1322named after the driver for this adapter in /proc/scsi. You'll also see a list 1323of all recognized SCSI devices in /proc/scsi:: 1324 1325 >cat /proc/scsi/scsi 1326 Attached devices: 1327 Host: scsi0 Channel: 00 Id: 00 Lun: 00 1328 Vendor: IBM Model: DGHS09U Rev: 03E0 1329 Type: Direct-Access ANSI SCSI revision: 03 1330 Host: scsi0 Channel: 00 Id: 06 Lun: 00 1331 Vendor: PIONEER Model: CD-ROM DR-U06S Rev: 1.04 1332 Type: CD-ROM ANSI SCSI revision: 02 1333 1334 1335The directory named after the driver has one file for each adapter found in 1336the system. These files contain information about the controller, including 1337the used IRQ and the IO address range. The amount of information shown is 1338dependent on the adapter you use. The example shows the output for an Adaptec 1339AHA-2940 SCSI adapter:: 1340 1341 > cat /proc/scsi/aic7xxx/0 1342 1343 Adaptec AIC7xxx driver version: 5.1.19/3.2.4 1344 Compile Options: 1345 TCQ Enabled By Default : Disabled 1346 AIC7XXX_PROC_STATS : Disabled 1347 AIC7XXX_RESET_DELAY : 5 1348 Adapter Configuration: 1349 SCSI Adapter: Adaptec AHA-294X Ultra SCSI host adapter 1350 Ultra Wide Controller 1351 PCI MMAPed I/O Base: 0xeb001000 1352 Adapter SEEPROM Config: SEEPROM found and used. 1353 Adaptec SCSI BIOS: Enabled 1354 IRQ: 10 1355 SCBs: Active 0, Max Active 2, 1356 Allocated 15, HW 16, Page 255 1357 Interrupts: 160328 1358 BIOS Control Word: 0x18b6 1359 Adapter Control Word: 0x005b 1360 Extended Translation: Enabled 1361 Disconnect Enable Flags: 0xffff 1362 Ultra Enable Flags: 0x0001 1363 Tag Queue Enable Flags: 0x0000 1364 Ordered Queue Tag Flags: 0x0000 1365 Default Tag Queue Depth: 8 1366 Tagged Queue By Device array for aic7xxx host instance 0: 1367 {255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255} 1368 Actual queue depth per device for aic7xxx host instance 0: 1369 {1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1} 1370 Statistics: 1371 (scsi0:0:0:0) 1372 Device using Wide/Sync transfers at 40.0 MByte/sec, offset 8 1373 Transinfo settings: current(12/8/1/0), goal(12/8/1/0), user(12/15/1/0) 1374 Total transfers 160151 (74577 reads and 85574 writes) 1375 (scsi0:0:6:0) 1376 Device using Narrow/Sync transfers at 5.0 MByte/sec, offset 15 1377 Transinfo settings: current(50/15/0/0), goal(50/15/0/0), user(50/15/0/0) 1378 Total transfers 0 (0 reads and 0 writes) 1379 1380 13811.6 Parallel port info in /proc/parport 1382--------------------------------------- 1383 1384The directory /proc/parport contains information about the parallel ports of 1385your system. It has one subdirectory for each port, named after the port 1386number (0,1,2,...). 1387 1388These directories contain the four files shown in Table 1-10. 1389 1390 1391.. table:: Table 1-10: Files in /proc/parport 1392 1393 ========= ==================================================================== 1394 File Content 1395 ========= ==================================================================== 1396 autoprobe Any IEEE-1284 device ID information that has been acquired. 1397 devices list of the device drivers using that port. A + will appear by the 1398 name of the device currently using the port (it might not appear 1399 against any). 1400 hardware Parallel port's base address, IRQ line and DMA channel. 1401 irq IRQ that parport is using for that port. This is in a separate 1402 file to allow you to alter it by writing a new value in (IRQ 1403 number or none). 1404 ========= ==================================================================== 1405 14061.7 TTY info in /proc/tty 1407------------------------- 1408 1409Information about the available and actually used tty's can be found in the 1410directory /proc/tty.You'll find entries for drivers and line disciplines in 1411this directory, as shown in Table 1-11. 1412 1413 1414.. table:: Table 1-11: Files in /proc/tty 1415 1416 ============= ============================================== 1417 File Content 1418 ============= ============================================== 1419 drivers list of drivers and their usage 1420 ldiscs registered line disciplines 1421 driver/serial usage statistic and status of single tty lines 1422 ============= ============================================== 1423 1424To see which tty's are currently in use, you can simply look into the file 1425/proc/tty/drivers:: 1426 1427 > cat /proc/tty/drivers 1428 pty_slave /dev/pts 136 0-255 pty:slave 1429 pty_master /dev/ptm 128 0-255 pty:master 1430 pty_slave /dev/ttyp 3 0-255 pty:slave 1431 pty_master /dev/pty 2 0-255 pty:master 1432 serial /dev/cua 5 64-67 