1------------------------------------------------------------------------------ 2 T H E /proc F I L E S Y S T E M 3------------------------------------------------------------------------------ 4/proc/sys Terrehon Bowden <terrehon@pacbell.net> October 7 1999 5 Bodo Bauer <bb@ricochet.net> 6 72.4.x update Jorge Nerin <comandante@zaralinux.com> November 14 2000 8move /proc/sys Shen Feng <shen@cn.fujitsu.com> April 1 2009 9------------------------------------------------------------------------------ 10Version 1.3 Kernel version 2.2.12 11 Kernel version 2.4.0-test11-pre4 12------------------------------------------------------------------------------ 13fixes/update part 1.1 Stefani Seibold <stefani@seibold.net> June 9 2009 14 15Table of Contents 16----------------- 17 18 0 Preface 19 0.1 Introduction/Credits 20 0.2 Legal Stuff 21 22 1 Collecting System Information 23 1.1 Process-Specific Subdirectories 24 1.2 Kernel data 25 1.3 IDE devices in /proc/ide 26 1.4 Networking info in /proc/net 27 1.5 SCSI info 28 1.6 Parallel port info in /proc/parport 29 1.7 TTY info in /proc/tty 30 1.8 Miscellaneous kernel statistics in /proc/stat 31 1.9 Ext4 file system parameters 32 33 2 Modifying System Parameters 34 35 3 Per-Process Parameters 36 3.1 /proc/<pid>/oom_adj & /proc/<pid>/oom_score_adj - Adjust the oom-killer 37 score 38 3.2 /proc/<pid>/oom_score - Display current oom-killer score 39 3.3 /proc/<pid>/io - Display the IO accounting fields 40 3.4 /proc/<pid>/coredump_filter - Core dump filtering settings 41 3.5 /proc/<pid>/mountinfo - Information about mounts 42 3.6 /proc/<pid>/comm & /proc/<pid>/task/<tid>/comm 43 3.7 /proc/<pid>/task/<tid>/children - Information about task children 44 3.8 /proc/<pid>/fdinfo/<fd> - Information about opened file 45 3.9 /proc/<pid>/map_files - Information about memory mapped files 46 3.10 /proc/<pid>/timerslack_ns - Task timerslack value 47 3.11 /proc/<pid>/patch_state - Livepatch patch operation state 48 49 4 Configuring procfs 50 4.1 Mount options 51 52------------------------------------------------------------------------------ 53Preface 54------------------------------------------------------------------------------ 55 560.1 Introduction/Credits 57------------------------ 58 59This documentation is part of a soon (or so we hope) to be released book on 60the SuSE Linux distribution. As there is no complete documentation for the 61/proc file system and we've used many freely available sources to write these 62chapters, it seems only fair to give the work back to the Linux community. 63This work is based on the 2.2.* kernel version and the upcoming 2.4.*. I'm 64afraid it's still far from complete, but we hope it will be useful. As far as 65we know, it is the first 'all-in-one' document about the /proc file system. It 66is focused on the Intel x86 hardware, so if you are looking for PPC, ARM, 67SPARC, AXP, etc., features, you probably won't find what you are looking for. 68It also only covers IPv4 networking, not IPv6 nor other protocols - sorry. But 69additions and patches are welcome and will be added to this document if you 70mail them to Bodo. 71 72We'd like to thank Alan Cox, Rik van Riel, and Alexey Kuznetsov and a lot of 73other people for help compiling this documentation. We'd also like to extend a 74special thank you to Andi Kleen for documentation, which we relied on heavily 75to create this document, as well as the additional information he provided. 76Thanks to everybody else who contributed source or docs to the Linux kernel 77and helped create a great piece of software... :) 78 79If you have any comments, corrections or additions, please don't hesitate to 80contact Bodo Bauer at bb@ricochet.net. We'll be happy to add them to this 81document. 82 83The latest version of this document is available online at 84http://tldp.org/LDP/Linux-Filesystem-Hierarchy/html/proc.html 85 86If the above direction does not works for you, you could try the kernel 87mailing list at linux-kernel@vger.kernel.org and/or try to reach me at 88comandante@zaralinux.com. 89 900.2 Legal Stuff 91--------------- 92 93We don't guarantee the correctness of this document, and if you come to us 94complaining about how you screwed up your system because of incorrect 95documentation, we won't feel responsible... 96 97------------------------------------------------------------------------------ 98CHAPTER 1: COLLECTING SYSTEM INFORMATION 99------------------------------------------------------------------------------ 100 101------------------------------------------------------------------------------ 102In This Chapter 103------------------------------------------------------------------------------ 104* Investigating the properties of the pseudo file system /proc and its 105 ability to provide information on the running Linux system 106* Examining /proc's structure 107* Uncovering various information about the kernel and the processes running 108 on the system 109------------------------------------------------------------------------------ 110 111 112The proc file system acts as an interface to internal data structures in the 113kernel. It can be used to obtain information about the system and to change 114certain kernel parameters at runtime (sysctl). 115 116First, we'll take a look at the read-only parts of /proc. In Chapter 2, we 117show you how you can use /proc/sys to change settings. 118 1191.1 Process-Specific Subdirectories 120----------------------------------- 121 122The directory /proc contains (among other things) one subdirectory for each 123process running on the system, which is named after the process ID (PID). 124 125The link self points to the process reading the file system. Each process 126subdirectory has the entries listed in Table 1-1. 127 128 129Table 1-1: Process specific entries in /proc 130.............................................................................. 131 File Content 132 clear_refs Clears page referenced bits shown in smaps output 133 cmdline Command line arguments 134 cpu Current and last cpu in which it was executed (2.4)(smp) 135 cwd Link to the current working directory 136 environ Values of environment variables 137 exe Link to the executable of this process 138 fd Directory, which contains all file descriptors 139 maps Memory maps to executables and library files (2.4) 140 mem Memory held by this process 141 root Link to the root directory of this process 142 stat Process status 143 statm Process memory status information 144 status Process status in human readable form 145 wchan Present with CONFIG_KALLSYMS=y: it shows the kernel function 146 symbol the task is blocked in - or "0" if not blocked. 147 pagemap Page table 148 stack Report full stack trace, enable via CONFIG_STACKTRACE 149 smaps an extension based on maps, showing the memory consumption of 150 each mapping and flags associated with it 151 numa_maps an extension based on maps, showing the memory locality and 152 binding policy as well as mem usage (in pages) of each mapping. 153.............................................................................. 154 155For example, to get the status information of a process, all you have to do is 156read the file /proc/PID/status: 157 158 >cat /proc/self/status 159 Name: cat 160 State: R (running) 161 Tgid: 5452 162 Pid: 5452 163 PPid: 743 164 TracerPid: 0 (2.4) 165 Uid: 501 501 501 501 166 Gid: 100 100 100 100 167 FDSize: 256 168 Groups: 100 14 16 169 VmPeak: 5004 kB 170 VmSize: 5004 kB 171 VmLck: 0 kB 172 VmHWM: 476 kB 173 VmRSS: 476 kB 174 RssAnon: 352 kB 175 RssFile: 120 kB 176 RssShmem: 4 kB 177 VmData: 156 kB 178 VmStk: 88 kB 179 VmExe: 68 kB 180 VmLib: 1412 kB 181 VmPTE: 20 kb 182 VmSwap: 0 kB 183 HugetlbPages: 0 kB 184 CoreDumping: 0 185 Threads: 1 186 SigQ: 0/28578 187 SigPnd: 0000000000000000 188 ShdPnd: 0000000000000000 189 SigBlk: 0000000000000000 190 SigIgn: 0000000000000000 191 SigCgt: 0000000000000000 192 CapInh: 00000000fffffeff 193 CapPrm: 0000000000000000 194 CapEff: 0000000000000000 195 CapBnd: ffffffffffffffff 196 NoNewPrivs: 0 197 Seccomp: 0 198 voluntary_ctxt_switches: 0 199 nonvoluntary_ctxt_switches: 1 200 201This shows you nearly the same information you would get if you viewed it with 202the ps command. In fact, ps uses the proc file system to obtain its 203information. But you get a more detailed view of the process by reading the 204file /proc/PID/status. It fields are described in table 1-2. 205 206The statm file contains more detailed information about the process 207memory usage. Its seven fields are explained in Table 1-3. The stat file 208contains details information about the process itself. Its fields are 209explained in Table 1-4. 210 211(for SMP CONFIG users) 212For making accounting scalable, RSS related information are handled in an 213asynchronous manner and the value may not be very precise. To see a precise 214snapshot of a moment, you can see /proc/<pid>/smaps file and scan page table. 215It's slow but very precise. 216 217Table 1-2: Contents of the status files (as of 4.8) 218.............................................................................. 219 Field Content 220 Name filename of the executable 221 Umask file mode creation mask 222 State state (R is running, S is sleeping, D is sleeping 223 in an uninterruptible wait, Z is zombie, 224 T is traced or stopped) 225 Tgid thread group ID 226 Ngid NUMA group ID (0 if none) 227 Pid process id 228 PPid process id of the parent process 229 TracerPid PID of process tracing this process (0 if not) 230 Uid Real, effective, saved set, and file system UIDs 231 Gid Real, effective, saved set, and file system GIDs 232 FDSize number of file descriptor slots currently allocated 233 Groups supplementary group list 234 NStgid descendant namespace thread group ID hierarchy 235 NSpid descendant namespace process ID hierarchy 236 NSpgid descendant namespace process group ID hierarchy 237 NSsid descendant namespace session ID hierarchy 238 VmPeak peak virtual memory size 239 VmSize total program size 240 VmLck locked memory size 241 VmPin pinned memory size 242 VmHWM peak resident set size ("high water mark") 243 VmRSS size of memory portions. It contains the three 244 following parts (VmRSS = RssAnon + RssFile + RssShmem) 245 RssAnon size of resident anonymous memory 246 RssFile size of resident file mappings 247 RssShmem size of resident shmem memory (includes SysV shm, 248 mapping of tmpfs and shared anonymous mappings) 249 VmData size of private data segments 250 VmStk size of stack segments 251 VmExe size of text segment 252 VmLib size of shared library code 253 VmPTE size of page table entries 254 VmSwap amount of swap used by anonymous private data 255 (shmem swap usage is not included) 256 HugetlbPages size of hugetlb memory portions 257 CoreDumping process's memory is currently being dumped 258 (killing the process may lead to a corrupted core) 259 Threads number of threads 260 SigQ number of signals queued/max. number for queue 261 SigPnd bitmap of pending signals for the thread 262 ShdPnd bitmap of shared pending signals for the process 263 SigBlk bitmap of blocked signals 264 SigIgn bitmap of ignored signals 265 SigCgt bitmap of caught signals 266 CapInh bitmap of inheritable capabilities 267 CapPrm bitmap of permitted capabilities 268 CapEff bitmap of effective capabilities 269 CapBnd bitmap of capabilities bounding set 270 NoNewPrivs no_new_privs, like prctl(PR_GET_NO_NEW_PRIV, ...) 