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 3.13 /proc/<pid>/fd - List of symlinks to open files 51 52 4 Configuring procfs 53 4.1 Mount options 54 55 5 Filesystem behavior 56 57Preface 58======= 59 600.1 Introduction/Credits 61------------------------ 62 63This documentation is part of a soon (or so we hope) to be released book on 64the SuSE Linux distribution. As there is no complete documentation for the 65/proc file system and we've used many freely available sources to write these 66chapters, it seems only fair to give the work back to the Linux community. 67This work is based on the 2.2.* kernel version and the upcoming 2.4.*. I'm 68afraid it's still far from complete, but we hope it will be useful. As far as 69we know, it is the first 'all-in-one' document about the /proc file system. It 70is focused on the Intel x86 hardware, so if you are looking for PPC, ARM, 71SPARC, AXP, etc., features, you probably won't find what you are looking for. 72It also only covers IPv4 networking, not IPv6 nor other protocols - sorry. But 73additions and patches are welcome and will be added to this document if you 74mail them to Bodo. 75 76We'd like to thank Alan Cox, Rik van Riel, and Alexey Kuznetsov and a lot of 77other people for help compiling this documentation. We'd also like to extend a 78special thank you to Andi Kleen for documentation, which we relied on heavily 79to create this document, as well as the additional information he provided. 80Thanks to everybody else who contributed source or docs to the Linux kernel 81and helped create a great piece of software... :) 82 83If you have any comments, corrections or additions, please don't hesitate to 84contact Bodo Bauer at bb@ricochet.net. We'll be happy to add them to this 85document. 86 87The latest version of this document is available online at 88https://www.kernel.org/doc/html/latest/filesystems/proc.html 89 90If the above direction does not works for you, you could try the kernel 91mailing list at linux-kernel@vger.kernel.org and/or try to reach me at 92comandante@zaralinux.com. 93 940.2 Legal Stuff 95--------------- 96 97We don't guarantee the correctness of this document, and if you come to us 98complaining about how you screwed up your system because of incorrect 99documentation, we won't feel responsible... 100 101Chapter 1: Collecting System Information 102======================================== 103 104In This Chapter 105--------------- 106* Investigating the properties of the pseudo file system /proc and its 107 ability to provide information on the running Linux system 108* Examining /proc's structure 109* Uncovering various information about the kernel and the processes running 110 on the system 111 112------------------------------------------------------------------------------ 113 114The proc file system acts as an interface to internal data structures in the 115kernel. It can be used to obtain information about the system and to change 116certain kernel parameters at runtime (sysctl). 117 118First, we'll take a look at the read-only parts of /proc. In Chapter 2, we 119show you how you can use /proc/sys to change settings. 120 1211.1 Process-Specific Subdirectories 122----------------------------------- 123 124The directory /proc contains (among other things) one subdirectory for each 125process running on the system, which is named after the process ID (PID). 126 127The link 'self' points to the process reading the file system. Each process 128subdirectory has the entries listed in Table 1-1. 129 130Note that an open file descriptor to /proc/<pid> or to any of its 131contained files or subdirectories does not prevent <pid> being reused 132for some other process in the event that <pid> exits. Operations on 133open /proc/<pid> file descriptors corresponding to dead processes 134never act on any new process that the kernel may, through chance, have 135also assigned the process ID <pid>. Instead, operations on these FDs 136usually fail with ESRCH. 137 138.. table:: Table 1-1: Process specific entries in /proc 139 140 ============= =============================================================== 141 File Content 142 ============= =============================================================== 143 clear_refs Clears page referenced bits shown in smaps output 144 cmdline Command line arguments 145 cpu Current and last cpu in which it was executed (2.4)(smp) 146 cwd Link to the current working directory 147 environ Values of environment variables 148 exe Link to the executable of this process 149 fd Directory, which contains all file descriptors 150 maps Memory maps to executables and library files (2.4) 151 mem Memory held by this process 152 root Link to the root directory of this process 153 stat Process status 154 statm Process memory status information 155 status Process status in human readable form 156 wchan Present with CONFIG_KALLSYMS=y: it shows the kernel function 157 symbol the task is blocked in - or "0" if not blocked. 158 pagemap Page table 159 stack Report full stack trace, enable via CONFIG_STACKTRACE 160 smaps An extension based on maps, showing the memory consumption of 161 each mapping and flags associated with it 162 smaps_rollup Accumulated smaps stats for all mappings of the process. This 163 can be derived from smaps, but is faster and more convenient 164 numa_maps An extension based on maps, showing the memory locality and 165 binding policy as well as mem usage (in pages) of each mapping. 166 ============= =============================================================== 167 168For example, to get the status information of a process, all you have to do is 169read the file /proc/PID/status:: 170 171 >cat /proc/self/status 172 Name: cat 173 State: R (running) 174 Tgid: 5452 175 Pid: 5452 176 PPid: 743 177 TracerPid: 0 (2.4) 178 Uid: 501 501 501 501 179 Gid: 100 100 100 100 180 FDSize: 256 181 Groups: 100 14 16 182 Kthread: 0 183 VmPeak: 5004 kB 184 VmSize: 5004 kB 185 VmLck: 0 kB 186 VmHWM: 476 kB 187 VmRSS: 476 kB 188 RssAnon: 352 kB 189 RssFile: 120 kB 190 RssShmem: 4 kB 191 VmData: 156 kB 192 VmStk: 88 kB 193 VmExe: 68 kB 194 VmLib: 1412 kB 195 VmPTE: 20 kb 196 VmSwap: 0 kB 197 HugetlbPages: 0 kB 198 CoreDumping: 0 199 THP_enabled: 1 200 Threads: 1 201 SigQ: 0/28578 202 SigPnd: 0000000000000000 203 ShdPnd: 0000000000000000 204 SigBlk: 0000000000000000 205 SigIgn: 0000000000000000 206 SigCgt: 0000000000000000 207 CapInh: 00000000fffffeff 208 CapPrm: 0000000000000000 209 CapEff: 0000000000000000 210 CapBnd: ffffffffffffffff 211 CapAmb: 0000000000000000 212 NoNewPrivs: 0 213 Seccomp: 0 214 Speculation_Store_Bypass: thread vulnerable 215 SpeculationIndirectBranch: conditional enabled 216 voluntary_ctxt_switches: 0 217 nonvoluntary_ctxt_switches: 1 218 219This shows you nearly the same information you would get if you viewed it with 220the ps command. In fact, ps uses the proc file system to obtain its 221information. But you get a more detailed view of the process by reading the 222file /proc/PID/status. It fields are described in table 1-2. 223 224The statm file contains more detailed information about the process 225memory usage. Its seven fields are explained in Table 1-3. The stat file 226contains detailed information about the process itself. Its fields are 227explained in Table 1-4. 228 229(for SMP CONFIG users) 230 231For making accounting scalable, RSS related information are handled in an 232asynchronous manner and the value may not be very precise. To see a precise 233snapshot of a moment, you can see /proc/<pid>/smaps file and scan page table. 234It's slow but very precise. 235 236.. table:: Table 1-2: Contents of the status fields (as of 4.19) 237 238 ========================== =================================================== 239 Field Content 240 ========================== =================================================== 241 Name filename of the executable 242 Umask file mode creation mask 243 State state (R is running, S is sleeping, D is sleeping 244 in an uninterruptible wait, Z is zombie, 245 T is traced or stopped) 246 Tgid thread group ID 247 Ngid NUMA group ID (0 if none) 248 Pid process id 249 PPid process id of the parent process 250 TracerPid PID of process tracing this process (0 if not, or 251 the tracer is outside of the current pid namespace) 252 Uid Real, effective, saved set, and file system UIDs 253 Gid Real, effective, saved set, and file system GIDs 254 FDSize number of file descriptor slots currently allocated 255 Groups supplementary group list 256 NStgid descendant namespace thread group ID hierarchy 257 NSpid descendant namespace process ID hierarchy 258 NSpgid descendant namespace process group ID hierarchy 259 NSsid descendant namespace session ID hierarchy 260 Kthread kernel thread flag, 1 is yes, 0 is no 261 VmPeak peak virtual memory size 262 VmSize total program size 263 VmLck locked memory size 264 VmPin pinned memory size 265 VmHWM peak resident set size ("high water mark") 266 VmRSS size of memory portions. It contains the three 267 following parts 268 (VmRSS = RssAnon + RssFile + RssShmem) 269 RssAnon size of resident anonymous memory 270 RssFile size of resident file mappings 271 RssShmem size of resident shmem memory (includes SysV shm, 272 mapping of tmpfs and shared anonymous mappings) 273 VmData size of private data segments 274 VmStk size of stack segments 275 VmExe size of text segment 276 VmLib size of shared library code 277 VmPTE size of page table entries 278 VmSwap amount of swap used by anonymous private data 279 (shmem swap usage is not included) 280 HugetlbPages size of hugetlb memory portions 281 CoreDumping process's memory is currently being dumped 282 (killing the process may lead to a corrupted core) 283 THP_enabled process is allowed to use THP (returns 0 when 284 PR_SET_THP_DISABLE is set on the process 285 Threads number of threads 286 SigQ number of signals queued/max. number for queue 287 SigPnd bitmap of pending signals for the thread 288 ShdPnd bitmap of shared pending signals for the process 289 SigBlk bitmap of blocked signals 290 SigIgn bitmap of ignored signals 291 SigCgt bitmap of caught signals 292 CapInh bitmap of inheritable capabilities 293 CapPrm bitmap of permitted capabilities 294 CapEff bitmap of effective capabilities 295 CapBnd bitmap of capabilities bounding set 296 CapAmb bitmap of ambient capabilities 297 NoNewPrivs no_new_privs, like prctl(PR_GET_NO_NEW_PRIV, ...) 298 Seccomp seccomp mode, like prctl(PR_GET_SECCOMP, ...) 