serial:callout 1433 serial /dev/ttyS 4 64-67 serial 1434 /dev/tty0 /dev/tty0 4 0 system:vtmaster 1435 /dev/ptmx /dev/ptmx 5 2 system 1436 /dev/console /dev/console 5 1 system:console 1437 /dev/tty /dev/tty 5 0 system:/dev/tty 1438 unknown /dev/tty 4 1-63 console 1439 1440 14411.8 Miscellaneous kernel statistics in /proc/stat 1442------------------------------------------------- 1443 1444Various pieces of information about kernel activity are available in the 1445/proc/stat file. All of the numbers reported in this file are aggregates 1446since the system first booted. For a quick look, simply cat the file:: 1447 1448 > cat /proc/stat 1449 cpu 2255 34 2290 22625563 6290 127 456 0 0 0 1450 cpu0 1132 34 1441 11311718 3675 127 438 0 0 0 1451 cpu1 1123 0 849 11313845 2614 0 18 0 0 0 1452 intr 114930548 113199788 3 0 5 263 0 4 [... lots more numbers ...] 1453 ctxt 1990473 1454 btime 1062191376 1455 processes 2915 1456 procs_running 1 1457 procs_blocked 0 1458 softirq 183433 0 21755 12 39 1137 231 21459 2263 1459 1460The very first "cpu" line aggregates the numbers in all of the other "cpuN" 1461lines. These numbers identify the amount of time the CPU has spent performing 1462different kinds of work. Time units are in USER_HZ (typically hundredths of a 1463second). The meanings of the columns are as follows, from left to right: 1464 1465- user: normal processes executing in user mode 1466- nice: niced processes executing in user mode 1467- system: processes executing in kernel mode 1468- idle: twiddling thumbs 1469- iowait: In a word, iowait stands for waiting for I/O to complete. But there 1470 are several problems: 1471 1472 1. Cpu will not wait for I/O to complete, iowait is the time that a task is 1473 waiting for I/O to complete. When cpu goes into idle state for 1474 outstanding task io, another task will be scheduled on this CPU. 1475 2. In a multi-core CPU, the task waiting for I/O to complete is not running 1476 on any CPU, so the iowait of each CPU is difficult to calculate. 1477 3. The value of iowait field in /proc/stat will decrease in certain 1478 conditions. 1479 1480 So, the iowait is not reliable by reading from /proc/stat. 1481- irq: servicing interrupts 1482- softirq: servicing softirqs 1483- steal: involuntary wait 1484- guest: running a normal guest 1485- guest_nice: running a niced guest 1486 1487The "intr" line gives counts of interrupts serviced since boot time, for each 1488of the possible system interrupts. The first column is the total of all 1489interrupts serviced including unnumbered architecture specific interrupts; 1490each subsequent column is the total for that particular numbered interrupt. 1491Unnumbered interrupts are not shown, only summed into the total. 1492 1493The "ctxt" line gives the total number of context switches across all CPUs. 1494 1495The "btime" line gives the time at which the system booted, in seconds since 1496the Unix epoch. 1497 1498The "processes" line gives the number of processes and threads created, which 1499includes (but is not limited to) those created by calls to the fork() and 1500clone() system calls. 1501 1502The "procs_running" line gives the total number of threads that are 1503running or ready to run (i.e., the total number of runnable threads). 1504 1505The "procs_blocked" line gives the number of processes currently blocked, 1506waiting for I/O to complete. 1507 1508The "softirq" line gives counts of softirqs serviced since boot time, for each 1509of the possible system softirqs. The first column is the total of all 1510softirqs serviced; each subsequent column is the total for that particular 1511softirq. 1512 1513 15141.9 Ext4 file system parameters 1515------------------------------- 1516 1517Information about mounted ext4 file systems can be found in 1518/proc/fs/ext4. Each mounted filesystem will have a directory in 1519/proc/fs/ext4 based on its device name (i.e., /proc/fs/ext4/hdc or 1520/proc/fs/ext4/dm-0). The files in each per-device directory are shown 1521in Table 1-12, below. 1522 1523.. table:: Table 1-12: Files in /proc/fs/ext4/<devname> 1524 1525 ============== ========================================================== 1526 File Content 1527 mb_groups details of multiblock allocator buddy cache of free blocks 1528 ============== ========================================================== 1529 15302.0 /proc/consoles 1531------------------ 1532Shows registered system console lines. 