271 Seccomp seccomp mode, like prctl(PR_GET_SECCOMP, ...) 272 Cpus_allowed mask of CPUs on which this process may run 273 Cpus_allowed_list Same as previous, but in "list format" 274 Mems_allowed mask of memory nodes allowed to this process 275 Mems_allowed_list Same as previous, but in "list format" 276 voluntary_ctxt_switches number of voluntary context switches 277 nonvoluntary_ctxt_switches number of non voluntary context switches 278.............................................................................. 279 280Table 1-3: Contents of the statm files (as of 2.6.8-rc3) 281.............................................................................. 282 Field Content 283 size total program size (pages) (same as VmSize in status) 284 resident size of memory portions (pages) (same as VmRSS in status) 285 shared number of pages that are shared (i.e. backed by a file, same 286 as RssFile+RssShmem in status) 287 trs number of pages that are 'code' (not including libs; broken, 288 includes data segment) 289 lrs number of pages of library (always 0 on 2.6) 290 drs number of pages of data/stack (including libs; broken, 291 includes library text) 292 dt number of dirty pages (always 0 on 2.6) 293.............................................................................. 294 295 296Table 1-4: Contents of the stat files (as of 2.6.30-rc7) 297.............................................................................. 298 Field Content 299 pid process id 300 tcomm filename of the executable 301 state state (R is running, S is sleeping, D is sleeping in an 302 uninterruptible wait, Z is zombie, T is traced or stopped) 303 ppid process id of the parent process 304 pgrp pgrp of the process 305 sid session id 306 tty_nr tty the process uses 307 tty_pgrp pgrp of the tty 308 flags task flags 309 min_flt number of minor faults 310 cmin_flt number of minor faults with child's 311 maj_flt number of major faults 312 cmaj_flt number of major faults with child's 313 utime user mode jiffies 314 stime kernel mode jiffies 315 cutime user mode jiffies with child's 316 cstime kernel mode jiffies with child's 317 priority priority level 318 nice nice level 319 num_threads number of threads 320 it_real_value (obsolete, always 0) 321 start_time time the process started after system boot 322 vsize virtual memory size 323 rss resident set memory size 324 rsslim current limit in bytes on the rss 325 start_code address above which program text can run 326 end_code address below which program text can run 327 start_stack address of the start of the main process stack 328 esp current value of ESP 329 eip current value of EIP 330 pending bitmap of pending signals 331 blocked bitmap of blocked signals 332 sigign bitmap of ignored signals 333 sigcatch bitmap of caught signals 334 0 (place holder, used to be the wchan address, use /proc/PID/wchan instead) 335 0 (place holder) 336 0 (place holder) 337 exit_signal signal to send to parent thread on exit 338 task_cpu which CPU the task is scheduled on 339 rt_priority realtime priority 340 policy scheduling policy (man sched_setscheduler) 341 blkio_ticks time spent waiting for block IO 342 gtime guest time of the task in jiffies 343 cgtime guest time of the task children in jiffies 344 start_data address above which program data+bss is placed 345 end_data address below which program data+bss is placed 346 start_brk address above which program heap can be expanded with brk() 347 arg_start address above which program command line is placed 348 arg_end address below which program command line is placed 349 env_start address above which program environment is placed 350 env_end address below which program environment is placed 351 exit_code the thread's exit_code in the form reported by the waitpid system call 352.............................................................................. 353 354The /proc/PID/maps file containing the currently mapped memory regions and 355their access permissions. 356 357The format is: 358 359address perms offset dev inode pathname 360 36108048000-08049000 r-xp 00000000 03:00 8312 /opt/test 36208049000-0804a000 rw-p 00001000 03:00 8312 /opt/test 3630804a000-0806b000 rw-p 00000000 00:00 0 [heap] 364a7cb1000-a7cb2000 ---p 00000000 00:00 0 365a7cb2000-a7eb2000 rw-p 00000000 00:00 0 366a7eb2000-a7eb3000 ---p 00000000 00:00 0 367a7eb3000-a7ed5000 rw-p 00000000 00:00 0 368a7ed5000-a8008000 r-xp 00000000 03:00 4222 /lib/libc.so.6 369a8008000-a800a000 r--p 00133000 03:00 4222 /lib/libc.so.6 370a800a000-a800b000 rw-p 00135000 03:00 4222 /lib/libc.so.6 371a800b000-a800e000 rw-p 00000000 00:00 0 372a800e000-a8022000 r-xp 00000000 03:00 14462 /lib/libpthread.so.0 373a8022000-a8023000 r--p 00013000 03:00 14462 /lib/libpthread.so.0 374a8023000-a8024000 rw-p 00014000 03:00 14462 /lib/libpthread.so.0 375a8024000-a8027000 rw-p 00000000 00:00 0 376a8027000-a8043000 r-xp 00000000 03:00 8317 /lib/ld-linux.so.2 377a8043000-a8044000 r--p 0001b000 03:00 8317 /lib/ld-linux.so.2 378a8044000-a8045000 rw-p 0001c000 03:00 8317 /lib/ld-linux.so.2 379aff35000-aff4a000 rw-p 00000000 00:00 0 [stack] 380ffffe000-fffff000 r-xp 00000000 00:00 0 [vdso] 381 382where "address" is the address space in the process that it occupies, "perms" 383is a set of permissions: 384 385 r = read 386 w = write 387 x = execute 388 s = shared 389 p = private (copy on write) 390 391"offset" is the offset into the mapping, "dev" is the device (major:minor), and 392"inode" is the inode on that device. 0 indicates that no inode is associated 393with the memory region, as the case would be with BSS (uninitialized data). 394The "pathname" shows the name associated file for this mapping. If the mapping 395is not associated with a file: 396 397 [heap] = the heap of the program 398 [stack] = the stack of the main process 399 [vdso] = the "virtual dynamic shared object", 400 the kernel system call handler 401 402 or if empty, the mapping is anonymous. 403 404The /proc/PID/smaps is an extension based on maps, showing the memory 405consumption for each of the process's mappings. For each of mappings there 406is a series of lines such as the following: 407 40808048000-080bc000 r-xp 00000000 03:02 13130 /bin/bash 409Size: 1084 kB 410Rss: 892 kB 411Pss: 374 kB 412Shared_Clean: 892 kB 413Shared_Dirty: 0 kB 414Private_Clean: 0 kB 415Private_Dirty: 0 kB 416Referenced: 892 kB 417Anonymous: 0 kB 418LazyFree: 0 kB 419AnonHugePages: 0 kB 420ShmemPmdMapped: 0 kB 421Shared_Hugetlb: 0 kB 422Private_Hugetlb: 0 kB 423Swap: 0 kB 424SwapPss: 0 kB 425KernelPageSize: 4 kB 426MMUPageSize: 4 kB 427Locked: 0 kB 428VmFlags: rd ex mr mw me dw 429 430the first of these lines shows the same information as is displayed for the 431mapping in /proc/PID/maps. The remaining lines show the size of the mapping 432(size), the amount of the mapping that is currently resident in RAM (RSS), the 433process' proportional share of this mapping (PSS), the number of clean and 434dirty private pages in the mapping. 435 436The "proportional set size" (PSS) of a process is the count of pages it has 437in memory, where each page is divided by the number of processes sharing it. 438So if a process has 1000 pages all to itself, and 1000 shared with one other 439process, its PSS will be 1500. 440Note that even a page which is part of a MAP_SHARED mapping, but has only 441a single pte mapped, i.e. is currently used by only one process, is accounted 442as private and not as shared. 443"Referenced" indicates the amount of memory currently marked as referenced or 444accessed. 445"Anonymous" shows the amount of memory that does not belong to any file. Even 446a mapping associated with a file may contain anonymous pages: when MAP_PRIVATE 447and a page is modified, the file page is replaced by a private anonymous copy. 448"LazyFree" shows the amount of memory which is marked by madvise(MADV_FREE). 449The memory isn't freed immediately with madvise(). It's freed in memory 450pressure if the memory is clean. Please note that the printed value might 451be lower than the real value due to optimizations used in the current 452implementation. If this is not desirable please file a bug report. 453"AnonHugePages" shows the ammount of memory backed by transparent hugepage. 454"ShmemPmdMapped" shows the ammount of shared (shmem/tmpfs) memory backed by 455huge pages. 456"Shared_Hugetlb" and "Private_Hugetlb" show the ammounts of memory backed by 457hugetlbfs page which is *not* counted in "RSS" or "PSS" field for historical 458reasons. And these are not included in {Shared,Private}_{Clean,Dirty} field. 459"Swap" shows how much would-be-anonymous memory is also used, but out on swap. 460For shmem mappings, "Swap" includes also the size of the mapped (and not 461replaced by copy-on-write) part of the underlying shmem object out on swap. 462"SwapPss" shows proportional swap share of this mapping. Unlike "Swap", this 463does not take into account swapped out page of underlying shmem objects. 464"Locked" indicates whether the mapping is locked in memory or not. 465 466"VmFlags" field deserves a separate description. This member represents the kernel 467flags associated with the particular virtual memory area in two letter encoded 468manner. The codes are the following: 469 rd - readable 470 wr - writeable 471 ex - executable 472 sh - shared 473 mr - may read 474 mw - may write 475 me - may execute 476 ms - may share 477 gd - stack segment growns down 478 pf - pure PFN range 479 dw - disabled write to the mapped file 480 lo - pages are locked in memory 481 io - memory mapped I/O area 482 sr - sequential read advise provided 483 rr - random read advise provided 484 dc - do not copy area on fork 485 de - do not expand area on remapping 486 ac - area is accountable 487 nr - swap space is not reserved for the area 488 ht - area uses huge tlb pages 489 ar - architecture specific flag 490 dd - do not include area into core dump 491 sd - soft-dirty flag 492 mm - mixed map area 493 hg - huge page advise flag 494 nh - no-huge page advise flag 495 mg - mergable advise flag 496 497Note that there is no guarantee that every flag and associated mnemonic will 498be present in all further kernel releases. Things get changed, the flags may 499be vanished or the reverse -- new added. 