299 Speculation_Store_Bypass speculative store bypass mitigation status 300 SpeculationIndirectBranch indirect branch speculation mode 301 Cpus_allowed mask of CPUs on which this process may run 302 Cpus_allowed_list Same as previous, but in "list format" 303 Mems_allowed mask of memory nodes allowed to this process 304 Mems_allowed_list Same as previous, but in "list format" 305 voluntary_ctxt_switches number of voluntary context switches 306 nonvoluntary_ctxt_switches number of non voluntary context switches 307 ========================== =================================================== 308 309 310.. table:: Table 1-3: Contents of the statm fields (as of 2.6.8-rc3) 311 312 ======== =============================== ============================== 313 Field Content 314 ======== =============================== ============================== 315 size total program size (pages) (same as VmSize in status) 316 resident size of memory portions (pages) (same as VmRSS in status) 317 shared number of pages that are shared (i.e. backed by a file, same 318 as RssFile+RssShmem in status) 319 trs number of pages that are 'code' (not including libs; broken, 320 includes data segment) 321 lrs number of pages of library (always 0 on 2.6) 322 drs number of pages of data/stack (including libs; broken, 323 includes library text) 324 dt number of dirty pages (always 0 on 2.6) 325 ======== =============================== ============================== 326 327 328.. table:: Table 1-4: Contents of the stat fields (as of 2.6.30-rc7) 329 330 ============= =============================================================== 331 Field Content 332 ============= =============================================================== 333 pid process id 334 tcomm filename of the executable 335 state state (R is running, S is sleeping, D is sleeping in an 336 uninterruptible wait, Z is zombie, T is traced or stopped) 337 ppid process id of the parent process 338 pgrp pgrp of the process 339 sid session id 340 tty_nr tty the process uses 341 tty_pgrp pgrp of the tty 342 flags task flags 343 min_flt number of minor faults 344 cmin_flt number of minor faults with child's 345 maj_flt number of major faults 346 cmaj_flt number of major faults with child's 347 utime user mode jiffies 348 stime kernel mode jiffies 349 cutime user mode jiffies with child's 350 cstime kernel mode jiffies with child's 351 priority priority level 352 nice nice level 353 num_threads number of threads 354 it_real_value (obsolete, always 0) 355 start_time time the process started after system boot 356 vsize virtual memory size 357 rss resident set memory size 358 rsslim current limit in bytes on the rss 359 start_code address above which program text can run 360 end_code address below which program text can run 361 start_stack address of the start of the main process stack 362 esp current value of ESP 363 eip current value of EIP 364 pending bitmap of pending signals 365 blocked bitmap of blocked signals 366 sigign bitmap of ignored signals 367 sigcatch bitmap of caught signals 368 0 (place holder, used to be the wchan address, 369 use /proc/PID/wchan instead) 370 0 (place holder) 371 0 (place holder) 372 exit_signal signal to send to parent thread on exit 373 task_cpu which CPU the task is scheduled on 374 rt_priority realtime priority 375 policy scheduling policy (man sched_setscheduler) 376 blkio_ticks time spent waiting for block IO 377 gtime guest time of the task in jiffies 378 cgtime guest time of the task children in jiffies 379 start_data address above which program data+bss is placed 380 end_data address below which program data+bss is placed 381 start_brk address above which program heap can be expanded with brk() 382 arg_start address above which program command line is placed 383 arg_end address below which program command line is placed 384 env_start address above which program environment is placed 385 env_end address below which program environment is placed 386 exit_code the thread's exit_code in the form reported by the waitpid 387 system call 388 ============= =============================================================== 389 390The /proc/PID/maps file contains the currently mapped memory regions and 391their access permissions. 392 393The format is:: 394 395 address perms offset dev inode pathname 396 397 08048000-08049000 r-xp 00000000 03:00 8312 /opt/test 398 08049000-0804a000 rw-p 00001000 03:00 8312 /opt/test 399 0804a000-0806b000 rw-p 00000000 00:00 0 [heap] 400 a7cb1000-a7cb2000 ---p 00000000 00:00 0 401 a7cb2000-a7eb2000 rw-p 00000000 00:00 0 402 a7eb2000-a7eb3000 ---p 00000000 00:00 0 403 a7eb3000-a7ed5000 rw-p 00000000 00:00 0 404 a7ed5000-a8008000 r-xp 00000000 03:00 4222 /lib/libc.so.6 405 a8008000-a800a000 r--p 00133000 03:00 4222 /lib/libc.so.6 406 a800a000-a800b000 rw-p 00135000 03:00 4222 /lib/libc.so.6 407 a800b000-a800e000 rw-p 00000000 00:00 0 408 a800e000-a8022000 r-xp 00000000 03:00 14462 /lib/libpthread.so.0 409 a8022000-a8023000 r--p 00013000 03:00 14462 /lib/libpthread.so.0 410 a8023000-a8024000 rw-p 00014000 03:00 14462 /lib/libpthread.so.0 411 a8024000-a8027000 rw-p 00000000 00:00 0 412 a8027000-a8043000 r-xp 00000000 03:00 8317 /lib/ld-linux.so.2 413 a8043000-a8044000 r--p 0001b000 03:00 8317 /lib/ld-linux.so.2 414 a8044000-a8045000 rw-p 0001c000 03:00 8317 /lib/ld-linux.so.2 415 aff35000-aff4a000 rw-p 00000000 00:00 0 [stack] 416 ffffe000-fffff000 r-xp 00000000 00:00 0 [vdso] 417 418where "address" is the address space in the process that it occupies, "perms" 419is a set of permissions:: 420 421 r = read 422 w = write 423 x = execute 424 s = shared 425 p = private (copy on write) 426 427"offset" is the offset into the mapping, "dev" is the device (major:minor), and 428"inode" is the inode on that device. 0 indicates that no inode is associated 429with the memory region, as the case would be with BSS (uninitialized data). 430The "pathname" shows the name associated file for this mapping. If the mapping 431is not associated with a file: 432 433 =================== =========================================== 434 [heap] the heap of the program 435 [stack] the stack of the main process 436 [vdso] the "virtual dynamic shared object", 437 the kernel system call handler 438 [anon:<name>] a private anonymous mapping that has been 439 named by userspace 440 [anon_shmem:<name>] an anonymous shared memory mapping that has 441 been named by userspace 442 =================== =========================================== 443 444 or if empty, the mapping is anonymous. 445 446The /proc/PID/smaps is an extension based on maps, showing the memory 447consumption for each of the process's mappings. For each mapping (aka Virtual 448Memory Area, or VMA) there is a series of lines such as the following:: 449 450 08048000-080bc000 r-xp 00000000 03:02 13130 /bin/bash 451 452 Size: 1084 kB 453 KernelPageSize: 4 kB 454 MMUPageSize: 4 kB 455 Rss: 892 kB 456 Pss: 374 kB 457 Pss_Dirty: 0 kB 458 Shared_Clean: 892 kB 459 Shared_Dirty: 0 kB 460 Private_Clean: 0 kB 461 Private_Dirty: 0 kB 462 Referenced: 892 kB 463 Anonymous: 0 kB 464 KSM: 0 kB 465 LazyFree: 0 kB 466 AnonHugePages: 0 kB 467 ShmemPmdMapped: 0 kB 468 Shared_Hugetlb: 0 kB 469 Private_Hugetlb: 0 kB 470 Swap: 0 kB 471 SwapPss: 0 kB 472 KernelPageSize: 4 kB 473 MMUPageSize: 4 kB 474 Locked: 0 kB 475 THPeligible: 0 476 VmFlags: rd ex mr mw me dw 477 478The first of these lines shows the same information as is displayed for the 479mapping in /proc/PID/maps. Following lines show the size of the mapping 480(size); the size of each page allocated when backing a VMA (KernelPageSize), 481which is usually the same as the size in the page table entries; the page size 482used by the MMU when backing a VMA (in most cases, the same as KernelPageSize); 483the amount of the mapping that is currently resident in RAM (RSS); the 484process' proportional share of this mapping (PSS); and the number of clean and 485dirty shared and private pages in the mapping. 486 487The "proportional set size" (PSS) of a process is the count of pages it has 488in memory, where each page is divided by the number of processes sharing it. 489So if a process has 1000 pages all to itself, and 1000 shared with one other 490process, its PSS will be 1500. "Pss_Dirty" is the portion of PSS which 491consists of dirty pages. ("Pss_Clean" is not included, but it can be 492calculated by subtracting "Pss_Dirty" from "Pss".) 493 494Note that even a page which is part of a MAP_SHARED mapping, but has only 495a single pte mapped, i.e. is currently used by only one process, is accounted 496as private and not as shared. 497 498"Referenced" indicates the amount of memory currently marked as referenced or 499accessed. 500 501"Anonymous" shows the amount of memory that does not belong to any file. Even 502a mapping associated with a file may contain anonymous pages: when MAP_PRIVATE 503and a page is modified, the file page is replaced by a private anonymous copy. 504 505"KSM" reports how many of the pages are KSM pages. Note that KSM-placed zeropages 506are not included, only actual KSM pages. 507 508"LazyFree" shows the amount of memory which is marked by madvise(MADV_FREE). 509The memory isn't freed immediately with madvise(). It's freed in memory 510pressure if the memory is clean. Please note that the printed value might 511be lower than the real value due to optimizations used in the current 512implementation. If this is not desirable please file a bug report. 513 514"AnonHugePages" shows the amount of memory backed by transparent hugepage. 515 516"ShmemPmdMapped" shows the amount of shared (shmem/tmpfs) memory backed by 517huge pages. 518 519"Shared_Hugetlb" and "Private_Hugetlb" show the amounts of memory backed by 520hugetlbfs page which is *not* counted in "RSS" or "PSS" field for historical 521reasons. And these are not included in {Shared,Private}_{Clean,Dirty} field. 522 523"Swap" shows how much would-be-anonymous memory is also used, but out on swap. 524 525For shmem mappings, "Swap" includes also the size of the mapped (and not 526replaced by copy-on-write) part of the underlying shmem object out on swap. 527"SwapPss" shows proportional swap share of this mapping. Unlike "Swap", this 528does not take into account swapped out page of underlying shmem objects. 529"Locked" indicates whether the mapping is locked in memory or not. 530 531"THPeligible" indicates whether the mapping is eligible for allocating THP 532pages as well as the THP is PMD mappable or not - 1 if true, 0 otherwise. 533It just shows the current status. 534 535"VmFlags" field deserves a separate description. This member represents the 536kernel flags associated with the particular virtual memory area in two letter 537encoded manner. The codes are the following: 538 539 == ======================================= 540 rd readable 541 wr writeable 542 ex executable 543 sh shared 544 mr may read 545 mw may write 546 me may execute 547 ms may share 548 gd stack segment growns down 549 pf pure PFN range 550 dw disabled write to the mapped file 551 lo pages are locked in memory 552 io memory mapped I/O area 553 sr sequential read advise provided 554 rr random read advise provided 555 dc do not copy area on fork 556 de do not expand area on remapping 557 ac area is accountable 558 nr swap space is not reserved for the area 559 ht area uses huge tlb pages 560 sf synchronous page fault 561 ar architecture specific flag 562 wf wipe on fork 563 dd do not include area into core dump 564 sd soft dirty flag 565 mm mixed map area 566 hg huge page advise flag 567 nh no huge page advise flag 568 mg mergeable advise flag 569 bt arm64 BTI guarded page 570 mt arm64 MTE allocation tags are enabled 571 um userfaultfd missing tracking 572 uw userfaultfd wr-protect tracking 573 ss shadow stack page 574 == ======================================= 575 576Note that there is no guarantee that every flag and associated mnemonic will 577be present in all further kernel releases. Things get changed, the flags may 578be vanished or the reverse -- new added. Interpretation of their meaning 579might change in future as well. So each consumer of these flags has to 580follow each specific kernel version for the exact semantic. 581 582This file is only present if the CONFIG_MMU kernel configuration option is 583enabled. 584 585Note: reading /proc/PID/maps or /proc/PID/smaps is inherently racy (consistent 586output can be achieved only in the single read call). 587 588This typically manifests when doing partial reads of these files while the 589memory map is being modified. Despite the races, we do provide the following 590guarantees: 591 5921) The mapped addresses never go backwards, which implies no two 593 regions will ever overlap. 