1533 1534To see which character device lines are currently used for the system console 1535/dev/console, you may simply look into the file /proc/consoles:: 1536 1537 > cat /proc/consoles 1538 tty0 -WU (ECp) 4:7 1539 ttyS0 -W- (Ep) 4:64 1540 1541The columns are: 1542 1543+--------------------+-------------------------------------------------------+ 1544| device | name of the device | 1545+====================+=======================================================+ 1546| operations | * R = can do read operations | 1547| | * W = can do write operations | 1548| | * U = can do unblank | 1549+--------------------+-------------------------------------------------------+ 1550| flags | * E = it is enabled | 1551| | * C = it is preferred console | 1552| | * B = it is primary boot console | 1553| | * p = it is used for printk buffer | 1554| | * b = it is not a TTY but a Braille device | 1555| | * a = it is safe to use when cpu is offline | 1556+--------------------+-------------------------------------------------------+ 1557| major:minor | major and minor number of the device separated by a | 1558| | colon | 1559+--------------------+-------------------------------------------------------+ 1560 1561Summary 1562------- 1563 1564The /proc file system serves information about the running system. It not only 1565allows access to process data but also allows you to request the kernel status 1566by reading files in the hierarchy. 1567 1568The directory structure of /proc reflects the types of information and makes 1569it easy, if not obvious, where to look for specific data. 1570 1571Chapter 2: Modifying System Parameters 1572====================================== 1573 1574In This Chapter 1575--------------- 1576 1577* Modifying kernel parameters by writing into files found in /proc/sys 1578* Exploring the files which modify certain parameters 1579* Review of the /proc/sys file tree 1580 1581------------------------------------------------------------------------------ 1582 1583A very interesting part of /proc is the directory /proc/sys. This is not only 1584a source of information, it also allows you to change parameters within the 1585kernel. Be very careful when attempting this. You can optimize your system, 1586but you can also cause it to crash. Never alter kernel parameters on a 1587production system. Set up a development machine and test to make sure that 1588everything works the way you want it to. You may have no alternative but to 1589reboot the machine once an error has been made. 1590 1591To change a value, simply echo the new value into the file. An example is 1592given below in the section on the file system data. You need to be root to do 1593this. You can create your own boot script to perform this every time your 1594system boots. 1595 1596The files in /proc/sys can be used to fine tune and monitor miscellaneous and 1597general things in the operation of the Linux kernel. Since some of the files 1598can inadvertently disrupt your system, it is advisable to read both 1599documentation and source before actually making adjustments. In any case, be 1600very careful when writing to any of these files. The entries in /proc may 1601change slightly between the 2.1.* and the 2.2 kernel, so if there is any doubt 1602review the kernel documentation in the directory /usr/src/linux/Documentation. 1603This chapter is heavily based on the documentation included in the pre 2.2 1604kernels, and became part of it in version 2.2.1 of the Linux kernel. 1605 1606Please see: Documentation/admin-guide/sysctl/ directory for descriptions of these 1607entries. 1608 1609Summary 1610------- 1611 1612Certain aspects of kernel behavior can be modified at runtime, without the 1613need to recompile the kernel, or even to reboot the system. The files in the 1614/proc/sys tree can not only be read, but also modified. You can use the echo 1615command to write value into these files, thereby changing the default settings 1616of the kernel. 1617 1618 1619Chapter 3: Per-process Parameters 1620================================= 1621 16223.1 /proc/<pid>/oom_adj & /proc/<pid>/oom_score_adj- Adjust the oom-killer score 1623-------------------------------------------------------------------------------- 1624 1625These file can be used to adjust the badness heuristic used to select which 1626process gets killed in out of memory conditions. 1627 1628The badness heuristic assigns a value to each candidate task ranging from 0 1629(never kill) to 1000 (always kill) to determine which process is targeted. The 1630units are roughly a proportion along that range of allowed memory the process 1631may allocate from based on an estimation of its current memory and swap use. 1632For example, if a task is using all allowed memory, its badness score will be 16331000. If it is using half of its allowed memory, its score will be 500. 