500 501This file is only present if the CONFIG_MMU kernel configuration option is 502enabled. 503 504Note: reading /proc/PID/maps or /proc/PID/smaps is inherently racy (consistent 505output can be achieved only in the single read call). 506This typically manifests when doing partial reads of these files while the 507memory map is being modified. Despite the races, we do provide the following 508guarantees: 509 5101) The mapped addresses never go backwards, which implies no two 511 regions will ever overlap. 5122) If there is something at a given vaddr during the entirety of the 513 life of the smaps/maps walk, there will be some output for it. 514 515 516The /proc/PID/clear_refs is used to reset the PG_Referenced and ACCESSED/YOUNG 517bits on both physical and virtual pages associated with a process, and the 518soft-dirty bit on pte (see Documentation/admin-guide/mm/soft-dirty.rst 519for details). 520To clear the bits for all the pages associated with the process 521 > echo 1 > /proc/PID/clear_refs 522 523To clear the bits for the anonymous pages associated with the process 524 > echo 2 > /proc/PID/clear_refs 525 526To clear the bits for the file mapped pages associated with the process 527 > echo 3 > /proc/PID/clear_refs 528 529To clear the soft-dirty bit 530 > echo 4 > /proc/PID/clear_refs 531 532To reset the peak resident set size ("high water mark") to the process's 533current value: 534 > echo 5 > /proc/PID/clear_refs 535 536Any other value written to /proc/PID/clear_refs will have no effect. 537 538The /proc/pid/pagemap gives the PFN, which can be used to find the pageflags 539using /proc/kpageflags and number of times a page is mapped using 540/proc/kpagecount. For detailed explanation, see 541Documentation/admin-guide/mm/pagemap.rst. 542 543The /proc/pid/numa_maps is an extension based on maps, showing the memory 544locality and binding policy, as well as the memory usage (in pages) of 545each mapping. The output follows a general format where mapping details get 546summarized separated by blank spaces, one mapping per each file line: 547 548address policy mapping details 549 55000400000 default file=/usr/local/bin/app mapped=1 active=0 N3=1 kernelpagesize_kB=4 55100600000 default file=/usr/local/bin/app anon=1 dirty=1 N3=1 kernelpagesize_kB=4 5523206000000 default file=/lib64/ld-2.12.so mapped=26 mapmax=6 N0=24 N3=2 kernelpagesize_kB=4 553320621f000 default file=/lib64/ld-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4 5543206220000 default file=/lib64/ld-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4 5553206221000 default anon=1 dirty=1 N3=1 kernelpagesize_kB=4 5563206800000 default file=/lib64/libc-2.12.so mapped=59 mapmax=21 active=55 N0=41 N3=18 kernelpagesize_kB=4 557320698b000 default file=/lib64/libc-2.12.so 5583206b8a000 default file=/lib64/libc-2.12.so anon=2 dirty=2 N3=2 kernelpagesize_kB=4 5593206b8e000 default file=/lib64/libc-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4 5603206b8f000 default anon=3 dirty=3 active=1 N3=3 kernelpagesize_kB=4 5617f4dc10a2000 default anon=3 dirty=3 N3=3 kernelpagesize_kB=4 5627f4dc10b4000 default anon=2 dirty=2 active=1 N3=2 kernelpagesize_kB=4 5637f4dc1200000 default file=/anon_hugepage\040(deleted) huge anon=1 dirty=1 N3=1 kernelpagesize_kB=2048 5647fff335f0000 default stack anon=3 dirty=3 N3=3 kernelpagesize_kB=4 5657fff3369d000 default mapped=1 mapmax=35 active=0 N3=1 kernelpagesize_kB=4 566 567Where: 568"address" is the starting address for the mapping; 569"policy" reports the NUMA memory policy set for the mapping (see Documentation/admin-guide/mm/numa_memory_policy.rst); 570"mapping details" summarizes mapping data such as mapping type, page usage counters, 571node locality page counters (N0 == node0, N1 == node1, ...) and the kernel page 572size, in KB, that is backing the mapping up. 573 5741.2 Kernel data 575--------------- 576 577Similar to the process entries, the kernel data files give information about 578the running kernel. The files used to obtain this information are contained in 579/proc and are listed in Table 1-5. Not all of these will be present in your 580system. It depends on the kernel configuration and the loaded modules, which 581files are there, and which are missing. 582 583Table 1-5: Kernel info in /proc 584.............................................................................. 585 File Content 586 apm Advanced power management info 587 buddyinfo Kernel memory allocator information (see text) (2.5) 588 bus Directory containing bus specific information 589 cmdline Kernel command line 590 cpuinfo Info about the CPU 591 devices Available devices (block and character) 592 dma Used DMS channels 593 filesystems Supported filesystems 594 driver Various drivers grouped here, currently rtc (2.4) 595 execdomains Execdomains, related to security (2.4) 596 fb Frame Buffer devices (2.4) 597 fs File system parameters, currently nfs/exports (2.4) 598 ide Directory containing info about the IDE subsystem 599 interrupts Interrupt usage 600 iomem Memory map (2.4) 601 ioports I/O port usage 602 irq Masks for irq to cpu affinity (2.4)(smp?) 603 isapnp ISA PnP (Plug&Play) Info (2.4) 604 kcore Kernel core image (can be ELF or A.OUT(deprecated in 2.4)) 605 kmsg Kernel messages 606 ksyms Kernel symbol table 607 loadavg Load average of last 1, 5 & 15 minutes 608 locks Kernel locks 609 meminfo Memory info 610 misc Miscellaneous 611 modules List of loaded modules 612 mounts Mounted filesystems 613 net Networking info (see text) 614 pagetypeinfo Additional page allocator information (see text) (2.5) 615 partitions Table of partitions known to the system 616 pci Deprecated info of PCI bus (new way -> /proc/bus/pci/, 617 decoupled by lspci (2.4) 618 rtc Real time clock 619 scsi SCSI info (see text) 620 slabinfo Slab pool info 621 softirqs softirq usage 622 stat Overall statistics 623 swaps Swap space utilization 624 sys See chapter 2 625 sysvipc Info of SysVIPC Resources (msg, sem, shm) (2.4) 626 tty Info of tty drivers 627 uptime Wall clock since boot, combined idle time of all cpus 628 version Kernel version 629 video bttv info of video resources (2.4) 630 vmallocinfo Show vmalloced areas 631.............................................................................. 632 633You can, for example, check which interrupts are currently in use and what 634they are used for by looking in the file /proc/interrupts: 635 636 > cat /proc/interrupts 637 CPU0 638 0: 8728810 XT-PIC timer 639 1: 895 XT-PIC keyboard 640 2: 0 XT-PIC cascade 641 3: 531695 XT-PIC aha152x 642 4: 2014133 XT-PIC serial 643 5: 44401 XT-PIC pcnet_cs 644 8: 2 XT-PIC rtc 645 11: 8 XT-PIC i82365 646 12: 182918 XT-PIC PS/2 Mouse 647 13: 1 XT-PIC fpu 648 14: 1232265 XT-PIC ide0 649 15: 7 XT-PIC ide1 650 NMI: 0 651 652In 2.4.* a couple of lines where added to this file LOC & ERR (this time is the 653output of a SMP machine): 654 655 > cat /proc/interrupts 656 657 CPU0 CPU1 658 0: 1243498 1214548 IO-APIC-edge timer 659 1: 8949 8958 IO-APIC-edge keyboard 660 2: 0 0 XT-PIC cascade 661 5: 11286 10161 IO-APIC-edge soundblaster 662 8: 1 0 IO-APIC-edge rtc 663 9: 27422 27407 IO-APIC-edge 3c503 664 12: 113645 113873 IO-APIC-edge PS/2 Mouse 665 13: 0 0 XT-PIC fpu 666 14: 22491 24012 IO-APIC-edge ide0 667 15: 2183 2415 IO-APIC-edge ide1 668 17: 30564 30414 IO-APIC-level eth0 669 18: 177 164 IO-APIC-level bttv 670 NMI: 2457961 2457959 671 LOC: 2457882 2457881 672 ERR: 2155 673 674NMI is incremented in this case because every timer interrupt generates a NMI 675(Non Maskable Interrupt) which is used by the NMI Watchdog to detect lockups. 676 677LOC is the local interrupt counter of the internal APIC of every CPU. 678 679ERR is incremented in the case of errors in the IO-APIC bus (the bus that 680connects the CPUs in a SMP system. This means that an error has been detected, 681the IO-APIC automatically retry the transmission, so it should not be a big 682problem, but you should read the SMP-FAQ. 683 684In 2.6.2* /proc/interrupts was expanded again. This time the goal was for 685/proc/interrupts to display every IRQ vector in use by the system, not 686just those considered 'most important'. The new vectors are: 687 688 THR -- interrupt raised when a machine check threshold counter 689 (typically counting ECC corrected errors of memory or cache) exceeds 690 a configurable threshold. Only available on some systems. 691 692 TRM -- a thermal event interrupt occurs when a temperature threshold 693 has been exceeded for the CPU. This interrupt may also be generated 694 when the temperature drops back to normal. 695 696 SPU -- a spurious interrupt is some interrupt that was raised then lowered 697 by some IO device before it could be fully processed by the APIC. Hence 698 the APIC sees the interrupt but does not know what device it came from. 699 For this case the APIC will generate the interrupt with a IRQ vector 700 of 0xff. This might also be generated by chipset bugs. 701 702 RES, CAL, TLB -- rescheduling, call and TLB flush interrupts are 703 sent from one CPU to another per the needs of the OS. Typically, 704 their statistics are used by kernel developers and interested users to 705 determine the occurrence of interrupts of the given type. 706 707The above IRQ vectors are displayed only when relevant. For example, 708the threshold vector does not exist on x86_64 platforms. Others are 709suppressed when the system is a uniprocessor. As of this writing, only 710i386 and x86_64 platforms support the new IRQ vector displays. 711 712Of some interest is the introduction of the /proc/irq directory to 2.4. 713It could be used to set IRQ to CPU affinity, this means that you can "hook" an 714IRQ to only one CPU, or to exclude a CPU of handling IRQs. The contents of the 715irq subdir is one subdir for each IRQ, and two files; default_smp_affinity and 716prof_cpu_mask. 717 718For example 719 > ls /proc/irq/ 720 0 10 12 14 16 18 2 4 6 8 prof_cpu_mask 721 1 11 13 15 17 19 3 5 7 9 default_smp_affinity 722 > ls /proc/irq/0/ 723 smp_affinity 724 725smp_affinity is a bitmask, in which you can specify which CPUs can handle the 726IRQ, you can set it by doing: 727 728 > echo 1 > /proc/irq/10/smp_affinity 729 730This means that only the first CPU will handle the IRQ, but you can also echo 7315 which means that only the first and third CPU can handle the IRQ. 732 733The contents of each smp_affinity file is the same by default: 734 735 > cat /proc/irq/0/smp_affinity 736 ffffffff 737 738There is an alternate interface, smp_affinity_list which allows specifying 739a cpu range instead of a bitmask: 740 741 > cat /proc/irq/0/smp_affinity_list 742 1024-1031 743 744The default_smp_affinity mask applies to all non-active IRQs, which are the 745IRQs which have not yet been allocated/activated, and hence which lack a 746/proc/irq/[0-9]* directory. 