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 532naturally aligned THP pages of any currently enabled size. 1 if true, 0 533otherwise. 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 bootconfig Kernel command line obtained from boot config, 693 and, if there were kernel parameters from the 694 boot loader, a "# Parameters from bootloader:" 695 line followed by a line containing those 696 parameters prefixed by "# ". (5.5) 697 buddyinfo Kernel memory allocator information (see text) (2.5) 698 bus Directory containing bus specific information 699 cmdline Kernel command line, both from bootloader and embedded 700 in the kernel image 701 cpuinfo Info about the CPU 702 devices Available devices (block and character) 703 dma Used DMS channels 704 filesystems Supported filesystems 705 driver Various drivers grouped here, currently rtc (2.4) 706 execdomains Execdomains, related to security (2.4) 707 fb Frame Buffer devices (2.4) 708 fs File system parameters, currently nfs/exports (2.4) 709 ide Directory containing info about the IDE subsystem 710 interrupts Interrupt usage 711 iomem Memory map (2.4) 712 ioports I/O port usage 713 irq Masks for irq to cpu affinity (2.4)(smp?) 714 isapnp ISA PnP (Plug&Play) Info (2.4) 715 kcore Kernel core image (can be ELF or A.OUT(deprecated in 2.4)) 716 kmsg Kernel messages 717 ksyms Kernel symbol table 718 loadavg Load average of last 1, 5 & 15 minutes; 719 number of processes currently runnable (running or on ready queue); 720 total number of processes in system; 721 last pid created. 722 All fields are separated by one space except "number of 723 processes currently runnable" and "total number of processes 724 in system", which are separated by a slash ('/'). Example: 725 0.61 0.61 0.55 3/828 22084 726 locks Kernel locks 727 meminfo Memory info 728 misc Miscellaneous 729 modules List of loaded modules 730 mounts Mounted filesystems 731 net Networking info (see text) 732 pagetypeinfo Additional page allocator information (see text) (2.5) 733 partitions Table of partitions known to the system 734 pci Deprecated info of PCI bus (new way -> /proc/bus/pci/, 735 decoupled by lspci (2.4) 736 rtc Real time clock 737 scsi SCSI info (see text) 738 slabinfo Slab pool info 739 softirqs softirq usage 740 stat Overall statistics 741 swaps Swap space utilization 742 sys See chapter 2 743 sysvipc Info of SysVIPC Resources (msg, sem, shm) (2.4) 744 tty Info of tty drivers 745 uptime Wall clock since boot, combined idle time of all cpus 746 version Kernel version 747 video bttv info of video resources (2.4) 748 vmallocinfo Show vmalloced areas 749 ============ =============================================================== 750 751You can, for example, check which interrupts are currently in use and what 752they are used for by looking in the file /proc/interrupts:: 753 754 > cat /proc/interrupts 755 CPU0 756 0: 8728810 XT-PIC timer 757 1: 895 XT-PIC keyboard 758 2: 0 XT-PIC cascade 759 3: 531695 XT-PIC aha152x 760 4: 2014133 XT-PIC serial 761 5: 44401 XT-PIC pcnet_cs 762 8: 2 XT-PIC rtc 763 11: 8 XT-PIC i82365 764 12: 182918 XT-PIC PS/2 Mouse 765 13: 1 XT-PIC fpu 766 14: 1232265 XT-PIC ide0 767 15: 7 XT-PIC ide1 768 NMI: 0 769 770In 2.4.* a couple of lines where added to this file LOC & ERR (this time is the 771output of a SMP machine):: 772 773 > cat /proc/interrupts 774 775 CPU0 CPU1 776 0: 1243498 1214548 IO-APIC-edge timer 777 1: 8949 8958 IO-APIC-edge keyboard 778 2: 0 0 XT-PIC cascade 779 5: 11286 10161 IO-APIC-edge soundblaster 780 8: 1 0 IO-APIC-edge rtc 781 9: 27422 27407 IO-APIC-edge 3c503 782 12: 113645 113873 IO-APIC-edge PS/2 Mouse 783 13: 0 0 XT-PIC fpu 784 14: 22491 24012 IO-APIC-edge ide0 785 15: 2183 2415 IO-APIC-edge ide1 786 17: 30564 30414 IO-APIC-level eth0 787 18: 177 164 IO-APIC-level bttv 788 NMI: 2457961 2457959 789 LOC: 2457882 2457881 790 ERR: 2155 791 792NMI is incremented in this case because every timer interrupt generates a NMI 793(Non Maskable Interrupt) which is used by the NMI Watchdog to detect lockups. 794 795LOC is the local interrupt counter of the internal APIC of every CPU. 796 797ERR is incremented in the case of errors in the IO-APIC bus (the bus that 798connects the CPUs in a SMP system. This means that an error has been detected, 799the IO-APIC automatically retry the transmission, so it should not be a big 800problem, but you should read the SMP-FAQ. 801 802In 2.6.2* /proc/interrupts was expanded again. This time the goal was for 803/proc/interrupts to display every IRQ vector in use by the system, not 804just those considered 'most important'. The new vectors are: 805 806THR 807 interrupt raised when a machine check threshold counter 808 (typically counting ECC corrected errors of memory or cache) exceeds 809 a configurable threshold. Only available on some systems. 810 811TRM 812 a thermal event interrupt occurs when a temperature threshold 813 has been exceeded for the CPU. This interrupt may also be generated 814 when the temperature drops back to normal. 815 816SPU 817 a spurious interrupt is some interrupt that was raised then lowered 818 by some IO device before it could be fully processed by the APIC. Hence 819 the APIC sees the interrupt but does not know what device it came from. 820 For this case the APIC will generate the interrupt with a IRQ vector 821 of 0xff. This might also be generated by chipset bugs. 822 823RES, CAL, TLB 824 rescheduling, call and TLB flush interrupts are 825 sent from one CPU to another per the needs of the OS. Typically, 826 their statistics are used by kernel developers and interested users to 827 determine the occurrence of interrupts of the given type. 828 829The above IRQ vectors are displayed only when relevant. For example, 830the threshold vector does not exist on x86_64 platforms. Others are 831suppressed when the system is a uniprocessor. As of this writing, only 832i386 and x86_64 platforms support the new IRQ vector displays. 833 834Of some interest is the introduction of the /proc/irq directory to 2.4. 835It could be used to set IRQ to CPU affinity. This means that you can "hook" an 836IRQ to only one CPU, or to exclude a CPU of handling IRQs. The contents of the 837irq subdir is one subdir for each IRQ, and two files; default_smp_affinity and 838prof_cpu_mask. 839 840For example:: 841 842 > ls /proc/irq/ 843 0 10 12 14 16 18 2 4 6 8 prof_cpu_mask 844 1 11 13 15 17 19 3 5 7 9 default_smp_affinity 845 > ls /proc/irq/0/ 846 smp_affinity 847 848smp_affinity is a bitmask, in which you can specify which CPUs can handle the 849IRQ. You can set it by doing:: 850 851 > echo 1 > /proc/irq/10/smp_affinity 852 853This means that only the first CPU will handle the IRQ, but you can also echo 8545 which means that only the first and third CPU can handle the IRQ. 855 856The contents of each smp_affinity file is the same by default:: 857 858 > cat /proc/irq/0/smp_affinity 859 ffffffff 860 861There is an alternate interface, smp_affinity_list which allows specifying 862a CPU range instead of a bitmask:: 863 864 > cat /proc/irq/0/smp_affinity_list 865 1024-1031 866 867The default_smp_affinity mask applies to all non-active IRQs, which are the 868IRQs which have not yet been allocated/activated, and hence which lack a 869/proc/irq/[0-9]* directory. 870 871The node file on an SMP system shows the node to which the device using the IRQ 872reports itself as being attached. This hardware locality information does not 873include information about any possible driver locality preference. 874 875prof_cpu_mask specifies which CPUs are to be profiled by the system wide 876profiler. Default value is ffffffff (all CPUs if there are only 32 of them). 877 878The way IRQs are routed is handled by the IO-APIC, and it's Round Robin 879between all the CPUs which are allowed to handle it. As usual the kernel has 880more info than you and does a better job than you, so the defaults are the 881best choice for almost everyone. [Note this applies only to those IO-APIC's 882that support "Round Robin" interrupt distribution.] 883 884There are three more important subdirectories in /proc: net, scsi, and sys. 885The general rule is that the contents, or even the existence of these 886directories, depend on your kernel configuration. If SCSI is not enabled, the 887directory scsi may not exist. The same is true with the net, which is there 888only when networking support is present in the running kernel. 