]>
Commit | Line | Data |
---|---|---|
1da177e4 LT |
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 | ||
7 | 2.4.x update Jorge Nerin <comandante@zaralinux.com> November 14 2000 | |
349888ee | 8 | move /proc/sys Shen Feng <shen@cn.fujitsu.com> April 1 2009 |
1da177e4 LT |
9 | ------------------------------------------------------------------------------ |
10 | Version 1.3 Kernel version 2.2.12 | |
11 | Kernel version 2.4.0-test11-pre4 | |
12 | ------------------------------------------------------------------------------ | |
349888ee | 13 | fixes/update part 1.1 Stefani Seibold <stefani@seibold.net> June 9 2009 |
1da177e4 LT |
14 | |
15 | Table 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 | |
760df93e | 31 | 1.9 Ext4 file system parameters |
1da177e4 LT |
32 | |
33 | 2 Modifying System Parameters | |
760df93e SF |
34 | |
35 | 3 Per-Process Parameters | |
36 | 3.1 /proc/<pid>/oom_adj - Adjust the oom-killer score | |
37 | 3.2 /proc/<pid>/oom_score - Display current oom-killer score | |
38 | 3.3 /proc/<pid>/io - Display the IO accounting fields | |
39 | 3.4 /proc/<pid>/coredump_filter - Core dump filtering settings | |
40 | 3.5 /proc/<pid>/mountinfo - Information about mounts | |
4614a696 | 41 | 3.6 /proc/<pid>/comm & /proc/<pid>/task/<tid>/comm |
760df93e | 42 | |
1da177e4 LT |
43 | |
44 | ------------------------------------------------------------------------------ | |
45 | Preface | |
46 | ------------------------------------------------------------------------------ | |
47 | ||
48 | 0.1 Introduction/Credits | |
49 | ------------------------ | |
50 | ||
51 | This documentation is part of a soon (or so we hope) to be released book on | |
52 | the SuSE Linux distribution. As there is no complete documentation for the | |
53 | /proc file system and we've used many freely available sources to write these | |
54 | chapters, it seems only fair to give the work back to the Linux community. | |
55 | This work is based on the 2.2.* kernel version and the upcoming 2.4.*. I'm | |
56 | afraid it's still far from complete, but we hope it will be useful. As far as | |
57 | we know, it is the first 'all-in-one' document about the /proc file system. It | |
58 | is focused on the Intel x86 hardware, so if you are looking for PPC, ARM, | |
59 | SPARC, AXP, etc., features, you probably won't find what you are looking for. | |
60 | It also only covers IPv4 networking, not IPv6 nor other protocols - sorry. But | |
61 | additions and patches are welcome and will be added to this document if you | |
62 | mail them to Bodo. | |
63 | ||
64 | We'd like to thank Alan Cox, Rik van Riel, and Alexey Kuznetsov and a lot of | |
65 | other people for help compiling this documentation. We'd also like to extend a | |
66 | special thank you to Andi Kleen for documentation, which we relied on heavily | |
67 | to create this document, as well as the additional information he provided. | |
68 | Thanks to everybody else who contributed source or docs to the Linux kernel | |
69 | and helped create a great piece of software... :) | |
70 | ||
71 | If you have any comments, corrections or additions, please don't hesitate to | |
72 | contact Bodo Bauer at bb@ricochet.net. We'll be happy to add them to this | |
73 | document. | |
74 | ||
75 | The latest version of this document is available online at | |
76 | http://skaro.nightcrawler.com/~bb/Docs/Proc as HTML version. | |
77 | ||
78 | If the above direction does not works for you, ypu could try the kernel | |
79 | mailing list at linux-kernel@vger.kernel.org and/or try to reach me at | |
80 | comandante@zaralinux.com. | |
81 | ||
82 | 0.2 Legal Stuff | |
83 | --------------- | |
84 | ||
85 | We don't guarantee the correctness of this document, and if you come to us | |
86 | complaining about how you screwed up your system because of incorrect | |