747 748The node file on an SMP system shows the node to which the device using the IRQ 749reports itself as being attached. This hardware locality information does not 750include information about any possible driver locality preference. 751 752prof_cpu_mask specifies which CPUs are to be profiled by the system wide 753profiler. Default value is ffffffff (all cpus if there are only 32 of them). 754 755The way IRQs are routed is handled by the IO-APIC, and it's Round Robin 756between all the CPUs which are allowed to handle it. As usual the kernel has 757more info than you and does a better job than you, so the defaults are the 758best choice for almost everyone. [Note this applies only to those IO-APIC's 759that support "Round Robin" interrupt distribution.] 760 761There are three more important subdirectories in /proc: net, scsi, and sys. 762The general rule is that the contents, or even the existence of these 763directories, depend on your kernel configuration. If SCSI is not enabled, the 764directory scsi may not exist. The same is true with the net, which is there 765only when networking support is present in the running kernel. 766 767The slabinfo file gives information about memory usage at the slab level. 768Linux uses slab pools for memory management above page level in version 2.2. 769Commonly used objects have their own slab pool (such as network buffers, 770directory cache, and so on). 771 772.............................................................................. 773 774> cat /proc/buddyinfo 775 776Node 0, zone DMA 0 4 5 4 4 3 ... 777Node 0, zone Normal 1 0 0 1 101 8 ... 778Node 0, zone HighMem 2 0 0 1 1 0 ... 779 780External fragmentation is a problem under some workloads, and buddyinfo is a 781useful tool for helping diagnose these problems. Buddyinfo will give you a 782clue as to how big an area you can safely allocate, or why a previous 783allocation failed. 784 785Each column represents the number of pages of a certain order which are 786available. In this case, there are 0 chunks of 2^0*PAGE_SIZE available in 787ZONE_DMA, 4 chunks of 2^1*PAGE_SIZE in ZONE_DMA, 101 chunks of 2^4*PAGE_SIZE 788available in ZONE_NORMAL, etc... 789 790More information relevant to external fragmentation can be found in 791pagetypeinfo. 792 793> cat /proc/pagetypeinfo 794Page block order: 9 795Pages per block: 512 796 797Free pages count per migrate type at order 0 1 2 3 4 5 6 7 8 9 10 798Node 0, zone DMA, type Unmovable 0 0 0 1 1 1 1 1 1 1 0 799Node 0, zone DMA, type Reclaimable 0 0 0 0 0 0 0 0 0 0 0 800Node 0, zone DMA, type Movable 1 1 2 1 2 1 1 0 1 0 2 801Node 0, zone DMA, type Reserve 0 0 0 0 0 0 0 0 0 1 0 802Node 0, zone DMA, type Isolate 0 0 0 0 0 0 0 0 0 0 0 803Node 0, zone DMA32, type Unmovable 103 54 77 1 1 1 11 8 7 1 9 804Node 0, zone DMA32, type Reclaimable 0 0 2 1 0 0 0 0 1 0 0 805Node 0, zone DMA32, type Movable 169 152 113 91 77 54 39 13 6 1 452 806Node 0, zone DMA32, type Reserve 1 2 2 2 2 0 1 1 1 1 0 807Node 0, zone DMA32, type Isolate 0 0 0 0 0 0 0 0 0 0 0 808 809Number of blocks type Unmovable Reclaimable Movable Reserve Isolate 810Node 0, zone DMA 2 0 5 1 0 811Node 0, zone DMA32 41 6 967 2 0 812 813Fragmentation avoidance in the kernel works by grouping pages of different 814migrate types into the same contiguous regions of memory called page blocks. 815A page block is typically the size of the default hugepage size e.g. 2MB on 816X86-64. By keeping pages grouped based on their ability to move, the kernel 817can reclaim pages within a page block to satisfy a high-order allocation. 818 819The pagetypinfo begins with information on the size of a page block. It 820then gives the same type of information as buddyinfo except broken down 821by migrate-type and finishes with details on how many page blocks of each 822type exist. 823 824If min_free_kbytes has been tuned correctly (recommendations made by hugeadm 825from libhugetlbfs https://github.com/libhugetlbfs/libhugetlbfs/), one can 826make an estimate of the likely number of huge pages that can be allocated 827at a given point in time. All the "Movable" blocks should be allocatable 828unless memory has been mlock()'d. Some of the Reclaimable blocks should 829also be allocatable although a lot of filesystem metadata may have to be 830reclaimed to achieve this. 831 832.............................................................................. 833 834meminfo: 835 836Provides information about distribution and utilization of memory. This 837varies by architecture and compile options. The following is from a 83816GB PIII, which has highmem enabled. You may not have all of these fields. 839 840> cat /proc/meminfo 841 842MemTotal: 16344972 kB 843MemFree: 13634064 kB 844MemAvailable: 14836172 kB 845Buffers: 3656 kB 846Cached: 1195708 kB 847SwapCached: 0 kB 848Active: 891636 kB 849Inactive: 1077224 kB 850HighTotal: 15597528 kB 851HighFree: 13629632 kB 852LowTotal: 747444 kB 853LowFree: 4432 kB 854SwapTotal: 0 kB 855SwapFree: 0 kB 856Dirty: 968 kB 857Writeback: 0 kB 858AnonPages: 861800 kB 859Mapped: 280372 kB 860Shmem: 644 kB 861Slab: 284364 kB 862SReclaimable: 159856 kB 863SUnreclaim: 124508 kB 864PageTables: 24448 kB 865NFS_Unstable: 0 kB 866Bounce: 0 kB 867WritebackTmp: 0 kB 868CommitLimit: 7669796 kB 869Committed_AS: 100056 kB 870VmallocTotal: 112216 kB 871VmallocUsed: 428 kB 872VmallocChunk: 111088 kB 873Percpu: 62080 kB 874HardwareCorrupted: 0 kB 875AnonHugePages: 49152 kB 876ShmemHugePages: 0 kB 877ShmemPmdMapped: 0 kB 878 879 880 MemTotal: Total usable ram (i.e. physical ram minus a few reserved 881 bits and the kernel binary code) 882 MemFree: The sum of LowFree+HighFree 883MemAvailable: An estimate of how much memory is available for starting new 884 applications, without swapping. Calculated from MemFree, 885 SReclaimable, the size of the file LRU lists, and the low 886 watermarks in each zone. 887 The estimate takes into account that the system needs some 888 page cache to function well, and that not all reclaimable 889 slab will be reclaimable, due to items being in use. The 890 impact of those factors will vary from system to system. 891 Buffers: Relatively temporary storage for raw disk blocks 892 shouldn't get tremendously large (20MB or so) 893 Cached: in-memory cache for files read from the disk (the 894 pagecache). Doesn't include SwapCached 895 SwapCached: Memory that once was swapped out, is swapped back in but 896 still also is in the swapfile (if memory is needed it 897 doesn't need to be swapped out AGAIN because it is already 898 in the swapfile. This saves I/O) 899 Active: Memory that has been used more recently and usually not 900 reclaimed unless absolutely necessary. 901 Inactive: Memory which has been less recently used. It is more 902 eligible to be reclaimed for other purposes 903 HighTotal: 904 HighFree: Highmem is all memory above ~860MB of physical memory 905 Highmem areas are for use by userspace programs, or 906 for the pagecache. The kernel must use tricks to access 907 this memory, making it slower to access than lowmem. 908 LowTotal: 909 LowFree: Lowmem is memory which can be used for everything that 910 highmem can be used for, but it is also available for the 911 kernel's use for its own data structures. Among many 912 other things, it is where everything from the Slab is 913 allocated. Bad things happen when you're out of lowmem. 914 SwapTotal: total amount of swap space available 915 SwapFree: Memory which has been evicted from RAM, and is temporarily 916 on the disk 917 Dirty: Memory which is waiting to get written back to the disk 918 Writeback: Memory which is actively being written back to the disk 919 AnonPages: Non-file backed pages mapped into userspace page tables 920HardwareCorrupted: The amount of RAM/memory in KB, the kernel identifies as 921 corrupted. 922AnonHugePages: Non-file backed huge pages mapped into userspace page tables 923 Mapped: files which have been mmaped, such as libraries 924 Shmem: Total memory used by shared memory (shmem) and tmpfs 925ShmemHugePages: Memory used by shared memory (shmem) and tmpfs allocated 926 with huge pages 927ShmemPmdMapped: Shared memory mapped into userspace with huge pages 928 Slab: in-kernel data structures cache 929SReclaimable: Part of Slab, that might be reclaimed, such as caches 930 SUnreclaim: Part of Slab, that cannot be reclaimed on memory pressure 931 PageTables: amount of memory dedicated to the lowest level of page 932 tables. 933NFS_Unstable: NFS pages sent to the server, but not yet committed to stable 934 storage 935 Bounce: Memory used for block device "bounce buffers" 936WritebackTmp: Memory used by FUSE for temporary writeback buffers 937 CommitLimit: Based on the overcommit ratio ('vm.overcommit_ratio'), 938 this is the total amount of memory currently available to 939 be allocated on the system. This limit is only adhered to 940 if strict overcommit accounting is enabled (mode 2 in 941 'vm.overcommit_memory'). 942 The CommitLimit is calculated with the following formula: 943 CommitLimit = ([total RAM pages] - [total huge TLB pages]) * 944 overcommit_ratio / 100 + [total swap pages] 945 For example, on a system with 1G of physical RAM and 7G 946 of swap with a `vm.overcommit_ratio` of 30 it would 947 yield a CommitLimit of 7.3G. 948 For more details, see the memory overcommit documentation 949 in vm/overcommit-accounting. 950Committed_AS: The amount of memory presently allocated on the system. 951 The committed memory is a sum of all of the memory which 952 has been allocated by processes, even if it has not been 953 "used" by them as of yet. A process which malloc()'s 1G 954 of memory, but only touches 300M of it will show up as 955 using 1G. This 1G is memory which has been "committed" to 956 by the VM and can be used at any time by the allocating 957 application. With strict overcommit enabled on the system 958 (mode 2 in 'vm.overcommit_memory'),allocations which would 959 exceed the CommitLimit (detailed above) will not be permitted. 960 This is useful if one needs to guarantee that processes will 961 not fail due to lack of memory once that memory has been 962 successfully allocated. 963VmallocTotal: total size of vmalloc memory area 964 VmallocUsed: amount of vmalloc area which is used 965VmallocChunk: largest contiguous block of vmalloc area which is free 966 Percpu: Memory allocated to the percpu allocator used to back percpu 967 allocations. This stat excludes the cost of metadata. 