5942) If there is something at a given vaddr during the entirety of the 595 life of the smaps/maps walk, there will be some output for it. 596 597The /proc/PID/smaps_rollup file includes the same fields as /proc/PID/smaps, 598but their values are the sums of the corresponding values for all mappings of 599the process. Additionally, it contains these fields: 600 601- Pss_Anon 602- Pss_File 603- Pss_Shmem 604 605They represent the proportional shares of anonymous, file, and shmem pages, as 606described for smaps above. These fields are omitted in smaps since each 607mapping identifies the type (anon, file, or shmem) of all pages it contains. 608Thus all information in smaps_rollup can be derived from smaps, but at a 609significantly higher cost. 610 611The /proc/PID/clear_refs is used to reset the PG_Referenced and ACCESSED/YOUNG 612bits on both physical and virtual pages associated with a process, and the 613soft-dirty bit on pte (see Documentation/admin-guide/mm/soft-dirty.rst 614for details). 615To clear the bits for all the pages associated with the process:: 616 617 > echo 1 > /proc/PID/clear_refs 618 619To clear the bits for the anonymous pages associated with the process:: 620 621 > echo 2 > /proc/PID/clear_refs 622 623To clear the bits for the file mapped pages associated with the process:: 624 625 > echo 3 > /proc/PID/clear_refs 626 627To clear the soft-dirty bit:: 628 629 > echo 4 > /proc/PID/clear_refs 630 631To reset the peak resident set size ("high water mark") to the process's 632current value:: 633 634 > echo 5 > /proc/PID/clear_refs 635 636Any other value written to /proc/PID/clear_refs will have no effect. 637 638The /proc/pid/pagemap gives the PFN, which can be used to find the pageflags 639using /proc/kpageflags and number of times a page is mapped using 640/proc/kpagecount. For detailed explanation, see 641Documentation/admin-guide/mm/pagemap.rst. 642 643The /proc/pid/numa_maps is an extension based on maps, showing the memory 644locality and binding policy, as well as the memory usage (in pages) of 645each mapping. The output follows a general format where mapping details get 646summarized separated by blank spaces, one mapping per each file line:: 647 648 address policy mapping details 649 650 00400000 default file=/usr/local/bin/app mapped=1 active=0 N3=1 kernelpagesize_kB=4 651 00600000 default file=/usr/local/bin/app anon=1 dirty=1 N3=1 kernelpagesize_kB=4 652 3206000000 default file=/lib64/ld-2.12.so mapped=26 mapmax=6 N0=24 N3=2 kernelpagesize_kB=4 653 320621f000 default file=/lib64/ld-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4 654 3206220000 default file=/lib64/ld-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4 655 3206221000 default anon=1 dirty=1 N3=1 kernelpagesize_kB=4 656 3206800000 default file=/lib64/libc-2.12.so mapped=59 mapmax=21 active=55 N0=41 N3=18 kernelpagesize_kB=4 657 320698b000 default file=/lib64/libc-2.12.so 658 3206b8a000 default file=/lib64/libc-2.12.so anon=2 dirty=2 N3=2 kernelpagesize_kB=4 659 3206b8e000 default file=/lib64/libc-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4 660 3206b8f000 default anon=3 dirty=3 active=1 N3=3 kernelpagesize_kB=4 661 7f4dc10a2000 default anon=3 dirty=3 N3=3 kernelpagesize_kB=4 662 7f4dc10b4000 default anon=2 dirty=2 active=1 N3=2 kernelpagesize_kB=4 663 7f4dc1200000 default file=/anon_hugepage\040(deleted) huge anon=1 dirty=1 N3=1 kernelpagesize_kB=2048 664 7fff335f0000 default stack anon=3 dirty=3 N3=3 kernelpagesize_kB=4 665 7fff3369d000 default mapped=1 mapmax=35 active=0 N3=1 kernelpagesize_kB=4 666 667Where: 668 669"address" is the starting address for the mapping; 670 671"policy" reports the NUMA memory policy set for the mapping (see Documentation/admin-guide/mm/numa_memory_policy.rst); 672 673"mapping details" summarizes mapping data such as mapping type, page usage counters, 674node locality page counters (N0 == node0, N1 == node1, ...) and the kernel page 675size, in KB, that is backing the mapping up. 676 6771.2 Kernel data 678--------------- 679 680Similar to the process entries, the kernel data files give information about 681the running kernel. The files used to obtain this information are contained in 682/proc and are listed in Table 1-5. Not all of these will be present in your 683system. It depends on the kernel configuration and the loaded modules, which 684files are there, and which are missing. 685 686.. table:: Table 1-5: Kernel info in /proc 687 688 ============ =============================================================== 689 File Content 690 ============ =============================================================== 691 apm Advanced power management info 692 buddyinfo Kernel memory allocator information (see text) (2.5) 693 bus Directory containing bus specific information 694 cmdline Kernel command line 695 cpuinfo Info about the CPU 696 devices Available devices (block and character) 697 dma Used DMS channels 698 filesystems Supported filesystems 699 driver Various drivers grouped here, currently rtc (2.4) 700 execdomains Execdomains, related to security (2.4) 701 fb Frame Buffer devices (2.4) 702 fs File system parameters, currently nfs/exports (2.4) 703 ide Directory containing info about the IDE subsystem 704 interrupts Interrupt usage 705 iomem Memory map (2.4) 706 ioports I/O port usage 707 irq Masks for irq to cpu affinity (2.4)(smp?) 708 isapnp ISA PnP (Plug&Play) Info (2.4) 709 kcore Kernel core image (can be ELF or A.OUT(deprecated in 2.4)) 710 kmsg Kernel messages 711 ksyms Kernel symbol table 712 loadavg Load average of last 1, 5 & 15 minutes; 713 number of processes currently runnable (running or on ready queue); 714 total number of processes in system; 715 last pid created. 716 All fields are separated by one space except "number of 717 processes currently runnable" and "total number of processes 718 in system", which are separated by a slash ('/'). Example: 719 0.61 0.61 0.55 3/828 22084 720 locks Kernel locks 721 meminfo Memory info 722 misc Miscellaneous 723 modules List of loaded modules 724 mounts Mounted filesystems 725 net Networking info (see text) 726 pagetypeinfo Additional page allocator information (see text) (2.5) 727 partitions Table of partitions known to the system 728 pci Deprecated info of PCI bus (new way -> /proc/bus/pci/, 729 decoupled by lspci (2.4) 730 rtc Real time clock 731 scsi SCSI info (see text) 732 slabinfo Slab pool info 733 softirqs softirq usage 734 stat Overall statistics 735 swaps Swap space utilization 736 sys See chapter 2 737 sysvipc Info of SysVIPC Resources (msg, sem, shm) (2.4) 738 tty Info of tty drivers 739 uptime Wall clock since boot, combined idle time of all cpus 740 version Kernel version 741 video bttv info of video resources (2.4) 742 vmallocinfo Show vmalloced areas 743 ============ =============================================================== 744 745You can, for example, check which interrupts are currently in use and what 746they are used for by looking in the file /proc/interrupts:: 747 748 > cat /proc/interrupts 749 CPU0 750 0: 8728810 XT-PIC timer 751 1: 895 XT-PIC keyboard 752 2: 0 XT-PIC cascade 753 3: 531695 XT-PIC aha152x 754 4: 2014133 XT-PIC serial 755 5: 44401 XT-PIC pcnet_cs 756 8: 2 XT-PIC rtc 757 11: 8 XT-PIC i82365 758 12: 182918 XT-PIC PS/2 Mouse 759 13: 1 XT-PIC fpu 760 14: 1232265 XT-PIC ide0 761 15: 7 XT-PIC ide1 762 NMI: 0 763 764In 2.4.* a couple of lines where added to this file LOC & ERR (this time is the 765output of a SMP machine):: 766 767 > cat /proc/interrupts 768 769 CPU0 CPU1 770 0: 1243498 1214548 IO-APIC-edge timer 771 1: 8949 8958 IO-APIC-edge keyboard 772 2: 0 0 XT-PIC cascade 773 5: 11286 10161 IO-APIC-edge soundblaster 774 8: 1 0 IO-APIC-edge rtc 775 9: 27422 27407 IO-APIC-edge 3c503 776 12: 113645 113873 IO-APIC-edge PS/2 Mouse 777 13: 0 0 XT-PIC fpu 778 14: 22491 24012 IO-APIC-edge ide0 779 15: 2183 2415 IO-APIC-edge ide1 780 17: 30564 30414 IO-APIC-level eth0 781 18: 177 164 IO-APIC-level bttv 782 NMI: 2457961 2457959 783 LOC: 2457882 2457881 784 ERR: 2155 785 786NMI is incremented in this case because every timer interrupt generates a NMI 787(Non Maskable Interrupt) which is used by the NMI Watchdog to detect lockups. 788 789LOC is the local interrupt counter of the internal APIC of every CPU. 790 791ERR is incremented in the case of errors in the IO-APIC bus (the bus that 792connects the CPUs in a SMP system. This means that an error has been detected, 793the IO-APIC automatically retry the transmission, so it should not be a big 794problem, but you should read the SMP-FAQ. 795 796In 2.6.2* /proc/interrupts was expanded again. This time the goal was for 797/proc/interrupts to display every IRQ vector in use by the system, not 798just those considered 'most important'. The new vectors are: 799 800THR 801 interrupt raised when a machine check threshold counter 802 (typically counting ECC corrected errors of memory or cache) exceeds 803 a configurable threshold. Only available on some systems. 804 805TRM 806 a thermal event interrupt occurs when a temperature threshold 807 has been exceeded for the CPU. This interrupt may also be generated 808 when the temperature drops back to normal. 809 810SPU 811 a spurious interrupt is some interrupt that was raised then lowered 812 by some IO device before it could be fully processed by the APIC. Hence 813 the APIC sees the interrupt but does not know what device it came from. 814 For this case the APIC will generate the interrupt with a IRQ vector 815 of 0xff. This might also be generated by chipset bugs. 816 817RES, CAL, TLB 818 rescheduling, call and TLB flush interrupts are 819 sent from one CPU to another per the needs of the OS. Typically, 820 their statistics are used by kernel developers and interested users to 821 determine the occurrence of interrupts of the given type. 822 823The above IRQ vectors are displayed only when relevant. For example, 824the threshold vector does not exist on x86_64 platforms. Others are 825suppressed when the system is a uniprocessor. As of this writing, only 826i386 and x86_64 platforms support the new IRQ vector displays. 827 828Of some interest is the introduction of the /proc/irq directory to 2.4. 829It could be used to set IRQ to CPU affinity. This means that you can "hook" an 830IRQ to only one CPU, or to exclude a CPU of handling IRQs. The contents of the 831irq subdir is one subdir for each IRQ, and two files; default_smp_affinity and 832prof_cpu_mask. 833 834For example:: 835 836 > ls /proc/irq/ 837 0 10 12 14 16 18 2 4 6 8 prof_cpu_mask 838 1 11 13 15 17 19 3 5 7 9 default_smp_affinity 839 > ls /proc/irq/0/ 840 smp_affinity 841 842smp_affinity is a bitmask, in which you can specify which CPUs can handle the 843IRQ. You can set it by doing:: 844 845 > echo 1 > /proc/irq/10/smp_affinity 846 847This means that only the first CPU will handle the IRQ, but you can also echo 8485 which means that only the first and third CPU can handle the IRQ. 849 850The contents of each smp_affinity file is the same by default:: 851 852 > cat /proc/irq/0/smp_affinity 853 ffffffff 854 855There is an alternate interface, smp_affinity_list which allows specifying 856a CPU range instead of a bitmask:: 857 858 > cat /proc/irq/0/smp_affinity_list 859 1024-1031 860 861The default_smp_affinity mask applies to all non-active IRQs, which are the 862IRQs which have not yet been allocated/activated, and hence which lack a 863/proc/irq/[0-9]* directory. 864 865The node file on an SMP system shows the node to which the device using the IRQ 866reports itself as being attached. This hardware locality information does not 867include information about any possible driver locality preference. 868 869prof_cpu_mask specifies which CPUs are to be profiled by the system wide 870profiler. Default value is ffffffff (all CPUs if there are only 32 of them). 