87 | documentation, we won't feel responsible... | |
88 | ||
89 | ------------------------------------------------------------------------------ | |
90 | CHAPTER 1: COLLECTING SYSTEM INFORMATION | |
91 | ------------------------------------------------------------------------------ | |
92 | ||
93 | ------------------------------------------------------------------------------ | |
94 | In This Chapter | |
95 | ------------------------------------------------------------------------------ | |
96 | * Investigating the properties of the pseudo file system /proc and its | |
97 | ability to provide information on the running Linux system | |
98 | * Examining /proc's structure | |
99 | * Uncovering various information about the kernel and the processes running | |
100 | on the system | |
101 | ------------------------------------------------------------------------------ | |
102 | ||
103 | ||
104 | The proc file system acts as an interface to internal data structures in the | |
105 | kernel. It can be used to obtain information about the system and to change | |
106 | certain kernel parameters at runtime (sysctl). | |
107 | ||
108 | First, we'll take a look at the read-only parts of /proc. In Chapter 2, we | |
109 | show you how you can use /proc/sys to change settings. | |
110 | ||
111 | 1.1 Process-Specific Subdirectories | |
112 | ----------------------------------- | |
113 | ||
114 | The directory /proc contains (among other things) one subdirectory for each | |
115 | process running on the system, which is named after the process ID (PID). | |
116 | ||
117 | The link self points to the process reading the file system. Each process | |
118 | subdirectory has the entries listed in Table 1-1. | |
119 | ||
120 | ||
349888ee | 121 | Table 1-1: Process specific entries in /proc |
1da177e4 | 122 | .............................................................................. |
b813e931 DR |
123 | File Content |
124 | clear_refs Clears page referenced bits shown in smaps output | |
125 | cmdline Command line arguments | |
126 | cpu Current and last cpu in which it was executed (2.4)(smp) | |
127 | cwd Link to the current working directory | |
128 | environ Values of environment variables | |
129 | exe Link to the executable of this process | |
130 | fd Directory, which contains all file descriptors | |
131 | maps Memory maps to executables and library files (2.4) | |
132 | mem Memory held by this process | |
133 | root Link to the root directory of this process | |
134 | stat Process status | |
135 | statm Process memory status information | |
136 | status Process status in human readable form | |
137 | wchan If CONFIG_KALLSYMS is set, a pre-decoded wchan | |
2ec220e2 | 138 | stack Report full stack trace, enable via CONFIG_STACKTRACE |
349888ee SS |
139 | smaps a extension based on maps, showing the memory consumption of |
140 | each mapping | |
1da177e4 LT |
141 | .............................................................................. |
142 | ||
143 | For example, to get the status information of a process, all you have to do is | |
144 | read the file /proc/PID/status: | |
145 | ||
349888ee SS |
146 | >cat /proc/self/status |
147 | Name: cat | |
148 | State: R (running) | |
149 | Tgid: 5452 | |
150 | Pid: 5452 | |
151 | PPid: 743 | |
1da177e4 | 152 | TracerPid: 0 (2.4) |
349888ee SS |
153 | Uid: 501 501 501 501 |
154 | Gid: 100 100 100 100 | |
155 | FDSize: 256 | |
156 | Groups: 100 14 16 | |
157 | VmPeak: 5004 kB | |
158 | VmSize: 5004 kB | |
159 | VmLck: 0 kB | |
160 | VmHWM: 476 kB | |
161 | VmRSS: 476 kB | |
162 | VmData: 156 kB | |
163 | VmStk: 88 kB | |
164 | VmExe: 68 kB | |
165 | VmLib: 1412 kB | |
166 | VmPTE: 20 kb | |
167 | Threads: 1 | |
168 | SigQ: 0/28578 | |
169 | SigPnd: 0000000000000000 | |
170 | ShdPnd: 0000000000000000 | |
171 | SigBlk: 0000000000000000 | |
