1.. SPDX-License-Identifier: GPL-2.0 2 3==================== 4The /proc Filesystem 5==================== 6 7===================== ======================================= ================ 8/proc/sys Terrehon Bowden <terrehon@pacbell.net>, October 7 1999 9 Bodo Bauer <bb@ricochet.net> 102.4.x update Jorge Nerin <comandante@zaralinux.com> November 14 2000 11move /proc/sys Shen Feng <shen@cn.fujitsu.com> April 1 2009 12fixes/update part 1.1 Stefani Seibold <stefani@seibold.net> June 9 2009 13===================== ======================================= ================ 14 15 16 17.. Table of Contents 18 19 0 Preface 20 0.1 Introduction/Credits 21 0.2 Legal Stuff 22 23 1 Collecting System Information 24 1.1 Process-Specific Subdirectories 25 1.2 Kernel data 26 1.3 IDE devices in /proc/ide 27 1.4 Networking info in /proc/net 28 1.5 SCSI info 29 1.6 Parallel port info in /proc/parport 30 1.7 TTY info in /proc/tty 31 1.8 Miscellaneous kernel statistics in /proc/stat 32 1.9 Ext4 file system parameters 33 34 2 Modifying System Parameters 35 36 3 Per-Process Parameters 37 3.1 /proc/<pid>/oom_adj & /proc/<pid>/oom_score_adj - Adjust the oom-killer 38 score 39 3.2 /proc/<pid>/oom_score - Display current oom-killer score 40 3.3 /proc/<pid>/io - Display the IO accounting fields 41 3.4 /proc/<pid>/coredump_filter - Core dump filtering settings 42 3.5 /proc/<pid>/mountinfo - Information about mounts 43 3.6 /proc/<pid>/comm & /proc/<pid>/task/<tid>/comm 44 3.7 /proc/<pid>/task/<tid>/children - Information about task children 45 3.8 /proc/<pid>/fdinfo/<fd> - Information about opened file 46 3.9 /proc/<pid>/map_files - Information about memory mapped files 47 3.10 /proc/<pid>/timerslack_ns - Task timerslack value 48 3.11 /proc/<pid>/patch_state - Livepatch patch operation state 49 3.12 /proc/<pid>/arch_status - Task architecture specific information 50 51 4 Configuring procfs 52 4.1 Mount options 53 54 5 Filesystem behavior 55 56Preface 57======= 58 590.1 Introduction/Credits 60------------------------ 61 62This documentation is part of a soon (or so we hope) to be released book on 63the SuSE Linux distribution. As there is no complete documentation for the 64/proc file system and we've used many freely available sources to write these 65chapters, it seems only fair to give the work back to the Linux community. 66This work is based on the 2.2.* kernel version and the upcoming 2.4.*. I'm 67afraid it's still far from complete, but we hope it will be useful. As far as 68we know, it is the first 'all-in-one' document about the /proc file system. It 69is focused on the Intel x86 hardware, so if you are looking for PPC, ARM, 70SPARC, AXP, etc., features, you probably won't find what you are looking for. 71It also only covers IPv4 networking, not IPv6 nor other protocols - sorry. But 72additions and patches are welcome and will be added to this document if you 73mail them to Bodo. 74 75We'd like to thank Alan Cox, Rik van Riel, and Alexey Kuznetsov and a lot of 76other people for help compiling this documentation. We'd also like to extend a 77special thank you to Andi Kleen for documentation, which we relied on heavily 78to create this document, as well as the additional information he provided. 79Thanks to everybody else who contributed source or docs to the Linux kernel 80and helped create a great piece of software... :) 81 82If you have any comments, corrections or additions, please don't hesitate to 83contact Bodo Bauer at bb@ricochet.net. We'll be happy to add them to this 84document. 85 86The latest version of this document is available online at 87http://tldp.org/LDP/Linux-Filesystem-Hierarchy/html/proc.html 88 89If the above direction does not works for you, you could try the kernel 90mailing list at linux-kernel@vger.kernel.org and/or try to reach me at 91comandante@zaralinux.com. 92 930.2 Legal Stuff 94--------------- 95 96We don't guarantee the correctness of this document, and if you come to us 97complaining about how you screwed up your system because of incorrect 98documentation, we won't feel responsible... 99 100Chapter 1: Collecting System Information 101======================================== 102 103In This Chapter 104--------------- 105* Investigating the properties of the pseudo file system /proc and its 106 ability to provide information on the running Linux system 107* Examining /proc's structure 108* Uncovering various information about the kernel and the processes running 109 on the system 110 111------------------------------------------------------------------------------ 112 113The proc file system acts as an interface to internal data structures in the 114kernel. It can be used to obtain information about the system and to change 115certain kernel parameters at runtime (sysctl). 116 117First, we'll take a look at the read-only parts of /proc. In Chapter 2, we 118show you how you can use /proc/sys to change settings. 119 1201.1 Process-Specific Subdirectories 121----------------------------------- 122 123The directory /proc contains (among other things) one subdirectory for each 124process running on the system, which is named after the process ID (PID). 125 126The link 'self' points to the process reading the file system. Each process 127subdirectory has the entries listed in Table 1-1. 128 129Note that an open file descriptor to /proc/<pid> or to any of its 130contained files or subdirectories does not prevent <pid> being reused 131for some other process in the event that <pid> exits. Operations on 132open /proc/<pid> file descriptors corresponding to dead processes 133never act on any new process that the kernel may, through chance, have 134also assigned the process ID <pid>. Instead, operations on these FDs 135usually fail with ESRCH. 136 137.. table:: Table 1-1: Process specific entries in /proc 138 139 ============= =============================================================== 140 File Content 141 ============= =============================================================== 142 clear_refs Clears page referenced bits shown in smaps output 143 cmdline Command line arguments 144 cpu Current and last cpu in which it was executed (2.4)(smp) 145 cwd Link to the current working directory 146 environ Values of environment variables 147 exe Link to the executable of this process 148 fd Directory, which contains all file descriptors 149 maps Memory maps to executables and library files (2.4) 150 mem Memory held by this process 151 root Link to the root directory of this process 152 stat Process status 153 statm Process memory status information 154 status Process status in human readable form 155 wchan Present with CONFIG_KALLSYMS=y: it shows the kernel function 156 symbol the task is blocked in - or "0" if not blocked. 157 pagemap Page table 158 stack Report full stack trace, enable via CONFIG_STACKTRACE 159 smaps An extension based on maps, showing the memory consumption of 160 each mapping and flags associated with it 161 smaps_rollup Accumulated smaps stats for all mappings of the process. This 162 can be derived from smaps, but is faster and more convenient 163 numa_maps An extension based on maps, showing the memory locality and 164 binding policy as well as mem usage (in pages) of each mapping. 165 ============= =============================================================== 166 167For example, to get the status information of a process, all you have to do is 168read the file /proc/PID/status:: 169 170 >cat /proc/self/status 171 Name: cat 172 State: R (running) 173 Tgid: 5452 174 Pid: 5452 175 PPid: 743 176 TracerPid: 0 (2.4) 177 Uid: 501 501 501 501 178 Gid: 100 100 100 100 179 FDSize: 256 180 Groups: 100 14 16 181 VmPeak: 5004 kB 182 VmSize: 5004 kB 183 VmLck: 0 kB 184 VmHWM: 476 kB 185 VmRSS: 476 kB 186 RssAnon: 352 kB 187 RssFile: 120 kB 188 RssShmem: 4 kB 189 VmData: 156 kB 190 VmStk: 88 kB 191 VmExe: 68 kB 192 VmLib: 1412 kB 193 VmPTE: 20 kb 194 VmSwap: 0 kB 195 HugetlbPages: 0 kB 196 CoreDumping: 0 197 THP_enabled: 1 198 Threads: 1 199 SigQ: 0/28578 200 SigPnd: 0000000000000000 201 ShdPnd: 0000000000000000 202 SigBlk: 0000000000000000 203 SigIgn: 0000000000000000 204 SigCgt: 0000000000000000 205 CapInh: 00000000fffffeff 206 CapPrm: 0000000000000000 207 CapEff: 0000000000000000 208 CapBnd: ffffffffffffffff 209 CapAmb: 0000000000000000 210 NoNewPrivs: 0 211 Seccomp: 0 212 Speculation_Store_Bypass: thread vulnerable 213 SpeculationIndirectBranch: conditional enabled 214 voluntary_ctxt_switches: 0 215 nonvoluntary_ctxt_switches: 1 216 217This shows you nearly the same information you would get if you viewed it with 218the ps command. In fact, ps uses the proc file system to obtain its 219information. But you get a more detailed view of the process by reading the 220file /proc/PID/status. It fields are described in table 1-2. 221 222The statm file contains more detailed information about the process 223memory usage. Its seven fields are explained in Table 1-3. The stat file 224contains detailed information about the process itself. Its fields are 225explained in Table 1-4. 226 227(for SMP CONFIG users) 228 229For making accounting scalable, RSS related information are handled in an 230asynchronous manner and the value may not be very precise. To see a precise 231snapshot of a moment, you can see /proc/<pid>/smaps file and scan page table. 232It's slow but very precise. 233 234.. table:: Table 1-2: Contents of the status files (as of 4.19) 235 236 ========================== =================================================== 237 Field Content 238 ========================== =================================================== 239 Name filename of the executable 240 Umask file mode creation mask 241 State state (R is running, S is sleeping, D is sleeping 242 in an uninterruptible wait, Z is zombie, 243 T is traced or stopped) 244 Tgid thread group ID 245 Ngid NUMA group ID (0 if none) 246 Pid process id 247 PPid process id of the parent process 248 TracerPid PID of process tracing this process (0 if not) 249 Uid Real, effective, saved set, and file system UIDs 250 Gid Real, effective, saved set, and file system GIDs 251 FDSize number of file descriptor slots currently allocated 252 Groups supplementary group list 253 NStgid descendant namespace thread group ID hierarchy 254 NSpid descendant namespace process ID hierarchy 255 NSpgid descendant namespace process group ID hierarchy 256 NSsid descendant namespace session ID hierarchy 257 VmPeak peak virtual memory size 258 VmSize total program size 259 VmLck locked memory size 260 VmPin pinned memory size 261 VmHWM peak resident set size ("high water mark") 262 VmRSS size of memory portions. It contains the three 263 following parts 264 (VmRSS = RssAnon + RssFile + RssShmem) 265 RssAnon size of resident anonymous memory 266 RssFile size of resident file mappings 267 RssShmem size of resident shmem memory (includes SysV shm, 268 mapping of tmpfs and shared anonymous mappings) 269 VmData size of private data segments 270 VmStk size of stack segments 271 VmExe size of text segment 272 VmLib size of shared library code 273 VmPTE size of page table entries 274 VmSwap amount of swap used by anonymous private data 275 (shmem swap usage is not included) 276 HugetlbPages size of hugetlb memory portions 277 CoreDumping process's memory is currently being dumped 278 (killing the process may lead to a corrupted core) 279 THP_enabled process is allowed to use THP (returns 0 when 280 PR_SET_THP_DISABLE is set on the process 281 Threads number of threads 282 SigQ number of signals queued/max. number for queue 283 SigPnd bitmap of pending signals for the thread 284 ShdPnd bitmap of shared pending signals for the process 285 SigBlk bitmap of blocked signals 286 SigIgn bitmap of ignored signals 287 SigCgt bitmap of caught signals 288 CapInh bitmap of inheritable capabilities 289 CapPrm bitmap of permitted capabilities 290 CapEff bitmap of effective capabilities 291 CapBnd bitmap of capabilities bounding set 292 CapAmb bitmap of ambient capabilities 293 NoNewPrivs no_new_privs, like prctl(PR_GET_NO_NEW_PRIV, ...) 