871 872The way IRQs are routed is handled by the IO-APIC, and it's Round Robin 873between all the CPUs which are allowed to handle it. As usual the kernel has 874more info than you and does a better job than you, so the defaults are the 875best choice for almost everyone. [Note this applies only to those IO-APIC's 876that support "Round Robin" interrupt distribution.] 877 878There are three more important subdirectories in /proc: net, scsi, and sys. 879The general rule is that the contents, or even the existence of these 880directories, depend on your kernel configuration. If SCSI is not enabled, the 881directory scsi may not exist. The same is true with the net, which is there 882only when networking support is present in the running kernel. 883 884The slabinfo file gives information about memory usage at the slab level. 885Linux uses slab pools for memory management above page level in version 2.2. 886Commonly used objects have their own slab pool (such as network buffers, 887directory cache, and so on). 888 889:: 890 891 > cat /proc/buddyinfo 892 893 Node 0, zone DMA 0 4 5 4 4 3 ... 894 Node 0, zone Normal 1 0 0 1 101 8 ... 895 Node 0, zone HighMem 2 0 0 1 1 0 ... 896 897External fragmentation is a problem under some workloads, and buddyinfo is a 898useful tool for helping diagnose these problems. Buddyinfo will give you a 899clue as to how big an area you can safely allocate, or why a previous 900allocation failed. 901 902Each column represents the number of pages of a certain order which are 903available. In this case, there are 0 chunks of 2^0*PAGE_SIZE available in 904ZONE_DMA, 4 chunks of 2^1*PAGE_SIZE in ZONE_DMA, 101 chunks of 2^4*PAGE_SIZE 905available in ZONE_NORMAL, etc... 906 907More information relevant to external fragmentation can be found in 908pagetypeinfo:: 909 910 > cat /proc/pagetypeinfo 911 Page block order: 9 912 Pages per block: 512 913 914 Free pages count per migrate type at order 0 1 2 3 4 5 6 7 8 9 10 915 Node 0, zone DMA, type Unmovable 0 0 0 1 1 1 1 1 1 1 0 916 Node 0, zone DMA, type Reclaimable 0 0 0 0 0 0 0 0 0 0 0 917 Node 0, zone DMA, type Movable 1 1 2 1 2 1 1 0 1 0 2 918 Node 0, zone DMA, type Reserve 0 0 0 0 0 0 0 0 0 1 0 919 Node 0, zone DMA, type Isolate 0 0 0 0 0 0 0 0 0 0 0 920 Node 0, zone DMA32, type Unmovable 103 54 77 1 1 1 11 8 7 1 9 921 Node 0, zone DMA32, type Reclaimable 0 0 2 1 0 0 0 0 1 0 0 922 Node 0, zone DMA32, type Movable 169 152 113 91 77 54 39 13 6 1 452 923 Node 0, zone DMA32, type Reserve 1 2 2 2 2 0 1 1 1 1 0 924 Node 0, zone DMA32, type Isolate 0 0 0 0 0 0 0 0 0 0 0 925 926 Number of blocks type Unmovable Reclaimable Movable Reserve Isolate 927 Node 0, zone DMA 2 0 5 1 0 928 Node 0, zone DMA32 41 6 967 2 0 929 930Fragmentation avoidance in the kernel works by grouping pages of different 931migrate types into the same contiguous regions of memory called page blocks. 932A page block is typically the size of the default hugepage size, e.g. 2MB on 933X86-64. By keeping pages grouped based on their ability to move, the kernel 934can reclaim pages within a page block to satisfy a high-order allocation. 935 936The pagetypinfo begins with information on the size of a page block. It 937then gives the same type of information as buddyinfo except broken down 938by migrate-type and finishes with details on how many page blocks of each 939type exist. 940 941If min_free_kbytes has been tuned correctly (recommendations made by hugeadm 942from libhugetlbfs https://github.com/libhugetlbfs/libhugetlbfs/), one can 943make an estimate of the likely number of huge pages that can be allocated 944at a given point in time. All the "Movable" blocks should be allocatable 945unless memory has been mlock()'d. Some of the Reclaimable blocks should 946also be allocatable although a lot of filesystem metadata may have to be 947reclaimed to achieve this. 948 949 950meminfo 951~~~~~~~ 952 953Provides information about distribution and utilization of memory. This 954varies by architecture and compile options. Some of the counters reported 955here overlap. The memory reported by the non overlapping counters may not 956add up to the overall memory usage and the difference for some workloads 957can be substantial. In many cases there are other means to find out 958additional memory using subsystem specific interfaces, for instance 959/proc/net/sockstat for TCP memory allocations. 960 961Example output. You may not have all of these fields. 962 963:: 964 965 > cat /proc/meminfo 966 967 MemTotal: 32858820 kB 968 MemFree: 21001236 kB 969 MemAvailable: 27214312 kB 970 Buffers: 581092 kB 971 Cached: 5587612 kB 972 SwapCached: 0 kB 973 Active: 3237152 kB 974 Inactive: 7586256 kB 975 Active(anon): 94064 kB 976 Inactive(anon): 4570616 kB 977 Active(file): 3143088 kB 978 Inactive(file): 3015640 kB 979 Unevictable: 0 kB 980 Mlocked: 0 kB 981 SwapTotal: 0 kB 982 SwapFree: 0 kB 983 Zswap: 1904 kB 984 Zswapped: 7792 kB 985 Dirty: 12 kB 986 Writeback: 0 kB 987 AnonPages: 4654780 kB 988 Mapped: 266244 kB 989 Shmem: 9976 kB 990 KReclaimable: 517708 kB 991 Slab: 660044 kB 992 SReclaimable: 517708 kB 993 SUnreclaim: 142336 kB 994 KernelStack: 11168 kB 995 PageTables: 20540 kB 996 SecPageTables: 0 kB 997 NFS_Unstable: 0 kB 998 Bounce: 0 kB 999 WritebackTmp: 0 kB 1000 CommitLimit: 16429408 kB 1001 Committed_AS: 7715148 kB 1002 VmallocTotal: 34359738367 kB 1003 VmallocUsed: 40444 kB 1004 VmallocChunk: 0 kB 1005 Percpu: 29312 kB 1006 EarlyMemtestBad: 0 kB 1007 HardwareCorrupted: 0 kB 1008 AnonHugePages: 4149248 kB 1009 ShmemHugePages: 0 kB 1010 ShmemPmdMapped: 0 kB 1011 FileHugePages: 0 kB 1012 FilePmdMapped: 0 kB 1013 CmaTotal: 0 kB 1014 CmaFree: 0 kB 1015 HugePages_Total: 0 1016 HugePages_Free: 0 1017 HugePages_Rsvd: 0 1018 HugePages_Surp: 0 1019 Hugepagesize: 2048 kB 1020 Hugetlb: 0 kB 1021 DirectMap4k: 401152 kB 1022 DirectMap2M: 10008576 kB 1023 DirectMap1G: 24117248 kB 1024 1025MemTotal 1026 Total usable RAM (i.e. physical RAM minus a few reserved 1027 bits and the kernel binary code) 1028MemFree 1029 Total free RAM. On highmem systems, the sum of LowFree+HighFree 1030MemAvailable 1031 An estimate of how much memory is available for starting new 1032 applications, without swapping. Calculated from MemFree, 1033 SReclaimable, the size of the file LRU lists, and the low 1034 watermarks in each zone. 1035 The estimate takes into account that the system needs some 1036 page cache to function well, and that not all reclaimable 1037 slab will be reclaimable, due to items being in use. The 1038 impact of those factors will vary from system to system. 1039Buffers 1040 Relatively temporary storage for raw disk blocks 1041 shouldn't get tremendously large (20MB or so) 1042Cached 1043 In-memory cache for files read from the disk (the 1044 pagecache) as well as tmpfs & shmem. 1045 Doesn't include SwapCached. 1046SwapCached 1047 Memory that once was swapped out, is swapped back in but 1048 still also is in the swapfile (if memory is needed it 1049 doesn't need to be swapped out AGAIN because it is already 1050 in the swapfile. This saves I/O) 1051Active 1052 Memory that has been used more recently and usually not 1053 reclaimed unless absolutely necessary. 1054Inactive 1055 Memory which has been less recently used. It is more 1056 eligible to be reclaimed for other purposes 1057Unevictable 1058 Memory allocated for userspace which cannot be reclaimed, such 1059 as mlocked pages, ramfs backing pages, secret memfd pages etc. 1060Mlocked 1061 Memory locked with mlock(). 1062HighTotal, HighFree 1063 Highmem is all memory above ~860MB of physical memory. 1064 Highmem areas are for use by userspace programs, or 1065 for the pagecache. The kernel must use tricks to access 1066 this memory, making it slower to access than lowmem. 1067LowTotal, LowFree 1068 Lowmem is memory which can be used for everything that 1069 highmem can be used for, but it is also available for the 1070 kernel's use for its own data structures. Among many 1071 other things, it is where everything from the Slab is 1072 allocated. Bad things happen when you're out of lowmem. 1073SwapTotal 1074 total amount of swap space available 1075SwapFree 1076 Memory which has been evicted from RAM, and is temporarily 1077 on the disk 1078Zswap 1079 Memory consumed by the zswap backend (compressed size) 1080Zswapped 1081 Amount of anonymous memory stored in zswap (original size) 1082Dirty 1083 Memory which is waiting to get written back to the disk 1084Writeback 1085 Memory which is actively being written back to the disk 1086AnonPages 1087 Non-file backed pages mapped into userspace page tables 1088Mapped 1089 files which have been mmapped, such as libraries 1090Shmem 1091 Total memory used by shared memory (shmem) and tmpfs 1092KReclaimable 1093 Kernel allocations that the kernel will attempt to reclaim 1094 under memory pressure. Includes SReclaimable (below), and other 1095 direct allocations with a shrinker. 1096Slab 1097 in-kernel data structures cache 1098SReclaimable 1099 Part of Slab, that might be reclaimed, such as caches 1100SUnreclaim 1101 Part of Slab, that cannot be reclaimed on memory pressure 1102KernelStack 1103 Memory consumed by the kernel stacks of all tasks 1104PageTables 1105 Memory consumed by userspace page tables 1106SecPageTables 1107 Memory consumed by secondary page tables, this currently 1108 currently includes KVM mmu allocations on x86 and arm64. 1109NFS_Unstable 1110 Always zero. Previous counted pages which had been written to 1111 the server, but has not been committed to stable storage. 1112Bounce 1113 Memory used for block device "bounce buffers" 1114WritebackTmp 1115 Memory used by FUSE for temporary writeback buffers 1116CommitLimit 1117 Based on the overcommit ratio ('vm.overcommit_ratio'), 1118 this is the total amount of memory currently available to 1119 be allocated on the system. This limit is only adhered to 1120 if strict overcommit accounting is enabled (mode 2 in 1121 'vm.overcommit_memory'). 1122 1123 The CommitLimit is calculated with the following formula:: 1124 1125 CommitLimit = ([total RAM pages] - [total huge TLB pages]) * 1126 overcommit_ratio / 100 + [total swap pages] 1127 1128 For example, on a system with 1G of physical RAM and 7G 1129 of swap with a `vm.overcommit_ratio` of 30 it would 1130 yield a CommitLimit of 7.3G. 1131 1132 For more details, see the memory overcommit documentation 1133 in mm/overcommit-accounting. 1134Committed_AS 1135 The amount of memory presently allocated on the system. 1136 The committed memory is a sum of all of the memory which 1137 has been allocated by processes, even if it has not been 1138 "used" by them as of yet. A process which malloc()'s 1G 1139 of memory, but only touches 300M of it will show up as 1140 using 1G. This 1G is memory which has been "committed" to 1141 by the VM and can be used at any time by the allocating 1142 application. With strict overcommit enabled on the system 1143 (mode 2 in 'vm.overcommit_memory'), allocations which would 1144 exceed the CommitLimit (detailed above) will not be permitted. 1145 This is useful if one needs to guarantee that processes will 1146 not fail due to lack of memory once that memory has been 1147 successfully allocated. 1148VmallocTotal 1149 total size of vmalloc virtual address space 1150VmallocUsed 1151 amount of vmalloc area which is used 1152VmallocChunk 1153 largest contiguous block of vmalloc area which is free 1154Percpu 1155 Memory allocated to the percpu allocator used to back percpu 1156 allocations. This stat excludes the cost of metadata. 1157EarlyMemtestBad 1158 The amount of RAM/memory in kB, that was identified as corrupted 1159 by early memtest. If memtest was not run, this field will not 1160 be displayed at all. Size is never rounded down to 0 kB. 1161 That means if 0 kB is reported, you can safely assume 1162 there was at least one pass of memtest and none of the passes 1163 found a single faulty byte of RAM. 1164HardwareCorrupted 1165 The amount of RAM/memory in KB, the kernel identifies as 1166 corrupted. 