172 | SigIgn: 0000000000000000 | |
173 | SigCgt: 0000000000000000 | |
174 | CapInh: 00000000fffffeff | |
175 | CapPrm: 0000000000000000 | |
176 | CapEff: 0000000000000000 | |
177 | CapBnd: ffffffffffffffff | |
178 | voluntary_ctxt_switches: 0 | |
179 | nonvoluntary_ctxt_switches: 1 | |
1da177e4 LT |
180 | |
181 | This shows you nearly the same information you would get if you viewed it with | |
182 | the ps command. In fact, ps uses the proc file system to obtain its | |
349888ee SS |
183 | information. But you get a more detailed view of the process by reading the |
184 | file /proc/PID/status. It fields are described in table 1-2. | |
185 | ||
186 | The statm file contains more detailed information about the process | |
187 | memory usage. Its seven fields are explained in Table 1-3. The stat file | |
188 | contains details information about the process itself. Its fields are | |
189 | explained in Table 1-4. | |
1da177e4 | 190 | |
34e55232 KH |
191 | (for SMP CONFIG users) |
192 | For making accounting scalable, RSS related information are handled in | |
193 | asynchronous manner and the vaule may not be very precise. To see a precise | |
194 | snapshot of a moment, you can see /proc/<pid>/smaps file and scan page table. | |
195 | It's slow but very precise. | |
196 | ||
349888ee SS |
197 | Table 1-2: Contents of the statm files (as of 2.6.30-rc7) |
198 | .............................................................................. | |
199 | Field Content | |
200 | Name filename of the executable | |
201 | State state (R is running, S is sleeping, D is sleeping | |
202 | in an uninterruptible wait, Z is zombie, | |
203 | T is traced or stopped) | |
204 | Tgid thread group ID | |
205 | Pid process id | |
206 | PPid process id of the parent process | |
207 | TracerPid PID of process tracing this process (0 if not) | |
208 | Uid Real, effective, saved set, and file system UIDs | |
209 | Gid Real, effective, saved set, and file system GIDs | |
210 | FDSize number of file descriptor slots currently allocated | |
211 | Groups supplementary group list | |
212 | VmPeak peak virtual memory size | |
213 | VmSize total program size | |
214 | VmLck locked memory size | |
215 | VmHWM peak resident set size ("high water mark") | |
216 | VmRSS size of memory portions | |
217 | VmData size of data, stack, and text segments | |
218 | VmStk size of data, stack, and text segments | |
219 | VmExe size of text segment | |
220 | VmLib size of shared library code | |
221 | VmPTE size of page table entries | |
222 | Threads number of threads | |
223 | SigQ number of signals queued/max. number for queue | |
224 | SigPnd bitmap of pending signals for the thread | |
225 | ShdPnd bitmap of shared pending signals for the process | |
226 | SigBlk bitmap of blocked signals | |
227 | SigIgn bitmap of ignored signals | |
228 | SigCgt bitmap of catched signals | |
229 | CapInh bitmap of inheritable capabilities | |
230 | CapPrm bitmap of permitted capabilities | |
231 | CapEff bitmap of effective capabilities | |
232 | CapBnd bitmap of capabilities bounding set | |
233 | Cpus_allowed mask of CPUs on which this process may run | |
234 | Cpus_allowed_list Same as previous, but in "list format" | |
235 | Mems_allowed mask of memory nodes allowed to this process | |
236 | Mems_allowed_list Same as previous, but in "list format" | |
237 | voluntary_ctxt_switches number of voluntary context switches | |
238 | nonvoluntary_ctxt_switches number of non voluntary context switches | |
239 | .............................................................................. | |
1da177e4 | 240 | |
349888ee | 241 | Table 1-3: Contents of the statm files (as of 2.6.8-rc3) |
1da177e4 LT |
242 | .............................................................................. |
243 | Field Content | |