968 969.............................................................................. 970 971vmallocinfo: 972 973Provides information about vmalloced/vmaped areas. One line per area, 974containing the virtual address range of the area, size in bytes, 975caller information of the creator, and optional information depending 976on the kind of area : 977 978 pages=nr number of pages 979 phys=addr if a physical address was specified 980 ioremap I/O mapping (ioremap() and friends) 981 vmalloc vmalloc() area 982 vmap vmap()ed pages 983 user VM_USERMAP area 984 vpages buffer for pages pointers was vmalloced (huge area) 985 N<node>=nr (Only on NUMA kernels) 986 Number of pages allocated on memory node <node> 987 988> cat /proc/vmallocinfo 9890xffffc20000000000-0xffffc20000201000 2101248 alloc_large_system_hash+0x204 ... 990 /0x2c0 pages=512 vmalloc N0=128 N1=128 N2=128 N3=128 9910xffffc20000201000-0xffffc20000302000 1052672 alloc_large_system_hash+0x204 ... 992 /0x2c0 pages=256 vmalloc N0=64 N1=64 N2=64 N3=64 9930xffffc20000302000-0xffffc20000304000 8192 acpi_tb_verify_table+0x21/0x4f... 994 phys=7fee8000 ioremap 9950xffffc20000304000-0xffffc20000307000 12288 acpi_tb_verify_table+0x21/0x4f... 996 phys=7fee7000 ioremap 9970xffffc2000031d000-0xffffc2000031f000 8192 init_vdso_vars+0x112/0x210 9980xffffc2000031f000-0xffffc2000032b000 49152 cramfs_uncompress_init+0x2e ... 999 /0x80 pages=11 vmalloc N0=3 N1=3 N2=2 N3=3 10000xffffc2000033a000-0xffffc2000033d000 12288 sys_swapon+0x640/0xac0 ... 1001 pages=2 vmalloc N1=2 10020xffffc20000347000-0xffffc2000034c000 20480 xt_alloc_table_info+0xfe ... 1003 /0x130 [x_tables] pages=4 vmalloc N0=4 10040xffffffffa0000000-0xffffffffa000f000 61440 sys_init_module+0xc27/0x1d00 ... 1005 pages=14 vmalloc N2=14 10060xffffffffa000f000-0xffffffffa0014000 20480 sys_init_module+0xc27/0x1d00 ... 1007 pages=4 vmalloc N1=4 10080xffffffffa0014000-0xffffffffa0017000 12288 sys_init_module+0xc27/0x1d00 ... 1009 pages=2 vmalloc N1=2 10100xffffffffa0017000-0xffffffffa0022000 45056 sys_init_module+0xc27/0x1d00 ... 1011 pages=10 vmalloc N0=10 1012 1013.............................................................................. 1014 1015softirqs: 1016 1017Provides counts of softirq handlers serviced since boot time, for each cpu. 1018 1019> cat /proc/softirqs 1020 CPU0 CPU1 CPU2 CPU3 1021 HI: 0 0 0 0 1022 TIMER: 27166 27120 27097 27034 1023 NET_TX: 0 0 0 17 1024 NET_RX: 42 0 0 39 1025 BLOCK: 0 0 107 1121 1026 TASKLET: 0 0 0 290 1027 SCHED: 27035 26983 26971 26746 1028 HRTIMER: 0 0 0 0 1029 RCU: 1678 1769 2178 2250 1030 1031 10321.3 IDE devices in /proc/ide 1033---------------------------- 1034 1035The subdirectory /proc/ide contains information about all IDE devices of which 1036the kernel is aware. There is one subdirectory for each IDE controller, the 1037file drivers and a link for each IDE device, pointing to the device directory 1038in the controller specific subtree. 1039 1040The file drivers contains general information about the drivers used for the 1041IDE devices: 1042 1043 > cat /proc/ide/drivers 1044 ide-cdrom version 4.53 1045 ide-disk version 1.08 1046 1047More detailed information can be found in the controller specific 1048subdirectories. These are named ide0, ide1 and so on. Each of these 1049directories contains the files shown in table 1-6. 1050 1051 1052Table 1-6: IDE controller info in /proc/ide/ide? 1053.............................................................................. 1054 File Content 1055 channel IDE channel (0 or 1) 1056 config Configuration (only for PCI/IDE bridge) 1057 mate Mate name 1058 model Type/Chipset of IDE controller 1059.............................................................................. 1060 1061Each device connected to a controller has a separate subdirectory in the 1062controllers directory. The files listed in table 1-7 are contained in these 1063directories. 1064 1065 1066Table 1-7: IDE device information 1067.............................................................................. 1068 File Content 1069 cache The cache 1070 capacity Capacity of the medium (in 512Byte blocks) 1071 driver driver and version 1072 geometry physical and logical geometry 1073 identify device identify block 1074 media media type 1075 model device identifier 1076 settings device setup 1077 smart_thresholds IDE disk management thresholds 1078 smart_values IDE disk management values 1079.............................................................................. 1080 1081The most interesting file is settings. This file contains a nice overview of 1082the drive parameters: 1083 1084 # cat /proc/ide/ide0/hda/settings 1085 name value min max mode 1086 ---- ----- --- --- ---- 1087 bios_cyl 526 0 65535 rw 1088 bios_head 255 0 255 rw 1089 bios_sect 63 0 63 rw 1090 breada_readahead 4 0 127 rw 1091 bswap 0 0 1 r 1092 file_readahead 72 0 2097151 rw 1093 io_32bit 0 0 3 rw 1094 keepsettings 0 0 1 rw 1095 max_kb_per_request 122 1 127 rw 1096 multcount 0 0 8 rw 1097 nice1 1 0 1 rw 1098 nowerr 0 0 1 rw 1099 pio_mode write-only 0 255 w 1100 slow 0 0 1 rw 1101 unmaskirq 0 0 1 rw 1102 using_dma 0 0 1 rw 1103 1104 11051.4 Networking info in /proc/net 1106-------------------------------- 1107 1108The subdirectory /proc/net follows the usual pattern. Table 1-8 shows the 1109additional values you get for IP version 6 if you configure the kernel to 1110support this. Table 1-9 lists the files and their meaning. 1111 1112 1113Table 1-8: IPv6 info in /proc/net 1114.............................................................................. 1115 File Content 1116 udp6 UDP sockets (IPv6) 1117 tcp6 TCP sockets (IPv6) 1118 raw6 Raw device statistics (IPv6) 1119 igmp6 IP multicast addresses, which this host joined (IPv6) 1120 if_inet6 List of IPv6 interface addresses 1121 ipv6_route Kernel routing table for IPv6 1122 rt6_stats Global IPv6 routing tables statistics 1123 sockstat6 Socket statistics (IPv6) 1124 snmp6 Snmp data (IPv6) 1125.............................................................................. 1126 1127 1128Table 1-9: Network info in /proc/net 1129.............................................................................. 1130 File Content 1131 arp Kernel ARP table 1132 dev network devices with statistics 1133 dev_mcast the Layer2 multicast groups a device is listening too 1134 (interface index, label, number of references, number of bound 1135 addresses). 1136 dev_stat network device status 1137 ip_fwchains Firewall chain linkage 1138 ip_fwnames Firewall chain names 1139 ip_masq Directory containing the masquerading tables 1140 ip_masquerade Major masquerading table 1141 netstat Network statistics 1142 raw raw device statistics 1143 route Kernel routing table 1144 rpc Directory containing rpc info 1145 rt_cache Routing cache 1146 snmp SNMP data 1147 sockstat Socket statistics 1148 tcp TCP sockets 1149 udp UDP sockets 1150 unix UNIX domain sockets 1151 wireless Wireless interface data (Wavelan etc) 1152 igmp IP multicast addresses, which this host joined 1153 psched Global packet scheduler parameters. 1154 netlink List of PF_NETLINK sockets 1155 ip_mr_vifs List of multicast virtual interfaces 1156 ip_mr_cache List of multicast routing cache 1157.............................................................................. 1158 1159You can use this information to see which network devices are available in 1160your system and how much traffic was routed over those devices: 1161 1162 > cat /proc/net/dev 1163 Inter-|Receive |[... 1164 face |bytes packets errs drop fifo frame compressed multicast|[... 1165 lo: 908188 5596 0 0 0 0 0 0 [... 1166 ppp0:15475140 20721 410 0 0 410 0 0 [... 1167 eth0: 614530 7085 0 0 0 0 0 1 [... 1168 1169 ...] Transmit 1170 ...] bytes packets errs drop fifo colls carrier compressed 1171 ...] 908188 5596 0 0 0 0 0 0 1172 ...] 1375103 17405 0 0 0 0 0 0 1173 ...] 1703981 5535 0 0 0 3 0 0 1174 1175In addition, each Channel Bond interface has its own directory. For 1176example, the bond0 device will have a directory called /proc/net/bond0/. 1177It will contain information that is specific to that bond, such as the 1178current slaves of the bond, the link status of the slaves, and how 1179many times the slaves link has failed. 1180 11811.5 SCSI info 1182------------- 1183 1184If you have a SCSI host adapter in your system, you'll find a subdirectory 1185named after the driver for this adapter in /proc/scsi. You'll also see a list 1186of all recognized SCSI devices in /proc/scsi: 1187 1188 >cat /proc/scsi/scsi 1189 Attached devices: 1190 Host: scsi0 Channel: 00 Id: 00 Lun: 00 1191 Vendor: IBM Model: DGHS09U Rev: 03E0 1192 Type: Direct-Access ANSI SCSI revision: 03 1193 Host: scsi0 Channel: 00 Id: 06 Lun: 00 1194 Vendor: PIONEER Model: CD-ROM DR-U06S Rev: 1.04 1195 Type: CD-ROM ANSI SCSI revision: 02 1196 1197 1198The directory named after the driver has one file for each adapter found in 1199the system. These files contain information about the controller, including 1200the used IRQ and the IO address range. The amount of information shown is 1201dependent on the adapter you use. The example shows the output for an Adaptec 1202AHA-2940 SCSI adapter: 1203 1204 > cat /proc/scsi/aic7xxx/0 1205 1206 Adaptec AIC7xxx driver version: 5.1.19/3.2.4 1207 Compile Options: 1208 TCQ Enabled By Default : Disabled 1209 AIC7XXX_PROC_STATS : Disabled 1210 AIC7XXX_RESET_DELAY : 5 1211 Adapter Configuration: 1212 SCSI Adapter: Adaptec AHA-294X Ultra SCSI host adapter 1213 Ultra Wide Controller 1214 PCI MMAPed I/O Base: 0xeb001000 1215 Adapter SEEPROM Config: SEEPROM found and used. 1216 Adaptec SCSI BIOS: Enabled 1217 IRQ: 10 1218 SCBs: Active 0, Max Active 2, 1219 Allocated 15, HW 16, Page 255 1220 Interrupts: 160328 1221 BIOS Control Word: 0x18b6 1222 Adapter Control Word: 0x005b 1223 Extended Translation: Enabled 1224 Disconnect Enable Flags: 0xffff 1225 Ultra Enable Flags: 0x0001 1226 Tag Queue Enable Flags: 0x0000 1227 Ordered Queue Tag Flags: 0x0000 1228 Default Tag Queue Depth: 8 1229 Tagged Queue By Device array for aic7xxx host instance 0: 1230 {255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255} 1231 Actual queue depth per device for aic7xxx host instance 0: 1232 {1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1} 1233 Statistics: 1234 (scsi0:0:0:0) 1235 Device using Wide/Sync transfers at 40.0 MByte/sec, offset 8 1236 Transinfo settings: current(12/8/1/0), goal(12/8/1/0), user(12/15/1/0) 1237 Total transfers 160151 (74577 reads and 85574 writes) 1238 (scsi0:0:6:0) 1239 Device using Narrow/Sync transfers at 5.0 MByte/sec, offset 15 1240 Transinfo settings: current(50/15/0/0), goal(50/15/0/0), user(50/15/0/0) 1241 Total transfers 0 (0 reads and 0 writes) 1242 1243 12441.6 Parallel port info in /proc/parport 1245--------------------------------------- 1246 1247The directory /proc/parport contains information about the parallel ports of 1248your system. It has one subdirectory for each port, named after the port 1249number (0,1,2,...). 