1167AnonHugePages 1168 Non-file backed huge pages mapped into userspace page tables 1169ShmemHugePages 1170 Memory used by shared memory (shmem) and tmpfs allocated 1171 with huge pages 1172ShmemPmdMapped 1173 Shared memory mapped into userspace with huge pages 1174FileHugePages 1175 Memory used for filesystem data (page cache) allocated 1176 with huge pages 1177FilePmdMapped 1178 Page cache mapped into userspace with huge pages 1179CmaTotal 1180 Memory reserved for the Contiguous Memory Allocator (CMA) 1181CmaFree 1182 Free remaining memory in the CMA reserves 1183HugePages_Total, HugePages_Free, HugePages_Rsvd, HugePages_Surp, Hugepagesize, Hugetlb 1184 See Documentation/admin-guide/mm/hugetlbpage.rst. 1185DirectMap4k, DirectMap2M, DirectMap1G 1186 Breakdown of page table sizes used in the kernel's 1187 identity mapping of RAM 1188 1189vmallocinfo 1190~~~~~~~~~~~ 1191 1192Provides information about vmalloced/vmaped areas. One line per area, 1193containing the virtual address range of the area, size in bytes, 1194caller information of the creator, and optional information depending 1195on the kind of area: 1196 1197 ========== =================================================== 1198 pages=nr number of pages 1199 phys=addr if a physical address was specified 1200 ioremap I/O mapping (ioremap() and friends) 1201 vmalloc vmalloc() area 1202 vmap vmap()ed pages 1203 user VM_USERMAP area 1204 vpages buffer for pages pointers was vmalloced (huge area) 1205 N<node>=nr (Only on NUMA kernels) 1206 Number of pages allocated on memory node <node> 1207 ========== =================================================== 1208 1209:: 1210 1211 > cat /proc/vmallocinfo 1212 0xffffc20000000000-0xffffc20000201000 2101248 alloc_large_system_hash+0x204 ... 1213 /0x2c0 pages=512 vmalloc N0=128 N1=128 N2=128 N3=128 1214 0xffffc20000201000-0xffffc20000302000 1052672 alloc_large_system_hash+0x204 ... 1215 /0x2c0 pages=256 vmalloc N0=64 N1=64 N2=64 N3=64 1216 0xffffc20000302000-0xffffc20000304000 8192 acpi_tb_verify_table+0x21/0x4f... 1217 phys=7fee8000 ioremap 1218 0xffffc20000304000-0xffffc20000307000 12288 acpi_tb_verify_table+0x21/0x4f... 1219 phys=7fee7000 ioremap 1220 0xffffc2000031d000-0xffffc2000031f000 8192 init_vdso_vars+0x112/0x210 1221 0xffffc2000031f000-0xffffc2000032b000 49152 cramfs_uncompress_init+0x2e ... 1222 /0x80 pages=11 vmalloc N0=3 N1=3 N2=2 N3=3 1223 0xffffc2000033a000-0xffffc2000033d000 12288 sys_swapon+0x640/0xac0 ... 1224 pages=2 vmalloc N1=2 1225 0xffffc20000347000-0xffffc2000034c000 20480 xt_alloc_table_info+0xfe ... 1226 /0x130 [x_tables] pages=4 vmalloc N0=4 1227 0xffffffffa0000000-0xffffffffa000f000 61440 sys_init_module+0xc27/0x1d00 ... 1228 pages=14 vmalloc N2=14 1229 0xffffffffa000f000-0xffffffffa0014000 20480 sys_init_module+0xc27/0x1d00 ... 1230 pages=4 vmalloc N1=4 1231 0xffffffffa0014000-0xffffffffa0017000 12288 sys_init_module+0xc27/0x1d00 ... 1232 pages=2 vmalloc N1=2 1233 0xffffffffa0017000-0xffffffffa0022000 45056 sys_init_module+0xc27/0x1d00 ... 1234 pages=10 vmalloc N0=10 1235 1236 1237softirqs 1238~~~~~~~~ 1239 1240Provides counts of softirq handlers serviced since boot time, for each CPU. 1241 1242:: 1243 1244 > cat /proc/softirqs 1245 CPU0 CPU1 CPU2 CPU3 1246 HI: 0 0 0 0 1247 TIMER: 27166 27120 27097 27034 1248 NET_TX: 0 0 0 17 1249 NET_RX: 42 0 0 39 1250 BLOCK: 0 0 107 1121 1251 TASKLET: 0 0 0 290 1252 SCHED: 27035 26983 26971 26746 1253 HRTIMER: 0 0 0 0 1254 RCU: 1678 1769 2178 2250 1255 12561.3 Networking info in /proc/net 1257-------------------------------- 1258 1259The subdirectory /proc/net follows the usual pattern. Table 1-8 shows the 1260additional values you get for IP version 6 if you configure the kernel to 1261support this. Table 1-9 lists the files and their meaning. 1262 1263 1264.. table:: Table 1-8: IPv6 info in /proc/net 1265 1266 ========== ===================================================== 1267 File Content 1268 ========== ===================================================== 1269 udp6 UDP sockets (IPv6) 1270 tcp6 TCP sockets (IPv6) 1271 raw6 Raw device statistics (IPv6) 1272 igmp6 IP multicast addresses, which this host joined (IPv6) 1273 if_inet6 List of IPv6 interface addresses 1274 ipv6_route Kernel routing table for IPv6 1275 rt6_stats Global IPv6 routing tables statistics 1276 sockstat6 Socket statistics (IPv6) 1277 snmp6 Snmp data (IPv6) 1278 ========== ===================================================== 1279 1280.. table:: Table 1-9: Network info in /proc/net 1281 1282 ============= ================================================================ 1283 File Content 1284 ============= ================================================================ 1285 arp Kernel ARP table 1286 dev network devices with statistics 1287 dev_mcast the Layer2 multicast groups a device is listening too 1288 (interface index, label, number of references, number of bound 1289 addresses). 1290 dev_stat network device status 1291 ip_fwchains Firewall chain linkage 1292 ip_fwnames Firewall chain names 1293 ip_masq Directory containing the masquerading tables 1294 ip_masquerade Major masquerading table 1295 netstat Network statistics 1296 raw raw device statistics 1297 route Kernel routing table 1298 rpc Directory containing rpc info 1299 rt_cache Routing cache 1300 snmp SNMP data 1301 sockstat Socket statistics 1302 softnet_stat Per-CPU incoming packets queues statistics of online CPUs 1303 tcp TCP sockets 1304 udp UDP sockets 1305 unix UNIX domain sockets 1306 wireless Wireless interface data (Wavelan etc) 1307 igmp IP multicast addresses, which this host joined 1308 psched Global packet scheduler parameters. 1309 netlink List of PF_NETLINK sockets 1310 ip_mr_vifs List of multicast virtual interfaces 1311 ip_mr_cache List of multicast routing cache 1312 ============= ================================================================ 1313 1314You can use this information to see which network devices are available in 1315your system and how much traffic was routed over those devices:: 1316 1317 > cat /proc/net/dev 1318 Inter-|Receive |[... 1319 face |bytes packets errs drop fifo frame compressed multicast|[... 1320 lo: 908188 5596 0 0 0 0 0 0 [... 1321 ppp0:15475140 20721 410 0 0 410 0 0 [... 1322 eth0: 614530 7085 0 0 0 0 0 1 [... 1323 1324 ...] Transmit 1325 ...] bytes packets errs drop fifo colls carrier compressed 1326 ...] 908188 5596 0 0 0 0 0 0 1327 ...] 1375103 17405 0 0 0 0 0 0 1328 ...] 1703981 5535 0 0 0 3 0 0 1329 1330In addition, each Channel Bond interface has its own directory. For 1331example, the bond0 device will have a directory called /proc/net/bond0/. 1332It will contain information that is specific to that bond, such as the 1333current slaves of the bond, the link status of the slaves, and how 1334many times the slaves link has failed. 1335 13361.4 SCSI info 1337------------- 1338 1339If you have a SCSI or ATA host adapter in your system, you'll find a 1340subdirectory named after the driver for this adapter in /proc/scsi. 1341You'll also see a list of all recognized SCSI devices in /proc/scsi:: 1342 1343 >cat /proc/scsi/scsi 1344 Attached devices: 1345 Host: scsi0 Channel: 00 Id: 00 Lun: 00 1346 Vendor: IBM Model: DGHS09U Rev: 03E0 1347 Type: Direct-Access ANSI SCSI revision: 03 1348 Host: scsi0 Channel: 00 Id: 06 Lun: 00 1349 Vendor: PIONEER Model: CD-ROM DR-U06S Rev: 1.04 1350 Type: CD-ROM ANSI SCSI revision: 02 1351 1352 1353The directory named after the driver has one file for each adapter found in 1354the system. These files contain information about the controller, including 1355the used IRQ and the IO address range. The amount of information shown is 1356dependent on the adapter you use. The example shows the output for an Adaptec 1357AHA-2940 SCSI adapter:: 1358 1359 > cat /proc/scsi/aic7xxx/0 1360 1361 Adaptec AIC7xxx driver version: 5.1.19/3.2.4 1362 Compile Options: 1363 TCQ Enabled By Default : Disabled 1364 AIC7XXX_PROC_STATS : Disabled 1365 AIC7XXX_RESET_DELAY : 5 1366 Adapter Configuration: 1367 SCSI Adapter: Adaptec AHA-294X Ultra SCSI host adapter 1368 Ultra Wide Controller 1369 PCI MMAPed I/O Base: 0xeb001000 1370 Adapter SEEPROM Config: SEEPROM found and used. 1371 Adaptec SCSI BIOS: Enabled 1372 IRQ: 10 1373 SCBs: Active 0, Max Active 2, 1374 Allocated 15, HW 16, Page 255 1375 Interrupts: 160328 1376 BIOS Control Word: 0x18b6 1377 Adapter Control Word: 0x005b 1378 Extended Translation: Enabled 1379 Disconnect Enable Flags: 0xffff 1380 Ultra Enable Flags: 0x0001 1381 Tag Queue Enable Flags: 0x0000 1382 Ordered Queue Tag Flags: 0x0000 1383 Default Tag Queue Depth: 8 1384 Tagged Queue By Device array for aic7xxx host instance 0: 1385 {255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255} 1386 Actual queue depth per device for aic7xxx host instance 0: 1387 {1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1} 1388 Statistics: 1389 (scsi0:0:0:0) 1390 Device using Wide/Sync transfers at 40.0 MByte/sec, offset 8 1391 Transinfo settings: current(12/8/1/0), goal(12/8/1/0), user(12/15/1/0) 1392 Total transfers 160151 (74577 reads and 85574 writes) 1393 (scsi0:0:6:0) 1394 Device using Narrow/Sync transfers at 5.0 MByte/sec, offset 15 1395 Transinfo settings: current(50/15/0/0), goal(50/15/0/0), user(50/15/0/0) 1396 Total transfers 0 (0 reads and 0 writes) 1397 1398 13991.5 Parallel port info in /proc/parport 1400--------------------------------------- 1401 1402The directory /proc/parport contains information about the parallel ports of 1403your system. It has one subdirectory for each port, named after the port 1404number (0,1,2,...). 1405 1406These directories contain the four files shown in Table 1-10. 1407 1408 1409.. table:: Table 1-10: Files in /proc/parport 1410 1411 ========= ==================================================================== 1412 File Content 1413 ========= ==================================================================== 1414 autoprobe Any IEEE-1284 device ID information that has been acquired. 1415 devices list of the device drivers using that port. A + will appear by the 1416 name of the device currently using the port (it might not appear 1417 against any). 1418 hardware Parallel port's base address, IRQ line and DMA channel. 1419 irq IRQ that parport is using for that port. This is in a separate 1420 file to allow you to alter it by writing a new value in (IRQ 1421 number or none). 1422 ========= ==================================================================== 1423 14241.6 TTY info in /proc/tty 1425------------------------- 1426 1427Information about the available and actually used tty's can be found in the 1428directory /proc/tty. You'll find entries for drivers and line disciplines in 1429this directory, as shown in Table 1-11. 