1634 1635There is an additional factor included in the badness score: the current memory 1636and swap usage is discounted by 3% for root processes. 1637 1638The amount of "allowed" memory depends on the context in which the oom killer 1639was called. If it is due to the memory assigned to the allocating task's cpuset 1640being exhausted, the allowed memory represents the set of mems assigned to that 1641cpuset. If it is due to a mempolicy's node(s) being exhausted, the allowed 1642memory represents the set of mempolicy nodes. If it is due to a memory 1643limit (or swap limit) being reached, the allowed memory is that configured 1644limit. Finally, if it is due to the entire system being out of memory, the 1645allowed memory represents all allocatable resources. 1646 1647The value of /proc/<pid>/oom_score_adj is added to the badness score before it 1648is used to determine which task to kill. Acceptable values range from -1000 1649(OOM_SCORE_ADJ_MIN) to +1000 (OOM_SCORE_ADJ_MAX). This allows userspace to 1650polarize the preference for oom killing either by always preferring a certain 1651task or completely disabling it. The lowest possible value, -1000, is 1652equivalent to disabling oom killing entirely for that task since it will always 1653report a badness score of 0. 1654 1655Consequently, it is very simple for userspace to define the amount of memory to 1656consider for each task. Setting a /proc/<pid>/oom_score_adj value of +500, for 1657example, is roughly equivalent to allowing the remainder of tasks sharing the 1658same system, cpuset, mempolicy, or memory controller resources to use at least 165950% more memory. A value of -500, on the other hand, would be roughly 1660equivalent to discounting 50% of the task's allowed memory from being considered 1661as scoring against the task. 1662 1663For backwards compatibility with previous kernels, /proc/<pid>/oom_adj may also 1664be used to tune the badness score. Its acceptable values range from -16 1665(OOM_ADJUST_MIN) to +15 (OOM_ADJUST_MAX) and a special value of -17 1666(OOM_DISABLE) to disable oom killing entirely for that task. Its value is 1667scaled linearly with /proc/<pid>/oom_score_adj. 1668 1669The value of /proc/<pid>/oom_score_adj may be reduced no lower than the last 1670value set by a CAP_SYS_RESOURCE process. To reduce the value any lower 1671requires CAP_SYS_RESOURCE. 1672 1673Caveat: when a parent task is selected, the oom killer will sacrifice any first 1674generation children with separate address spaces instead, if possible. This 1675avoids servers and important system daemons from being killed and loses the 1676minimal amount of work. 1677 1678 16793.2 /proc/<pid>/oom_score - Display current oom-killer score 1680------------------------------------------------------------- 1681 1682This file can be used to check the current score used by the oom-killer is for 1683any given <pid>. Use it together with /proc/<pid>/oom_score_adj to tune which 1684process should be killed in an out-of-memory situation. 1685 1686 16873.3 /proc/<pid>/io - Display the IO accounting fields 1688------------------------------------------------------- 1689 1690This file contains IO statistics for each running process 1691 1692Example 1693~~~~~~~ 1694 1695:: 1696 1697 test:/tmp # dd if=/dev/zero of=/tmp/test.dat & 1698 [1] 3828 1699 1700 test:/tmp # cat /proc/3828/io 1701 rchar: 323934931 1702 wchar: 323929600 1703 syscr: 632687 1704 syscw: 632675 1705 read_bytes: 0 1706 write_bytes: 323932160 1707 cancelled_write_bytes: 0 1708 1709 1710Description 1711~~~~~~~~~~~ 1712 1713rchar 1714^^^^^ 1715 1716I/O counter: chars read 1717The number of bytes which this task has caused to be read from storage. This 1718is simply the sum of bytes which this process passed to read() and pread(). 1719It includes things like tty IO and it is unaffected by whether or not actual 1720physical disk IO was required (the read might have been satisfied from 1721pagecache) 1722 1723 1724wchar 1725^^^^^ 1726 1727I/O counter: chars written 1728The number of bytes which this task has caused, or shall cause to be written 1729to disk. Similar caveats apply here as with rchar. 1730 1731 1732syscr 1733^^^^^ 1734 1735I/O counter: read syscalls 1736Attempt to count the number of read I/O operations, i.e. syscalls like read() 1737and pread(). 