294 Seccomp seccomp mode, like prctl(PR_GET_SECCOMP, ...) 295 Speculation_Store_Bypass speculative store bypass mitigation status 296 SpeculationIndirectBranch indirect branch speculation mode 297 Cpus_allowed mask of CPUs on which this process may run 298 Cpus_allowed_list Same as previous, but in "list format" 299 Mems_allowed mask of memory nodes allowed to this process 300 Mems_allowed_list Same as previous, but in "list format" 301 voluntary_ctxt_switches number of voluntary context switches 302 nonvoluntary_ctxt_switches number of non voluntary context switches 303 ========================== =================================================== 304 305 306.. table:: Table 1-3: Contents of the statm files (as of 2.6.8-rc3) 307 308 ======== =============================== ============================== 309 Field Content 310 ======== =============================== ============================== 311 size total program size (pages) (same as VmSize in status) 312 resident size of memory portions (pages) (same as VmRSS in status) 313 shared number of pages that are shared (i.e. backed by a file, same 314 as RssFile+RssShmem in status) 315 trs number of pages that are 'code' (not including libs; broken, 316 includes data segment) 317 lrs number of pages of library (always 0 on 2.6) 318 drs number of pages of data/stack (including libs; broken, 319 includes library text) 320 dt number of dirty pages (always 0 on 2.6) 321 ======== =============================== ============================== 322 323 324.. table:: Table 1-4: Contents of the stat files (as of 2.6.30-rc7) 325 326 ============= =============================================================== 327 Field Content 328 ============= =============================================================== 329 pid process id 330 tcomm filename of the executable 331 state state (R is running, S is sleeping, D is sleeping in an 332 uninterruptible wait, Z is zombie, T is traced or stopped) 333 ppid process id of the parent process 334 pgrp pgrp of the process 335 sid session id 336 tty_nr tty the process uses 337 tty_pgrp pgrp of the tty 338 flags task flags 339 min_flt number of minor faults 340 cmin_flt number of minor faults with child's 341 maj_flt number of major faults 342 cmaj_flt number of major faults with child's 343 utime user mode jiffies 344 stime kernel mode jiffies 345 cutime user mode jiffies with child's 346 cstime kernel mode jiffies with child's 347 priority priority level 348 nice nice level 349 num_threads number of threads 350 it_real_value (obsolete, always 0) 351 start_time time the process started after system boot 352 vsize virtual memory size 353 rss resident set memory size 354 rsslim current limit in bytes on the rss 355 start_code address above which program text can run 356 end_code address below which program text can run 357 start_stack address of the start of the main process stack 358 esp current value of ESP 359 eip current value of EIP 360 pending bitmap of pending signals 361 blocked bitmap of blocked signals 362 sigign bitmap of ignored signals 363 sigcatch bitmap of caught signals 364 0 (place holder, used to be the wchan address, 365 use /proc/PID/wchan instead) 366 0 (place holder) 367 0 (place holder) 368 exit_signal signal to send to parent thread on exit 369 task_cpu which CPU the task is scheduled on 370 rt_priority realtime priority 371 policy scheduling policy (man sched_setscheduler) 372 blkio_ticks time spent waiting for block IO 373 gtime guest time of the task in jiffies 374 cgtime guest time of the task children in jiffies 375 start_data address above which program data+bss is placed 376 end_data address below which program data+bss is placed 377 start_brk address above which program heap can be expanded with brk() 378 arg_start address above which program command line is placed 379 arg_end address below which program command line is placed 380 env_start address above which program environment is placed 381 env_end address below which program environment is placed 382 exit_code the thread's exit_code in the form reported by the waitpid 383 system call 384 ============= =============================================================== 385 386The /proc/PID/maps file contains the currently mapped memory regions and 387their access permissions. 388 389The format is:: 390 391 address perms offset dev inode pathname 392 393 08048000-08049000 r-xp 00000000 03:00 8312 /opt/test 394 08049000-0804a000 rw-p 00001000 03:00 8312 /opt/test 395 0804a000-0806b000 rw-p 00000000 00:00 0 [heap] 396 a7cb1000-a7cb2000 ---p 00000000 00:00 0 397 a7cb2000-a7eb2000 rw-p 00000000 00:00 0 398 a7eb2000-a7eb3000 ---p 00000000 00:00 0 399 a7eb3000-a7ed5000 rw-p 00000000 00:00 0 400 a7ed5000-a8008000 r-xp 00000000 03:00 4222 /lib/libc.so.6 401 a8008000-a800a000 r--p 00133000 03:00 4222 /lib/libc.so.6 402 a800a000-a800b000 rw-p 00135000 03:00 4222 /lib/libc.so.6 403 a800b000-a800e000 rw-p 00000000 00:00 0 404 a800e000-a8022000 r-xp 00000000 03:00 14462 /lib/libpthread.so.0 405 a8022000-a8023000 r--p 00013000 03:00 14462 /lib/libpthread.so.0 406 a8023000-a8024000 rw-p 00014000 03:00 14462 /lib/libpthread.so.0 407 a8024000-a8027000 rw-p 00000000 00:00 0 408 a8027000-a8043000 r-xp 00000000 03:00 8317 /lib/ld-linux.so.2 409 a8043000-a8044000 r--p 0001b000 03:00 8317 /lib/ld-linux.so.2 410 a8044000-a8045000 rw-p 0001c000 03:00 8317 /lib/ld-linux.so.2 411 aff35000-aff4a000 rw-p 00000000 00:00 0 [stack] 412 ffffe000-fffff000 r-xp 00000000 00:00 0 [vdso] 413 414where "address" is the address space in the process that it occupies, "perms" 415is a set of permissions:: 416 417 r = read 418 w = write 419 x = execute 420 s = shared 421 p = private (copy on write) 422 423"offset" is the offset into the mapping, "dev" is the device (major:minor), and 424"inode" is the inode on that device. 0 indicates that no inode is associated 425with the memory region, as the case would be with BSS (uninitialized data). 426The "pathname" shows the name associated file for this mapping. If the mapping 427is not associated with a file: 428 429 ======= ==================================== 430 [heap] the heap of the program 431 [stack] the stack of the main process 432 [vdso] the "virtual dynamic shared object", 433 the kernel system call handler 434 ======= ==================================== 435 436 or if empty, the mapping is anonymous. 437 438The /proc/PID/smaps is an extension based on maps, showing the memory 439consumption for each of the process's mappings. For each mapping (aka Virtual 440Memory Area, or VMA) there is a series of lines such as the following:: 441 442 08048000-080bc000 r-xp 00000000 03:02 13130 /bin/bash 443 444 Size: 1084 kB 445 KernelPageSize: 4 kB 446 MMUPageSize: 4 kB 447 Rss: 892 kB 448 Pss: 374 kB 449 Shared_Clean: 892 kB 450 Shared_Dirty: 0 kB 451 Private_Clean: 0 kB 452 Private_Dirty: 0 kB 453 Referenced: 892 kB 454 Anonymous: 0 kB 455 LazyFree: 0 kB 456 AnonHugePages: 0 kB 457 ShmemPmdMapped: 0 kB 458 Shared_Hugetlb: 0 kB 459 Private_Hugetlb: 0 kB 460 Swap: 0 kB 461 SwapPss: 0 kB 462 KernelPageSize: 4 kB 463 MMUPageSize: 4 kB 464 Locked: 0 kB 465 THPeligible: 0 466 VmFlags: rd ex mr mw me dw 467 468The first of these lines shows the same information as is displayed for the 469mapping in /proc/PID/maps. Following lines show the size of the mapping 470(size); the size of each page allocated when backing a VMA (KernelPageSize), 471which is usually the same as the size in the page table entries; the page size 472used by the MMU when backing a VMA (in most cases, the same as KernelPageSize); 473the amount of the mapping that is currently resident in RAM (RSS); the 474process' proportional share of this mapping (PSS); and the number of clean and 475dirty shared and private pages in the mapping. 476 477The "proportional set size" (PSS) of a process is the count of pages it has 478in memory, where each page is divided by the number of processes sharing it. 479So if a process has 1000 pages all to itself, and 1000 shared with one other 480process, its PSS will be 1500. 481 482Note that even a page which is part of a MAP_SHARED mapping, but has only 483a single pte mapped, i.e. is currently used by only one process, is accounted 484as private and not as shared. 485 486"Referenced" indicates the amount of memory currently marked as referenced or 487accessed. 488 489"Anonymous" shows the amount of memory that does not belong to any file. Even 490a mapping associated with a file may contain anonymous pages: when MAP_PRIVATE 491and a page is modified, the file page is replaced by a private anonymous copy. 492 493"LazyFree" shows the amount of memory which is marked by madvise(MADV_FREE). 494The memory isn't freed immediately with madvise(). It's freed in memory 495pressure if the memory is clean. Please note that the printed value might 496be lower than the real value due to optimizations used in the current 497implementation. If this is not desirable please file a bug report. 498 499"AnonHugePages" shows the ammount of memory backed by transparent hugepage. 500 501"ShmemPmdMapped" shows the ammount of shared (shmem/tmpfs) memory backed by 502huge pages. 503 504"Shared_Hugetlb" and "Private_Hugetlb" show the ammounts of memory backed by 505hugetlbfs page which is *not* counted in "RSS" or "PSS" field for historical 506reasons. And these are not included in {Shared,Private}_{Clean,Dirty} field. 507 508"Swap" shows how much would-be-anonymous memory is also used, but out on swap. 509 510For shmem mappings, "Swap" includes also the size of the mapped (and not 511replaced by copy-on-write) part of the underlying shmem object out on swap. 512"SwapPss" shows proportional swap share of this mapping. Unlike "Swap", this 513does not take into account swapped out page of underlying shmem objects. 514"Locked" indicates whether the mapping is locked in memory or not. 515"THPeligible" indicates whether the mapping is eligible for allocating THP 516pages - 1 if true, 0 otherwise. It just shows the current status. 517 518"VmFlags" field deserves a separate description. This member represents the 519kernel flags associated with the particular virtual memory area in two letter 520encoded manner. The codes are the following: 521 522 == ======================================= 523 rd readable 524 wr writeable 525 ex executable 526 sh shared 527 mr may read 528 mw may write 529 me may execute 530 ms may share 531 gd stack segment growns down 532 pf pure PFN range 533 dw disabled write to the mapped file 534 lo pages are locked in memory 535 io memory mapped I/O area 536 sr sequential read advise provided 537 rr random read advise provided 538 dc do not copy area on fork 539 de do not expand area on remapping 540 ac area is accountable 541 nr swap space is not reserved for the area 542 ht area uses huge tlb pages 543 ar architecture specific flag 544 dd do not include area into core dump 545 sd soft dirty flag 546 mm mixed map area 547 hg huge page advise flag 548 nh no huge page advise flag 549 mg mergable advise flag 550 bt arm64 BTI guarded page 551 mt arm64 MTE allocation tags are enabled 552 == ======================================= 553 554Note that there is no guarantee that every flag and associated mnemonic will 555be present in all further kernel releases. Things get changed, the flags may 556be vanished or the reverse -- new added. Interpretation of their meaning 557might change in future as well. So each consumer of these flags has to 558follow each specific kernel version for the exact semantic. 