889 890The slabinfo file gives information about memory usage at the slab level. 891Linux uses slab pools for memory management above page level in version 2.2. 892Commonly used objects have their own slab pool (such as network buffers, 893directory cache, and so on). 894 895:: 896 897 > cat /proc/buddyinfo 898 899 Node 0, zone DMA 0 4 5 4 4 3 ... 900 Node 0, zone Normal 1 0 0 1 101 8 ... 901 Node 0, zone HighMem 2 0 0 1 1 0 ... 902 903External fragmentation is a problem under some workloads, and buddyinfo is a 904useful tool for helping diagnose these problems. Buddyinfo will give you a 905clue as to how big an area you can safely allocate, or why a previous 906allocation failed. 907 908Each column represents the number of pages of a certain order which are 909available. In this case, there are 0 chunks of 2^0*PAGE_SIZE available in 910ZONE_DMA, 4 chunks of 2^1*PAGE_SIZE in ZONE_DMA, 101 chunks of 2^4*PAGE_SIZE 911available in ZONE_NORMAL, etc... 912 913More information relevant to external fragmentation can be found in 914pagetypeinfo:: 915 916 > cat /proc/pagetypeinfo 917 Page block order: 9 918 Pages per block: 512 919 920 Free pages count per migrate type at order 0 1 2 3 4 5 6 7 8 9 10 921 Node 0, zone DMA, type Unmovable 0 0 0 1 1 1 1 1 1 1 0 922 Node 0, zone DMA, type Reclaimable 0 0 0 0 0 0 0 0 0 0 0 923 Node 0, zone DMA, type Movable 1 1 2 1 2 1 1 0 1 0 2 924 Node 0, zone DMA, type Reserve 0 0 0 0 0 0 0 0 0 1 0 925 Node 0, zone DMA, type Isolate 0 0 0 0 0 0 0 0 0 0 0 926 Node 0, zone DMA32, type Unmovable 103 54 77 1 1 1 11 8 7 1 9 927 Node 0, zone DMA32, type Reclaimable 0 0 2 1 0 0 0 0 1 0 0 928 Node 0, zone DMA32, type Movable 169 152 113 91 77 54 39 13 6 1 452 929 Node 0, zone DMA32, type Reserve 1 2 2 2 2 0 1 1 1 1 0 930 Node 0, zone DMA32, type Isolate 0 0 0 0 0 0 0 0 0 0 0 931 932 Number of blocks type Unmovable Reclaimable Movable Reserve Isolate 933 Node 0, zone DMA 2 0 5 1 0 934 Node 0, zone DMA32 41 6 967 2 0 935 936Fragmentation avoidance in the kernel works by grouping pages of different 937migrate types into the same contiguous regions of memory called page blocks. 938A page block is typically the size of the default hugepage size, e.g. 2MB on 939X86-64. By keeping pages grouped based on their ability to move, the kernel 940can reclaim pages within a page block to satisfy a high-order allocation. 941 942The pagetypinfo begins with information on the size of a page block. It 943then gives the same type of information as buddyinfo except broken down 944by migrate-type and finishes with details on how many page blocks of each 945type exist. 946 947If min_free_kbytes has been tuned correctly (recommendations made by hugeadm 948from libhugetlbfs https://github.com/libhugetlbfs/libhugetlbfs/), one can 949make an estimate of the likely number of huge pages that can be allocated 950at a given point in time. All the "Movable" blocks should be allocatable 951unless memory has been mlock()'d. Some of the Reclaimable blocks should 952also be allocatable although a lot of filesystem metadata may have to be 953reclaimed to achieve this. 954 955 956meminfo 957~~~~~~~ 958 959Provides information about distribution and utilization of memory. This 960varies by architecture and compile options. Some of the counters reported 961here overlap. The memory reported by the non overlapping counters may not 962add up to the overall memory usage and the difference for some workloads 963can be substantial. In many cases there are other means to find out 964additional memory using subsystem specific interfaces, for instance 965/proc/net/sockstat for TCP memory allocations. 966 967Example output. You may not have all of these fields. 968 969:: 970 971 > cat /proc/meminfo 972 973 MemTotal: 32858820 kB 974 MemFree: 21001236 kB 975 MemAvailable: 27214312 kB 976 Buffers: 581092 kB 977 Cached: 5587612 kB 978 SwapCached: 0 kB 979 Active: 3237152 kB 980 Inactive: 7586256 kB 981 Active(anon): 94064 kB 982 Inactive(anon): 4570616 kB 983 Active(file): 3143088 kB 984 Inactive(file): 3015640 kB 985 Unevictable: 0 kB 986 Mlocked: 0 kB 987 SwapTotal: 0 kB 988 SwapFree: 0 kB 989 Zswap: 1904 kB 990 Zswapped: 7792 kB 991 Dirty: 12 kB 992 Writeback: 0 kB 993 AnonPages: 4654780 kB 994 Mapped: 266244 kB 995 Shmem: 9976 kB 996 KReclaimable: 517708 kB 997 Slab: 660044 kB 998 SReclaimable: 517708 kB 999 SUnreclaim: 142336 kB 1000 KernelStack: 11168 kB 1001 PageTables: 20540 kB 1002 SecPageTables: 0 kB 1003 NFS_Unstable: 0 kB 1004 Bounce: 0 kB 1005 WritebackTmp: 0 kB 1006 CommitLimit: 16429408 kB 1007 Committed_AS: 7715148 kB 1008 VmallocTotal: 34359738367 kB 1009 VmallocUsed: 40444 kB 1010 VmallocChunk: 0 kB 1011 Percpu: 29312 kB 1012 EarlyMemtestBad: 0 kB 1013 HardwareCorrupted: 0 kB 1014 AnonHugePages: 4149248 kB 1015 ShmemHugePages: 0 kB 1016 ShmemPmdMapped: 0 kB 1017 FileHugePages: 0 kB 1018 FilePmdMapped: 0 kB 1019 CmaTotal: 0 kB 1020 CmaFree: 0 kB 1021 HugePages_Total: 0 1022 HugePages_Free: 0 1023 HugePages_Rsvd: 0 1024 HugePages_Surp: 0 1025 Hugepagesize: 2048 kB 1026 Hugetlb: 0 kB 1027 DirectMap4k: 401152 kB 1028 DirectMap2M: 10008576 kB 1029 DirectMap1G: 24117248 kB 1030 1031MemTotal 1032 Total usable RAM (i.e. physical RAM minus a few reserved 1033 bits and the kernel binary code) 1034MemFree 1035 Total free RAM. On highmem systems, the sum of LowFree+HighFree 1036MemAvailable 1037 An estimate of how much memory is available for starting new 1038 applications, without swapping. Calculated from MemFree, 1039 SReclaimable, the size of the file LRU lists, and the low 1040 watermarks in each zone. 1041 The estimate takes into account that the system needs some 1042 page cache to function well, and that not all reclaimable 1043 slab will be reclaimable, due to items being in use. The 1044 impact of those factors will vary from system to system. 1045Buffers 1046 Relatively temporary storage for raw disk blocks 1047 shouldn't get tremendously large (20MB or so) 1048Cached 1049 In-memory cache for files read from the disk (the 1050 pagecache) as well as tmpfs & shmem. 1051 Doesn't include SwapCached. 1052SwapCached 1053 Memory that once was swapped out, is swapped back in but 1054 still also is in the swapfile (if memory is needed it 1055 doesn't need to be swapped out AGAIN because it is already 1056 in the swapfile. This saves I/O) 1057Active 1058 Memory that has been used more recently and usually not 1059 reclaimed unless absolutely necessary. 1060Inactive 1061 Memory which has been less recently used. It is more 1062 eligible to be reclaimed for other purposes 1063Unevictable 1064 Memory allocated for userspace which cannot be reclaimed, such 1065 as mlocked pages, ramfs backing pages, secret memfd pages etc. 1066Mlocked 1067 Memory locked with mlock(). 1068HighTotal, HighFree 1069 Highmem is all memory above ~860MB of physical memory. 1070 Highmem areas are for use by userspace programs, or 1071 for the pagecache. The kernel must use tricks to access 1072 this memory, making it slower to access than lowmem. 1073LowTotal, LowFree 1074 Lowmem is memory which can be used for everything that 1075 highmem can be used for, but it is also available for the 1076 kernel's use for its own data structures. Among many 1077 other things, it is where everything from the Slab is 1078 allocated. Bad things happen when you're out of lowmem. 1079SwapTotal 1080 total amount of swap space available 1081SwapFree 1082 Memory which has been evicted from RAM, and is temporarily 1083 on the disk 1084Zswap 1085 Memory consumed by the zswap backend (compressed size) 1086Zswapped 1087 Amount of anonymous memory stored in zswap (original size) 1088Dirty 1089 Memory which is waiting to get written back to the disk 1090Writeback 1091 Memory which is actively being written back to the disk 1092AnonPages 1093 Non-file backed pages mapped into userspace page tables 1094Mapped 1095 files which have been mmapped, such as libraries 1096Shmem 1097 Total memory used by shared memory (shmem) and tmpfs 1098KReclaimable 1099 Kernel allocations that the kernel will attempt to reclaim 1100 under memory pressure. Includes SReclaimable (below), and other 1101 direct allocations with a shrinker. 