1250 1251These directories contain the four files shown in Table 1-10. 1252 1253 1254Table 1-10: Files in /proc/parport 1255.............................................................................. 1256 File Content 1257 autoprobe Any IEEE-1284 device ID information that has been acquired. 1258 devices list of the device drivers using that port. A + will appear by the 1259 name of the device currently using the port (it might not appear 1260 against any). 1261 hardware Parallel port's base address, IRQ line and DMA channel. 1262 irq IRQ that parport is using for that port. This is in a separate 1263 file to allow you to alter it by writing a new value in (IRQ 1264 number or none). 1265.............................................................................. 1266 12671.7 TTY info in /proc/tty 1268------------------------- 1269 1270Information about the available and actually used tty's can be found in the 1271directory /proc/tty.You'll find entries for drivers and line disciplines in 1272this directory, as shown in Table 1-11. 1273 1274 1275Table 1-11: Files in /proc/tty 1276.............................................................................. 1277 File Content 1278 drivers list of drivers and their usage 1279 ldiscs registered line disciplines 1280 driver/serial usage statistic and status of single tty lines 1281.............................................................................. 1282 1283To see which tty's are currently in use, you can simply look into the file 1284/proc/tty/drivers: 1285 1286 > cat /proc/tty/drivers 1287 pty_slave /dev/pts 136 0-255 pty:slave 1288 pty_master /dev/ptm 128 0-255 pty:master 1289 pty_slave /dev/ttyp 3 0-255 pty:slave 1290 pty_master /dev/pty 2 0-255 pty:master 1291 serial /dev/cua 5 64-67 serial:callout 1292 serial /dev/ttyS 4 64-67 serial 1293 /dev/tty0 /dev/tty0 4 0 system:vtmaster 1294 /dev/ptmx /dev/ptmx 5 2 system 1295 /dev/console /dev/console 5 1 system:console 1296 /dev/tty /dev/tty 5 0 system:/dev/tty 1297 unknown /dev/tty 4 1-63 console 1298 1299 13001.8 Miscellaneous kernel statistics in /proc/stat 1301------------------------------------------------- 1302 1303Various pieces of information about kernel activity are available in the 1304/proc/stat file. All of the numbers reported in this file are aggregates 1305since the system first booted. For a quick look, simply cat the file: 1306 1307 > cat /proc/stat 1308 cpu 2255 34 2290 22625563 6290 127 456 0 0 0 1309 cpu0 1132 34 1441 11311718 3675 127 438 0 0 0 1310 cpu1 1123 0 849 11313845 2614 0 18 0 0 0 1311 intr 114930548 113199788 3 0 5 263 0 4 [... lots more numbers ...] 1312 ctxt 1990473 1313 btime 1062191376 1314 processes 2915 1315 procs_running 1 1316 procs_blocked 0 1317 softirq 183433 0 21755 12 39 1137 231 21459 2263 1318 1319The very first "cpu" line aggregates the numbers in all of the other "cpuN" 1320lines. These numbers identify the amount of time the CPU has spent performing 1321different kinds of work. Time units are in USER_HZ (typically hundredths of a 1322second). The meanings of the columns are as follows, from left to right: 1323 1324- user: normal processes executing in user mode 1325- nice: niced processes executing in user mode 1326- system: processes executing in kernel mode 1327- idle: twiddling thumbs 1328- iowait: In a word, iowait stands for waiting for I/O to complete. But there 1329 are several problems: 1330 1. Cpu will not wait for I/O to complete, iowait is the time that a task is 1331 waiting for I/O to complete. When cpu goes into idle state for 1332 outstanding task io, another task will be scheduled on this CPU. 1333 2. In a multi-core CPU, the task waiting for I/O to complete is not running 1334 on any CPU, so the iowait of each CPU is difficult to calculate. 1335 3. The value of iowait field in /proc/stat will decrease in certain 1336 conditions. 1337 So, the iowait is not reliable by reading from /proc/stat. 1338- irq: servicing interrupts 1339- softirq: servicing softirqs 1340- steal: involuntary wait 1341- guest: running a normal guest 1342- guest_nice: running a niced guest 1343 1344The "intr" line gives counts of interrupts serviced since boot time, for each 1345of the possible system interrupts. The first column is the total of all 1346interrupts serviced including unnumbered architecture specific interrupts; 1347each subsequent column is the total for that particular numbered interrupt. 1348Unnumbered interrupts are not shown, only summed into the total. 1349 1350The "ctxt" line gives the total number of context switches across all CPUs. 1351 1352The "btime" line gives the time at which the system booted, in seconds since 1353the Unix epoch. 1354 1355The "processes" line gives the number of processes and threads created, which 1356includes (but is not limited to) those created by calls to the fork() and 1357clone() system calls. 1358 1359The "procs_running" line gives the total number of threads that are 1360running or ready to run (i.e., the total number of runnable threads). 1361 1362The "procs_blocked" line gives the number of processes currently blocked, 1363waiting for I/O to complete. 1364 1365The "softirq" line gives counts of softirqs serviced since boot time, for each 1366of the possible system softirqs. The first column is the total of all 1367softirqs serviced; each subsequent column is the total for that particular 1368softirq. 1369 1370 13711.9 Ext4 file system parameters 1372------------------------------- 1373 1374Information about mounted ext4 file systems can be found in 1375/proc/fs/ext4. Each mounted filesystem will have a directory in 1376/proc/fs/ext4 based on its device name (i.e., /proc/fs/ext4/hdc or 1377/proc/fs/ext4/dm-0). The files in each per-device directory are shown 1378in Table 1-12, below. 1379 1380Table 1-12: Files in /proc/fs/ext4/<devname> 1381.............................................................................. 1382 File Content 1383 mb_groups details of multiblock allocator buddy cache of free blocks 1384.............................................................................. 1385 13862.0 /proc/consoles 1387------------------ 1388Shows registered system console lines. 1389 1390To see which character device lines are currently used for the system console 1391/dev/console, you may simply look into the file /proc/consoles: 1392 1393 > cat /proc/consoles 1394 tty0 -WU (ECp) 4:7 1395 ttyS0 -W- (Ep) 4:64 1396 1397The columns are: 1398 1399 device name of the device 1400 operations R = can do read operations 1401 W = can do write operations 1402 U = can do unblank 1403 flags E = it is enabled 1404 C = it is preferred console 1405 B = it is primary boot console 1406 p = it is used for printk buffer 1407 b = it is not a TTY but a Braille device 1408 a = it is safe to use when cpu is offline 1409 major:minor major and minor number of the device separated by a colon 1410 1411------------------------------------------------------------------------------ 1412Summary 1413------------------------------------------------------------------------------ 1414The /proc file system serves information about the running system. It not only 1415allows access to process data but also allows you to request the kernel status 1416by reading files in the hierarchy. 1417 1418The directory structure of /proc reflects the types of information and makes 1419it easy, if not obvious, where to look for specific data. 1420------------------------------------------------------------------------------ 1421 1422------------------------------------------------------------------------------ 1423CHAPTER 2: MODIFYING SYSTEM PARAMETERS 1424------------------------------------------------------------------------------ 1425 1426------------------------------------------------------------------------------ 1427In This Chapter 1428------------------------------------------------------------------------------ 1429* Modifying kernel parameters by writing into files found in /proc/sys 1430* Exploring the files which modify certain parameters 1431* Review of the /proc/sys file tree 1432------------------------------------------------------------------------------ 1433 1434 1435A very interesting part of /proc is the directory /proc/sys. This is not only 1436a source of information, it also allows you to change parameters within the 1437kernel. Be very careful when attempting this. You can optimize your system, 1438but you can also cause it to crash. Never alter kernel parameters on a 1439production system. Set up a development machine and test to make sure that 1440everything works the way you want it to. You may have no alternative but to 1441reboot the machine once an error has been made. 1442 1443To change a value, simply echo the new value into the file. An example is 1444given below in the section on the file system data. You need to be root to do 1445this. You can create your own boot script to perform this every time your 1446system boots. 1447 1448The files in /proc/sys can be used to fine tune and monitor miscellaneous and 1449general things in the operation of the Linux kernel. Since some of the files 1450can inadvertently disrupt your system, it is advisable to read both 1451documentation and source before actually making adjustments. In any case, be 1452very careful when writing to any of these files. The entries in /proc may 1453change slightly between the 2.1.* and the 2.2 kernel, so if there is any doubt 1454review the kernel documentation in the directory /usr/src/linux/Documentation. 1455This chapter is heavily based on the documentation included in the pre 2.2 1456kernels, and became part of it in version 2.2.1 of the Linux kernel. 1457 1458Please see: Documentation/sysctl/ directory for descriptions of these 1459entries. 1460 1461------------------------------------------------------------------------------ 1462Summary 1463------------------------------------------------------------------------------ 1464Certain aspects of kernel behavior can be modified at runtime, without the 1465need to recompile the kernel, or even to reboot the system. The files in the 1466/proc/sys tree can not only be read, but also modified. You can use the echo 1467command to write value into these files, thereby changing the default settings 1468of the kernel. 