559 560This file is only present if the CONFIG_MMU kernel configuration option is 561enabled. 562 563Note: reading /proc/PID/maps or /proc/PID/smaps is inherently racy (consistent 564output can be achieved only in the single read call). 565 566This typically manifests when doing partial reads of these files while the 567memory map is being modified. Despite the races, we do provide the following 568guarantees: 569 5701) The mapped addresses never go backwards, which implies no two 571 regions will ever overlap. 5722) If there is something at a given vaddr during the entirety of the 573 life of the smaps/maps walk, there will be some output for it. 574 575The /proc/PID/smaps_rollup file includes the same fields as /proc/PID/smaps, 576but their values are the sums of the corresponding values for all mappings of 577the process. Additionally, it contains these fields: 578 579- Pss_Anon 580- Pss_File 581- Pss_Shmem 582 583They represent the proportional shares of anonymous, file, and shmem pages, as 584described for smaps above. These fields are omitted in smaps since each 585mapping identifies the type (anon, file, or shmem) of all pages it contains. 586Thus all information in smaps_rollup can be derived from smaps, but at a 587significantly higher cost. 588 589The /proc/PID/clear_refs is used to reset the PG_Referenced and ACCESSED/YOUNG 590bits on both physical and virtual pages associated with a process, and the 591soft-dirty bit on pte (see Documentation/admin-guide/mm/soft-dirty.rst 592for details). 593To clear the bits for all the pages associated with the process:: 594 595 > echo 1 > /proc/PID/clear_refs 596 597To clear the bits for the anonymous pages associated with the process:: 598 599 > echo 2 > /proc/PID/clear_refs 600 601To clear the bits for the file mapped pages associated with the process:: 602 603 > echo 3 > /proc/PID/clear_refs 604 605To clear the soft-dirty bit:: 606 607 > echo 4 > /proc/PID/clear_refs 608 609To reset the peak resident set size ("high water mark") to the process's 610current value:: 611 612 > echo 5 > /proc/PID/clear_refs 613 614Any other value written to /proc/PID/clear_refs will have no effect. 615 616The /proc/pid/pagemap gives the PFN, which can be used to find the pageflags 617using /proc/kpageflags and number of times a page is mapped using 618/proc/kpagecount. For detailed explanation, see 619Documentation/admin-guide/mm/pagemap.rst. 620 621The /proc/pid/numa_maps is an extension based on maps, showing the memory 622locality and binding policy, as well as the memory usage (in pages) of 623each mapping. The output follows a general format where mapping details get 624summarized separated by blank spaces, one mapping per each file line:: 625 626 address policy mapping details 627 628 00400000 default file=/usr/local/bin/app mapped=1 active=0 N3=1 kernelpagesize_kB=4 629 00600000 default file=/usr/local/bin/app anon=1 dirty=1 N3=1 kernelpagesize_kB=4 630 3206000000 default file=/lib64/ld-2.12.so mapped=26 mapmax=6 N0=24 N3=2 kernelpagesize_kB=4 631 320621f000 default file=/lib64/ld-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4 632 3206220000 default file=/lib64/ld-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4 633 3206221000 default anon=1 dirty=1 N3=1 kernelpagesize_kB=4 634 3206800000 default file=/lib64/libc-2.12.so mapped=59 mapmax=21 active=55 N0=41 N3=18 kernelpagesize_kB=4 635 320698b000 default file=/lib64/libc-2.12.so 636 3206b8a000 default file=/lib64/libc-2.12.so anon=2 dirty=2 N3=2 kernelpagesize_kB=4 637 3206b8e000 default file=/lib64/libc-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4 638 3206b8f000 default anon=3 dirty=3 active=1 N3=3 kernelpagesize_kB=4 639 7f4dc10a2000 default anon=3 dirty=3 N3=3 kernelpagesize_kB=4 640 7f4dc10b4000 default anon=2 dirty=2 active=1 N3=2 kernelpagesize_kB=4 641 7f4dc1200000 default file=/anon_hugepage\040(deleted) huge anon=1 dirty=1 N3=1 kernelpagesize_kB=2048 642 7fff335f0000 default stack anon=3 dirty=3 N3=3 kernelpagesize_kB=4 643 7fff3369d000 default mapped=1 mapmax=35 active=0 N3=1 kernelpagesize_kB=4 644 645Where: 646 647"address" is the starting address for the mapping; 648 649"policy" reports the NUMA memory policy set for the mapping (see Documentation/admin-guide/mm/numa_memory_policy.rst); 650 651"mapping details" summarizes mapping data such as mapping type, page usage counters, 652node locality page counters (N0 == node0, N1 == node1, ...) and the kernel page 653size, in KB, that is backing the mapping up. 654 6551.2 Kernel data 656--------------- 657 658Similar to the process entries, the kernel data files give information about 659the running kernel. The files used to obtain this information are contained in 660/proc and are listed in Table 1-5. Not all of these will be present in your 661system. It depends on the kernel configuration and the loaded modules, which 662files are there, and which are missing. 663 664.. table:: Table 1-5: Kernel info in /proc 665 666 ============ =============================================================== 667 File Content 668 ============ =============================================================== 669 apm Advanced power management info 670 buddyinfo Kernel memory allocator information (see text) (2.5) 671 bus Directory containing bus specific information 672 cmdline Kernel command line 673 cpuinfo Info about the CPU 674 devices Available devices (block and character) 675 dma Used DMS channels 676 filesystems Supported filesystems 677 driver Various drivers grouped here, currently rtc (2.4) 678 execdomains Execdomains, related to security (2.4) 679 fb Frame Buffer devices (2.4) 680 fs File system parameters, currently nfs/exports (2.4) 681 ide Directory containing info about the IDE subsystem 682 interrupts Interrupt usage 683 iomem Memory map (2.4) 684 ioports I/O port usage 685 irq Masks for irq to cpu affinity (2.4)(smp?) 686 isapnp ISA PnP (Plug&Play) Info (2.4) 687 kcore Kernel core image (can be ELF or A.OUT(deprecated in 2.4)) 688 kmsg Kernel messages 689 ksyms Kernel symbol table 690 loadavg Load average of last 1, 5 & 15 minutes; 691 number of processes currently runnable (running or on ready queue); 692 total number of processes in system; 693 last pid created. 694 locks Kernel locks 695 meminfo Memory info 696 misc Miscellaneous 697 modules List of loaded modules 698 mounts Mounted filesystems 699 net Networking info (see text) 700 pagetypeinfo Additional page allocator information (see text) (2.5) 701 partitions Table of partitions known to the system 702 pci Deprecated info of PCI bus (new way -> /proc/bus/pci/, 703 decoupled by lspci (2.4) 704 rtc Real time clock 705 scsi SCSI info (see text) 706 slabinfo Slab pool info 707 softirqs softirq usage 708 stat Overall statistics 709 swaps Swap space utilization 710 sys See chapter 2 711 sysvipc Info of SysVIPC Resources (msg, sem, shm) (2.4) 712 tty Info of tty drivers 713 uptime Wall clock since boot, combined idle time of all cpus 714 version Kernel version 715 video bttv info of video resources (2.4) 716 vmallocinfo Show vmalloced areas 717 ============ =============================================================== 718 719You can, for example, check which interrupts are currently in use and what 720they are used for by looking in the file /proc/interrupts:: 721 722 > cat /proc/interrupts 723 CPU0 724 0: 8728810 XT-PIC timer 725 1: 895 XT-PIC keyboard 726 2: 0 XT-PIC cascade 727 3: 531695 XT-PIC aha152x 728 4: 2014133 XT-PIC serial 729 5: 44401 XT-PIC pcnet_cs 730 8: 2 XT-PIC rtc 731 11: 8 XT-PIC i82365 732 12: 182918 XT-PIC PS/2 Mouse 733 13: 1 XT-PIC fpu 734 14: 1232265 XT-PIC ide0 735 15: 7 XT-PIC ide1 736 NMI: 0 737 738In 2.4.* a couple of lines where added to this file LOC & ERR (this time is the 739output of a SMP machine):: 740 741 > cat /proc/interrupts 742 743 CPU0 CPU1 744 0: 1243498 1214548 IO-APIC-edge timer 745 1: 8949 8958 IO-APIC-edge keyboard 746 2: 0 0 XT-PIC cascade 747 5: 11286 10161 IO-APIC-edge soundblaster 748 8: 1 0 IO-APIC-edge rtc 749 9: 27422 27407 IO-APIC-edge 3c503 750 12: 113645 113873 IO-APIC-edge PS/2 Mouse 751 13: 0 0 XT-PIC fpu 752 14: 22491 24012 IO-APIC-edge ide0 753 15: 2183 2415 IO-APIC-edge ide1 754 17: 30564 30414 IO-APIC-level eth0 755 18: 177 164 IO-APIC-level bttv 756 NMI: 2457961 2457959 757 LOC: 2457882 2457881 758 ERR: 2155 759 760NMI is incremented in this case because every timer interrupt generates a NMI 761(Non Maskable Interrupt) which is used by the NMI Watchdog to detect lockups. 762 763LOC is the local interrupt counter of the internal APIC of every CPU. 764 765ERR is incremented in the case of errors in the IO-APIC bus (the bus that 766connects the CPUs in a SMP system. This means that an error has been detected, 767the IO-APIC automatically retry the transmission, so it should not be a big 768problem, but you should read the SMP-FAQ. 769 770In 2.6.2* /proc/interrupts was expanded again. This time the goal was for 771/proc/interrupts to display every IRQ vector in use by the system, not 772just those considered 'most important'. The new vectors are: 773 774THR 775 interrupt raised when a machine check threshold counter 776 (typically counting ECC corrected errors of memory or cache) exceeds 777 a configurable threshold. Only available on some systems. 778 779TRM 780 a thermal event interrupt occurs when a temperature threshold 781 has been exceeded for the CPU. This interrupt may also be generated 782 when the temperature drops back to normal. 783 784SPU 785 a spurious interrupt is some interrupt that was raised then lowered 786 by some IO device before it could be fully processed by the APIC. Hence 787 the APIC sees the interrupt but does not know what device it came from. 788 For this case the APIC will generate the interrupt with a IRQ vector 789 of 0xff. This might also be generated by chipset bugs. 790 791RES, CAL, TLB 792 rescheduling, call and TLB flush interrupts are 793 sent from one CPU to another per the needs of the OS. Typically, 794 their statistics are used by kernel developers and interested users to 795 determine the occurrence of interrupts of the given type. 796 797The above IRQ vectors are displayed only when relevant. For example, 798the threshold vector does not exist on x86_64 platforms. Others are 799suppressed when the system is a uniprocessor. As of this writing, only 800i386 and x86_64 platforms support the new IRQ vector displays. 801 802Of some interest is the introduction of the /proc/irq directory to 2.4. 803It could be used to set IRQ to CPU affinity. This means that you can "hook" an 804IRQ to only one CPU, or to exclude a CPU of handling IRQs. The contents of the 805irq subdir is one subdir for each IRQ, and two files; default_smp_affinity and 806prof_cpu_mask. 807 808For example:: 809 810 > ls /proc/irq/ 811 0 10 12 14 16 18 2 4 6 8 prof_cpu_mask 812 1 11 13 15 17 19 3 5 7 9 default_smp_affinity 813 > ls /proc/irq/0/ 814 smp_affinity 815 816smp_affinity is a bitmask, in which you can specify which CPUs can handle the 817IRQ. You can set it by doing:: 818 819 > echo 1 > /proc/irq/10/smp_affinity 820 821This means that only the first CPU will handle the IRQ, but you can also echo 8225 which means that only the first and third CPU can handle the IRQ. 823 824The contents of each smp_affinity file is the same by default:: 825 826 > cat /proc/irq/0/smp_affinity 827 ffffffff 828 829There is an alternate interface, smp_affinity_list which allows specifying 830a CPU range instead of a bitmask:: 831 832 > cat /proc/irq/0/smp_affinity_list 833 1024-1031 834 835The default_smp_affinity mask applies to all non-active IRQs, which are the 836IRQs which have not yet been allocated/activated, and hence which lack a 837/proc/irq/[0-9]* directory. 