1430 1431 1432.. table:: Table 1-11: Files in /proc/tty 1433 1434 ============= ============================================== 1435 File Content 1436 ============= ============================================== 1437 drivers list of drivers and their usage 1438 ldiscs registered line disciplines 1439 driver/serial usage statistic and status of single tty lines 1440 ============= ============================================== 1441 1442To see which tty's are currently in use, you can simply look into the file 1443/proc/tty/drivers:: 1444 1445 > cat /proc/tty/drivers 1446 pty_slave /dev/pts 136 0-255 pty:slave 1447 pty_master /dev/ptm 128 0-255 pty:master 1448 pty_slave /dev/ttyp 3 0-255 pty:slave 1449 pty_master /dev/pty 2 0-255 pty:master 1450 serial /dev/cua 5 64-67 serial:callout 1451 serial /dev/ttyS 4 64-67 serial 1452 /dev/tty0 /dev/tty0 4 0 system:vtmaster 1453 /dev/ptmx /dev/ptmx 5 2 system 1454 /dev/console /dev/console 5 1 system:console 1455 /dev/tty /dev/tty 5 0 system:/dev/tty 1456 unknown /dev/tty 4 1-63 console 1457 1458 14591.7 Miscellaneous kernel statistics in /proc/stat 1460------------------------------------------------- 1461 1462Various pieces of information about kernel activity are available in the 1463/proc/stat file. All of the numbers reported in this file are aggregates 1464since the system first booted. For a quick look, simply cat the file:: 1465 1466 > cat /proc/stat 1467 cpu 237902850 368826709 106375398 1873517540 1135548 0 14507935 0 0 0 1468 cpu0 60045249 91891769 26331539 468411416 495718 0 5739640 0 0 0 1469 cpu1 59746288 91759249 26609887 468860630 312281 0 4384817 0 0 0 1470 cpu2 59489247 92985423 26904446 467808813 171668 0 2268998 0 0 0 1471 cpu3 58622065 92190267 26529524 468436680 155879 0 2114478 0 0 0 1472 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> 1473 ctxt 22848221062 1474 btime 1605316999 1475 processes 746787147 1476 procs_running 2 1477 procs_blocked 0 1478 softirq 12121874454 100099120 3938138295 127375644 2795979 187870761 0 173808342 3072582055 52608 224184354 1479 1480The very first "cpu" line aggregates the numbers in all of the other "cpuN" 1481lines. These numbers identify the amount of time the CPU has spent performing 1482different kinds of work. Time units are in USER_HZ (typically hundredths of a 1483second). The meanings of the columns are as follows, from left to right: 1484 1485- user: normal processes executing in user mode 1486- nice: niced processes executing in user mode 1487- system: processes executing in kernel mode 1488- idle: twiddling thumbs 1489- iowait: In a word, iowait stands for waiting for I/O to complete. But there 1490 are several problems: 1491 1492 1. CPU will not wait for I/O to complete, iowait is the time that a task is 1493 waiting for I/O to complete. When CPU goes into idle state for 1494 outstanding task I/O, another task will be scheduled on this CPU. 1495 2. In a multi-core CPU, the task waiting for I/O to complete is not running 1496 on any CPU, so the iowait of each CPU is difficult to calculate. 1497 3. The value of iowait field in /proc/stat will decrease in certain 1498 conditions. 1499 1500 So, the iowait is not reliable by reading from /proc/stat. 1501- irq: servicing interrupts 1502- softirq: servicing softirqs 1503- steal: involuntary wait 1504- guest: running a normal guest 1505- guest_nice: running a niced guest 1506 1507The "intr" line gives counts of interrupts serviced since boot time, for each 1508of the possible system interrupts. The first column is the total of all 1509interrupts serviced including unnumbered architecture specific interrupts; 1510each subsequent column is the total for that particular numbered interrupt. 1511Unnumbered interrupts are not shown, only summed into the total. 1512 1513The "ctxt" line gives the total number of context switches across all CPUs. 1514 1515The "btime" line gives the time at which the system booted, in seconds since 1516the Unix epoch. 1517 1518The "processes" line gives the number of processes and threads created, which 1519includes (but is not limited to) those created by calls to the fork() and 1520clone() system calls. 1521 1522The "procs_running" line gives the total number of threads that are 1523running or ready to run (i.e., the total number of runnable threads). 1524 1525The "procs_blocked" line gives the number of processes currently blocked, 1526waiting for I/O to complete. 1527 1528The "softirq" line gives counts of softirqs serviced since boot time, for each 1529of the possible system softirqs. The first column is the total of all 1530softirqs serviced; each subsequent column is the total for that particular 1531softirq. 1532 1533 15341.8 Ext4 file system parameters 1535------------------------------- 1536 1537Information about mounted ext4 file systems can be found in 1538/proc/fs/ext4. Each mounted filesystem will have a directory in 1539/proc/fs/ext4 based on its device name (i.e., /proc/fs/ext4/hdc or 1540/proc/fs/ext4/sda9 or /proc/fs/ext4/dm-0). The files in each per-device 1541directory are shown in Table 1-12, below. 1542 1543.. table:: Table 1-12: Files in /proc/fs/ext4/<devname> 1544 1545 ============== ========================================================== 1546 File Content 1547 mb_groups details of multiblock allocator buddy cache of free blocks 1548 ============== ========================================================== 1549 15501.9 /proc/consoles 1551------------------- 1552Shows registered system console lines. 1553 1554To see which character device lines are currently used for the system console 1555/dev/console, you may simply look into the file /proc/consoles:: 1556 1557 > cat /proc/consoles 1558 tty0 -WU (ECp) 4:7 1559 ttyS0 -W- (Ep) 4:64 1560 1561The columns are: 1562 1563+--------------------+-------------------------------------------------------+ 1564| device | name of the device | 1565+====================+=======================================================+ 1566| operations | * R = can do read operations | 1567| | * W = can do write operations | 1568| | * U = can do unblank | 1569+--------------------+-------------------------------------------------------+ 1570| flags | * E = it is enabled | 1571| | * C = it is preferred console | 1572| | * B = it is primary boot console | 1573| | * p = it is used for printk buffer | 1574| | * b = it is not a TTY but a Braille device | 1575| | * a = it is safe to use when cpu is offline | 1576+--------------------+-------------------------------------------------------+ 1577| major:minor | major and minor number of the device separated by a | 1578| | colon | 1579+--------------------+-------------------------------------------------------+ 1580 1581Summary 1582------- 1583 1584The /proc file system serves information about the running system. It not only 1585allows access to process data but also allows you to request the kernel status 1586by reading files in the hierarchy. 1587 1588The directory structure of /proc reflects the types of information and makes 1589it easy, if not obvious, where to look for specific data. 1590 1591Chapter 2: Modifying System Parameters 1592====================================== 1593 1594In This Chapter 1595--------------- 1596 1597* Modifying kernel parameters by writing into files found in /proc/sys 1598* Exploring the files which modify certain parameters 1599* Review of the /proc/sys file tree 1600 1601------------------------------------------------------------------------------ 1602 1603A very interesting part of /proc is the directory /proc/sys. This is not only 1604a source of information, it also allows you to change parameters within the 1605kernel. Be very careful when attempting this. You can optimize your system, 1606but you can also cause it to crash. Never alter kernel parameters on a 1607production system. Set up a development machine and test to make sure that 1608everything works the way you want it to. You may have no alternative but to 1609reboot the machine once an error has been made. 1610 1611To change a value, simply echo the new value into the file. 1612You need to be root to do this. You can create your own boot script 1613to perform this every time your system boots. 1614 1615The files in /proc/sys can be used to fine tune and monitor miscellaneous and 1616general things in the operation of the Linux kernel. Since some of the files 1617can inadvertently disrupt your system, it is advisable to read both 1618documentation and source before actually making adjustments. In any case, be 1619very careful when writing to any of these files. The entries in /proc may 1620change slightly between the 2.1.* and the 2.2 kernel, so if there is any doubt 1621review the kernel documentation in the directory linux/Documentation. 1622This chapter is heavily based on the documentation included in the pre 2.2 1623kernels, and became part of it in version 2.2.1 of the Linux kernel. 1624 1625Please see: Documentation/admin-guide/sysctl/ directory for descriptions of 1626these entries. 1627 1628Summary 1629------- 1630 1631Certain aspects of kernel behavior can be modified at runtime, without the 1632need to recompile the kernel, or even to reboot the system. The files in the 1633/proc/sys tree can not only be read, but also modified. You can use the echo 1634command to write value into these files, thereby changing the default settings 1635of the kernel. 1636 1637 1638Chapter 3: Per-process Parameters 1639================================= 1640 16413.1 /proc/<pid>/oom_adj & /proc/<pid>/oom_score_adj- Adjust the oom-killer score 1642-------------------------------------------------------------------------------- 1643 1644These files can be used to adjust the badness heuristic used to select which 1645process gets killed in out of memory (oom) conditions. 1646 1647The badness heuristic assigns a value to each candidate task ranging from 0 1648(never kill) to 1000 (always kill) to determine which process is targeted. The 1649units are roughly a proportion along that range of allowed memory the process 1650may allocate from based on an estimation of its current memory and swap use. 1651For example, if a task is using all allowed memory, its badness score will be 16521000. If it is using half of its allowed memory, its score will be 500. 1653 1654The amount of "allowed" memory depends on the context in which the oom killer 1655was called. If it is due to the memory assigned to the allocating task's cpuset 1656being exhausted, the allowed memory represents the set of mems assigned to that 1657cpuset. If it is due to a mempolicy's node(s) being exhausted, the allowed 1658memory represents the set of mempolicy nodes. If it is due to a memory 1659limit (or swap limit) being reached, the allowed memory is that configured 1660limit. Finally, if it is due to the entire system being out of memory, the 1661allowed memory represents all allocatable resources. 1662 1663The value of /proc/<pid>/oom_score_adj is added to the badness score before it 1664is used to determine which task to kill. Acceptable values range from -1000 1665(OOM_SCORE_ADJ_MIN) to +1000 (OOM_SCORE_ADJ_MAX). This allows userspace to 1666polarize the preference for oom killing either by always preferring a certain 1667task or completely disabling it. The lowest possible value, -1000, is 1668equivalent to disabling oom killing entirely for that task since it will always 1669report a badness score of 0. 1670 1671Consequently, it is very simple for userspace to define the amount of memory to 1672consider for each task. Setting a /proc/<pid>/oom_score_adj value of +500, for 1673example, is roughly equivalent to allowing the remainder of tasks sharing the 1674same system, cpuset, mempolicy, or memory controller resources to use at least 167550% more memory. A value of -500, on the other hand, would be roughly 1676equivalent to discounting 50% of the task's allowed memory from being considered 1677as scoring against the task. 1678 1679For backwards compatibility with previous kernels, /proc/<pid>/oom_adj may also 1680be used to tune the badness score. Its acceptable values range from -16 1681(OOM_ADJUST_MIN) to +15 (OOM_ADJUST_MAX) and a special value of -17 1682(OOM_DISABLE) to disable oom killing entirely for that task. Its value is 1683scaled linearly with /proc/<pid>/oom_score_adj. 1684 1685The value of /proc/<pid>/oom_score_adj may be reduced no lower than the last 1686value set by a CAP_SYS_RESOURCE process. To reduce the value any lower 1687requires CAP_SYS_RESOURCE. 