1469------------------------------------------------------------------------------ 1470 1471------------------------------------------------------------------------------ 1472CHAPTER 3: PER-PROCESS PARAMETERS 1473------------------------------------------------------------------------------ 1474 14753.1 /proc/<pid>/oom_adj & /proc/<pid>/oom_score_adj- Adjust the oom-killer score 1476-------------------------------------------------------------------------------- 1477 1478These file can be used to adjust the badness heuristic used to select which 1479process gets killed in out of memory conditions. 1480 1481The badness heuristic assigns a value to each candidate task ranging from 0 1482(never kill) to 1000 (always kill) to determine which process is targeted. The 1483units are roughly a proportion along that range of allowed memory the process 1484may allocate from based on an estimation of its current memory and swap use. 1485For example, if a task is using all allowed memory, its badness score will be 14861000. If it is using half of its allowed memory, its score will be 500. 1487 1488There is an additional factor included in the badness score: the current memory 1489and swap usage is discounted by 3% for root processes. 1490 1491The amount of "allowed" memory depends on the context in which the oom killer 1492was called. If it is due to the memory assigned to the allocating task's cpuset 1493being exhausted, the allowed memory represents the set of mems assigned to that 1494cpuset. If it is due to a mempolicy's node(s) being exhausted, the allowed 1495memory represents the set of mempolicy nodes. If it is due to a memory 1496limit (or swap limit) being reached, the allowed memory is that configured 1497limit. Finally, if it is due to the entire system being out of memory, the 1498allowed memory represents all allocatable resources. 1499 1500The value of /proc/<pid>/oom_score_adj is added to the badness score before it 1501is used to determine which task to kill. Acceptable values range from -1000 1502(OOM_SCORE_ADJ_MIN) to +1000 (OOM_SCORE_ADJ_MAX). This allows userspace to 1503polarize the preference for oom killing either by always preferring a certain 1504task or completely disabling it. The lowest possible value, -1000, is 1505equivalent to disabling oom killing entirely for that task since it will always 1506report a badness score of 0. 1507 1508Consequently, it is very simple for userspace to define the amount of memory to 1509consider for each task. Setting a /proc/<pid>/oom_score_adj value of +500, for 1510example, is roughly equivalent to allowing the remainder of tasks sharing the 1511same system, cpuset, mempolicy, or memory controller resources to use at least 151250% more memory. A value of -500, on the other hand, would be roughly 1513equivalent to discounting 50% of the task's allowed memory from being considered 1514as scoring against the task. 1515 1516For backwards compatibility with previous kernels, /proc/<pid>/oom_adj may also 1517be used to tune the badness score. Its acceptable values range from -16 1518(OOM_ADJUST_MIN) to +15 (OOM_ADJUST_MAX) and a special value of -17 1519(OOM_DISABLE) to disable oom killing entirely for that task. Its value is 1520scaled linearly with /proc/<pid>/oom_score_adj. 1521 1522The value of /proc/<pid>/oom_score_adj may be reduced no lower than the last 1523value set by a CAP_SYS_RESOURCE process. To reduce the value any lower 1524requires CAP_SYS_RESOURCE. 1525 1526Caveat: when a parent task is selected, the oom killer will sacrifice any first 1527generation children with separate address spaces instead, if possible. This 1528avoids servers and important system daemons from being killed and loses the 1529minimal amount of work. 1530 1531 15323.2 /proc/<pid>/oom_score - Display current oom-killer score 1533------------------------------------------------------------- 1534 1535This file can be used to check the current score used by the oom-killer is for 1536any given <pid>. Use it together with /proc/<pid>/oom_score_adj to tune which 1537process should be killed in an out-of-memory situation. 1538 1539 15403.3 /proc/<pid>/io - Display the IO accounting fields 1541------------------------------------------------------- 1542 1543This file contains IO statistics for each running process 1544 1545Example 1546------- 1547 1548test:/tmp # dd if=/dev/zero of=/tmp/test.dat & 1549[1] 3828 1550 1551test:/tmp # cat /proc/3828/io 1552rchar: 323934931 1553wchar: 323929600 1554syscr: 632687 1555syscw: 632675 1556read_bytes: 0 1557write_bytes: 323932160 1558cancelled_write_bytes: 0 1559 1560 1561Description 1562----------- 1563 1564rchar 1565----- 1566 1567I/O counter: chars read 1568The number of bytes which this task has caused to be read from storage. This 1569is simply the sum of bytes which this process passed to read() and pread(). 1570It includes things like tty IO and it is unaffected by whether or not actual 1571physical disk IO was required (the read might have been satisfied from 1572pagecache) 1573 1574 1575wchar 1576----- 1577 1578I/O counter: chars written 1579The number of bytes which this task has caused, or shall cause to be written 1580to disk. Similar caveats apply here as with rchar. 1581 1582 1583syscr 1584----- 1585 1586I/O counter: read syscalls 1587Attempt to count the number of read I/O operations, i.e. syscalls like read() 1588and pread(). 1589 1590 1591syscw 1592----- 1593 1594I/O counter: write syscalls 1595Attempt to count the number of write I/O operations, i.e. syscalls like 1596write() and pwrite(). 1597 1598 1599read_bytes 1600---------- 1601 1602I/O counter: bytes read 1603Attempt to count the number of bytes which this process really did cause to 1604be fetched from the storage layer. Done at the submit_bio() level, so it is 1605accurate for block-backed filesystems. <please add status regarding NFS and 1606CIFS at a later time> 1607 1608 1609write_bytes 1610----------- 1611 1612I/O counter: bytes written 1613Attempt to count the number of bytes which this process caused to be sent to 1614the storage layer. This is done at page-dirtying time. 1615 1616 1617cancelled_write_bytes 1618--------------------- 1619 1620The big inaccuracy here is truncate. If a process writes 1MB to a file and 1621then deletes the file, it will in fact perform no writeout. But it will have 1622been accounted as having caused 1MB of write. 1623In other words: The number of bytes which this process caused to not happen, 1624by truncating pagecache. A task can cause "negative" IO too. If this task 1625truncates some dirty pagecache, some IO which another task has been accounted 1626for (in its write_bytes) will not be happening. We _could_ just subtract that 1627from the truncating task's write_bytes, but there is information loss in doing 1628that. 1629 1630 1631Note 1632---- 1633 1634At its current implementation state, this is a bit racy on 32-bit machines: if 1635process A reads process B's /proc/pid/io while process B is updating one of 1636those 64-bit counters, process A could see an intermediate result. 1637 1638 1639More information about this can be found within the taskstats documentation in 1640Documentation/accounting. 1641 16423.4 /proc/<pid>/coredump_filter - Core dump filtering settings 1643--------------------------------------------------------------- 1644When a process is dumped, all anonymous memory is written to a core file as 1645long as the size of the core file isn't limited. But sometimes we don't want 1646to dump some memory segments, for example, huge shared memory or DAX. 1647Conversely, sometimes we want to save file-backed memory segments into a core 1648file, not only the individual files. 1649 1650/proc/<pid>/coredump_filter allows you to customize which memory segments 1651will be dumped when the <pid> process is dumped. coredump_filter is a bitmask 1652of memory types. If a bit of the bitmask is set, memory segments of the 1653corresponding memory type are dumped, otherwise they are not dumped. 1654 1655The following 9 memory types are supported: 1656 - (bit 0) anonymous private memory 1657 - (bit 1) anonymous shared memory 1658 - (bit 2) file-backed private memory 1659 - (bit 3) file-backed shared memory 1660 - (bit 4) ELF header pages in file-backed private memory areas (it is 1661 effective only if the bit 2 is cleared) 1662 - (bit 5) hugetlb private memory 1663 - (bit 6) hugetlb shared memory 1664 - (bit 7) DAX private memory 1665 - (bit 8) DAX shared memory 1666 1667 Note that MMIO pages such as frame buffer are never dumped and vDSO pages 1668 are always dumped regardless of the bitmask status. 1669 1670 Note that bits 0-4 don't affect hugetlb or DAX memory. hugetlb memory is 1671 only affected by bit 5-6, and DAX is only affected by bits 7-8. 1672 1673The default value of coredump_filter is 0x33; this means all anonymous memory 1674segments, ELF header pages and hugetlb private memory are dumped. 1675 1676If you don't want to dump all shared memory segments attached to pid 1234, 1677write 0x31 to the process's proc file. 1678 1679 $ echo 0x31 > /proc/1234/coredump_filter 1680 1681When a new process is created, the process inherits the bitmask status from its 1682parent. It is useful to set up coredump_filter before the program runs. 1683For example: 1684 1685 $ echo 0x7 > /proc/self/coredump_filter 1686 $ ./some_program 1687 16883.5 /proc/<pid>/mountinfo - Information about mounts 1689-------------------------------------------------------- 1690 1691This file contains lines of the form: 1692 169336 35 98:0 /mnt1 /mnt2 rw,noatime master:1 - ext3 /dev/root rw,errors=continue 1694(1)(2)(3) (4) (5) (6) (7) (8) (9) (10) (11) 1695 1696(1) mount ID: unique identifier of the mount (may be reused after umount) 1697(2) parent ID: ID of parent (or of self for the top of the mount tree) 1698(3) major:minor: value of st_dev for files on filesystem 1699(4) root: root of the mount within the filesystem 1700(5) mount point: mount point relative to the process's root 1701(6) mount options: per mount options 1702(7) optional fields: zero or more fields of the form "tag[:value]" 1703(8) separator: marks the end of the optional fields 1704(9) filesystem type: name of filesystem of the form "type[.subtype]" 1705(10) mount source: filesystem specific information or "none" 1706(11) super options: per super block options 1707 1708Parsers should ignore all unrecognised optional fields. Currently the 1709possible optional fields are: 1710 1711shared:X mount is shared in peer group X 1712master:X mount is slave to peer group X 1713propagate_from:X mount is slave and receives propagation from peer group X (*) 1714unbindable mount is unbindable 1715 1716(*) X is the closest dominant peer group under the process's root. If 1717X is the immediate master of the mount, or if there's no dominant peer 1718group under the same root, then only the "master:X" field is present 1719and not the "propagate_from:X" field. 