1102Slab 1103 in-kernel data structures cache 1104SReclaimable 1105 Part of Slab, that might be reclaimed, such as caches 1106SUnreclaim 1107 Part of Slab, that cannot be reclaimed on memory pressure 1108KernelStack 1109 Memory consumed by the kernel stacks of all tasks 1110PageTables 1111 Memory consumed by userspace page tables 1112SecPageTables 1113 Memory consumed by secondary page tables, this currently 1114 currently includes KVM mmu allocations on x86 and arm64. 1115NFS_Unstable 1116 Always zero. Previous counted pages which had been written to 1117 the server, but has not been committed to stable storage. 1118Bounce 1119 Memory used for block device "bounce buffers" 1120WritebackTmp 1121 Memory used by FUSE for temporary writeback buffers 1122CommitLimit 1123 Based on the overcommit ratio ('vm.overcommit_ratio'), 1124 this is the total amount of memory currently available to 1125 be allocated on the system. This limit is only adhered to 1126 if strict overcommit accounting is enabled (mode 2 in 1127 'vm.overcommit_memory'). 1128 1129 The CommitLimit is calculated with the following formula:: 1130 1131 CommitLimit = ([total RAM pages] - [total huge TLB pages]) * 1132 overcommit_ratio / 100 + [total swap pages] 1133 1134 For example, on a system with 1G of physical RAM and 7G 1135 of swap with a `vm.overcommit_ratio` of 30 it would 1136 yield a CommitLimit of 7.3G. 1137 1138 For more details, see the memory overcommit documentation 1139 in mm/overcommit-accounting. 1140Committed_AS 1141 The amount of memory presently allocated on the system. 1142 The committed memory is a sum of all of the memory which 1143 has been allocated by processes, even if it has not been 1144 "used" by them as of yet. A process which malloc()'s 1G 1145 of memory, but only touches 300M of it will show up as 1146 using 1G. This 1G is memory which has been "committed" to 1147 by the VM and can be used at any time by the allocating 1148 application. With strict overcommit enabled on the system 1149 (mode 2 in 'vm.overcommit_memory'), allocations which would 1150 exceed the CommitLimit (detailed above) will not be permitted. 1151 This is useful if one needs to guarantee that processes will 1152 not fail due to lack of memory once that memory has been 1153 successfully allocated. 1154VmallocTotal 1155 total size of vmalloc virtual address space 1156VmallocUsed 1157 amount of vmalloc area which is used 1158VmallocChunk 1159 largest contiguous block of vmalloc area which is free 1160Percpu 1161 Memory allocated to the percpu allocator used to back percpu 1162 allocations. This stat excludes the cost of metadata. 1163EarlyMemtestBad 1164 The amount of RAM/memory in kB, that was identified as corrupted 1165 by early memtest. If memtest was not run, this field will not 1166 be displayed at all. Size is never rounded down to 0 kB. 1167 That means if 0 kB is reported, you can safely assume 1168 there was at least one pass of memtest and none of the passes 1169 found a single faulty byte of RAM. 1170HardwareCorrupted 1171 The amount of RAM/memory in KB, the kernel identifies as 1172 corrupted. 1173AnonHugePages 1174 Non-file backed huge pages mapped into userspace page tables 1175ShmemHugePages 1176 Memory used by shared memory (shmem) and tmpfs allocated 1177 with huge pages 1178ShmemPmdMapped 1179 Shared memory mapped into userspace with huge pages 1180FileHugePages 1181 Memory used for filesystem data (page cache) allocated 1182 with huge pages 1183FilePmdMapped 1184 Page cache mapped into userspace with huge pages 1185CmaTotal 1186 Memory reserved for the Contiguous Memory Allocator (CMA) 1187CmaFree 1188 Free remaining memory in the CMA reserves 1189HugePages_Total, HugePages_Free, HugePages_Rsvd, HugePages_Surp, Hugepagesize, Hugetlb 1190 See Documentation/admin-guide/mm/hugetlbpage.rst. 1191DirectMap4k, DirectMap2M, DirectMap1G 1192 Breakdown of page table sizes used in the kernel's 1193 identity mapping of RAM 1194 1195vmallocinfo 1196~~~~~~~~~~~ 1197 1198Provides information about vmalloced/vmaped areas. One line per area, 1199containing the virtual address range of the area, size in bytes, 1200caller information of the creator, and optional information depending 1201on the kind of area: 1202 1203 ========== =================================================== 1204 pages=nr number of pages 1205 phys=addr if a physical address was specified 1206 ioremap I/O mapping (ioremap() and friends) 1207 vmalloc vmalloc() area 1208 vmap vmap()ed pages 1209 user VM_USERMAP area 1210 vpages buffer for pages pointers was vmalloced (huge area) 1211 N<node>=nr (Only on NUMA kernels) 1212 Number of pages allocated on memory node <node> 1213 ========== =================================================== 1214 1215:: 1216 1217 > cat /proc/vmallocinfo 1218 0xffffc20000000000-0xffffc20000201000 2101248 alloc_large_system_hash+0x204 ... 1219 /0x2c0 pages=512 vmalloc N0=128 N1=128 N2=128 N3=128 1220 0xffffc20000201000-0xffffc20000302000 1052672 alloc_large_system_hash+0x204 ... 1221 /0x2c0 pages=256 vmalloc N0=64 N1=64 N2=64 N3=64 1222 0xffffc20000302000-0xffffc20000304000 8192 acpi_tb_verify_table+0x21/0x4f... 1223 phys=7fee8000 ioremap 1224 0xffffc20000304000-0xffffc20000307000 12288 acpi_tb_verify_table+0x21/0x4f... 1225 phys=7fee7000 ioremap 1226 0xffffc2000031d000-0xffffc2000031f000 8192 init_vdso_vars+0x112/0x210 1227 0xffffc2000031f000-0xffffc2000032b000 49152 cramfs_uncompress_init+0x2e ... 1228 /0x80 pages=11 vmalloc N0=3 N1=3 N2=2 N3=3 1229 0xffffc2000033a000-0xffffc2000033d000 12288 sys_swapon+0x640/0xac0 ... 1230 pages=2 vmalloc N1=2 1231 0xffffc20000347000-0xffffc2000034c000 20480 xt_alloc_table_info+0xfe ... 1232 /0x130 [x_tables] pages=4 vmalloc N0=4 1233 0xffffffffa0000000-0xffffffffa000f000 61440 sys_init_module+0xc27/0x1d00 ... 1234 pages=14 vmalloc N2=14 1235 0xffffffffa000f000-0xffffffffa0014000 20480 sys_init_module+0xc27/0x1d00 ... 1236 pages=4 vmalloc N1=4 1237 0xffffffffa0014000-0xffffffffa0017000 12288 sys_init_module+0xc27/0x1d00 ... 1238 pages=2 vmalloc N1=2 1239 0xffffffffa0017000-0xffffffffa0022000 45056 sys_init_module+0xc27/0x1d00 ... 1240 pages=10 vmalloc N0=10 1241 1242 1243softirqs 1244~~~~~~~~ 1245 1246Provides counts of softirq handlers serviced since boot time, for each CPU. 1247 1248:: 1249 1250 > cat /proc/softirqs 1251 CPU0 CPU1 CPU2 CPU3 1252 HI: 0 0 0 0 1253 TIMER: 27166 27120 27097 27034 1254 NET_TX: 0 0 0 17 1255 NET_RX: 42 0 0 39 1256 BLOCK: 0 0 107 1121 1257 TASKLET: 0 0 0 290 1258 SCHED: 27035 26983 26971 26746 1259 HRTIMER: 0 0 0 0 1260 RCU: 1678 1769 2178 2250 1261 12621.3 Networking info in /proc/net 1263-------------------------------- 1264 1265The subdirectory /proc/net follows the usual pattern. Table 1-8 shows the 1266additional values you get for IP version 6 if you configure the kernel to 1267support this. Table 1-9 lists the files and their meaning. 1268 1269 1270.. table:: Table 1-8: IPv6 info in /proc/net 1271 1272 ========== ===================================================== 1273 File Content 1274 ========== ===================================================== 1275 udp6 UDP sockets (IPv6) 1276 tcp6 TCP sockets (IPv6) 1277 raw6 Raw device statistics (IPv6) 1278 igmp6 IP multicast addresses, which this host joined (IPv6) 1279 if_inet6 List of IPv6 interface addresses 1280 ipv6_route Kernel routing table for IPv6 1281 rt6_stats Global IPv6 routing tables statistics 1282 sockstat6 Socket statistics (IPv6) 1283 snmp6 Snmp data (IPv6) 1284 ========== ===================================================== 1285 1286.. table:: Table 1-9: Network info in /proc/net 1287 1288 ============= ================================================================ 1289 File Content 1290 ============= ================================================================ 1291 arp Kernel ARP table 1292 dev network devices with statistics 1293 dev_mcast the Layer2 multicast groups a device is listening too 1294 (interface index, label, number of references, number of bound 1295 addresses). 