838 839The node file on an SMP system shows the node to which the device using the IRQ 840reports itself as being attached. This hardware locality information does not 841include information about any possible driver locality preference. 842 843prof_cpu_mask specifies which CPUs are to be profiled by the system wide 844profiler. Default value is ffffffff (all CPUs if there are only 32 of them). 845 846The way IRQs are routed is handled by the IO-APIC, and it's Round Robin 847between all the CPUs which are allowed to handle it. As usual the kernel has 848more info than you and does a better job than you, so the defaults are the 849best choice for almost everyone. [Note this applies only to those IO-APIC's 850that support "Round Robin" interrupt distribution.] 851 852There are three more important subdirectories in /proc: net, scsi, and sys. 853The general rule is that the contents, or even the existence of these 854directories, depend on your kernel configuration. If SCSI is not enabled, the 855directory scsi may not exist. The same is true with the net, which is there 856only when networking support is present in the running kernel. 857 858The slabinfo file gives information about memory usage at the slab level. 859Linux uses slab pools for memory management above page level in version 2.2. 860Commonly used objects have their own slab pool (such as network buffers, 861directory cache, and so on). 862 863:: 864 865 > cat /proc/buddyinfo 866 867 Node 0, zone DMA 0 4 5 4 4 3 ... 868 Node 0, zone Normal 1 0 0 1 101 8 ... 869 Node 0, zone HighMem 2 0 0 1 1 0 ... 870 871External fragmentation is a problem under some workloads, and buddyinfo is a 872useful tool for helping diagnose these problems. Buddyinfo will give you a 873clue as to how big an area you can safely allocate, or why a previous 874allocation failed. 875 876Each column represents the number of pages of a certain order which are 877available. In this case, there are 0 chunks of 2^0*PAGE_SIZE available in 878ZONE_DMA, 4 chunks of 2^1*PAGE_SIZE in ZONE_DMA, 101 chunks of 2^4*PAGE_SIZE 879available in ZONE_NORMAL, etc... 880 881More information relevant to external fragmentation can be found in 882pagetypeinfo:: 883 884 > cat /proc/pagetypeinfo 885 Page block order: 9 886 Pages per block: 512 887 888 Free pages count per migrate type at order 0 1 2 3 4 5 6 7 8 9 10 889 Node 0, zone DMA, type Unmovable 0 0 0 1 1 1 1 1 1 1 0 890 Node 0, zone DMA, type Reclaimable 0 0 0 0 0 0 0 0 0 0 0 891 Node 0, zone DMA, type Movable 1 1 2 1 2 1 1 0 1 0 2 892 Node 0, zone DMA, type Reserve 0 0 0 0 0 0 0 0 0 1 0 893 Node 0, zone DMA, type Isolate 0 0 0 0 0 0 0 0 0 0 0 894 Node 0, zone DMA32, type Unmovable 103 54 77 1 1 1 11 8 7 1 9 895 Node 0, zone DMA32, type Reclaimable 0 0 2 1 0 0 0 0 1 0 0 896 Node 0, zone DMA32, type Movable 169 152 113 91 77 54 39 13 6 1 452 897 Node 0, zone DMA32, type Reserve 1 2 2 2 2 0 1 1 1 1 0 898 Node 0, zone DMA32, type Isolate 0 0 0 0 0 0 0 0 0 0 0 899 900 Number of blocks type Unmovable Reclaimable Movable Reserve Isolate 901 Node 0, zone DMA 2 0 5 1 0 902 Node 0, zone DMA32 41 6 967 2 0 903 904Fragmentation avoidance in the kernel works by grouping pages of different 905migrate types into the same contiguous regions of memory called page blocks. 906A page block is typically the size of the default hugepage size, e.g. 2MB on 907X86-64. By keeping pages grouped based on their ability to move, the kernel 908can reclaim pages within a page block to satisfy a high-order allocation. 909 910The pagetypinfo begins with information on the size of a page block. It 911then gives the same type of information as buddyinfo except broken down 912by migrate-type and finishes with details on how many page blocks of each 913type exist. 914 915If min_free_kbytes has been tuned correctly (recommendations made by hugeadm 916from libhugetlbfs https://github.com/libhugetlbfs/libhugetlbfs/), one can 917make an estimate of the likely number of huge pages that can be allocated 918at a given point in time. All the "Movable" blocks should be allocatable 919unless memory has been mlock()'d. Some of the Reclaimable blocks should 920also be allocatable although a lot of filesystem metadata may have to be 921reclaimed to achieve this. 922 923 924meminfo 925~~~~~~~ 926 927Provides information about distribution and utilization of memory. This 928varies by architecture and compile options. The following is from a 92916GB PIII, which has highmem enabled. You may not have all of these fields. 930 931:: 932 933 > cat /proc/meminfo 934 935 MemTotal: 16344972 kB 936 MemFree: 13634064 kB 937 MemAvailable: 14836172 kB 938 Buffers: 3656 kB 939 Cached: 1195708 kB 940 SwapCached: 0 kB 941 Active: 891636 kB 942 Inactive: 1077224 kB 943 HighTotal: 15597528 kB 944 HighFree: 13629632 kB 945 LowTotal: 747444 kB 946 LowFree: 4432 kB 947 SwapTotal: 0 kB 948 SwapFree: 0 kB 949 Dirty: 968 kB 950 Writeback: 0 kB 951 AnonPages: 861800 kB 952 Mapped: 280372 kB 953 Shmem: 644 kB 954 KReclaimable: 168048 kB 955 Slab: 284364 kB 956 SReclaimable: 159856 kB 957 SUnreclaim: 124508 kB 958 PageTables: 24448 kB 959 NFS_Unstable: 0 kB 960 Bounce: 0 kB 961 WritebackTmp: 0 kB 962 CommitLimit: 7669796 kB 963 Committed_AS: 100056 kB 964 VmallocTotal: 112216 kB 965 VmallocUsed: 428 kB 966 VmallocChunk: 111088 kB 967 Percpu: 62080 kB 968 HardwareCorrupted: 0 kB 969 AnonHugePages: 49152 kB 970 ShmemHugePages: 0 kB 971 ShmemPmdMapped: 0 kB 972 973MemTotal 974 Total usable RAM (i.e. physical RAM minus a few reserved 975 bits and the kernel binary code) 976MemFree 977 The sum of LowFree+HighFree 978MemAvailable 979 An estimate of how much memory is available for starting new 980 applications, without swapping. Calculated from MemFree, 981 SReclaimable, the size of the file LRU lists, and the low 982 watermarks in each zone. 983 The estimate takes into account that the system needs some 984 page cache to function well, and that not all reclaimable 985 slab will be reclaimable, due to items being in use. The 986 impact of those factors will vary from system to system. 987Buffers 988 Relatively temporary storage for raw disk blocks 989 shouldn't get tremendously large (20MB or so) 990Cached 991 in-memory cache for files read from the disk (the 992 pagecache). Doesn't include SwapCached 993SwapCached 994 Memory that once was swapped out, is swapped back in but 995 still also is in the swapfile (if memory is needed it 996 doesn't need to be swapped out AGAIN because it is already 997 in the swapfile. This saves I/O) 998Active 999 Memory that has been used more recently and usually not 1000 reclaimed unless absolutely necessary. 1001Inactive 1002 Memory which has been less recently used. It is more 1003 eligible to be reclaimed for other purposes 1004HighTotal, HighFree 1005 Highmem is all memory above ~860MB of physical memory. 1006 Highmem areas are for use by userspace programs, or 1007 for the pagecache. The kernel must use tricks to access 1008 this memory, making it slower to access than lowmem. 1009LowTotal, LowFree 1010 Lowmem is memory which can be used for everything that 1011 highmem can be used for, but it is also available for the 1012 kernel's use for its own data structures. Among many 1013 other things, it is where everything from the Slab is 1014 allocated. Bad things happen when you're out of lowmem. 1015SwapTotal 1016 total amount of swap space available 1017SwapFree 1018 Memory which has been evicted from RAM, and is temporarily 1019 on the disk 1020Dirty 1021 Memory which is waiting to get written back to the disk 1022Writeback 1023 Memory which is actively being written back to the disk 1024AnonPages 1025 Non-file backed pages mapped into userspace page tables 1026HardwareCorrupted 1027 The amount of RAM/memory in KB, the kernel identifies as 1028 corrupted. 1029AnonHugePages 1030 Non-file backed huge pages mapped into userspace page tables 1031Mapped 1032 files which have been mmaped, such as libraries 1033Shmem 1034 Total memory used by shared memory (shmem) and tmpfs 1035ShmemHugePages 1036 Memory used by shared memory (shmem) and tmpfs allocated 1037 with huge pages 1038ShmemPmdMapped 1039 Shared memory mapped into userspace with huge pages 1040KReclaimable 1041 Kernel allocations that the kernel will attempt to reclaim 1042 under memory pressure. Includes SReclaimable (below), and other 1043 direct allocations with a shrinker. 1044Slab 1045 in-kernel data structures cache 1046SReclaimable 1047 Part of Slab, that might be reclaimed, such as caches 1048SUnreclaim 1049 Part of Slab, that cannot be reclaimed on memory pressure 1050PageTables 1051 amount of memory dedicated to the lowest level of page 1052 tables. 1053NFS_Unstable 1054 Always zero. Previous counted pages which had been written to 1055 the server, but has not been committed to stable storage. 1056Bounce 1057 Memory used for block device "bounce buffers" 1058WritebackTmp 1059 Memory used by FUSE for temporary writeback buffers 1060CommitLimit 1061 Based on the overcommit ratio ('vm.overcommit_ratio'), 1062 this is the total amount of memory currently available to 1063 be allocated on the system. This limit is only adhered to 1064 if strict overcommit accounting is enabled (mode 2 in 1065 'vm.overcommit_memory'). 1066 1067 The CommitLimit is calculated with the following formula:: 1068 1069 CommitLimit = ([total RAM pages] - [total huge TLB pages]) * 1070 overcommit_ratio / 100 + [total swap pages] 1071 1072 For example, on a system with 1G of physical RAM and 7G 1073 of swap with a `vm.overcommit_ratio` of 30 it would 1074 yield a CommitLimit of 7.3G. 1075 1076 For more details, see the memory overcommit documentation 1077 in vm/overcommit-accounting. 1078Committed_AS 1079 The amount of memory presently allocated on the system. 1080 The committed memory is a sum of all of the memory which 1081 has been allocated by processes, even if it has not been 1082 "used" by them as of yet. A process which malloc()'s 1G 1083 of memory, but only touches 300M of it will show up as 1084 using 1G. This 1G is memory which has been "committed" to 1085 by the VM and can be used at any time by the allocating 1086 application. With strict overcommit enabled on the system 1087 (mode 2 in 'vm.overcommit_memory'), allocations which would 1088 exceed the CommitLimit (detailed above) will not be permitted. 1089 This is useful if one needs to guarantee that processes will 1090 not fail due to lack of memory once that memory has been 1091 successfully allocated. 1092VmallocTotal 1093 total size of vmalloc memory area 1094VmallocUsed 1095 amount of vmalloc area which is used 1096VmallocChunk 1097 largest contiguous block of vmalloc area which is free 1098Percpu 1099 Memory allocated to the percpu allocator used to back percpu 1100 allocations. This stat excludes the cost of metadata. 