1738 1739 1740syscw 1741^^^^^ 1742 1743I/O counter: write syscalls 1744Attempt to count the number of write I/O operations, i.e. syscalls like 1745write() and pwrite(). 1746 1747 1748read_bytes 1749^^^^^^^^^^ 1750 1751I/O counter: bytes read 1752Attempt to count the number of bytes which this process really did cause to 1753be fetched from the storage layer. Done at the submit_bio() level, so it is 1754accurate for block-backed filesystems. <please add status regarding NFS and 1755CIFS at a later time> 1756 1757 1758write_bytes 1759^^^^^^^^^^^ 1760 1761I/O counter: bytes written 1762Attempt to count the number of bytes which this process caused to be sent to 1763the storage layer. This is done at page-dirtying time. 1764 1765 1766cancelled_write_bytes 1767^^^^^^^^^^^^^^^^^^^^^ 1768 1769The big inaccuracy here is truncate. If a process writes 1MB to a file and 1770then deletes the file, it will in fact perform no writeout. But it will have 1771been accounted as having caused 1MB of write. 1772In other words: The number of bytes which this process caused to not happen, 1773by truncating pagecache. A task can cause "negative" IO too. If this task 1774truncates some dirty pagecache, some IO which another task has been accounted 1775for (in its write_bytes) will not be happening. We _could_ just subtract that 1776from the truncating task's write_bytes, but there is information loss in doing 1777that. 1778 1779 1780.. Note:: 1781 1782 At its current implementation state, this is a bit racy on 32-bit machines: 1783 if process A reads process B's /proc/pid/io while process B is updating one 1784 of those 64-bit counters, process A could see an intermediate result. 1785 1786 1787More information about this can be found within the taskstats documentation in 1788Documentation/accounting. 1789 17903.4 /proc/<pid>/coredump_filter - Core dump filtering settings 1791--------------------------------------------------------------- 1792When a process is dumped, all anonymous memory is written to a core file as 1793long as the size of the core file isn't limited. But sometimes we don't want 1794to dump some memory segments, for example, huge shared memory or DAX. 1795Conversely, sometimes we want to save file-backed memory segments into a core 1796file, not only the individual files. 1797 1798/proc/<pid>/coredump_filter allows you to customize which memory segments 1799will be dumped when the <pid> process is dumped. coredump_filter is a bitmask 1800of memory types. If a bit of the bitmask is set, memory segments of the 1801corresponding memory type are dumped, otherwise they are not dumped. 1802 1803The following 9 memory types are supported: 1804 1805 - (bit 0) anonymous private memory 1806 - (bit 1) anonymous shared memory 1807 - (bit 2) file-backed private memory 1808 - (bit 3) file-backed shared memory 1809 - (bit 4) ELF header pages in file-backed private memory areas (it is 1810 effective only if the bit 2 is cleared) 1811 - (bit 5) hugetlb private memory 1812 - (bit 6) hugetlb shared memory 1813 - (bit 7) DAX private memory 1814 - (bit 8) DAX shared memory 1815 1816 Note that MMIO pages such as frame buffer are never dumped and vDSO pages 1817 are always dumped regardless of the bitmask status. 1818 1819 Note that bits 0-4 don't affect hugetlb or DAX memory. hugetlb memory is 1820 only affected by bit 5-6, and DAX is only affected by bits 7-8. 1821 1822The default value of coredump_filter is 0x33; this means all anonymous memory 1823segments, ELF header pages and hugetlb private memory are dumped. 1824 1825If you don't want to dump all shared memory segments attached to pid 1234, 1826write 0x31 to the process's proc file:: 1827 1828 $ echo 0x31 > /proc/1234/coredump_filter 1829 1830When a new process is created, the process inherits the bitmask status from its 1831parent. It is useful to set up coredump_filter before the program runs. 1832For example:: 1833 1834 $ echo 0x7 > /proc/self/coredump_filter 1835 $ ./some_program 1836 18373.5 /proc/<pid>/mountinfo - Information about mounts 1838-------------------------------------------------------- 1839 1840This file contains lines of the form:: 1841 1842 36 35 98:0 /mnt1 /mnt2 rw,noatime master:1 - ext3 /dev/root rw,errors=continue 1843 (1)(2)(3) (4) (5) (6) (7) (8) (9) (10) (11) 1844 1845 (1) mount ID: unique identifier of the mount (may be reused after umount) 1846 (2) parent ID: ID of parent (or of self for the top of the mount tree) 1847 (3) major:minor: value of st_dev for files on filesystem 1848 (4) root: root of the mount within the filesystem 1849 (5) mount point: mount point relative to the process's root 