1296 dev_stat network device status 1297 ip_fwchains Firewall chain linkage 1298 ip_fwnames Firewall chain names 1299 ip_masq Directory containing the masquerading tables 1300 ip_masquerade Major masquerading table 1301 netstat Network statistics 1302 raw raw device statistics 1303 route Kernel routing table 1304 rpc Directory containing rpc info 1305 rt_cache Routing cache 1306 snmp SNMP data 1307 sockstat Socket statistics 1308 softnet_stat Per-CPU incoming packets queues statistics of online CPUs 1309 tcp TCP sockets 1310 udp UDP sockets 1311 unix UNIX domain sockets 1312 wireless Wireless interface data (Wavelan etc) 1313 igmp IP multicast addresses, which this host joined 1314 psched Global packet scheduler parameters. 1315 netlink List of PF_NETLINK sockets 1316 ip_mr_vifs List of multicast virtual interfaces 1317 ip_mr_cache List of multicast routing cache 1318 ============= ================================================================ 1319 1320You can use this information to see which network devices are available in 1321your system and how much traffic was routed over those devices:: 1322 1323 > cat /proc/net/dev 1324 Inter-|Receive |[... 1325 face |bytes packets errs drop fifo frame compressed multicast|[... 1326 lo: 908188 5596 0 0 0 0 0 0 [... 1327 ppp0:15475140 20721 410 0 0 410 0 0 [... 1328 eth0: 614530 7085 0 0 0 0 0 1 [... 1329 1330 ...] Transmit 1331 ...] bytes packets errs drop fifo colls carrier compressed 1332 ...] 908188 5596 0 0 0 0 0 0 1333 ...] 1375103 17405 0 0 0 0 0 0 1334 ...] 1703981 5535 0 0 0 3 0 0 1335 1336In addition, each Channel Bond interface has its own directory. For 1337example, the bond0 device will have a directory called /proc/net/bond0/. 1338It will contain information that is specific to that bond, such as the 1339current slaves of the bond, the link status of the slaves, and how 1340many times the slaves link has failed. 1341 13421.4 SCSI info 1343------------- 1344 1345If you have a SCSI or ATA host adapter in your system, you'll find a 1346subdirectory named after the driver for this adapter in /proc/scsi. 1347You'll also see a list of all recognized SCSI devices in /proc/scsi:: 1348 1349 >cat /proc/scsi/scsi 1350 Attached devices: 1351 Host: scsi0 Channel: 00 Id: 00 Lun: 00 1352 Vendor: IBM Model: DGHS09U Rev: 03E0 1353 Type: Direct-Access ANSI SCSI revision: 03 1354 Host: scsi0 Channel: 00 Id: 06 Lun: 00 1355 Vendor: PIONEER Model: CD-ROM DR-U06S Rev: 1.04 1356 Type: CD-ROM ANSI SCSI revision: 02 1357 1358 1359The directory named after the driver has one file for each adapter found in 1360the system. These files contain information about the controller, including 1361the used IRQ and the IO address range. The amount of information shown is 1362dependent on the adapter you use. The example shows the output for an Adaptec 1363AHA-2940 SCSI adapter:: 1364 1365 > cat /proc/scsi/aic7xxx/0 1366 1367 Adaptec AIC7xxx driver version: 5.1.19/3.2.4 1368 Compile Options: 1369 TCQ Enabled By Default : Disabled 1370 AIC7XXX_PROC_STATS : Disabled 1371 AIC7XXX_RESET_DELAY : 5 1372 Adapter Configuration: 1373 SCSI Adapter: Adaptec AHA-294X Ultra SCSI host adapter 1374 Ultra Wide Controller 1375 PCI MMAPed I/O Base: 0xeb001000 1376 Adapter SEEPROM Config: SEEPROM found and used. 1377 Adaptec SCSI BIOS: Enabled 1378 IRQ: 10 1379 SCBs: Active 0, Max Active 2, 1380 Allocated 15, HW 16, Page 255 1381 Interrupts: 160328 1382 BIOS Control Word: 0x18b6 1383 Adapter Control Word: 0x005b 1384 Extended Translation: Enabled 1385 Disconnect Enable Flags: 0xffff 1386 Ultra Enable Flags: 0x0001 1387 Tag Queue Enable Flags: 0x0000 1388 Ordered Queue Tag Flags: 0x0000 1389 Default Tag Queue Depth: 8 1390 Tagged Queue By Device array for aic7xxx host instance 0: 1391 {255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255} 1392 Actual queue depth per device for aic7xxx host instance 0: 1393 {1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1} 1394 Statistics: 1395 (scsi0:0:0:0) 1396 Device using Wide/Sync transfers at 40.0 MByte/sec, offset 8 1397 Transinfo settings: current(12/8/1/0), goal(12/8/1/0), user(12/15/1/0) 1398 Total transfers 160151 (74577 reads and 85574 writes) 1399 (scsi0:0:6:0) 1400 Device using Narrow/Sync transfers at 5.0 MByte/sec, offset 15 1401 Transinfo settings: current(50/15/0/0), goal(50/15/0/0), user(50/15/0/0) 1402 Total transfers 0 (0 reads and 0 writes) 1403 1404 14051.5 Parallel port info in /proc/parport 1406--------------------------------------- 1407 1408The directory /proc/parport contains information about the parallel ports of 1409your system. It has one subdirectory for each port, named after the port 1410number (0,1,2,...). 1411 1412These directories contain the four files shown in Table 1-10. 1413 1414 1415.. table:: Table 1-10: Files in /proc/parport 1416 1417 ========= ==================================================================== 1418 File Content 1419 ========= ==================================================================== 1420 autoprobe Any IEEE-1284 device ID information that has been acquired. 1421 devices list of the device drivers using that port. A + will appear by the 1422 name of the device currently using the port (it might not appear 1423 against any). 1424 hardware Parallel port's base address, IRQ line and DMA channel. 1425 irq IRQ that parport is using for that port. This is in a separate 1426 file to allow you to alter it by writing a new value in (IRQ 1427 number or none). 1428 ========= ==================================================================== 1429 14301.6 TTY info in /proc/tty 1431------------------------- 1432 1433Information about the available and actually used tty's can be found in the 1434directory /proc/tty. You'll find entries for drivers and line disciplines in 1435this directory, as shown in Table 1-11. 1436 1437 1438.. table:: Table 1-11: Files in /proc/tty 1439 1440 ============= ============================================== 1441 File Content 1442 ============= ============================================== 1443 drivers list of drivers and their usage 1444 ldiscs registered line disciplines 1445 driver/serial usage statistic and status of single tty lines 1446 ============= ============================================== 1447 1448To see which tty's are currently in use, you can simply look into the file 1449/proc/tty/drivers:: 1450 1451 > cat /proc/tty/drivers 1452 pty_slave /dev/pts 136 0-255 pty:slave 1453 pty_master /dev/ptm 128 0-255 pty:master 1454 pty_slave /dev/ttyp 3 0-255 pty:slave 1455 pty_master /dev/pty 2 0-255 pty:master 1456 serial /dev/cua 5 64-67 serial:callout 1457 serial /dev/ttyS 4 64-67 serial 1458 /dev/tty0 /dev/tty0 4 0 system:vtmaster 1459 /dev/ptmx /dev/ptmx 5 2 system 1460 /dev/console /dev/console 5 1 system:console 1461 /dev/tty /dev/tty 5 0 system:/dev/tty 1462 unknown /dev/tty 4 1-63 console 1463 1464 14651.7 Miscellaneous kernel statistics in /proc/stat 1466------------------------------------------------- 1467 1468Various pieces of information about kernel activity are available in the 1469/proc/stat file. All of the numbers reported in this file are aggregates 1470since the system first booted. For a quick look, simply cat the file:: 1471 1472 > cat /proc/stat 1473 cpu 237902850 368826709 106375398 1873517540 1135548 0 14507935 0 0 0 1474 cpu0 60045249 91891769 26331539 468411416 495718 0 5739640 0 0 0 1475 cpu1 59746288 91759249 26609887 468860630 312281 0 4384817 0 0 0 1476 cpu2 59489247 92985423 26904446 467808813 171668 0 2268998 0 0 0 1477 cpu3 58622065 92190267 26529524 468436680 155879 0 2114478 0 0 0 1478 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> 1479 ctxt 22848221062 1480 btime 1605316999 1481 processes 746787147 1482 procs_running 2 1483 procs_blocked 0 1484 softirq 12121874454 100099120 3938138295 127375644 2795979 187870761 0 173808342 3072582055 52608 224184354 1485 1486The very first "cpu" line aggregates the numbers in all of the other "cpuN" 1487lines. These numbers identify the amount of time the CPU has spent performing 1488different kinds of work. Time units are in USER_HZ (typically hundredths of a 1489second). The meanings of the columns are as follows, from left to right: 1490 1491- user: normal processes executing in user mode 1492- nice: niced processes executing in user mode 1493- system: processes executing in kernel mode 1494- idle: twiddling thumbs 1495- iowait: In a word, iowait stands for waiting for I/O to complete. But there 1496 are several problems: 1497 1498 1. CPU will not wait for I/O to complete, iowait is the time that a task is 1499 waiting for I/O to complete. When CPU goes into idle state for 1500 outstanding task I/O, another task will be scheduled on this CPU. 1501 2. In a multi-core CPU, the task waiting for I/O to complete is not running 1502 on any CPU, so the iowait of each CPU is difficult to calculate. 