244 | size total program size (pages) (same as VmSize in status) | |
245 | resident size of memory portions (pages) (same as VmRSS in status) | |
246 | shared number of pages that are shared (i.e. backed by a file) | |
247 | trs number of pages that are 'code' (not including libs; broken, | |
248 | includes data segment) | |
249 | lrs number of pages of library (always 0 on 2.6) | |
250 | drs number of pages of data/stack (including libs; broken, | |
251 | includes library text) | |
252 | dt number of dirty pages (always 0 on 2.6) | |
253 | .............................................................................. | |
254 | ||
18d96779 | 255 | |
349888ee | 256 | Table 1-4: Contents of the stat files (as of 2.6.30-rc7) |
18d96779 KC |
257 | .............................................................................. |
258 | Field Content | |
259 | pid process id | |
260 | tcomm filename of the executable | |
261 | state state (R is running, S is sleeping, D is sleeping in an | |
262 | uninterruptible wait, Z is zombie, T is traced or stopped) | |
263 | ppid process id of the parent process | |
264 | pgrp pgrp of the process | |
265 | sid session id | |
266 | tty_nr tty the process uses | |
267 | tty_pgrp pgrp of the tty | |
268 | flags task flags | |
269 | min_flt number of minor faults | |
270 | cmin_flt number of minor faults with child's | |
271 | maj_flt number of major faults | |
272 | cmaj_flt number of major faults with child's | |
273 | utime user mode jiffies | |
274 | stime kernel mode jiffies | |
275 | cutime user mode jiffies with child's | |
276 | cstime kernel mode jiffies with child's | |
277 | priority priority level | |
278 | nice nice level | |
279 | num_threads number of threads | |
2e01e00e | 280 | it_real_value (obsolete, always 0) |
18d96779 KC |
281 | start_time time the process started after system boot |
282 | vsize virtual memory size | |
283 | rss resident set memory size | |
284 | rsslim current limit in bytes on the rss | |
285 | start_code address above which program text can run | |
286 | end_code address below which program text can run | |
287 | start_stack address of the start of the stack | |
288 | esp current value of ESP | |
289 | eip current value of EIP | |
349888ee SS |
290 | pending bitmap of pending signals |
291 | blocked bitmap of blocked signals | |
292 | sigign bitmap of ignored signals | |
293 | sigcatch bitmap of catched signals | |
18d96779 KC |
294 | wchan address where process went to sleep |
295 | 0 (place holder) | |
296 | 0 (place holder) | |
297 | exit_signal signal to send to parent thread on exit | |
298 | task_cpu which CPU the task is scheduled on | |
299 | rt_priority realtime priority | |
300 | policy scheduling policy (man sched_setscheduler) | |
301 | blkio_ticks time spent waiting for block IO | |
349888ee SS |
302 | gtime guest time of the task in jiffies |
303 | cgtime guest time of the task children in jiffies | |
18d96779 KC |
304 | .............................................................................. |
305 | ||
349888ee SS |
306 | The /proc/PID/map file containing the currently mapped memory regions and |
307 | their access permissions. | |
308 | ||
309 | The format is: | |
310 | ||
311 | address perms offset dev inode pathname | |
312 | ||
313 | 08048000-08049000 r-xp 00000000 03:00 8312 /opt/test | |
314 | 08049000-0804a000 rw-p 00001000 03:00 8312 /opt/test | |
315 | 0804a000-0806b000 rw-p 00000000 00:00 0 [heap] | |
316 | a7cb1000-a7cb2000 ---p 00000000 00:00 0 | |
d899bf7b | 317 | a7cb2000-a7eb2000 rw-p 00000000 00:00 0 [threadstack:001ff4b4] |
349888ee SS |
318 | a7eb2000-a7eb3000 ---p 00000000 00:00 0 |
319 | a7eb3000-a7ed5000 rw-p 00000000 00:00 0 | |
320 | a7ed5000-a8008000 r-xp 00000000 03:00 4222 /lib/libc.so.6 | |
321 | a8008000-a800a000 r--p 00133000 03:00 4222 /lib/libc.so.6 | |