1101 1102vmallocinfo 1103~~~~~~~~~~~ 1104 1105Provides information about vmalloced/vmaped areas. One line per area, 1106containing the virtual address range of the area, size in bytes, 1107caller information of the creator, and optional information depending 1108on the kind of area: 1109 1110 ========== =================================================== 1111 pages=nr number of pages 1112 phys=addr if a physical address was specified 1113 ioremap I/O mapping (ioremap() and friends) 1114 vmalloc vmalloc() area 1115 vmap vmap()ed pages 1116 user VM_USERMAP area 1117 vpages buffer for pages pointers was vmalloced (huge area) 1118 N<node>=nr (Only on NUMA kernels) 1119 Number of pages allocated on memory node <node> 1120 ========== =================================================== 1121 1122:: 1123 1124 > cat /proc/vmallocinfo 1125 0xffffc20000000000-0xffffc20000201000 2101248 alloc_large_system_hash+0x204 ... 1126 /0x2c0 pages=512 vmalloc N0=128 N1=128 N2=128 N3=128 1127 0xffffc20000201000-0xffffc20000302000 1052672 alloc_large_system_hash+0x204 ... 1128 /0x2c0 pages=256 vmalloc N0=64 N1=64 N2=64 N3=64 1129 0xffffc20000302000-0xffffc20000304000 8192 acpi_tb_verify_table+0x21/0x4f... 1130 phys=7fee8000 ioremap 1131 0xffffc20000304000-0xffffc20000307000 12288 acpi_tb_verify_table+0x21/0x4f... 1132 phys=7fee7000 ioremap 1133 0xffffc2000031d000-0xffffc2000031f000 8192 init_vdso_vars+0x112/0x210 1134 0xffffc2000031f000-0xffffc2000032b000 49152 cramfs_uncompress_init+0x2e ... 1135 /0x80 pages=11 vmalloc N0=3 N1=3 N2=2 N3=3 1136 0xffffc2000033a000-0xffffc2000033d000 12288 sys_swapon+0x640/0xac0 ... 1137 pages=2 vmalloc N1=2 1138 0xffffc20000347000-0xffffc2000034c000 20480 xt_alloc_table_info+0xfe ... 1139 /0x130 [x_tables] pages=4 vmalloc N0=4 1140 0xffffffffa0000000-0xffffffffa000f000 61440 sys_init_module+0xc27/0x1d00 ... 1141 pages=14 vmalloc N2=14 1142 0xffffffffa000f000-0xffffffffa0014000 20480 sys_init_module+0xc27/0x1d00 ... 1143 pages=4 vmalloc N1=4 1144 0xffffffffa0014000-0xffffffffa0017000 12288 sys_init_module+0xc27/0x1d00 ... 1145 pages=2 vmalloc N1=2 1146 0xffffffffa0017000-0xffffffffa0022000 45056 sys_init_module+0xc27/0x1d00 ... 1147 pages=10 vmalloc N0=10 1148 1149 1150softirqs 1151~~~~~~~~ 1152 1153Provides counts of softirq handlers serviced since boot time, for each CPU. 1154 1155:: 1156 1157 > cat /proc/softirqs 1158 CPU0 CPU1 CPU2 CPU3 1159 HI: 0 0 0 0 1160 TIMER: 27166 27120 27097 27034 1161 NET_TX: 0 0 0 17 1162 NET_RX: 42 0 0 39 1163 BLOCK: 0 0 107 1121 1164 TASKLET: 0 0 0 290 1165 SCHED: 27035 26983 26971 26746 1166 HRTIMER: 0 0 0 0 1167 RCU: 1678 1769 2178 2250 1168 1169 11701.3 IDE devices in /proc/ide 1171---------------------------- 1172 1173The subdirectory /proc/ide contains information about all IDE devices of which 1174the kernel is aware. There is one subdirectory for each IDE controller, the 1175file drivers and a link for each IDE device, pointing to the device directory 1176in the controller specific subtree. 1177 1178The file 'drivers' contains general information about the drivers used for the 1179IDE devices:: 1180 1181 > cat /proc/ide/drivers 1182 ide-cdrom version 4.53 1183 ide-disk version 1.08 1184 1185More detailed information can be found in the controller specific 1186subdirectories. These are named ide0, ide1 and so on. Each of these 1187directories contains the files shown in table 1-6. 1188 1189 1190.. table:: Table 1-6: IDE controller info in /proc/ide/ide? 1191 1192 ======= ======================================= 1193 File Content 1194 ======= ======================================= 1195 channel IDE channel (0 or 1) 1196 config Configuration (only for PCI/IDE bridge) 1197 mate Mate name 1198 model Type/Chipset of IDE controller 1199 ======= ======================================= 1200 1201Each device connected to a controller has a separate subdirectory in the 1202controllers directory. The files listed in table 1-7 are contained in these 1203directories. 1204 1205 1206.. table:: Table 1-7: IDE device information 1207 1208 ================ ========================================== 1209 File Content 1210 ================ ========================================== 1211 cache The cache 1212 capacity Capacity of the medium (in 512Byte blocks) 1213 driver driver and version 1214 geometry physical and logical geometry 1215 identify device identify block 1216 media media type 1217 model device identifier 1218 settings device setup 1219 smart_thresholds IDE disk management thresholds 1220 smart_values IDE disk management values 1221 ================ ========================================== 1222 1223The most interesting file is ``settings``. This file contains a nice 1224overview of the drive parameters:: 1225 1226 # cat /proc/ide/ide0/hda/settings 1227 name value min max mode 1228 ---- ----- --- --- ---- 1229 bios_cyl 526 0 65535 rw 1230 bios_head 255 0 255 rw 1231 bios_sect 63 0 63 rw 1232 breada_readahead 4 0 127 rw 1233 bswap 0 0 1 r 1234 file_readahead 72 0 2097151 rw 1235 io_32bit 0 0 3 rw 1236 keepsettings 0 0 1 rw 1237 max_kb_per_request 122 1 127 rw 1238 multcount 0 0 8 rw 1239 nice1 1 0 1 rw 1240 nowerr 0 0 1 rw 1241 pio_mode write-only 0 255 w 1242 slow 0 0 1 rw 1243 unmaskirq 0 0 1 rw 1244 using_dma 0 0 1 rw 1245 1246 12471.4 Networking info in /proc/net 1248-------------------------------- 1249 1250The subdirectory /proc/net follows the usual pattern. Table 1-8 shows the 1251additional values you get for IP version 6 if you configure the kernel to 1252support this. Table 1-9 lists the files and their meaning. 1253 1254 1255.. table:: Table 1-8: IPv6 info in /proc/net 1256 1257 ========== ===================================================== 1258 File Content 1259 ========== ===================================================== 1260 udp6 UDP sockets (IPv6) 1261 tcp6 TCP sockets (IPv6) 1262 raw6 Raw device statistics (IPv6) 1263 igmp6 IP multicast addresses, which this host joined (IPv6) 1264 if_inet6 List of IPv6 interface addresses 1265 ipv6_route Kernel routing table for IPv6 1266 rt6_stats Global IPv6 routing tables statistics 1267 sockstat6 Socket statistics (IPv6) 1268 snmp6 Snmp data (IPv6) 1269 ========== ===================================================== 1270 1271.. table:: Table 1-9: Network info in /proc/net 1272 1273 ============= ================================================================ 1274 File Content 1275 ============= ================================================================ 1276 arp Kernel ARP table 1277 dev network devices with statistics 1278 dev_mcast the Layer2 multicast groups a device is listening too 1279 (interface index, label, number of references, number of bound 1280 addresses). 1281 dev_stat network device status 1282 ip_fwchains Firewall chain linkage 1283 ip_fwnames Firewall chain names 1284 ip_masq Directory containing the masquerading tables 1285 ip_masquerade Major masquerading table 1286 netstat Network statistics 1287 raw raw device statistics 1288 route Kernel routing table 1289 rpc Directory containing rpc info 1290 rt_cache Routing cache 1291 snmp SNMP data 1292 sockstat Socket statistics 1293 tcp TCP sockets 1294 udp UDP sockets 1295 unix UNIX domain sockets 1296 wireless Wireless interface data (Wavelan etc) 1297 igmp IP multicast addresses, which this host joined 1298 psched Global packet scheduler parameters. 1299 netlink List of PF_NETLINK sockets 1300 ip_mr_vifs List of multicast virtual interfaces 1301 ip_mr_cache List of multicast routing cache 1302 ============= ================================================================ 1303 1304You can use this information to see which network devices are available in 1305your system and how much traffic was routed over those devices:: 1306 1307 > cat /proc/net/dev 1308 Inter-|Receive |[... 1309 face |bytes packets errs drop fifo frame compressed multicast|[... 1310 lo: 908188 5596 0 0 0 0 0 0 [... 1311 ppp0:15475140 20721 410 0 0 410 0 0 [... 1312 eth0: 614530 7085 0 0 0 0 0 1 [... 1313 1314 ...] Transmit 1315 ...] bytes packets errs drop fifo colls carrier compressed 1316 ...] 908188 5596 0 0 0 0 0 0 1317 ...] 1375103 17405 0 0 0 0 0 0 1318 ...] 1703981 5535 0 0 0 3 0 0 1319 1320In addition, each Channel Bond interface has its own directory. For 1321example, the bond0 device will have a directory called /proc/net/bond0/. 1322It will contain information that is specific to that bond, such as the 1323current slaves of the bond, the link status of the slaves, and how 1324many times the slaves link has failed. 1325 13261.5 SCSI info 1327------------- 1328 1329If you have a SCSI host adapter in your system, you'll find a subdirectory 1330named after the driver for this adapter in /proc/scsi. You'll also see a list 1331of all recognized SCSI devices in /proc/scsi:: 1332 1333 >cat /proc/scsi/scsi 1334 Attached devices: 1335 Host: scsi0 Channel: 00 Id: 00 Lun: 00 1336 Vendor: IBM Model: DGHS09U Rev: 03E0 1337 Type: Direct-Access ANSI SCSI revision: 03 1338 Host: scsi0 Channel: 00 Id: 06 Lun: 00 1339 Vendor: PIONEER Model: CD-ROM DR-U06S Rev: 1.04 1340 Type: CD-ROM ANSI SCSI revision: 02 1341 1342 1343The directory named after the driver has one file for each adapter found in 1344the system. These files contain information about the controller, including 1345the used IRQ and the IO address range. The amount of information shown is 1346dependent on the adapter you use. The example shows the output for an Adaptec 1347AHA-2940 SCSI adapter:: 1348 1349 > cat /proc/scsi/aic7xxx/0 1350 1351 Adaptec AIC7xxx driver version: 5.1.19/3.2.4 1352 Compile Options: 1353 TCQ Enabled By Default : Disabled 1354 AIC7XXX_PROC_STATS : Disabled 1355 AIC7XXX_RESET_DELAY : 5 1356 Adapter Configuration: 1357 SCSI Adapter: Adaptec AHA-294X Ultra SCSI host adapter 1358 Ultra Wide Controller 1359 PCI MMAPed I/O Base: 0xeb001000 1360 Adapter SEEPROM Config: SEEPROM found and used. 1361 Adaptec SCSI BIOS: Enabled 1362 IRQ: 10 1363 SCBs: Active 0, Max Active 2, 1364 Allocated 15, HW 16, Page 255 1365 Interrupts: 160328 1366 BIOS Control Word: 0x18b6 1367 Adapter Control Word: 0x005b 1368 Extended Translation: Enabled 1369 Disconnect Enable Flags: 0xffff 1370 Ultra Enable Flags: 0x0001 1371 Tag Queue Enable Flags: 0x0000 1372 Ordered Queue Tag Flags: 0x0000 1373 Default Tag Queue Depth: 8 1374 Tagged Queue By Device array for aic7xxx host instance 0: 1375 {255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255} 1376 Actual queue depth per device for aic7xxx host instance 0: 1377 {1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1} 1378 Statistics: 1379 (scsi0:0:0:0) 1380 Device using Wide/Sync transfers at 40.0 MByte/sec, offset 8 1381 Transinfo settings: current(12/8/1/0), goal(12/8/1/0), user(12/15/1/0) 1382 Total transfers 160151 (74577 reads and 85574 writes) 1383 (scsi0:0:6:0) 1384 Device using Narrow/Sync transfers at 5.0 MByte/sec, offset 15 1385 Transinfo settings: current(50/15/0/0), goal(50/15/0/0), user(50/15/0/0) 1386 Total transfers 0 (0 reads and 0 writes) 1387 1388 13891.6 Parallel port info in /proc/parport 1390--------------------------------------- 1391 1392The directory /proc/parport contains information about the parallel ports of 1393your system. It has one subdirectory for each port, named after the port 1394number (0,1,2,...). 1395 1396These directories contain the four files shown in Table 1-10. 1397 1398 1399.. table:: Table 1-10: Files in /proc/parport 1400 1401 ========= ==================================================================== 1402 File Content 1403 ========= ==================================================================== 1404 autoprobe Any IEEE-1284 device ID information that has been acquired. 1405 devices list of the device drivers using that port. A + will appear by the 1406 name of the device currently using the port (it might not appear 1407 against any). 1408 hardware Parallel port's base address, IRQ line and DMA channel. 1409 irq IRQ that parport is using for that port. This is in a separate 1410 file to allow you to alter it by writing a new value in (IRQ 1411 number or none). 