1503 3. The value of iowait field in /proc/stat will decrease in certain 1504 conditions. 1505 1506 So, the iowait is not reliable by reading from /proc/stat. 1507- irq: servicing interrupts 1508- softirq: servicing softirqs 1509- steal: involuntary wait 1510- guest: running a normal guest 1511- guest_nice: running a niced guest 1512 1513The "intr" line gives counts of interrupts serviced since boot time, for each 1514of the possible system interrupts. The first column is the total of all 1515interrupts serviced including unnumbered architecture specific interrupts; 1516each subsequent column is the total for that particular numbered interrupt. 1517Unnumbered interrupts are not shown, only summed into the total. 1518 1519The "ctxt" line gives the total number of context switches across all CPUs. 1520 1521The "btime" line gives the time at which the system booted, in seconds since 1522the Unix epoch. 1523 1524The "processes" line gives the number of processes and threads created, which 1525includes (but is not limited to) those created by calls to the fork() and 1526clone() system calls. 1527 1528The "procs_running" line gives the total number of threads that are 1529running or ready to run (i.e., the total number of runnable threads). 1530 1531The "procs_blocked" line gives the number of processes currently blocked, 1532waiting for I/O to complete. 1533 1534The "softirq" line gives counts of softirqs serviced since boot time, for each 1535of the possible system softirqs. The first column is the total of all 1536softirqs serviced; each subsequent column is the total for that particular 1537softirq. 1538 1539 15401.8 Ext4 file system parameters 1541------------------------------- 1542 1543Information about mounted ext4 file systems can be found in 1544/proc/fs/ext4. Each mounted filesystem will have a directory in 1545/proc/fs/ext4 based on its device name (i.e., /proc/fs/ext4/hdc or 1546/proc/fs/ext4/sda9 or /proc/fs/ext4/dm-0). The files in each per-device 1547directory are shown in Table 1-12, below. 1548 1549.. table:: Table 1-12: Files in /proc/fs/ext4/<devname> 1550 1551 ============== ========================================================== 1552 File Content 1553 mb_groups details of multiblock allocator buddy cache of free blocks 1554 ============== ========================================================== 1555 15561.9 /proc/consoles 1557------------------- 1558Shows registered system console lines. 1559 1560To see which character device lines are currently used for the system console 1561/dev/console, you may simply look into the file /proc/consoles:: 1562 1563 > cat /proc/consoles 1564 tty0 -WU (ECp) 4:7 1565 ttyS0 -W- (Ep) 4:64 1566 1567The columns are: 1568 1569+--------------------+-------------------------------------------------------+ 1570| device | name of the device | 1571+====================+=======================================================+ 1572| operations | * R = can do read operations | 1573| | * W = can do write operations | 1574| | * U = can do unblank | 1575+--------------------+-------------------------------------------------------+ 1576| flags | * E = it is enabled | 1577| | * C = it is preferred console | 1578| | * B = it is primary boot console | 1579| | * p = it is used for printk buffer | 1580| | * b = it is not a TTY but a Braille device | 1581| | * a = it is safe to use when cpu is offline | 1582+--------------------+-------------------------------------------------------+ 1583| major:minor | major and minor number of the device separated by a | 1584| | colon | 1585+--------------------+-------------------------------------------------------+ 1586 1587Summary 1588------- 1589 1590The /proc file system serves information about the running system. It not only 1591allows access to process data but also allows you to request the kernel status 1592by reading files in the hierarchy. 1593 1594The directory structure of /proc reflects the types of information and makes 1595it easy, if not obvious, where to look for specific data. 1596 1597Chapter 2: Modifying System Parameters 1598====================================== 1599 1600In This Chapter 1601--------------- 1602 1603* Modifying kernel parameters by writing into files found in /proc/sys 1604* Exploring the files which modify certain parameters 1605* Review of the /proc/sys file tree 1606 1607------------------------------------------------------------------------------ 1608 1609A very interesting part of /proc is the directory /proc/sys. This is not only 1610a source of information, it also allows you to change parameters within the 1611kernel. Be very careful when attempting this. You can optimize your system, 1612but you can also cause it to crash. Never alter kernel parameters on a 1613production system. Set up a development machine and test to make sure that 1614everything works the way you want it to. You may have no alternative but to 1615reboot the machine once an error has been made. 1616 1617To change a value, simply echo the new value into the file. 1618You need to be root to do this. You can create your own boot script 1619to perform this every time your system boots. 1620 1621The files in /proc/sys can be used to fine tune and monitor miscellaneous and 1622general things in the operation of the Linux kernel. Since some of the files 1623can inadvertently disrupt your system, it is advisable to read both 1624documentation and source before actually making adjustments. In any case, be 1625very careful when writing to any of these files. The entries in /proc may 1626change slightly between the 2.1.* and the 2.2 kernel, so if there is any doubt 1627review the kernel documentation in the directory linux/Documentation. 1628This chapter is heavily based on the documentation included in the pre 2.2 1629kernels, and became part of it in version 2.2.1 of the Linux kernel. 1630 1631Please see: Documentation/admin-guide/sysctl/ directory for descriptions of 1632these entries. 1633 1634Summary 1635------- 1636 1637Certain aspects of kernel behavior can be modified at runtime, without the 1638need to recompile the kernel, or even to reboot the system. The files in the 1639/proc/sys tree can not only be read, but also modified. You can use the echo 1640command to write value into these files, thereby changing the default settings 1641of the kernel. 1642 1643 1644Chapter 3: Per-process Parameters 1645================================= 1646 16473.1 /proc/<pid>/oom_adj & /proc/<pid>/oom_score_adj- Adjust the oom-killer score 1648-------------------------------------------------------------------------------- 1649 1650These files can be used to adjust the badness heuristic used to select which 1651process gets killed in out of memory (oom) conditions. 1652 1653The badness heuristic assigns a value to each candidate task ranging from 0 1654(never kill) to 1000 (always kill) to determine which process is targeted. The 1655units are roughly a proportion along that range of allowed memory the process 1656may allocate from based on an estimation of its current memory and swap use. 1657For example, if a task is using all allowed memory, its badness score will be 16581000. If it is using half of its allowed memory, its score will be 500. 1659 1660The amount of "allowed" memory depends on the context in which the oom killer 1661was called. If it is due to the memory assigned to the allocating task's cpuset 1662being exhausted, the allowed memory represents the set of mems assigned to that 1663cpuset. If it is due to a mempolicy's node(s) being exhausted, the allowed 1664memory represents the set of mempolicy nodes. If it is due to a memory 1665limit (or swap limit) being reached, the allowed memory is that configured 1666limit. Finally, if it is due to the entire system being out of memory, the 1667allowed memory represents all allocatable resources. 