1688 1689 16903.2 /proc/<pid>/oom_score - Display current oom-killer score 1691------------------------------------------------------------- 1692 1693This file can be used to check the current score used by the oom-killer for 1694any given <pid>. Use it together with /proc/<pid>/oom_score_adj to tune which 1695process should be killed in an out-of-memory situation. 1696 1697Please note that the exported value includes oom_score_adj so it is 1698effectively in range [0,2000]. 1699 1700 17013.3 /proc/<pid>/io - Display the IO accounting fields 1702------------------------------------------------------- 1703 1704This file contains IO statistics for each running process. 1705 1706Example 1707~~~~~~~ 1708 1709:: 1710 1711 test:/tmp # dd if=/dev/zero of=/tmp/test.dat & 1712 [1] 3828 1713 1714 test:/tmp # cat /proc/3828/io 1715 rchar: 323934931 1716 wchar: 323929600 1717 syscr: 632687 1718 syscw: 632675 1719 read_bytes: 0 1720 write_bytes: 323932160 1721 cancelled_write_bytes: 0 1722 1723 1724Description 1725~~~~~~~~~~~ 1726 1727rchar 1728^^^^^ 1729 1730I/O counter: chars read 1731The number of bytes which this task has caused to be read from storage. This 1732is simply the sum of bytes which this process passed to read() and pread(). 1733It includes things like tty IO and it is unaffected by whether or not actual 1734physical disk IO was required (the read might have been satisfied from 1735pagecache). 1736 1737 1738wchar 1739^^^^^ 1740 1741I/O counter: chars written 1742The number of bytes which this task has caused, or shall cause to be written 1743to disk. Similar caveats apply here as with rchar. 1744 1745 1746syscr 1747^^^^^ 1748 1749I/O counter: read syscalls 1750Attempt to count the number of read I/O operations, i.e. syscalls like read() 1751and pread(). 1752 1753 1754syscw 1755^^^^^ 1756 1757I/O counter: write syscalls 1758Attempt to count the number of write I/O operations, i.e. syscalls like 1759write() and pwrite(). 1760 1761 1762read_bytes 1763^^^^^^^^^^ 1764 1765I/O counter: bytes read 1766Attempt to count the number of bytes which this process really did cause to 1767be fetched from the storage layer. Done at the submit_bio() level, so it is 1768accurate for block-backed filesystems. <please add status regarding NFS and 1769CIFS at a later time> 1770 1771 1772write_bytes 1773^^^^^^^^^^^ 1774 1775I/O counter: bytes written 1776Attempt to count the number of bytes which this process caused to be sent to 1777the storage layer. This is done at page-dirtying time. 1778 1779 1780cancelled_write_bytes 1781^^^^^^^^^^^^^^^^^^^^^ 1782 1783The big inaccuracy here is truncate. If a process writes 1MB to a file and 1784then deletes the file, it will in fact perform no writeout. But it will have 1785been accounted as having caused 1MB of write. 1786In other words: The number of bytes which this process caused to not happen, 1787by truncating pagecache. A task can cause "negative" IO too. If this task 1788truncates some dirty pagecache, some IO which another task has been accounted 1789for (in its write_bytes) will not be happening. We _could_ just subtract that 1790from the truncating task's write_bytes, but there is information loss in doing 1791that. 1792 1793 1794.. Note:: 1795 1796 At its current implementation state, this is a bit racy on 32-bit machines: 1797 if process A reads process B's /proc/pid/io while process B is updating one 1798 of those 64-bit counters, process A could see an intermediate result. 1799 1800 1801More information about this can be found within the taskstats documentation in 1802Documentation/accounting. 1803 18043.4 /proc/<pid>/coredump_filter - Core dump filtering settings 1805--------------------------------------------------------------- 1806When a process is dumped, all anonymous memory is written to a core file as 1807long as the size of the core file isn't limited. But sometimes we don't want 1808to dump some memory segments, for example, huge shared memory or DAX. 1809Conversely, sometimes we want to save file-backed memory segments into a core 1810file, not only the individual files. 1811 1812/proc/<pid>/coredump_filter allows you to customize which memory segments 1813will be dumped when the <pid> process is dumped. coredump_filter is a bitmask 1814of memory types. If a bit of the bitmask is set, memory segments of the 1815corresponding memory type are dumped, otherwise they are not dumped. 1816 1817The following 9 memory types are supported: 1818 1819 - (bit 0) anonymous private memory 1820 - (bit 1) anonymous shared memory 1821 - (bit 2) file-backed private memory 1822 - (bit 3) file-backed shared memory 1823 - (bit 4) ELF header pages in file-backed private memory areas (it is 1824 effective only if the bit 2 is cleared) 1825 - (bit 5) hugetlb private memory 1826 - (bit 6) hugetlb shared memory 1827 - (bit 7) DAX private memory 1828 - (bit 8) DAX shared memory 1829 1830 Note that MMIO pages such as frame buffer are never dumped and vDSO pages 1831 are always dumped regardless of the bitmask status. 1832 1833 Note that bits 0-4 don't affect hugetlb or DAX memory. hugetlb memory is 1834 only affected by bit 5-6, and DAX is only affected by bits 7-8. 1835 1836The default value of coredump_filter is 0x33; this means all anonymous memory 1837segments, ELF header pages and hugetlb private memory are dumped. 1838 1839If you don't want to dump all shared memory segments attached to pid 1234, 1840write 0x31 to the process's proc file:: 1841 1842 $ echo 0x31 > /proc/1234/coredump_filter 1843 1844When a new process is created, the process inherits the bitmask status from its 1845parent. It is useful to set up coredump_filter before the program runs. 1846For example:: 1847 1848 $ echo 0x7 > /proc/self/coredump_filter 1849 $ ./some_program 1850 18513.5 /proc/<pid>/mountinfo - Information about mounts 1852-------------------------------------------------------- 1853 1854This file contains lines of the form:: 1855 1856 36 35 98:0 /mnt1 /mnt2 rw,noatime master:1 - ext3 /dev/root rw,errors=continue 1857 (1)(2)(3) (4) (5) (6) (n…m) (m+1)(m+2) (m+3) (m+4) 1858 1859 (1) mount ID: unique identifier of the mount (may be reused after umount) 1860 (2) parent ID: ID of parent (or of self for the top of the mount tree) 1861 (3) major:minor: value of st_dev for files on filesystem 1862 (4) root: root of the mount within the filesystem 1863 (5) mount point: mount point relative to the process's root 1864 (6) mount options: per mount options 1865 (n…m) optional fields: zero or more fields of the form "tag[:value]" 1866 (m+1) separator: marks the end of the optional fields 1867 (m+2) filesystem type: name of filesystem of the form "type[.subtype]" 1868 (m+3) mount source: filesystem specific information or "none" 1869 (m+4) super options: per super block options 1870 1871Parsers should ignore all unrecognised optional fields. Currently the 1872possible optional fields are: 1873 1874================ ============================================================== 1875shared:X mount is shared in peer group X 1876master:X mount is slave to peer group X 1877propagate_from:X mount is slave and receives propagation from peer group X [#]_ 1878unbindable mount is unbindable 1879================ ============================================================== 1880 1881.. [#] X is the closest dominant peer group under the process's root. If 1882 X is the immediate master of the mount, or if there's no dominant peer 1883 group under the same root, then only the "master:X" field is present 1884 and not the "propagate_from:X" field. 1885 1886For more information on mount propagation see: 1887 1888 Documentation/filesystems/sharedsubtree.rst 1889 1890 18913.6 /proc/<pid>/comm & /proc/<pid>/task/<tid>/comm 1892-------------------------------------------------------- 1893These files provide a method to access a task's comm value. It also allows for 1894a task to set its own or one of its thread siblings comm value. The comm value 1895is limited in size compared to the cmdline value, so writing anything longer 1896then the kernel's TASK_COMM_LEN (currently 16 chars) will result in a truncated 1897comm value. 1898 1899 19003.7 /proc/<pid>/task/<tid>/children - Information about task children 1901------------------------------------------------------------------------- 1902This file provides a fast way to retrieve first level children pids 1903of a task pointed by <pid>/<tid> pair. The format is a space separated 1904stream of pids. 1905 1906Note the "first level" here -- if a child has its own children they will 1907not be listed here; one needs to read /proc/<children-pid>/task/<tid>/children 1908to obtain the descendants. 1909 1910Since this interface is intended to be fast and cheap it doesn't 1911guarantee to provide precise results and some children might be 1912skipped, especially if they've exited right after we printed their 1913pids, so one needs to either stop or freeze processes being inspected 1914if precise results are needed. 1915 1916 19173.8 /proc/<pid>/fdinfo/<fd> - Information about opened file 1918--------------------------------------------------------------- 1919This file provides information associated with an opened file. The regular 1920files have at least four fields -- 'pos', 'flags', 'mnt_id' and 'ino'. 1921The 'pos' represents the current offset of the opened file in decimal 1922form [see lseek(2) for details], 'flags' denotes the octal O_xxx mask the 1923file has been created with [see open(2) for details] and 'mnt_id' represents 1924mount ID of the file system containing the opened file [see 3.5 1925/proc/<pid>/mountinfo for details]. 'ino' represents the inode number of 1926the file. 1927 1928A typical output is:: 1929 1930 pos: 0 1931 flags: 0100002 1932 mnt_id: 19 1933 ino: 63107 1934 1935All locks associated with a file descriptor are shown in its fdinfo too:: 1936 1937 lock: 1: FLOCK ADVISORY WRITE 359 00:13:11691 0 EOF 1938 1939The files such as eventfd, fsnotify, signalfd, epoll among the regular pos/flags 1940pair provide additional information particular to the objects they represent. 1941 1942Eventfd files 1943~~~~~~~~~~~~~ 1944 1945:: 1946 1947 pos: 0 1948 flags: 04002 1949 mnt_id: 9 1950 ino: 63107 1951 eventfd-count: 5a 1952 1953where 'eventfd-count' is hex value of a counter. 1954 1955Signalfd files 1956~~~~~~~~~~~~~~ 1957 1958:: 1959 1960 pos: 0 1961 flags: 04002 1962 mnt_id: 9 1963 ino: 63107 1964 sigmask: 0000000000000200 1965 1966where 'sigmask' is hex value of the signal mask associated 1967with a file. 1968 1969Epoll files 1970~~~~~~~~~~~ 1971 1972:: 1973 1974 pos: 0 1975 flags: 02 1976 mnt_id: 9 1977 ino: 63107 1978 tfd: 5 events: 1d data: ffffffffffffffff pos:0 ino:61af sdev:7 1979 1980where 'tfd' is a target file descriptor number in decimal form, 1981'events' is events mask being watched and the 'data' is data 1982associated with a target [see epoll(7) for more details]. 1983 1984The 'pos' is current offset of the target file in decimal form 1985[see lseek(2)], 'ino' and 'sdev' are inode and device numbers 1986where target file resides, all in hex format. 1987 1988Fsnotify files 1989~~~~~~~~~~~~~~ 1990For inotify files the format is the following:: 1991 1992 pos: 0 1993 flags: 02000000 1994 mnt_id: 9 1995 ino: 63107 1996 inotify wd:3 ino:9e7e sdev:800013 mask:800afce ignored_mask:0 fhandle-bytes:8 fhandle-type:1 f_handle:7e9e0000640d1b6d 1997 1998where 'wd' is a watch descriptor in decimal form, i.e. a target file 1999descriptor number, 'ino' and 'sdev' are inode and device where the 2000target file resides and the 'mask' is the mask of events, all in hex 2001form [see inotify(7) for more details]. 2002 2003If the kernel was built with exportfs support, the path to the target 2004file is encoded as a file handle. The file handle is provided by three 2005fields 'fhandle-bytes', 'fhandle-type' and 'f_handle', all in hex 2006format. 