322 | a800a000-a800b000 rw-p 00135000 03:00 4222 /lib/libc.so.6 | |
323 | a800b000-a800e000 rw-p 00000000 00:00 0 | |
324 | a800e000-a8022000 r-xp 00000000 03:00 14462 /lib/libpthread.so.0 | |
325 | a8022000-a8023000 r--p 00013000 03:00 14462 /lib/libpthread.so.0 | |
326 | a8023000-a8024000 rw-p 00014000 03:00 14462 /lib/libpthread.so.0 | |
327 | a8024000-a8027000 rw-p 00000000 00:00 0 | |
328 | a8027000-a8043000 r-xp 00000000 03:00 8317 /lib/ld-linux.so.2 | |
329 | a8043000-a8044000 r--p 0001b000 03:00 8317 /lib/ld-linux.so.2 | |
330 | a8044000-a8045000 rw-p 0001c000 03:00 8317 /lib/ld-linux.so.2 | |
331 | aff35000-aff4a000 rw-p 00000000 00:00 0 [stack] | |
332 | ffffe000-fffff000 r-xp 00000000 00:00 0 [vdso] | |
333 | ||
334 | where "address" is the address space in the process that it occupies, "perms" | |
335 | is a set of permissions: | |
336 | ||
337 | r = read | |
338 | w = write | |
339 | x = execute | |
340 | s = shared | |
341 | p = private (copy on write) | |
342 | ||
343 | "offset" is the offset into the mapping, "dev" is the device (major:minor), and | |
344 | "inode" is the inode on that device. 0 indicates that no inode is associated | |
345 | with the memory region, as the case would be with BSS (uninitialized data). | |
346 | The "pathname" shows the name associated file for this mapping. If the mapping | |
347 | is not associated with a file: | |
348 | ||
349 | [heap] = the heap of the program | |
350 | [stack] = the stack of the main process | |
351 | [vdso] = the "virtual dynamic shared object", | |
352 | the kernel system call handler | |
d899bf7b | 353 | [threadstack:xxxxxxxx] = the stack of the thread, xxxxxxxx is the stack size |
349888ee SS |
354 | |
355 | or if empty, the mapping is anonymous. | |
356 | ||
357 | ||
358 | The /proc/PID/smaps is an extension based on maps, showing the memory | |
359 | consumption for each of the process's mappings. For each of mappings there | |
360 | is a series of lines such as the following: | |
361 | ||
362 | 08048000-080bc000 r-xp 00000000 03:02 13130 /bin/bash | |
363 | Size: 1084 kB | |
364 | Rss: 892 kB | |
365 | Pss: 374 kB | |
366 | Shared_Clean: 892 kB | |
367 | Shared_Dirty: 0 kB | |
368 | Private_Clean: 0 kB | |
369 | Private_Dirty: 0 kB | |
370 | Referenced: 892 kB | |
371 | Swap: 0 kB | |
372 | KernelPageSize: 4 kB | |
373 | MMUPageSize: 4 kB | |
374 | ||
375 | The first of these lines shows the same information as is displayed for the | |
376 | mapping in /proc/PID/maps. The remaining lines show the size of the mapping, | |
377 | the amount of the mapping that is currently resident in RAM, the "proportional | |
378 | set size” (divide each shared page by the number of processes sharing it), the | |
379 | number of clean and dirty shared pages in the mapping, and the number of clean | |
380 | and dirty private pages in the mapping. The "Referenced" indicates the amount | |
381 | of memory currently marked as referenced or accessed. | |
382 | ||
383 | This file is only present if the CONFIG_MMU kernel configuration option is | |
384 | enabled. | |
18d96779 | 385 | |
398499d5 MB |
386 | The /proc/PID/clear_refs is used to reset the PG_Referenced and ACCESSED/YOUNG |
387 | bits on both physical and virtual pages associated with a process. | |
388 | To clear the bits for all the pages associated with the process | |
389 | > echo 1 > /proc/PID/clear_refs | |
390 | ||
391 | To clear the bits for the anonymous pages associated with the process | |
392 | > echo 2 > /proc/PID/clear_refs | |
393 | ||
394 | To clear the bits for the file mapped pages associated with the process | |
395 | > echo 3 > /proc/PID/clear_refs | |
396 | Any other value written to /proc/PID/clear_refs will have no effect. | |
397 | ||
398 | ||
1da177e4 LT |
399 | 1.2 Kernel data |
400 | --------------- | |
401 | ||