1668 1669The value of /proc/<pid>/oom_score_adj is added to the badness score before it 1670is used to determine which task to kill. Acceptable values range from -1000 1671(OOM_SCORE_ADJ_MIN) to +1000 (OOM_SCORE_ADJ_MAX). This allows userspace to 1672polarize the preference for oom killing either by always preferring a certain 1673task or completely disabling it. The lowest possible value, -1000, is 1674equivalent to disabling oom killing entirely for that task since it will always 1675report a badness score of 0. 1676 1677Consequently, it is very simple for userspace to define the amount of memory to 1678consider for each task. Setting a /proc/<pid>/oom_score_adj value of +500, for 1679example, is roughly equivalent to allowing the remainder of tasks sharing the 1680same system, cpuset, mempolicy, or memory controller resources to use at least 168150% more memory. A value of -500, on the other hand, would be roughly 1682equivalent to discounting 50% of the task's allowed memory from being considered 1683as scoring against the task. 1684 1685For backwards compatibility with previous kernels, /proc/<pid>/oom_adj may also 1686be used to tune the badness score. Its acceptable values range from -16 1687(OOM_ADJUST_MIN) to +15 (OOM_ADJUST_MAX) and a special value of -17 1688(OOM_DISABLE) to disable oom killing entirely for that task. Its value is 1689scaled linearly with /proc/<pid>/oom_score_adj. 1690 1691The value of /proc/<pid>/oom_score_adj may be reduced no lower than the last 1692value set by a CAP_SYS_RESOURCE process. To reduce the value any lower 1693requires CAP_SYS_RESOURCE. 1694 1695 16963.2 /proc/<pid>/oom_score - Display current oom-killer score 1697------------------------------------------------------------- 1698 1699This file can be used to check the current score used by the oom-killer for 1700any given <pid>. Use it together with /proc/<pid>/oom_score_adj to tune which 1701process should be killed in an out-of-memory situation. 1702 1703Please note that the exported value includes oom_score_adj so it is 1704effectively in range [0,2000]. 1705 1706 17073.3 /proc/<pid>/io - Display the IO accounting fields 1708------------------------------------------------------- 1709 1710This file contains IO statistics for each running process. 1711 1712Example 1713~~~~~~~ 1714 1715:: 1716 1717 test:/tmp # dd if=/dev/zero of=/tmp/test.dat & 1718 [1] 3828 1719 1720 test:/tmp # cat /proc/3828/io 1721 rchar: 323934931 1722 wchar: 323929600 1723 syscr: 632687 1724 syscw: 632675 1725 read_bytes: 0 1726 write_bytes: 323932160 1727 cancelled_write_bytes: 0 1728 1729 1730Description 1731~~~~~~~~~~~ 1732 1733rchar 1734^^^^^ 1735 1736I/O counter: chars read 1737The number of bytes which this task has caused to be read from storage. This 1738is simply the sum of bytes which this process passed to read() and pread(). 1739It includes things like tty IO and it is unaffected by whether or not actual 1740physical disk IO was required (the read might have been satisfied from 1741pagecache). 1742 1743 1744wchar 1745^^^^^ 1746 1747I/O counter: chars written 1748The number of bytes which this task has caused, or shall cause to be written 1749to disk. Similar caveats apply here as with rchar. 1750 1751 1752syscr 1753^^^^^ 1754 1755I/O counter: read syscalls 1756Attempt to count the number of read I/O operations, i.e. syscalls like read() 1757and pread(). 1758 1759 1760syscw 1761^^^^^ 1762 1763I/O counter: write syscalls 1764Attempt to count the number of write I/O operations, i.e. syscalls like 1765write() and pwrite(). 1766 1767 1768read_bytes 1769^^^^^^^^^^ 1770 1771I/O counter: bytes read 1772Attempt to count the number of bytes which this process really did cause to 1773be fetched from the storage layer. Done at the submit_bio() level, so it is 1774accurate for block-backed filesystems. <please add status regarding NFS and 1775CIFS at a later time> 1776 1777 1778write_bytes 1779^^^^^^^^^^^ 1780 1781I/O counter: bytes written 1782Attempt to count the number of bytes which this process caused to be sent to 1783the storage layer. This is done at page-dirtying time. 1784 1785 1786cancelled_write_bytes 1787^^^^^^^^^^^^^^^^^^^^^ 1788 1789The big inaccuracy here is truncate. If a process writes 1MB to a file and 1790then deletes the file, it will in fact perform no writeout. But it will have 1791been accounted as having caused 1MB of write. 1792In other words: The number of bytes which this process caused to not happen, 1793by truncating pagecache. A task can cause "negative" IO too. If this task 1794truncates some dirty pagecache, some IO which another task has been accounted 1795for (in its write_bytes) will not be happening. We _could_ just subtract that 1796from the truncating task's write_bytes, but there is information loss in doing 1797that. 1798 1799 1800.. Note:: 1801 1802 At its current implementation state, this is a bit racy on 32-bit machines: 1803 if process A reads process B's /proc/pid/io while process B is updating one 1804 of those 64-bit counters, process A could see an intermediate result. 1805 1806 1807More information about this can be found within the taskstats documentation in 1808Documentation/accounting. 1809 18103.4 /proc/<pid>/coredump_filter - Core dump filtering settings 1811--------------------------------------------------------------- 1812When a process is dumped, all anonymous memory is written to a core file as 1813long as the size of the core file isn't limited. But sometimes we don't want 1814to dump some memory segments, for example, huge shared memory or DAX. 1815Conversely, sometimes we want to save file-backed memory segments into a core 1816file, not only the individual files. 1817 1818/proc/<pid>/coredump_filter allows you to customize which memory segments 1819will be dumped when the <pid> process is dumped. coredump_filter is a bitmask 1820of memory types. If a bit of the bitmask is set, memory segments of the 1821corresponding memory type are dumped, otherwise they are not dumped. 1822 1823The following 9 memory types are supported: 1824 1825 - (bit 0) anonymous private memory 1826 - (bit 1) anonymous shared memory 1827 - (bit 2) file-backed private memory 1828 - (bit 3) file-backed shared memory 1829 - (bit 4) ELF header pages in file-backed private memory areas (it is 1830 effective only if the bit 2 is cleared) 1831 - (bit 5) hugetlb private memory 1832 - (bit 6) hugetlb shared memory 1833 - (bit 7) DAX private memory 1834 - (bit 8) DAX shared memory 1835 1836 Note that MMIO pages such as frame buffer are never dumped and vDSO pages 1837 are always dumped regardless of the bitmask status. 1838 1839 Note that bits 0-4 don't affect hugetlb or DAX memory. hugetlb memory is 1840 only affected by bit 5-6, and DAX is only affected by bits 7-8. 1841 1842The default value of coredump_filter is 0x33; this means all anonymous memory 1843segments, ELF header pages and hugetlb private memory are dumped. 1844 1845If you don't want to dump all shared memory segments attached to pid 1234, 1846write 0x31 to the process's proc file:: 1847 1848 $ echo 0x31 > /proc/1234/coredump_filter 1849 1850When a new process is created, the process inherits the bitmask status from its 1851parent. It is useful to set up coredump_filter before the program runs. 1852For example:: 1853 1854 $ echo 0x7 > /proc/self/coredump_filter 1855 $ ./some_program 1856 18573.5 /proc/<pid>/mountinfo - Information about mounts 1858-------------------------------------------------------- 1859 1860This file contains lines of the form:: 1861 1862 36 35 98:0 /mnt1 /mnt2 rw,noatime master:1 - ext3 /dev/root rw,errors=continue 1863 (1)(2)(3) (4) (5) (6) (n…m) (m+1)(m+2) (m+3) (m+4) 1864 1865 (1) mount ID: unique identifier of the mount (may be reused after umount) 1866 (2) parent ID: ID of parent (or of self for the top of the mount tree) 1867 (3) major:minor: value of st_dev for files on filesystem 1868 (4) root: root of the mount within the filesystem 1869 (5) mount point: mount point relative to the process's root 1870 (6) mount options: per mount options 1871 (n…m) optional fields: zero or more fields of the form "tag[:value]" 1872 (m+1) separator: marks the end of the optional fields 1873 (m+2) filesystem type: name of filesystem of the form "type[.subtype]" 1874 (m+3) mount source: filesystem specific information or "none" 1875 (m+4) super options: per super block options 1876 1877Parsers should ignore all unrecognised optional fields. Currently the 1878possible optional fields are: 1879 1880================ ============================================================== 1881shared:X mount is shared in peer group X 1882master:X mount is slave to peer group X 1883propagate_from:X mount is slave and receives propagation from peer group X [#]_ 1884unbindable mount is unbindable 1885================ ============================================================== 1886 1887.. [#] X is the closest dominant peer group under the process's root. If 1888 X is the immediate master of the mount, or if there's no dominant peer 1889 group under the same root, then only the "master:X" field is present 1890 and not the "propagate_from:X" field. 