1850 (6) mount options: per mount options 1851 (7) optional fields: zero or more fields of the form "tag[:value]" 1852 (8) separator: marks the end of the optional fields 1853 (9) filesystem type: name of filesystem of the form "type[.subtype]" 1854 (10) mount source: filesystem specific information or "none" 1855 (11) super options: per super block options 1856 1857Parsers should ignore all unrecognised optional fields. Currently the 1858possible optional fields are: 1859 1860================ ============================================================== 1861shared:X mount is shared in peer group X 1862master:X mount is slave to peer group X 1863propagate_from:X mount is slave and receives propagation from peer group X [#]_ 1864unbindable mount is unbindable 1865================ ============================================================== 1866 1867.. [#] X is the closest dominant peer group under the process's root. If 1868 X is the immediate master of the mount, or if there's no dominant peer 1869 group under the same root, then only the "master:X" field is present 1870 and not the "propagate_from:X" field. 1871 1872For more information on mount propagation see: 1873 1874 Documentation/filesystems/sharedsubtree.rst 1875 1876 18773.6 /proc/<pid>/comm & /proc/<pid>/task/<tid>/comm 1878-------------------------------------------------------- 1879These files provide a method to access a tasks comm value. It also allows for 1880a task to set its own or one of its thread siblings comm value. The comm value 1881is limited in size compared to the cmdline value, so writing anything longer 1882then the kernel's TASK_COMM_LEN (currently 16 chars) will result in a truncated 1883comm value. 1884 1885 18863.7 /proc/<pid>/task/<tid>/children - Information about task children 1887------------------------------------------------------------------------- 1888This file provides a fast way to retrieve first level children pids 1889of a task pointed by <pid>/<tid> pair. The format is a space separated 1890stream of pids. 1891 1892Note the "first level" here -- if a child has own children they will 1893not be listed here, one needs to read /proc/<children-pid>/task/<tid>/children 1894to obtain the descendants. 1895 1896Since this interface is intended to be fast and cheap it doesn't 1897guarantee to provide precise results and some children might be 1898skipped, especially if they've exited right after we printed their 1899pids, so one need to either stop or freeze processes being inspected 1900if precise results are needed. 1901 1902 19033.8 /proc/<pid>/fdinfo/<fd> - Information about opened file 1904--------------------------------------------------------------- 1905This file provides information associated with an opened file. The regular 1906files have at least three fields -- 'pos', 'flags' and mnt_id. The 'pos' 1907represents the current offset of the opened file in decimal form [see lseek(2) 1908for details], 'flags' denotes the octal O_xxx mask the file has been 1909created with [see open(2) for details] and 'mnt_id' represents mount ID of 1910the file system containing the opened file [see 3.5 /proc/<pid>/mountinfo 1911for details]. 1912 1913A typical output is:: 1914 1915 pos: 0 1916 flags: 0100002 1917 mnt_id: 19 1918 1919All locks associated with a file descriptor are shown in its fdinfo too:: 1920 1921 lock: 1: FLOCK ADVISORY WRITE 359 00:13:11691 0 EOF 1922 1923The files such as eventfd, fsnotify, signalfd, epoll among the regular pos/flags 1924pair provide additional information particular to the objects they represent. 1925 1926Eventfd files 1927~~~~~~~~~~~~~ 1928 1929:: 1930 1931 pos: 0 1932 flags: 04002 1933 mnt_id: 9 1934 eventfd-count: 5a 1935 1936where 'eventfd-count' is hex value of a counter. 1937 1938Signalfd files 1939~~~~~~~~~~~~~~ 1940 1941:: 1942 1943 pos: 0 1944 flags: 04002 1945 mnt_id: 9 1946 sigmask: 0000000000000200 1947 1948where 'sigmask' is hex value of the signal mask associated 1949with a file. 1950 1951Epoll files 1952~~~~~~~~~~~ 1953 1954:: 1955 1956 pos: 0 1957 flags: 02 1958 mnt_id: 9 1959 tfd: 5 events: 1d data: ffffffffffffffff pos:0 ino:61af sdev:7 1960 1961where 'tfd' is a target file descriptor number in decimal form, 1962'events' is events mask being watched and the 'data' is data 1963associated with a target [see epoll(7) for more details]. 1964 1965The 'pos' is current offset of the target file in decimal form 1966[see lseek(2)], 'ino' and 'sdev' are inode and device numbers 1967where target file resides, all in hex format. 