1412 ========= ==================================================================== 1413 14141.7 TTY info in /proc/tty 1415------------------------- 1416 1417Information about the available and actually used tty's can be found in the 1418directory /proc/tty. You'll find entries for drivers and line disciplines in 1419this directory, as shown in Table 1-11. 1420 1421 1422.. table:: Table 1-11: Files in /proc/tty 1423 1424 ============= ============================================== 1425 File Content 1426 ============= ============================================== 1427 drivers list of drivers and their usage 1428 ldiscs registered line disciplines 1429 driver/serial usage statistic and status of single tty lines 1430 ============= ============================================== 1431 1432To see which tty's are currently in use, you can simply look into the file 1433/proc/tty/drivers:: 1434 1435 > cat /proc/tty/drivers 1436 pty_slave /dev/pts 136 0-255 pty:slave 1437 pty_master /dev/ptm 128 0-255 pty:master 1438 pty_slave /dev/ttyp 3 0-255 pty:slave 1439 pty_master /dev/pty 2 0-255 pty:master 1440 serial /dev/cua 5 64-67 serial:callout 1441 serial /dev/ttyS 4 64-67 serial 1442 /dev/tty0 /dev/tty0 4 0 system:vtmaster 1443 /dev/ptmx /dev/ptmx 5 2 system 1444 /dev/console /dev/console 5 1 system:console 1445 /dev/tty /dev/tty 5 0 system:/dev/tty 1446 unknown /dev/tty 4 1-63 console 1447 1448 14491.8 Miscellaneous kernel statistics in /proc/stat 1450------------------------------------------------- 1451 1452Various pieces of information about kernel activity are available in the 1453/proc/stat file. All of the numbers reported in this file are aggregates 1454since the system first booted. For a quick look, simply cat the file:: 1455 1456 > cat /proc/stat 1457 cpu 2255 34 2290 22625563 6290 127 456 0 0 0 1458 cpu0 1132 34 1441 11311718 3675 127 438 0 0 0 1459 cpu1 1123 0 849 11313845 2614 0 18 0 0 0 1460 intr 114930548 113199788 3 0 5 263 0 4 [... lots more numbers ...] 1461 ctxt 1990473 1462 btime 1062191376 1463 processes 2915 1464 procs_running 1 1465 procs_blocked 0 1466 softirq 183433 0 21755 12 39 1137 231 21459 2263 1467 1468The very first "cpu" line aggregates the numbers in all of the other "cpuN" 1469lines. These numbers identify the amount of time the CPU has spent performing 1470different kinds of work. Time units are in USER_HZ (typically hundredths of a 1471second). The meanings of the columns are as follows, from left to right: 1472 1473- user: normal processes executing in user mode 1474- nice: niced processes executing in user mode 1475- system: processes executing in kernel mode 1476- idle: twiddling thumbs 1477- iowait: In a word, iowait stands for waiting for I/O to complete. But there 1478 are several problems: 1479 1480 1. CPU will not wait for I/O to complete, iowait is the time that a task is 1481 waiting for I/O to complete. When CPU goes into idle state for 1482 outstanding task I/O, another task will be scheduled on this CPU. 1483 2. In a multi-core CPU, the task waiting for I/O to complete is not running 1484 on any CPU, so the iowait of each CPU is difficult to calculate. 1485 3. The value of iowait field in /proc/stat will decrease in certain 1486 conditions. 1487 1488 So, the iowait is not reliable by reading from /proc/stat. 1489- irq: servicing interrupts 1490- softirq: servicing softirqs 1491- steal: involuntary wait 1492- guest: running a normal guest 1493- guest_nice: running a niced guest 1494 1495The "intr" line gives counts of interrupts serviced since boot time, for each 1496of the possible system interrupts. The first column is the total of all 1497interrupts serviced including unnumbered architecture specific interrupts; 1498each subsequent column is the total for that particular numbered interrupt. 1499Unnumbered interrupts are not shown, only summed into the total. 1500 1501The "ctxt" line gives the total number of context switches across all CPUs. 1502 1503The "btime" line gives the time at which the system booted, in seconds since 1504the Unix epoch. 1505 1506The "processes" line gives the number of processes and threads created, which 1507includes (but is not limited to) those created by calls to the fork() and 1508clone() system calls. 1509 1510The "procs_running" line gives the total number of threads that are 1511running or ready to run (i.e., the total number of runnable threads). 1512 1513The "procs_blocked" line gives the number of processes currently blocked, 1514waiting for I/O to complete. 1515 1516The "softirq" line gives counts of softirqs serviced since boot time, for each 1517of the possible system softirqs. The first column is the total of all 1518softirqs serviced; each subsequent column is the total for that particular 1519softirq. 1520 1521 15221.9 Ext4 file system parameters 1523------------------------------- 1524 1525Information about mounted ext4 file systems can be found in 1526/proc/fs/ext4. Each mounted filesystem will have a directory in 1527/proc/fs/ext4 based on its device name (i.e., /proc/fs/ext4/hdc or 1528/proc/fs/ext4/dm-0). The files in each per-device directory are shown 1529in Table 1-12, below. 1530 1531.. table:: Table 1-12: Files in /proc/fs/ext4/<devname> 1532 1533 ============== ========================================================== 1534 File Content 1535 mb_groups details of multiblock allocator buddy cache of free blocks 1536 ============== ========================================================== 1537 15381.10 /proc/consoles 1539------------------- 1540Shows registered system console lines. 1541 1542To see which character device lines are currently used for the system console 1543/dev/console, you may simply look into the file /proc/consoles:: 1544 1545 > cat /proc/consoles 1546 tty0 -WU (ECp) 4:7 1547 ttyS0 -W- (Ep) 4:64 1548 1549The columns are: 1550 1551+--------------------+-------------------------------------------------------+ 1552| device | name of the device | 1553+====================+=======================================================+ 1554| operations | * R = can do read operations | 1555| | * W = can do write operations | 1556| | * U = can do unblank | 1557+--------------------+-------------------------------------------------------+ 1558| flags | * E = it is enabled | 1559| | * C = it is preferred console | 1560| | * B = it is primary boot console | 1561| | * p = it is used for printk buffer | 1562| | * b = it is not a TTY but a Braille device | 1563| | * a = it is safe to use when cpu is offline | 1564+--------------------+-------------------------------------------------------+ 1565| major:minor | major and minor number of the device separated by a | 1566| | colon | 1567+--------------------+-------------------------------------------------------+ 1568 1569Summary 1570------- 1571 1572The /proc file system serves information about the running system. It not only 1573allows access to process data but also allows you to request the kernel status 1574by reading files in the hierarchy. 1575 1576The directory structure of /proc reflects the types of information and makes 1577it easy, if not obvious, where to look for specific data. 1578 1579Chapter 2: Modifying System Parameters 1580====================================== 1581 1582In This Chapter 1583--------------- 1584 1585* Modifying kernel parameters by writing into files found in /proc/sys 1586* Exploring the files which modify certain parameters 1587* Review of the /proc/sys file tree 1588 1589------------------------------------------------------------------------------ 1590 1591A very interesting part of /proc is the directory /proc/sys. This is not only 1592a source of information, it also allows you to change parameters within the 1593kernel. Be very careful when attempting this. You can optimize your system, 1594but you can also cause it to crash. Never alter kernel parameters on a 1595production system. Set up a development machine and test to make sure that 1596everything works the way you want it to. You may have no alternative but to 1597reboot the machine once an error has been made. 1598 1599To change a value, simply echo the new value into the file. 1600You need to be root to do this. You can create your own boot script 1601to perform this every time your system boots. 1602 1603The files in /proc/sys can be used to fine tune and monitor miscellaneous and 1604general things in the operation of the Linux kernel. Since some of the files 1605can inadvertently disrupt your system, it is advisable to read both 1606documentation and source before actually making adjustments. In any case, be 1607very careful when writing to any of these files. The entries in /proc may 1608change slightly between the 2.1.* and the 2.2 kernel, so if there is any doubt 1609review the kernel documentation in the directory /usr/src/linux/Documentation. 1610This chapter is heavily based on the documentation included in the pre 2.2 1611kernels, and became part of it in version 2.2.1 of the Linux kernel. 1612 1613Please see: Documentation/admin-guide/sysctl/ directory for descriptions of these 1614entries. 1615 1616Summary 1617------- 1618 1619Certain aspects of kernel behavior can be modified at runtime, without the 1620need to recompile the kernel, or even to reboot the system. The files in the 1621/proc/sys tree can not only be read, but also modified. You can use the echo 1622command to write value into these files, thereby changing the default settings 1623of the kernel. 1624 1625 1626Chapter 3: Per-process Parameters 1627================================= 1628 16293.1 /proc/<pid>/oom_adj & /proc/<pid>/oom_score_adj- Adjust the oom-killer score 1630-------------------------------------------------------------------------------- 1631 1632These files can be used to adjust the badness heuristic used to select which 1633process gets killed in out of memory (oom) conditions. 1634 1635The badness heuristic assigns a value to each candidate task ranging from 0 1636(never kill) to 1000 (always kill) to determine which process is targeted. The 1637units are roughly a proportion along that range of allowed memory the process 1638may allocate from based on an estimation of its current memory and swap use. 1639For example, if a task is using all allowed memory, its badness score will be 16401000. If it is using half of its allowed memory, its score will be 500. 1641 1642The amount of "allowed" memory depends on the context in which the oom killer 1643was called. If it is due to the memory assigned to the allocating task's cpuset 1644being exhausted, the allowed memory represents the set of mems assigned to that 1645cpuset. If it is due to a mempolicy's node(s) being exhausted, the allowed 1646memory represents the set of mempolicy nodes. If it is due to a memory 1647limit (or swap limit) being reached, the allowed memory is that configured 1648limit. Finally, if it is due to the entire system being out of memory, the 1649allowed memory represents all allocatable resources. 1650 1651The value of /proc/<pid>/oom_score_adj is added to the badness score before it 1652is used to determine which task to kill. Acceptable values range from -1000 1653(OOM_SCORE_ADJ_MIN) to +1000 (OOM_SCORE_ADJ_MAX). This allows userspace to 1654polarize the preference for oom killing either by always preferring a certain 1655task or completely disabling it. The lowest possible value, -1000, is 1656equivalent to disabling oom killing entirely for that task since it will always 1657report a badness score of 0. 