2007 2008If the kernel is built without exportfs support the file handle won't be 2009printed out. 2010 2011If there is no inotify mark attached yet the 'inotify' line will be omitted. 2012 2013For fanotify files the format is:: 2014 2015 pos: 0 2016 flags: 02 2017 mnt_id: 9 2018 ino: 63107 2019 fanotify flags:10 event-flags:0 2020 fanotify mnt_id:12 mflags:40 mask:38 ignored_mask:40000003 2021 fanotify ino:4f969 sdev:800013 mflags:0 mask:3b ignored_mask:40000000 fhandle-bytes:8 fhandle-type:1 f_handle:69f90400c275b5b4 2022 2023where fanotify 'flags' and 'event-flags' are values used in fanotify_init 2024call, 'mnt_id' is the mount point identifier, 'mflags' is the value of 2025flags associated with mark which are tracked separately from events 2026mask. 'ino' and 'sdev' are target inode and device, 'mask' is the events 2027mask and 'ignored_mask' is the mask of events which are to be ignored. 2028All are in hex format. Incorporation of 'mflags', 'mask' and 'ignored_mask' 2029provide information about flags and mask used in fanotify_mark 2030call [see fsnotify manpage for details]. 2031 2032While the first three lines are mandatory and always printed, the rest is 2033optional and may be omitted if no marks created yet. 2034 2035Timerfd files 2036~~~~~~~~~~~~~ 2037 2038:: 2039 2040 pos: 0 2041 flags: 02 2042 mnt_id: 9 2043 ino: 63107 2044 clockid: 0 2045 ticks: 0 2046 settime flags: 01 2047 it_value: (0, 49406829) 2048 it_interval: (1, 0) 2049 2050where 'clockid' is the clock type and 'ticks' is the number of the timer expirations 2051that have occurred [see timerfd_create(2) for details]. 'settime flags' are 2052flags in octal form been used to setup the timer [see timerfd_settime(2) for 2053details]. 'it_value' is remaining time until the timer expiration. 2054'it_interval' is the interval for the timer. Note the timer might be set up 2055with TIMER_ABSTIME option which will be shown in 'settime flags', but 'it_value' 2056still exhibits timer's remaining time. 2057 2058DMA Buffer files 2059~~~~~~~~~~~~~~~~ 2060 2061:: 2062 2063 pos: 0 2064 flags: 04002 2065 mnt_id: 9 2066 ino: 63107 2067 size: 32768 2068 count: 2 2069 exp_name: system-heap 2070 2071where 'size' is the size of the DMA buffer in bytes. 'count' is the file count of 2072the DMA buffer file. 'exp_name' is the name of the DMA buffer exporter. 2073 20743.9 /proc/<pid>/map_files - Information about memory mapped files 2075--------------------------------------------------------------------- 2076This directory contains symbolic links which represent memory mapped files 2077the process is maintaining. Example output:: 2078 2079 | lr-------- 1 root root 64 Jan 27 11:24 333c600000-333c620000 -> /usr/lib64/ld-2.18.so 2080 | lr-------- 1 root root 64 Jan 27 11:24 333c81f000-333c820000 -> /usr/lib64/ld-2.18.so 2081 | lr-------- 1 root root 64 Jan 27 11:24 333c820000-333c821000 -> /usr/lib64/ld-2.18.so 2082 | ... 2083 | lr-------- 1 root root 64 Jan 27 11:24 35d0421000-35d0422000 -> /usr/lib64/libselinux.so.1 2084 | lr-------- 1 root root 64 Jan 27 11:24 400000-41a000 -> /usr/bin/ls 2085 2086The name of a link represents the virtual memory bounds of a mapping, i.e. 2087vm_area_struct::vm_start-vm_area_struct::vm_end. 2088 2089The main purpose of the map_files is to retrieve a set of memory mapped 2090files in a fast way instead of parsing /proc/<pid>/maps or 2091/proc/<pid>/smaps, both of which contain many more records. At the same 2092time one can open(2) mappings from the listings of two processes and 2093comparing their inode numbers to figure out which anonymous memory areas 2094are actually shared. 2095 20963.10 /proc/<pid>/timerslack_ns - Task timerslack value 2097--------------------------------------------------------- 2098This file provides the value of the task's timerslack value in nanoseconds. 2099This value specifies an amount of time that normal timers may be deferred 2100in order to coalesce timers and avoid unnecessary wakeups. 2101 2102This allows a task's interactivity vs power consumption tradeoff to be 2103adjusted. 2104 2105Writing 0 to the file will set the task's timerslack to the default value. 2106 2107Valid values are from 0 - ULLONG_MAX 2108 2109An application setting the value must have PTRACE_MODE_ATTACH_FSCREDS level 2110permissions on the task specified to change its timerslack_ns value. 2111 21123.11 /proc/<pid>/patch_state - Livepatch patch operation state 2113----------------------------------------------------------------- 2114When CONFIG_LIVEPATCH is enabled, this file displays the value of the 2115patch state for the task. 2116 2117A value of '-1' indicates that no patch is in transition. 2118 2119A value of '0' indicates that a patch is in transition and the task is 2120unpatched. If the patch is being enabled, then the task hasn't been 2121patched yet. If the patch is being disabled, then the task has already 2122been unpatched. 2123 2124A value of '1' indicates that a patch is in transition and the task is 2125patched. If the patch is being enabled, then the task has already been 2126patched. If the patch is being disabled, then the task hasn't been 2127unpatched yet. 2128 21293.12 /proc/<pid>/arch_status - task architecture specific status 2130------------------------------------------------------------------- 2131When CONFIG_PROC_PID_ARCH_STATUS is enabled, this file displays the 2132architecture specific status of the task. 2133 2134Example 2135~~~~~~~ 2136 2137:: 2138 2139 $ cat /proc/6753/arch_status 2140 AVX512_elapsed_ms: 8 2141 2142Description 2143~~~~~~~~~~~ 2144 2145x86 specific entries 2146~~~~~~~~~~~~~~~~~~~~~ 2147 2148AVX512_elapsed_ms 2149^^^^^^^^^^^^^^^^^^ 2150 2151 If AVX512 is supported on the machine, this entry shows the milliseconds 2152 elapsed since the last time AVX512 usage was recorded. The recording 2153 happens on a best effort basis when a task is scheduled out. This means 2154 that the value depends on two factors: 2155 2156 1) The time which the task spent on the CPU without being scheduled 2157 out. With CPU isolation and a single runnable task this can take 2158 several seconds. 2159 2160 2) The time since the task was scheduled out last. Depending on the 2161 reason for being scheduled out (time slice exhausted, syscall ...) 2162 this can be arbitrary long time. 2163 2164 As a consequence the value cannot be considered precise and authoritative 2165 information. The application which uses this information has to be aware 2166 of the overall scenario on the system in order to determine whether a 2167 task is a real AVX512 user or not. Precise information can be obtained 2168 with performance counters. 2169 2170 A special value of '-1' indicates that no AVX512 usage was recorded, thus 2171 the task is unlikely an AVX512 user, but depends on the workload and the 2172 scheduling scenario, it also could be a false negative mentioned above. 2173 21743.13 /proc/<pid>/fd - List of symlinks to open files 2175------------------------------------------------------- 2176This directory contains symbolic links which represent open files 2177the process is maintaining. Example output:: 2178 2179 lr-x------ 1 root root 64 Sep 20 17:53 0 -> /dev/null 2180 l-wx------ 1 root root 64 Sep 20 17:53 1 -> /dev/null 2181 lrwx------ 1 root root 64 Sep 20 17:53 10 -> 'socket:[12539]' 2182 lrwx------ 1 root root 64 Sep 20 17:53 11 -> 'socket:[12540]' 2183 lrwx------ 1 root root 64 Sep 20 17:53 12 -> 'socket:[12542]' 2184 2185The number of open files for the process is stored in 'size' member 2186of stat() output for /proc/<pid>/fd for fast access. 2187------------------------------------------------------- 2188 2189 2190Chapter 4: Configuring procfs 2191============================= 2192 21934.1 Mount options 2194--------------------- 2195 2196The following mount options are supported: 2197 2198 ========= ======================================================== 2199 hidepid= Set /proc/<pid>/ access mode. 2200 gid= Set the group authorized to learn processes information. 2201 subset= Show only the specified subset of procfs. 2202 ========= ======================================================== 2203 2204hidepid=off or hidepid=0 means classic mode - everybody may access all 2205/proc/<pid>/ directories (default). 2206 2207hidepid=noaccess or hidepid=1 means users may not access any /proc/<pid>/ 2208directories but their own. Sensitive files like cmdline, sched*, status are now 2209protected against other users. This makes it impossible to learn whether any 2210user runs specific program (given the program doesn't reveal itself by its 2211behaviour). As an additional bonus, as /proc/<pid>/cmdline is unaccessible for 2212other users, poorly written programs passing sensitive information via program 2213arguments are now protected against local eavesdroppers. 2214 2215hidepid=invisible or hidepid=2 means hidepid=1 plus all /proc/<pid>/ will be 2216fully invisible to other users. It doesn't mean that it hides a fact whether a 2217process with a specific pid value exists (it can be learned by other means, e.g. 2218by "kill -0 $PID"), but it hides process' uid and gid, which may be learned by 2219stat()'ing /proc/<pid>/ otherwise. It greatly complicates an intruder's task of 2220gathering information about running processes, whether some daemon runs with 2221elevated privileges, whether other user runs some sensitive program, whether 2222other users run any program at all, etc. 2223 2224hidepid=ptraceable or hidepid=4 means that procfs should only contain 2225/proc/<pid>/ directories that the caller can ptrace. 2226 2227gid= defines a group authorized to learn processes information otherwise 2228prohibited by hidepid=. If you use some daemon like identd which needs to learn 2229information about processes information, just add identd to this group. 2230 2231subset=pid hides all top level files and directories in the procfs that 2232are not related to tasks. 2233 2234Chapter 5: Filesystem behavior 2235============================== 2236 2237Originally, before the advent of pid namespace, procfs was a global file 2238system. It means that there was only one procfs instance in the system. 2239 2240When pid namespace was added, a separate procfs instance was mounted in 2241each pid namespace. So, procfs mount options are global among all 2242mountpoints within the same namespace:: 2243 2244 # grep ^proc /proc/mounts 2245 proc /proc proc rw,relatime,hidepid=2 0 0 2246 2247 # strace -e mount mount -o hidepid=1 -t proc proc /tmp/proc 2248 mount("proc", "/tmp/proc", "proc", 0, "hidepid=1") = 0 2249 +++ exited with 0 +++ 2250 2251 # grep ^proc /proc/mounts 2252 proc /proc proc rw,relatime,hidepid=2 0 0 2253 proc /tmp/proc proc rw,relatime,hidepid=2 0 0 2254 2255and only after remounting procfs mount options will change at all 2256mountpoints:: 2257 2258 # mount -o remount,hidepid=1 -t proc proc /tmp/proc 2259 2260 # grep ^proc /proc/mounts 2261 proc /proc proc rw,relatime,hidepid=1 0 0 2262 proc /tmp/proc proc rw,relatime,hidepid=1 0 0 2263 2264This behavior is different from the behavior of other filesystems. 2265 2266The new procfs behavior is more like other filesystems. Each procfs mount 2267creates a new procfs instance. Mount options affect own procfs instance. 2268It means that it became possible to have several procfs instances 2269displaying tasks with different filtering options in one pid namespace:: 2270 2271 # mount -o hidepid=invisible -t proc proc /proc 2272 # mount -o hidepid=noaccess -t proc proc /tmp/proc 2273 # grep ^proc /proc/mounts 2274 proc /proc proc rw,relatime,hidepid=invisible 0 0 2275 proc /tmp/proc proc rw,relatime,hidepid=noaccess 0 0 2276