1968 1969Fsnotify files 1970~~~~~~~~~~~~~~ 1971For inotify files the format is the following:: 1972 1973 pos: 0 1974 flags: 02000000 1975 inotify wd:3 ino:9e7e sdev:800013 mask:800afce ignored_mask:0 fhandle-bytes:8 fhandle-type:1 f_handle:7e9e0000640d1b6d 1976 1977where 'wd' is a watch descriptor in decimal form, ie a target file 1978descriptor number, 'ino' and 'sdev' are inode and device where the 1979target file resides and the 'mask' is the mask of events, all in hex 1980form [see inotify(7) for more details]. 1981 1982If the kernel was built with exportfs support, the path to the target 1983file is encoded as a file handle. The file handle is provided by three 1984fields 'fhandle-bytes', 'fhandle-type' and 'f_handle', all in hex 1985format. 1986 1987If the kernel is built without exportfs support the file handle won't be 1988printed out. 1989 1990If there is no inotify mark attached yet the 'inotify' line will be omitted. 1991 1992For fanotify files the format is:: 1993 1994 pos: 0 1995 flags: 02 1996 mnt_id: 9 1997 fanotify flags:10 event-flags:0 1998 fanotify mnt_id:12 mflags:40 mask:38 ignored_mask:40000003 1999 fanotify ino:4f969 sdev:800013 mflags:0 mask:3b ignored_mask:40000000 fhandle-bytes:8 fhandle-type:1 f_handle:69f90400c275b5b4 2000 2001where fanotify 'flags' and 'event-flags' are values used in fanotify_init 2002call, 'mnt_id' is the mount point identifier, 'mflags' is the value of 2003flags associated with mark which are tracked separately from events 2004mask. 'ino', 'sdev' are target inode and device, 'mask' is the events 2005mask and 'ignored_mask' is the mask of events which are to be ignored. 2006All in hex format. Incorporation of 'mflags', 'mask' and 'ignored_mask' 2007does provide information about flags and mask used in fanotify_mark 2008call [see fsnotify manpage for details]. 2009 2010While the first three lines are mandatory and always printed, the rest is 2011optional and may be omitted if no marks created yet. 2012 2013Timerfd files 2014~~~~~~~~~~~~~ 2015 2016:: 2017 2018 pos: 0 2019 flags: 02 2020 mnt_id: 9 2021 clockid: 0 2022 ticks: 0 2023 settime flags: 01 2024 it_value: (0, 49406829) 2025 it_interval: (1, 0) 2026 2027where 'clockid' is the clock type and 'ticks' is the number of the timer expirations 2028that have occurred [see timerfd_create(2) for details]. 'settime flags' are 2029flags in octal form been used to setup the timer [see timerfd_settime(2) for 2030details]. 'it_value' is remaining time until the timer exiration. 2031'it_interval' is the interval for the timer. Note the timer might be set up 2032with TIMER_ABSTIME option which will be shown in 'settime flags', but 'it_value' 2033still exhibits timer's remaining time. 2034 20353.9 /proc/<pid>/map_files - Information about memory mapped files 2036--------------------------------------------------------------------- 2037This directory contains symbolic links which represent memory mapped files 2038the process is maintaining. Example output:: 2039 2040 | lr-------- 1 root root 64 Jan 27 11:24 333c600000-333c620000 -> /usr/lib64/ld-2.18.so 2041 | lr-------- 1 root root 64 Jan 27 11:24 333c81f000-333c820000 -> /usr/lib64/ld-2.18.so 2042 | lr-------- 1 root root 64 Jan 27 11:24 333c820000-333c821000 -> /usr/lib64/ld-2.18.so 2043 | ... 2044 | lr-------- 1 root root 64 Jan 27 11:24 35d0421000-35d0422000 -> /usr/lib64/libselinux.so.1 2045 | lr-------- 1 root root 64 Jan 27 11:24 400000-41a000 -> /usr/bin/ls 2046 2047The name of a link represents the virtual memory bounds of a mapping, i.e. 2048vm_area_struct::vm_start-vm_area_struct::vm_end. 2049 2050The main purpose of the map_files is to retrieve a set of memory mapped 2051files in a fast way instead of parsing /proc/<pid>/maps or 2052/proc/<pid>/smaps, both of which contain many more records. At the same 2053time one can open(2) mappings from the listings of two processes and 2054comparing their inode numbers to figure out which anonymous memory areas 2055are actually shared. 2056 20573.10 /proc/<pid>/timerslack_ns - Task timerslack value 2058--------------------------------------------------------- 2059This file provides the value of the task's timerslack value in nanoseconds. 2060This value specifies a amount of time that normal timers may be deferred 2061in order to coalesce timers and avoid unnecessary wakeups. 2062 2063This allows a task's interactivity vs power consumption trade off to be 2064adjusted. 2065 2066Writing 0 to the file will set the tasks timerslack to the default value. 