402 | Similar to the process entries, the kernel data files give information about | |
403 | the running kernel. The files used to obtain this information are contained in | |
349888ee | 404 | /proc and are listed in Table 1-5. Not all of these will be present in your |
1da177e4 LT |
405 | system. It depends on the kernel configuration and the loaded modules, which |
406 | files are there, and which are missing. | |
407 | ||
349888ee | 408 | Table 1-5: Kernel info in /proc |
1da177e4 LT |
409 | .............................................................................. |
410 | File Content | |
411 | apm Advanced power management info | |
412 | buddyinfo Kernel memory allocator information (see text) (2.5) | |
413 | bus Directory containing bus specific information | |
414 | cmdline Kernel command line | |
415 | cpuinfo Info about the CPU | |
416 | devices Available devices (block and character) | |
417 | dma Used DMS channels | |
418 | filesystems Supported filesystems | |
419 | driver Various drivers grouped here, currently rtc (2.4) | |
420 | execdomains Execdomains, related to security (2.4) | |
421 | fb Frame Buffer devices (2.4) | |
422 | fs File system parameters, currently nfs/exports (2.4) | |
423 | ide Directory containing info about the IDE subsystem | |
424 | interrupts Interrupt usage | |
425 | iomem Memory map (2.4) | |
426 | ioports I/O port usage | |
427 | irq Masks for irq to cpu affinity (2.4)(smp?) | |
428 | isapnp ISA PnP (Plug&Play) Info (2.4) | |
429 | kcore Kernel core image (can be ELF or A.OUT(deprecated in 2.4)) | |
430 | kmsg Kernel messages | |
431 | ksyms Kernel symbol table | |
432 | loadavg Load average of last 1, 5 & 15 minutes | |
433 | locks Kernel locks | |
434 | meminfo Memory info | |
435 | misc Miscellaneous | |
436 | modules List of loaded modules | |
437 | mounts Mounted filesystems | |
438 | net Networking info (see text) | |
439 | partitions Table of partitions known to the system | |
8b60756a | 440 | pci Deprecated info of PCI bus (new way -> /proc/bus/pci/, |
1da177e4 LT |
441 | decoupled by lspci (2.4) |
442 | rtc Real time clock | |
443 | scsi SCSI info (see text) | |
444 | slabinfo Slab pool info | |
d3d64df2 | 445 | softirqs softirq usage |
1da177e4 LT |
446 | stat Overall statistics |
447 | swaps Swap space utilization | |
448 | sys See chapter 2 | |
449 | sysvipc Info of SysVIPC Resources (msg, sem, shm) (2.4) | |
450 | tty Info of tty drivers | |
451 | uptime System uptime | |
452 | version Kernel version | |
453 | video bttv info of video resources (2.4) | |
a47a126a | 454 | vmallocinfo Show vmalloced areas |
1da177e4 LT |
455 | .............................................................................. |
456 | ||
457 | You can, for example, check which interrupts are currently in use and what | |
458 | they are used for by looking in the file /proc/interrupts: | |
459 | ||
460 | > cat /proc/interrupts | |
461 | CPU0 | |
462 | 0: 8728810 XT-PIC timer | |
463 | 1: 895 XT-PIC keyboard | |
464 | 2: 0 XT-PIC cascade | |
465 | 3: 531695 XT-PIC aha152x | |
466 | 4: 2014133 XT-PIC serial | |
467 | 5: 44401 XT-PIC pcnet_cs | |
468 | 8: 2 XT-PIC rtc | |
469 | 11: 8 XT-PIC i82365 | |
470 | 12: 182918 XT-PIC PS/2 Mouse | |
471 | 13: 1 XT-PIC fpu | |
472 | 14: 1232265 XT-PIC ide0 | |
473 | 15: 7 XT-PIC ide1 | |
474 | NMI: 0 | |
475 | ||
476 | In 2.4.* a couple of lines where added to this file LOC & ERR (this time is the | |
477 | output of a SMP machine): | |
478 | ||
479 | > cat /proc/interrupts | |
480 | ||
481 | CPU0 CPU1 | |
482 | 0: 1243498 1214548 IO-APIC-edge timer | |
483 | 1: 8949 8958 IO-APIC-edge keyboard | |
484 | 2: 0 0 XT-PIC cascade | |
485 | 5: 11286 10161 IO-APIC-edge soundblaster | |
486 | 8: 1 0 IO-APIC-edge rtc | |
487 | 9: 27422 27407 IO-APIC-edge 3c503 | |
488 | 12: 113645 113873 IO-APIC-edge PS/2 Mouse | |