1891 1892For more information on mount propagation see: 1893 1894 Documentation/filesystems/sharedsubtree.rst 1895 1896 18973.6 /proc/<pid>/comm & /proc/<pid>/task/<tid>/comm 1898-------------------------------------------------------- 1899These files provide a method to access a task's comm value. It also allows for 1900a task to set its own or one of its thread siblings comm value. The comm value 1901is limited in size compared to the cmdline value, so writing anything longer 1902then the kernel's TASK_COMM_LEN (currently 16 chars) will result in a truncated 1903comm value. 1904 1905 19063.7 /proc/<pid>/task/<tid>/children - Information about task children 1907------------------------------------------------------------------------- 1908This file provides a fast way to retrieve first level children pids 1909of a task pointed by <pid>/<tid> pair. The format is a space separated 1910stream of pids. 1911 1912Note the "first level" here -- if a child has its own children they will 1913not be listed here; one needs to read /proc/<children-pid>/task/<tid>/children 1914to obtain the descendants. 1915 1916Since this interface is intended to be fast and cheap it doesn't 1917guarantee to provide precise results and some children might be 1918skipped, especially if they've exited right after we printed their 1919pids, so one needs to either stop or freeze processes being inspected 1920if precise results are needed. 1921 1922 19233.8 /proc/<pid>/fdinfo/<fd> - Information about opened file 1924--------------------------------------------------------------- 1925This file provides information associated with an opened file. The regular 1926files have at least four fields -- 'pos', 'flags', 'mnt_id' and 'ino'. 1927The 'pos' represents the current offset of the opened file in decimal 1928form [see lseek(2) for details], 'flags' denotes the octal O_xxx mask the 1929file has been created with [see open(2) for details] and 'mnt_id' represents 1930mount ID of the file system containing the opened file [see 3.5 1931/proc/<pid>/mountinfo for details]. 'ino' represents the inode number of 1932the file. 1933 1934A typical output is:: 1935 1936 pos: 0 1937 flags: 0100002 1938 mnt_id: 19 1939 ino: 63107 1940 1941All locks associated with a file descriptor are shown in its fdinfo too:: 1942 1943 lock: 1: FLOCK ADVISORY WRITE 359 00:13:11691 0 EOF 1944 1945The files such as eventfd, fsnotify, signalfd, epoll among the regular pos/flags 1946pair provide additional information particular to the objects they represent. 1947 1948Eventfd files 1949~~~~~~~~~~~~~ 1950 1951:: 1952 1953 pos: 0 1954 flags: 04002 1955 mnt_id: 9 1956 ino: 63107 1957 eventfd-count: 5a 1958 1959where 'eventfd-count' is hex value of a counter. 1960 1961Signalfd files 1962~~~~~~~~~~~~~~ 1963 1964:: 1965 1966 pos: 0 1967 flags: 04002 1968 mnt_id: 9 1969 ino: 63107 1970 sigmask: 0000000000000200 1971 1972where 'sigmask' is hex value of the signal mask associated 1973with a file. 1974 1975Epoll files 1976~~~~~~~~~~~ 1977 1978:: 1979 1980 pos: 0 1981 flags: 02 1982 mnt_id: 9 1983 ino: 63107 1984 tfd: 5 events: 1d data: ffffffffffffffff pos:0 ino:61af sdev:7 1985 1986where 'tfd' is a target file descriptor number in decimal form, 1987'events' is events mask being watched and the 'data' is data 1988associated with a target [see epoll(7) for more details]. 1989 1990The 'pos' is current offset of the target file in decimal form 1991[see lseek(2)], 'ino' and 'sdev' are inode and device numbers 1992where target file resides, all in hex format. 1993 1994Fsnotify files 1995~~~~~~~~~~~~~~ 1996For inotify files the format is the following:: 1997 1998 pos: 0 1999 flags: 02000000 2000 mnt_id: 9 2001 ino: 63107 2002 inotify wd:3 ino:9e7e sdev:800013 mask:800afce ignored_mask:0 fhandle-bytes:8 fhandle-type:1 f_handle:7e9e0000640d1b6d 2003 2004where 'wd' is a watch descriptor in decimal form, i.e. a target file 2005descriptor number, 'ino' and 'sdev' are inode and device where the 2006target file resides and the 'mask' is the mask of events, all in hex 2007form [see inotify(7) for more details]. 2008 2009If the kernel was built with exportfs support, the path to the target 2010file is encoded as a file handle. The file handle is provided by three 2011fields 'fhandle-bytes', 'fhandle-type' and 'f_handle', all in hex 2012format. 2013 2014If the kernel is built without exportfs support the file handle won't be 2015printed out. 2016 2017If there is no inotify mark attached yet the 'inotify' line will be omitted. 2018 2019For fanotify files the format is:: 2020 2021 pos: 0 2022 flags: 02 2023 mnt_id: 9 2024 ino: 63107 2025 fanotify flags:10 event-flags:0 2026 fanotify mnt_id:12 mflags:40 mask:38 ignored_mask:40000003 2027 fanotify ino:4f969 sdev:800013 mflags:0 mask:3b ignored_mask:40000000 fhandle-bytes:8 fhandle-type:1 f_handle:69f90400c275b5b4 2028 2029where fanotify 'flags' and 'event-flags' are values used in fanotify_init 2030call, 'mnt_id' is the mount point identifier, 'mflags' is the value of 2031flags associated with mark which are tracked separately from events 2032mask. 'ino' and 'sdev' are target inode and device, 'mask' is the events 2033mask and 'ignored_mask' is the mask of events which are to be ignored. 2034All are in hex format. Incorporation of 'mflags', 'mask' and 'ignored_mask' 2035provide information about flags and mask used in fanotify_mark 2036call [see fsnotify manpage for details]. 2037 2038While the first three lines are mandatory and always printed, the rest is 2039optional and may be omitted if no marks created yet. 2040 2041Timerfd files 2042~~~~~~~~~~~~~ 2043 2044:: 2045 2046 pos: 0 2047 flags: 02 2048 mnt_id: 9 2049 ino: 63107 2050 clockid: 0 2051 ticks: 0 2052 settime flags: 01 2053 it_value: (0, 49406829) 2054 it_interval: (1, 0) 2055 2056where 'clockid' is the clock type and 'ticks' is the number of the timer expirations 2057that have occurred [see timerfd_create(2) for details]. 'settime flags' are 2058flags in octal form been used to setup the timer [see timerfd_settime(2) for 2059details]. 'it_value' is remaining time until the timer expiration. 2060'it_interval' is the interval for the timer. Note the timer might be set up 2061with TIMER_ABSTIME option which will be shown in 'settime flags', but 'it_value' 2062still exhibits timer's remaining time. 2063 2064DMA Buffer files 2065~~~~~~~~~~~~~~~~ 2066 2067:: 2068 2069 pos: 0 2070 flags: 04002 2071 mnt_id: 9 2072 ino: 63107 2073 size: 32768 2074 count: 2 2075 exp_name: system-heap 2076 2077where 'size' is the size of the DMA buffer in bytes. 'count' is the file count of 2078the DMA buffer file. 'exp_name' is the name of the DMA buffer exporter. 2079 20803.9 /proc/<pid>/map_files - Information about memory mapped files 2081--------------------------------------------------------------------- 2082This directory contains symbolic links which represent memory mapped files 2083the process is maintaining. Example output:: 2084 2085 | lr-------- 1 root root 64 Jan 27 11:24 333c600000-333c620000 -> /usr/lib64/ld-2.18.so 2086 | lr-------- 1 root root 64 Jan 27 11:24 333c81f000-333c820000 -> /usr/lib64/ld-2.18.so 2087 | lr-------- 1 root root 64 Jan 27 11:24 333c820000-333c821000 -> /usr/lib64/ld-2.18.so 2088 | ... 2089 | lr-------- 1 root root 64 Jan 27 11:24 35d0421000-35d0422000 -> /usr/lib64/libselinux.so.1 2090 | lr-------- 1 root root 64 Jan 27 11:24 400000-41a000 -> /usr/bin/ls 2091 2092The name of a link represents the virtual memory bounds of a mapping, i.e. 2093vm_area_struct::vm_start-vm_area_struct::vm_end. 2094 2095The main purpose of the map_files is to retrieve a set of memory mapped 2096files in a fast way instead of parsing /proc/<pid>/maps or 2097/proc/<pid>/smaps, both of which contain many more records. At the same 2098time one can open(2) mappings from the listings of two processes and 2099comparing their inode numbers to figure out which anonymous memory areas 2100are actually shared. 