2067 2068Valid values are from 0 - ULLONG_MAX 2069 2070An application setting the value must have PTRACE_MODE_ATTACH_FSCREDS level 2071permissions on the task specified to change its timerslack_ns value. 2072 20733.11 /proc/<pid>/patch_state - Livepatch patch operation state 2074----------------------------------------------------------------- 2075When CONFIG_LIVEPATCH is enabled, this file displays the value of the 2076patch state for the task. 2077 2078A value of '-1' indicates that no patch is in transition. 2079 2080A value of '0' indicates that a patch is in transition and the task is 2081unpatched. If the patch is being enabled, then the task hasn't been 2082patched yet. If the patch is being disabled, then the task has already 2083been unpatched. 2084 2085A value of '1' indicates that a patch is in transition and the task is 2086patched. If the patch is being enabled, then the task has already been 2087patched. If the patch is being disabled, then the task hasn't been 2088unpatched yet. 2089 20903.12 /proc/<pid>/arch_status - task architecture specific status 2091------------------------------------------------------------------- 2092When CONFIG_PROC_PID_ARCH_STATUS is enabled, this file displays the 2093architecture specific status of the task. 2094 2095Example 2096~~~~~~~ 2097 2098:: 2099 2100 $ cat /proc/6753/arch_status 2101 AVX512_elapsed_ms: 8 2102 2103Description 2104~~~~~~~~~~~ 2105 2106x86 specific entries: 2107~~~~~~~~~~~~~~~~~~~~~ 2108 2109AVX512_elapsed_ms: 2110^^^^^^^^^^^^^^^^^^ 2111 2112 If AVX512 is supported on the machine, this entry shows the milliseconds 2113 elapsed since the last time AVX512 usage was recorded. The recording 2114 happens on a best effort basis when a task is scheduled out. This means 2115 that the value depends on two factors: 2116 2117 1) The time which the task spent on the CPU without being scheduled 2118 out. With CPU isolation and a single runnable task this can take 2119 several seconds. 2120 2121 2) The time since the task was scheduled out last. Depending on the 2122 reason for being scheduled out (time slice exhausted, syscall ...) 2123 this can be arbitrary long time. 2124 2125 As a consequence the value cannot be considered precise and authoritative 2126 information. The application which uses this information has to be aware 2127 of the overall scenario on the system in order to determine whether a 2128 task is a real AVX512 user or not. Precise information can be obtained 2129 with performance counters. 2130 2131 A special value of '-1' indicates that no AVX512 usage was recorded, thus 2132 the task is unlikely an AVX512 user, but depends on the workload and the 2133 scheduling scenario, it also could be a false negative mentioned above. 2134 2135Configuring procfs 2136------------------ 2137 21384.1 Mount options 2139--------------------- 2140 2141The following mount options are supported: 2142 2143 ========= ======================================================== 2144 hidepid= Set /proc/<pid>/ access mode. 2145 gid= Set the group authorized to learn processes information. 2146 ========= ======================================================== 2147 2148hidepid=0 means classic mode - everybody may access all /proc/<pid>/ directories 2149(default). 2150 2151hidepid=1 means users may not access any /proc/<pid>/ directories but their 2152own. Sensitive files like cmdline, sched*, status are now protected against 2153other users. This makes it impossible to learn whether any user runs 2154specific program (given the program doesn't reveal itself by its behaviour). 2155As an additional bonus, as /proc/<pid>/cmdline is unaccessible for other users, 2156poorly written programs passing sensitive information via program arguments are 2157now protected against local eavesdroppers. 2158 2159hidepid=2 means hidepid=1 plus all /proc/<pid>/ will be fully invisible to other 2160users. It doesn't mean that it hides a fact whether a process with a specific 2161pid value exists (it can be learned by other means, e.g. by "kill -0 $PID"), 2162but it hides process' uid and gid, which may be learned by stat()'ing 2163/proc/<pid>/ otherwise. It greatly complicates an intruder's task of gathering 2164information about running processes, whether some daemon runs with elevated 2165privileges, whether other user runs some sensitive program, whether other users 2166run any program at all, etc. 2167 2168gid= defines a group authorized to learn processes information otherwise 2169prohibited by hidepid=. If you use some daemon like identd which needs to learn 2170information about processes information, just add identd to this group. 2171