1658 1659Consequently, it is very simple for userspace to define the amount of memory to 1660consider for each task. Setting a /proc/<pid>/oom_score_adj value of +500, for 1661example, is roughly equivalent to allowing the remainder of tasks sharing the 1662same system, cpuset, mempolicy, or memory controller resources to use at least 166350% more memory. A value of -500, on the other hand, would be roughly 1664equivalent to discounting 50% of the task's allowed memory from being considered 1665as scoring against the task. 1666 1667For backwards compatibility with previous kernels, /proc/<pid>/oom_adj may also 1668be used to tune the badness score. Its acceptable values range from -16 1669(OOM_ADJUST_MIN) to +15 (OOM_ADJUST_MAX) and a special value of -17 1670(OOM_DISABLE) to disable oom killing entirely for that task. Its value is 1671scaled linearly with /proc/<pid>/oom_score_adj. 1672 1673The value of /proc/<pid>/oom_score_adj may be reduced no lower than the last 1674value set by a CAP_SYS_RESOURCE process. To reduce the value any lower 1675requires CAP_SYS_RESOURCE. 1676 1677 16783.2 /proc/<pid>/oom_score - Display current oom-killer score 1679------------------------------------------------------------- 1680 1681This file can be used to check the current score used by the oom-killer for 1682any given <pid>. Use it together with /proc/<pid>/oom_score_adj to tune which 1683process should be killed in an out-of-memory situation. 1684 1685Please note that the exported value includes oom_score_adj so it is 1686effectively in range [0,2000]. 1687 1688 16893.3 /proc/<pid>/io - Display the IO accounting fields 1690------------------------------------------------------- 1691 1692This file contains IO statistics for each running process. 1693 1694Example 1695~~~~~~~ 1696 1697:: 1698 1699 test:/tmp # dd if=/dev/zero of=/tmp/test.dat & 1700 [1] 3828 1701 1702 test:/tmp # cat /proc/3828/io 1703 rchar: 323934931 1704 wchar: 323929600 1705 syscr: 632687 1706 syscw: 632675 1707 read_bytes: 0 1708 write_bytes: 323932160 1709 cancelled_write_bytes: 0 1710 1711 1712Description 1713~~~~~~~~~~~ 1714 1715rchar 1716^^^^^ 1717 1718I/O counter: chars read 1719The number of bytes which this task has caused to be read from storage. This 1720is simply the sum of bytes which this process passed to read() and pread(). 1721It includes things like tty IO and it is unaffected by whether or not actual 1722physical disk IO was required (the read might have been satisfied from 1723pagecache). 1724 1725 1726wchar 1727^^^^^ 1728 1729I/O counter: chars written 1730The number of bytes which this task has caused, or shall cause to be written 1731to disk. Similar caveats apply here as with rchar. 1732 1733 1734syscr 1735^^^^^ 1736 1737I/O counter: read syscalls 1738Attempt to count the number of read I/O operations, i.e. syscalls like read() 1739and pread(). 1740 1741 1742syscw 1743^^^^^ 1744 1745I/O counter: write syscalls 1746Attempt to count the number of write I/O operations, i.e. syscalls like 1747write() and pwrite(). 1748 1749 1750read_bytes 1751^^^^^^^^^^ 1752 1753I/O counter: bytes read 1754Attempt to count the number of bytes which this process really did cause to 1755be fetched from the storage layer. Done at the submit_bio() level, so it is 1756accurate for block-backed filesystems. <please add status regarding NFS and 1757CIFS at a later time> 1758 1759 1760write_bytes 1761^^^^^^^^^^^ 1762 1763I/O counter: bytes written 1764Attempt to count the number of bytes which this process caused to be sent to 1765the storage layer. This is done at page-dirtying time. 1766 1767 1768cancelled_write_bytes 1769^^^^^^^^^^^^^^^^^^^^^ 1770 1771The big inaccuracy here is truncate. If a process writes 1MB to a file and 1772then deletes the file, it will in fact perform no writeout. But it will have 1773been accounted as having caused 1MB of write. 1774In other words: The number of bytes which this process caused to not happen, 1775by truncating pagecache. A task can cause "negative" IO too. If this task 1776truncates some dirty pagecache, some IO which another task has been accounted 1777for (in its write_bytes) will not be happening. We _could_ just subtract that 1778from the truncating task's write_bytes, but there is information loss in doing 1779that. 1780 1781 1782.. Note:: 1783 1784 At its current implementation state, this is a bit racy on 32-bit machines: 1785 if process A reads process B's /proc/pid/io while process B is updating one 1786 of those 64-bit counters, process A could see an intermediate result. 1787 1788 1789More information about this can be found within the taskstats documentation in 1790Documentation/accounting. 1791 17923.4 /proc/<pid>/coredump_filter - Core dump filtering settings 1793--------------------------------------------------------------- 1794When a process is dumped, all anonymous memory is written to a core file as 1795long as the size of the core file isn't limited. But sometimes we don't want 1796to dump some memory segments, for example, huge shared memory or DAX. 1797Conversely, sometimes we want to save file-backed memory segments into a core 1798file, not only the individual files. 1799 1800/proc/<pid>/coredump_filter allows you to customize which memory segments 1801will be dumped when the <pid> process is dumped. coredump_filter is a bitmask 1802of memory types. If a bit of the bitmask is set, memory segments of the 1803corresponding memory type are dumped, otherwise they are not dumped. 1804 1805The following 9 memory types are supported: 1806 1807 - (bit 0) anonymous private memory 1808 - (bit 1) anonymous shared memory 1809 - (bit 2) file-backed private memory 1810 - (bit 3) file-backed shared memory 1811 - (bit 4) ELF header pages in file-backed private memory areas (it is 1812 effective only if the bit 2 is cleared) 1813 - (bit 5) hugetlb private memory 1814 - (bit 6) hugetlb shared memory 1815 - (bit 7) DAX private memory 1816 - (bit 8) DAX shared memory 1817 1818 Note that MMIO pages such as frame buffer are never dumped and vDSO pages 1819 are always dumped regardless of the bitmask status. 1820 1821 Note that bits 0-4 don't affect hugetlb or DAX memory. hugetlb memory is 1822 only affected by bit 5-6, and DAX is only affected by bits 7-8. 1823 1824The default value of coredump_filter is 0x33; this means all anonymous memory 1825segments, ELF header pages and hugetlb private memory are dumped. 1826 1827If you don't want to dump all shared memory segments attached to pid 1234, 1828write 0x31 to the process's proc file:: 1829 1830 $ echo 0x31 > /proc/1234/coredump_filter 1831 1832When a new process is created, the process inherits the bitmask status from its 1833parent. It is useful to set up coredump_filter before the program runs. 1834For example:: 1835 1836 $ echo 0x7 > /proc/self/coredump_filter 1837 $ ./some_program 1838 18393.5 /proc/<pid>/mountinfo - Information about mounts 1840-------------------------------------------------------- 1841 1842This file contains lines of the form:: 1843 1844 36 35 98:0 /mnt1 /mnt2 rw,noatime master:1 - ext3 /dev/root rw,errors=continue 1845 (1)(2)(3) (4) (5) (6) (7) (8) (9) (10) (11) 1846 1847 (1) mount ID: unique identifier of the mount (may be reused after umount) 1848 (2) parent ID: ID of parent (or of self for the top of the mount tree) 1849 (3) major:minor: value of st_dev for files on filesystem 1850 (4) root: root of the mount within the filesystem 1851 (5) mount point: mount point relative to the process's root 1852 (6) mount options: per mount options 1853 (7) optional fields: zero or more fields of the form "tag[:value]" 1854 (8) separator: marks the end of the optional fields 1855 (9) filesystem type: name of filesystem of the form "type[.subtype]" 1856 (10) mount source: filesystem specific information or "none" 1857 (11) super options: per super block options 1858 1859Parsers should ignore all unrecognised optional fields. Currently the 1860possible optional fields are: 1861 1862================ ============================================================== 1863shared:X mount is shared in peer group X 1864master:X mount is slave to peer group X 1865propagate_from:X mount is slave and receives propagation from peer group X [#]_ 1866unbindable mount is unbindable 1867================ ============================================================== 1868 1869.. [#] X is the closest dominant peer group under the process's root. If 1870 X is the immediate master of the mount, or if there's no dominant peer 1871 group under the same root, then only the "master:X" field is present 1872 and not the "propagate_from:X" field. 1873 1874For more information on mount propagation see: 1875 1876 Documentation/filesystems/sharedsubtree.rst 1877 1878 18793.6 /proc/<pid>/comm & /proc/<pid>/task/<tid>/comm 1880-------------------------------------------------------- 1881These files provide a method to access a task's comm value. It also allows for 1882a task to set its own or one of its thread siblings comm value. The comm value 1883is limited in size compared to the cmdline value, so writing anything longer 1884then the kernel's TASK_COMM_LEN (currently 16 chars) will result in a truncated 1885comm value. 1886 1887 18883.7 /proc/<pid>/task/<tid>/children - Information about task children 1889------------------------------------------------------------------------- 1890This file provides a fast way to retrieve first level children pids 1891of a task pointed by <pid>/<tid> pair. The format is a space separated 1892stream of pids. 1893 1894Note the "first level" here -- if a child has its own children they will 1895not be listed here; one needs to read /proc/<children-pid>/task/<tid>/children 1896to obtain the descendants. 1897 1898Since this interface is intended to be fast and cheap it doesn't 1899guarantee to provide precise results and some children might be 1900skipped, especially if they've exited right after we printed their 1901pids, so one needs to either stop or freeze processes being inspected 1902if precise results are needed. 1903 1904 19053.8 /proc/<pid>/fdinfo/<fd> - Information about opened file 1906--------------------------------------------------------------- 1907This file provides information associated with an opened file. The regular 1908files have at least three fields -- 'pos', 'flags' and 'mnt_id'. The 'pos' 1909represents the current offset of the opened file in decimal form [see lseek(2) 1910for details], 'flags' denotes the octal O_xxx mask the file has been 1911created with [see open(2) for details] and 'mnt_id' represents mount ID of 1912the file system containing the opened file [see 3.5 /proc/<pid>/mountinfo 1913for details]. 1914 1915A typical output is:: 1916 1917 pos: 0 1918 flags: 0100002 1919 mnt_id: 19 1920 1921All locks associated with a file descriptor are shown in its fdinfo too:: 1922 1923 lock: 1: FLOCK ADVISORY WRITE 359 00:13:11691 0 EOF 1924 1925The files such as eventfd, fsnotify, signalfd, epoll among the regular pos/flags 1926pair provide additional information particular to the objects they represent. 1927 1928Eventfd files 1929~~~~~~~~~~~~~ 1930 1931:: 1932 1933 pos: 0 1934 flags: 04002 1935 mnt_id: 9 1936 eventfd-count: 5a 1937 1938where 'eventfd-count' is hex value of a counter. 1939 1940Signalfd files 1941~~~~~~~~~~~~~~ 1942 1943:: 1944 1945 pos: 0 1946 flags: 04002 1947 mnt_id: 9 1948 sigmask: 0000000000000200 1949 1950where 'sigmask' is hex value of the signal mask associated 1951with a file. 1952 1953Epoll files 1954~~~~~~~~~~~ 1955 1956:: 1957 1958 pos: 0 1959 flags: 02 1960 mnt_id: 9 1961 tfd: 5 events: 1d data: ffffffffffffffff pos:0 ino:61af sdev:7 1962 1963where 'tfd' is a target file descriptor number in decimal form, 1964'events' is events mask being watched and the 'data' is data 1965associated with a target [see epoll(7) for more details]. 