2101 21023.10 /proc/<pid>/timerslack_ns - Task timerslack value 2103--------------------------------------------------------- 2104This file provides the value of the task's timerslack value in nanoseconds. 2105This value specifies an amount of time that normal timers may be deferred 2106in order to coalesce timers and avoid unnecessary wakeups. 2107 2108This allows a task's interactivity vs power consumption tradeoff to be 2109adjusted. 2110 2111Writing 0 to the file will set the task's timerslack to the default value. 2112 2113Valid values are from 0 - ULLONG_MAX 2114 2115An application setting the value must have PTRACE_MODE_ATTACH_FSCREDS level 2116permissions on the task specified to change its timerslack_ns value. 2117 21183.11 /proc/<pid>/patch_state - Livepatch patch operation state 2119----------------------------------------------------------------- 2120When CONFIG_LIVEPATCH is enabled, this file displays the value of the 2121patch state for the task. 2122 2123A value of '-1' indicates that no patch is in transition. 2124 2125A value of '0' indicates that a patch is in transition and the task is 2126unpatched. If the patch is being enabled, then the task hasn't been 2127patched yet. If the patch is being disabled, then the task has already 2128been unpatched. 2129 2130A value of '1' indicates that a patch is in transition and the task is 2131patched. If the patch is being enabled, then the task has already been 2132patched. If the patch is being disabled, then the task hasn't been 2133unpatched yet. 2134 21353.12 /proc/<pid>/arch_status - task architecture specific status 2136------------------------------------------------------------------- 2137When CONFIG_PROC_PID_ARCH_STATUS is enabled, this file displays the 2138architecture specific status of the task. 2139 2140Example 2141~~~~~~~ 2142 2143:: 2144 2145 $ cat /proc/6753/arch_status 2146 AVX512_elapsed_ms: 8 2147 2148Description 2149~~~~~~~~~~~ 2150 2151x86 specific entries 2152~~~~~~~~~~~~~~~~~~~~~ 2153 2154AVX512_elapsed_ms 2155^^^^^^^^^^^^^^^^^^ 2156 2157 If AVX512 is supported on the machine, this entry shows the milliseconds 2158 elapsed since the last time AVX512 usage was recorded. The recording 2159 happens on a best effort basis when a task is scheduled out. This means 2160 that the value depends on two factors: 2161 2162 1) The time which the task spent on the CPU without being scheduled 2163 out. With CPU isolation and a single runnable task this can take 2164 several seconds. 2165 2166 2) The time since the task was scheduled out last. Depending on the 2167 reason for being scheduled out (time slice exhausted, syscall ...) 2168 this can be arbitrary long time. 2169 2170 As a consequence the value cannot be considered precise and authoritative 2171 information. The application which uses this information has to be aware 2172 of the overall scenario on the system in order to determine whether a 2173 task is a real AVX512 user or not. Precise information can be obtained 2174 with performance counters. 2175 2176 A special value of '-1' indicates that no AVX512 usage was recorded, thus 2177 the task is unlikely an AVX512 user, but depends on the workload and the 2178 scheduling scenario, it also could be a false negative mentioned above. 2179 21803.13 /proc/<pid>/fd - List of symlinks to open files 2181------------------------------------------------------- 2182This directory contains symbolic links which represent open files 2183the process is maintaining. Example output:: 2184 2185 lr-x------ 1 root root 64 Sep 20 17:53 0 -> /dev/null 2186 l-wx------ 1 root root 64 Sep 20 17:53 1 -> /dev/null 2187 lrwx------ 1 root root 64 Sep 20 17:53 10 -> 'socket:[12539]' 2188 lrwx------ 1 root root 64 Sep 20 17:53 11 -> 'socket:[12540]' 2189 lrwx------ 1 root root 64 Sep 20 17:53 12 -> 'socket:[12542]' 2190 2191The number of open files for the process is stored in 'size' member 2192of stat() output for /proc/<pid>/fd for fast access. 2193------------------------------------------------------- 2194 2195 2196Chapter 4: Configuring procfs 2197============================= 2198 21994.1 Mount options 2200--------------------- 2201 2202The following mount options are supported: 2203 2204 ========= ======================================================== 2205 hidepid= Set /proc/<pid>/ access mode. 2206 gid= Set the group authorized to learn processes information. 2207 subset= Show only the specified subset of procfs. 2208 ========= ======================================================== 2209 2210hidepid=off or hidepid=0 means classic mode - everybody may access all 2211/proc/<pid>/ directories (default). 2212 2213hidepid=noaccess or hidepid=1 means users may not access any /proc/<pid>/ 2214directories but their own. Sensitive files like cmdline, sched*, status are now 2215protected against other users. This makes it impossible to learn whether any 2216user runs specific program (given the program doesn't reveal itself by its 2217behaviour). As an additional bonus, as /proc/<pid>/cmdline is unaccessible for 2218other users, poorly written programs passing sensitive information via program 2219arguments are now protected against local eavesdroppers. 2220 2221hidepid=invisible or hidepid=2 means hidepid=1 plus all /proc/<pid>/ will be 2222fully invisible to other users. It doesn't mean that it hides a fact whether a 2223process with a specific pid value exists (it can be learned by other means, e.g. 2224by "kill -0 $PID"), but it hides process' uid and gid, which may be learned by 2225stat()'ing /proc/<pid>/ otherwise. It greatly complicates an intruder's task of 2226gathering information about running processes, whether some daemon runs with 2227elevated privileges, whether other user runs some sensitive program, whether 2228other users run any program at all, etc. 2229 2230hidepid=ptraceable or hidepid=4 means that procfs should only contain 2231/proc/<pid>/ directories that the caller can ptrace. 2232 2233gid= defines a group authorized to learn processes information otherwise 2234prohibited by hidepid=. If you use some daemon like identd which needs to learn 2235information about processes information, just add identd to this group. 2236 2237subset=pid hides all top level files and directories in the procfs that 2238are not related to tasks. 2239 2240Chapter 5: Filesystem behavior 2241============================== 2242 2243Originally, before the advent of pid namespace, procfs was a global file 2244system. It means that there was only one procfs instance in the system. 2245 2246When pid namespace was added, a separate procfs instance was mounted in 2247each pid namespace. So, procfs mount options are global among all 2248mountpoints within the same namespace:: 2249 2250 # grep ^proc /proc/mounts 2251 proc /proc proc rw,relatime,hidepid=2 0 0 2252 2253 # strace -e mount mount -o hidepid=1 -t proc proc /tmp/proc 2254 mount("proc", "/tmp/proc", "proc", 0, "hidepid=1") = 0 2255 +++ exited with 0 +++ 2256 2257 # grep ^proc /proc/mounts 2258 proc /proc proc rw,relatime,hidepid=2 0 0 2259 proc /tmp/proc proc rw,relatime,hidepid=2 0 0 2260 2261and only after remounting procfs mount options will change at all 2262mountpoints:: 2263 2264 # mount -o remount,hidepid=1 -t proc proc /tmp/proc 2265 2266 # grep ^proc /proc/mounts 2267 proc /proc proc rw,relatime,hidepid=1 0 0 2268 proc /tmp/proc proc rw,relatime,hidepid=1 0 0 2269 2270This behavior is different from the behavior of other filesystems. 2271 2272The new procfs behavior is more like other filesystems. Each procfs mount 2273creates a new procfs instance. Mount options affect own procfs instance. 2274It means that it became possible to have several procfs instances 2275displaying tasks with different filtering options in one pid namespace:: 2276 2277 # mount -o hidepid=invisible -t proc proc /proc 2278 # mount -o hidepid=noaccess -t proc proc /tmp/proc 2279 # grep ^proc /proc/mounts 2280 proc /proc proc rw,relatime,hidepid=invisible 0 0 2281 proc /tmp/proc proc rw,relatime,hidepid=noaccess 0 0 2282