1720 1721For more information on mount propagation see: 1722 1723 Documentation/filesystems/sharedsubtree.txt 1724 1725 17263.6 /proc/<pid>/comm & /proc/<pid>/task/<tid>/comm 1727-------------------------------------------------------- 1728These files provide a method to access a tasks comm value. It also allows for 1729a task to set its own or one of its thread siblings comm value. The comm value 1730is limited in size compared to the cmdline value, so writing anything longer 1731then the kernel's TASK_COMM_LEN (currently 16 chars) will result in a truncated 1732comm value. 1733 1734 17353.7 /proc/<pid>/task/<tid>/children - Information about task children 1736------------------------------------------------------------------------- 1737This file provides a fast way to retrieve first level children pids 1738of a task pointed by <pid>/<tid> pair. The format is a space separated 1739stream of pids. 1740 1741Note the "first level" here -- if a child has own children they will 1742not be listed here, one needs to read /proc/<children-pid>/task/<tid>/children 1743to obtain the descendants. 1744 1745Since this interface is intended to be fast and cheap it doesn't 1746guarantee to provide precise results and some children might be 1747skipped, especially if they've exited right after we printed their 1748pids, so one need to either stop or freeze processes being inspected 1749if precise results are needed. 1750 1751 17523.8 /proc/<pid>/fdinfo/<fd> - Information about opened file 1753--------------------------------------------------------------- 1754This file provides information associated with an opened file. The regular 1755files have at least three fields -- 'pos', 'flags' and mnt_id. The 'pos' 1756represents the current offset of the opened file in decimal form [see lseek(2) 1757for details], 'flags' denotes the octal O_xxx mask the file has been 1758created with [see open(2) for details] and 'mnt_id' represents mount ID of 1759the file system containing the opened file [see 3.5 /proc/<pid>/mountinfo 1760for details]. 1761 1762A typical output is 1763 1764 pos: 0 1765 flags: 0100002 1766 mnt_id: 19 1767 1768All locks associated with a file descriptor are shown in its fdinfo too. 1769 1770lock: 1: FLOCK ADVISORY WRITE 359 00:13:11691 0 EOF 1771 1772The files such as eventfd, fsnotify, signalfd, epoll among the regular pos/flags 1773pair provide additional information particular to the objects they represent. 1774 1775 Eventfd files 1776 ~~~~~~~~~~~~~ 1777 pos: 0 1778 flags: 04002 1779 mnt_id: 9 1780 eventfd-count: 5a 1781 1782 where 'eventfd-count' is hex value of a counter. 1783 1784 Signalfd files 1785 ~~~~~~~~~~~~~~ 1786 pos: 0 1787 flags: 04002 1788 mnt_id: 9 1789 sigmask: 0000000000000200 1790 1791 where 'sigmask' is hex value of the signal mask associated 1792 with a file. 1793 1794 Epoll files 1795 ~~~~~~~~~~~ 1796 pos: 0 1797 flags: 02 1798 mnt_id: 9 1799 tfd: 5 events: 1d data: ffffffffffffffff pos:0 ino:61af sdev:7 1800 1801 where 'tfd' is a target file descriptor number in decimal form, 1802 'events' is events mask being watched and the 'data' is data 1803 associated with a target [see epoll(7) for more details]. 1804 1805 The 'pos' is current offset of the target file in decimal form 1806 [see lseek(2)], 'ino' and 'sdev' are inode and device numbers 1807 where target file resides, all in hex format. 1808 1809 Fsnotify files 1810 ~~~~~~~~~~~~~~ 1811 For inotify files the format is the following 1812 1813 pos: 0 1814 flags: 02000000 1815 inotify wd:3 ino:9e7e sdev:800013 mask:800afce ignored_mask:0 fhandle-bytes:8 fhandle-type:1 f_handle:7e9e0000640d1b6d 1816 1817 where 'wd' is a watch descriptor in decimal form, ie a target file 1818 descriptor number, 'ino' and 'sdev' are inode and device where the 1819 target file resides and the 'mask' is the mask of events, all in hex 1820 form [see inotify(7) for more details]. 1821 1822 If the kernel was built with exportfs support, the path to the target 1823 file is encoded as a file handle. The file handle is provided by three 1824 fields 'fhandle-bytes', 'fhandle-type' and 'f_handle', all in hex 1825 format. 1826 1827 If the kernel is built without exportfs support the file handle won't be 1828 printed out. 1829 1830 If there is no inotify mark attached yet the 'inotify' line will be omitted. 1831 1832 For fanotify files the format is 1833 1834 pos: 0 1835 flags: 02 1836 mnt_id: 9 1837 fanotify flags:10 event-flags:0 1838 fanotify mnt_id:12 mflags:40 mask:38 ignored_mask:40000003 1839 fanotify ino:4f969 sdev:800013 mflags:0 mask:3b ignored_mask:40000000 fhandle-bytes:8 fhandle-type:1 f_handle:69f90400c275b5b4 1840 1841 where fanotify 'flags' and 'event-flags' are values used in fanotify_init 1842 call, 'mnt_id' is the mount point identifier, 'mflags' is the value of 1843 flags associated with mark which are tracked separately from events 1844 mask. 'ino', 'sdev' are target inode and device, 'mask' is the events 1845 mask and 'ignored_mask' is the mask of events which are to be ignored. 1846 All in hex format. Incorporation of 'mflags', 'mask' and 'ignored_mask' 1847 does provide information about flags and mask used in fanotify_mark 1848 call [see fsnotify manpage for details]. 1849 1850 While the first three lines are mandatory and always printed, the rest is 1851 optional and may be omitted if no marks created yet. 1852 1853 Timerfd files 1854 ~~~~~~~~~~~~~ 1855 1856 pos: 0 1857 flags: 02 1858 mnt_id: 9 1859 clockid: 0 1860 ticks: 0 1861 settime flags: 01 1862 it_value: (0, 49406829) 1863 it_interval: (1, 0) 1864 1865 where 'clockid' is the clock type and 'ticks' is the number of the timer expirations 1866 that have occurred [see timerfd_create(2) for details]. 'settime flags' are 1867 flags in octal form been used to setup the timer [see timerfd_settime(2) for 1868 details]. 'it_value' is remaining time until the timer exiration. 1869 'it_interval' is the interval for the timer. Note the timer might be set up 1870 with TIMER_ABSTIME option which will be shown in 'settime flags', but 'it_value' 1871 still exhibits timer's remaining time. 1872 18733.9 /proc/<pid>/map_files - Information about memory mapped files 1874--------------------------------------------------------------------- 1875This directory contains symbolic links which represent memory mapped files 1876the process is maintaining. Example output: 1877 1878 | lr-------- 1 root root 64 Jan 27 11:24 333c600000-333c620000 -> /usr/lib64/ld-2.18.so 1879 | lr-------- 1 root root 64 Jan 27 11:24 333c81f000-333c820000 -> /usr/lib64/ld-2.18.so 1880 | lr-------- 1 root root 64 Jan 27 11:24 333c820000-333c821000 -> /usr/lib64/ld-2.18.so 1881 | ... 1882 | lr-------- 1 root root 64 Jan 27 11:24 35d0421000-35d0422000 -> /usr/lib64/libselinux.so.1 1883 | lr-------- 1 root root 64 Jan 27 11:24 400000-41a000 -> /usr/bin/ls 1884 1885The name of a link represents the virtual memory bounds of a mapping, i.e. 1886vm_area_struct::vm_start-vm_area_struct::vm_end. 1887 1888The main purpose of the map_files is to retrieve a set of memory mapped 1889files in a fast way instead of parsing /proc/<pid>/maps or 1890/proc/<pid>/smaps, both of which contain many more records. At the same 1891time one can open(2) mappings from the listings of two processes and 1892comparing their inode numbers to figure out which anonymous memory areas 1893are actually shared. 1894 18953.10 /proc/<pid>/timerslack_ns - Task timerslack value 1896--------------------------------------------------------- 1897This file provides the value of the task's timerslack value in nanoseconds. 1898This value specifies a amount of time that normal timers may be deferred 1899in order to coalesce timers and avoid unnecessary wakeups. 1900 1901This allows a task's interactivity vs power consumption trade off to be 1902adjusted. 1903 1904Writing 0 to the file will set the tasks timerslack to the default value. 1905 1906Valid values are from 0 - ULLONG_MAX 1907 1908An application setting the value must have PTRACE_MODE_ATTACH_FSCREDS level 1909permissions on the task specified to change its timerslack_ns value. 1910 19113.11 /proc/<pid>/patch_state - Livepatch patch operation state 1912----------------------------------------------------------------- 1913When CONFIG_LIVEPATCH is enabled, this file displays the value of the 1914patch state for the task. 1915 1916A value of '-1' indicates that no patch is in transition. 1917 1918A value of '0' indicates that a patch is in transition and the task is 1919unpatched. If the patch is being enabled, then the task hasn't been 1920patched yet. If the patch is being disabled, then the task has already 1921been unpatched. 1922 1923A value of '1' indicates that a patch is in transition and the task is 1924patched. If the patch is being enabled, then the task has already been 1925patched. If the patch is being disabled, then the task hasn't been 1926unpatched yet. 1927 1928 1929------------------------------------------------------------------------------ 1930Configuring procfs 1931------------------------------------------------------------------------------ 1932 19334.1 Mount options 1934--------------------- 1935 1936The following mount options are supported: 1937 1938 hidepid= Set /proc/<pid>/ access mode. 1939 gid= Set the group authorized to learn processes information. 1940 1941hidepid=0 means classic mode - everybody may access all /proc/<pid>/ directories 1942(default). 1943 1944hidepid=1 means users may not access any /proc/<pid>/ directories but their 1945own. Sensitive files like cmdline, sched*, status are now protected against 1946other users. This makes it impossible to learn whether any user runs 1947specific program (given the program doesn't reveal itself by its behaviour). 1948As an additional bonus, as /proc/<pid>/cmdline is unaccessible for other users, 1949poorly written programs passing sensitive information via program arguments are 1950now protected against local eavesdroppers. 1951 1952hidepid=2 means hidepid=1 plus all /proc/<pid>/ will be fully invisible to other 1953users. It doesn't mean that it hides a fact whether a process with a specific 1954pid value exists (it can be learned by other means, e.g. by "kill -0 $PID"), 1955but it hides process' uid and gid, which may be learned by stat()'ing 1956/proc/<pid>/ otherwise. It greatly complicates an intruder's task of gathering 1957information about running processes, whether some daemon runs with elevated 1958privileges, whether other user runs some sensitive program, whether other users 1959run any program at all, etc. 1960 1961gid= defines a group authorized to learn processes information otherwise 1962prohibited by hidepid=. If you use some daemon like identd which needs to learn 1963information about processes information, just add identd to this group. 1964