1966 1967The 'pos' is current offset of the target file in decimal form 1968[see lseek(2)], 'ino' and 'sdev' are inode and device numbers 1969where target file resides, all in hex format. 1970 1971Fsnotify files 1972~~~~~~~~~~~~~~ 1973For inotify files the format is the following:: 1974 1975 pos: 0 1976 flags: 02000000 1977 inotify wd:3 ino:9e7e sdev:800013 mask:800afce ignored_mask:0 fhandle-bytes:8 fhandle-type:1 f_handle:7e9e0000640d1b6d 1978 1979where 'wd' is a watch descriptor in decimal form, i.e. a target file 1980descriptor number, 'ino' and 'sdev' are inode and device where the 1981target file resides and the 'mask' is the mask of events, all in hex 1982form [see inotify(7) for more details]. 1983 1984If the kernel was built with exportfs support, the path to the target 1985file is encoded as a file handle. The file handle is provided by three 1986fields 'fhandle-bytes', 'fhandle-type' and 'f_handle', all in hex 1987format. 1988 1989If the kernel is built without exportfs support the file handle won't be 1990printed out. 1991 1992If there is no inotify mark attached yet the 'inotify' line will be omitted. 1993 1994For fanotify files the format is:: 1995 1996 pos: 0 1997 flags: 02 1998 mnt_id: 9 1999 fanotify flags:10 event-flags:0 2000 fanotify mnt_id:12 mflags:40 mask:38 ignored_mask:40000003 2001 fanotify ino:4f969 sdev:800013 mflags:0 mask:3b ignored_mask:40000000 fhandle-bytes:8 fhandle-type:1 f_handle:69f90400c275b5b4 2002 2003where fanotify 'flags' and 'event-flags' are values used in fanotify_init 2004call, 'mnt_id' is the mount point identifier, 'mflags' is the value of 2005flags associated with mark which are tracked separately from events 2006mask. 'ino' and 'sdev' are target inode and device, 'mask' is the events 2007mask and 'ignored_mask' is the mask of events which are to be ignored. 2008All are in hex format. Incorporation of 'mflags', 'mask' and 'ignored_mask' 2009provide information about flags and mask used in fanotify_mark 2010call [see fsnotify manpage for details]. 2011 2012While the first three lines are mandatory and always printed, the rest is 2013optional and may be omitted if no marks created yet. 2014 2015Timerfd files 2016~~~~~~~~~~~~~ 2017 2018:: 2019 2020 pos: 0 2021 flags: 02 2022 mnt_id: 9 2023 clockid: 0 2024 ticks: 0 2025 settime flags: 01 2026 it_value: (0, 49406829) 2027 it_interval: (1, 0) 2028 2029where 'clockid' is the clock type and 'ticks' is the number of the timer expirations 2030that have occurred [see timerfd_create(2) for details]. 'settime flags' are 2031flags in octal form been used to setup the timer [see timerfd_settime(2) for 2032details]. 'it_value' is remaining time until the timer expiration. 2033'it_interval' is the interval for the timer. Note the timer might be set up 2034with TIMER_ABSTIME option which will be shown in 'settime flags', but 'it_value' 2035still exhibits timer's remaining time. 2036 20373.9 /proc/<pid>/map_files - Information about memory mapped files 2038--------------------------------------------------------------------- 2039This directory contains symbolic links which represent memory mapped files 2040the process is maintaining. Example output:: 2041 2042 | lr-------- 1 root root 64 Jan 27 11:24 333c600000-333c620000 -> /usr/lib64/ld-2.18.so 2043 | lr-------- 1 root root 64 Jan 27 11:24 333c81f000-333c820000 -> /usr/lib64/ld-2.18.so 2044 | lr-------- 1 root root 64 Jan 27 11:24 333c820000-333c821000 -> /usr/lib64/ld-2.18.so 2045 | ... 2046 | lr-------- 1 root root 64 Jan 27 11:24 35d0421000-35d0422000 -> /usr/lib64/libselinux.so.1 2047 | lr-------- 1 root root 64 Jan 27 11:24 400000-41a000 -> /usr/bin/ls 2048 2049The name of a link represents the virtual memory bounds of a mapping, i.e. 2050vm_area_struct::vm_start-vm_area_struct::vm_end. 2051 2052The main purpose of the map_files is to retrieve a set of memory mapped 2053files in a fast way instead of parsing /proc/<pid>/maps or 2054/proc/<pid>/smaps, both of which contain many more records. At the same 2055time one can open(2) mappings from the listings of two processes and 2056comparing their inode numbers to figure out which anonymous memory areas 2057are actually shared. 2058 20593.10 /proc/<pid>/timerslack_ns - Task timerslack value 2060--------------------------------------------------------- 2061This file provides the value of the task's timerslack value in nanoseconds. 2062This value specifies an amount of time that normal timers may be deferred 2063in order to coalesce timers and avoid unnecessary wakeups. 2064 2065This allows a task's interactivity vs power consumption tradeoff to be 2066adjusted. 2067 2068Writing 0 to the file will set the task's timerslack to the default value. 2069 2070Valid values are from 0 - ULLONG_MAX 2071 2072An application setting the value must have PTRACE_MODE_ATTACH_FSCREDS level 2073permissions on the task specified to change its timerslack_ns value. 2074 20753.11 /proc/<pid>/patch_state - Livepatch patch operation state 2076----------------------------------------------------------------- 2077When CONFIG_LIVEPATCH is enabled, this file displays the value of the 2078patch state for the task. 2079 2080A value of '-1' indicates that no patch is in transition. 2081 2082A value of '0' indicates that a patch is in transition and the task is 2083unpatched. If the patch is being enabled, then the task hasn't been 2084patched yet. If the patch is being disabled, then the task has already 2085been unpatched. 2086 2087A value of '1' indicates that a patch is in transition and the task is 2088patched. If the patch is being enabled, then the task has already been 2089patched. If the patch is being disabled, then the task hasn't been 2090unpatched yet. 2091 20923.12 /proc/<pid>/arch_status - task architecture specific status 2093------------------------------------------------------------------- 2094When CONFIG_PROC_PID_ARCH_STATUS is enabled, this file displays the 2095architecture specific status of the task. 2096 2097Example 2098~~~~~~~ 2099 2100:: 2101 2102 $ cat /proc/6753/arch_status 2103 AVX512_elapsed_ms: 8 2104 2105Description 2106~~~~~~~~~~~ 2107 2108x86 specific entries 2109~~~~~~~~~~~~~~~~~~~~~ 2110 2111AVX512_elapsed_ms 2112^^^^^^^^^^^^^^^^^^ 2113 2114 If AVX512 is supported on the machine, this entry shows the milliseconds 2115 elapsed since the last time AVX512 usage was recorded. The recording 2116 happens on a best effort basis when a task is scheduled out. This means 2117 that the value depends on two factors: 2118 2119 1) The time which the task spent on the CPU without being scheduled 2120 out. With CPU isolation and a single runnable task this can take 2121 several seconds. 2122 2123 2) The time since the task was scheduled out last. Depending on the 2124 reason for being scheduled out (time slice exhausted, syscall ...) 2125 this can be arbitrary long time. 2126 2127 As a consequence the value cannot be considered precise and authoritative 2128 information. The application which uses this information has to be aware 2129 of the overall scenario on the system in order to determine whether a 2130 task is a real AVX512 user or not. Precise information can be obtained 2131 with performance counters. 2132 2133 A special value of '-1' indicates that no AVX512 usage was recorded, thus 2134 the task is unlikely an AVX512 user, but depends on the workload and the 2135 scheduling scenario, it also could be a false negative mentioned above. 2136 2137Chapter 4: Configuring procfs 2138============================= 2139 21404.1 Mount options 2141--------------------- 2142 2143The following mount options are supported: 2144 2145 ========= ======================================================== 2146 hidepid= Set /proc/<pid>/ access mode. 2147 gid= Set the group authorized to learn processes information. 2148 subset= Show only the specified subset of procfs. 2149 ========= ======================================================== 2150 2151hidepid=off or hidepid=0 means classic mode - everybody may access all 2152/proc/<pid>/ directories (default). 2153 2154hidepid=noaccess or hidepid=1 means users may not access any /proc/<pid>/ 2155directories but their own. Sensitive files like cmdline, sched*, status are now 2156protected against other users. This makes it impossible to learn whether any 2157user runs specific program (given the program doesn't reveal itself by its 2158behaviour). As an additional bonus, as /proc/<pid>/cmdline is unaccessible for 2159other users, poorly written programs passing sensitive information via program 2160arguments are now protected against local eavesdroppers. 2161 2162hidepid=invisible or hidepid=2 means hidepid=1 plus all /proc/<pid>/ will be 2163fully invisible to other users. It doesn't mean that it hides a fact whether a 2164process with a specific pid value exists (it can be learned by other means, e.g. 2165by "kill -0 $PID"), but it hides process' uid and gid, which may be learned by 2166stat()'ing /proc/<pid>/ otherwise. It greatly complicates an intruder's task of 2167gathering information about running processes, whether some daemon runs with 2168elevated privileges, whether other user runs some sensitive program, whether 2169other users run any program at all, etc. 2170 2171hidepid=ptraceable or hidepid=4 means that procfs should only contain 2172/proc/<pid>/ directories that the caller can ptrace. 2173 2174gid= defines a group authorized to learn processes information otherwise 2175prohibited by hidepid=. If you use some daemon like identd which needs to learn 2176information about processes information, just add identd to this group. 2177 2178subset=pid hides all top level files and directories in the procfs that 2179are not related to tasks. 2180 2181Chapter 5: Filesystem behavior 2182============================== 2183 2184Originally, before the advent of pid namepsace, procfs was a global file 2185system. It means that there was only one procfs instance in the system. 2186 2187When pid namespace was added, a separate procfs instance was mounted in 2188each pid namespace. So, procfs mount options are global among all 2189mountpoints within the same namespace:: 2190 2191 # grep ^proc /proc/mounts 2192 proc /proc proc rw,relatime,hidepid=2 0 0 2193 2194 # strace -e mount mount -o hidepid=1 -t proc proc /tmp/proc 2195 mount("proc", "/tmp/proc", "proc", 0, "hidepid=1") = 0 2196 +++ exited with 0 +++ 2197 2198 # grep ^proc /proc/mounts 2199 proc /proc proc rw,relatime,hidepid=2 0 0 2200 proc /tmp/proc proc rw,relatime,hidepid=2 0 0 2201 2202and only after remounting procfs mount options will change at all 2203mountpoints:: 2204 2205 # mount -o remount,hidepid=1 -t proc proc /tmp/proc 2206 2207 # grep ^proc /proc/mounts 2208 proc /proc proc rw,relatime,hidepid=1 0 0 2209 proc /tmp/proc proc rw,relatime,hidepid=1 0 0 2210 2211This behavior is different from the behavior of other filesystems. 2212 2213The new procfs behavior is more like other filesystems. Each procfs mount 2214creates a new procfs instance. Mount options affect own procfs instance. 2215It means that it became possible to have several procfs instances 2216displaying tasks with different filtering options in one pid namespace:: 2217 2218 # mount -o hidepid=invisible -t proc proc /proc 2219 # mount -o hidepid=noaccess -t proc proc /tmp/proc 2220 # grep ^proc /proc/mounts 2221 proc /proc proc rw,relatime,hidepid=invisible 0 0 2222 proc /tmp/proc proc rw,relatime,hidepid=noaccess 0 0 2223