489 | 13: 0 0 XT-PIC fpu | |
490 | 14: 22491 24012 IO-APIC-edge ide0 | |
491 | 15: 2183 2415 IO-APIC-edge ide1 | |
492 | 17: 30564 30414 IO-APIC-level eth0 | |
493 | 18: 177 164 IO-APIC-level bttv | |
494 | NMI: 2457961 2457959 | |
495 | LOC: 2457882 2457881 | |
496 | ERR: 2155 | |
497 | ||
498 | NMI is incremented in this case because every timer interrupt generates a NMI | |
499 | (Non Maskable Interrupt) which is used by the NMI Watchdog to detect lockups. | |
500 | ||
501 | LOC is the local interrupt counter of the internal APIC of every CPU. | |
502 | ||
503 | ERR is incremented in the case of errors in the IO-APIC bus (the bus that | |
504 | connects the CPUs in a SMP system. This means that an error has been detected, | |
505 | the IO-APIC automatically retry the transmission, so it should not be a big | |
506 | problem, but you should read the SMP-FAQ. | |
507 | ||
38e760a1 JK |
508 | In 2.6.2* /proc/interrupts was expanded again. This time the goal was for |
509 | /proc/interrupts to display every IRQ vector in use by the system, not | |
510 | just those considered 'most important'. The new vectors are: | |
511 | ||
512 | THR -- interrupt raised when a machine check threshold counter | |
513 | (typically counting ECC corrected errors of memory or cache) exceeds | |
514 | a configurable threshold. Only available on some systems. | |
515 | ||
516 | TRM -- a thermal event interrupt occurs when a temperature threshold | |
517 | has been exceeded for the CPU. This interrupt may also be generated | |
518 | when the temperature drops back to normal. | |
519 | ||
520 | SPU -- a spurious interrupt is some interrupt that was raised then lowered | |
521 | by some IO device before it could be fully processed by the APIC. Hence | |
522 | the APIC sees the interrupt but does not know what device it came from. | |
523 | For this case the APIC will generate the interrupt with a IRQ vector | |
524 | of 0xff. This might also be generated by chipset bugs. | |
525 | ||
526 | RES, CAL, TLB -- rescheduling, call and TLB flush interrupts are | |
527 | sent from one CPU to another per the needs of the OS. Typically, | |
528 | their statistics are used by kernel developers and interested users to | |
19f59460 | 529 | determine the occurrence of interrupts of the given type. |
38e760a1 JK |
530 | |
531 | The above IRQ vectors are displayed only when relevent. For example, | |
532 | the threshold vector does not exist on x86_64 platforms. Others are | |
533 | suppressed when the system is a uniprocessor. As of this writing, only | |
534 | i386 and x86_64 platforms support the new IRQ vector displays. | |
535 | ||
536 | Of some interest is the introduction of the /proc/irq directory to 2.4. | |
1da177e4 LT |
537 | It could be used to set IRQ to CPU affinity, this means that you can "hook" an |
538 | IRQ to only one CPU, or to exclude a CPU of handling IRQs. The contents of the | |
18404756 MK |
539 | irq subdir is one subdir for each IRQ, and two files; default_smp_affinity and |
540 | prof_cpu_mask. | |
1da177e4 LT |
541 | |
542 | For example | |
543 | > ls /proc/irq/ | |
544 | 0 10 12 14 16 18 2 4 6 8 prof_cpu_mask | |
18404756 | 545 | 1 11 13 15 17 19 3 5 7 9 default_smp_affinity |
1da177e4 LT |
546 | > ls /proc/irq/0/ |
547 | smp_affinity | |
548 | ||
18404756 MK |
549 | smp_affinity is a bitmask, in which you can specify which CPUs can handle the |
550 | IRQ, you can set it by doing: | |
1da177e4 | 551 | |
18404756 MK |
552 | > echo 1 > /proc/irq/10/smp_affinity |
553 | ||
554 | This means that only the first CPU will handle the IRQ, but you can also echo | |
555 | 5 which means that only the first and fourth CPU can handle the IRQ. | |
1da177e4 | 556 | |
18404756 MK |
557 | The contents of each smp_affinity file is the same by default: |
558 | ||
559 | > cat /proc/irq/0/smp_affinity | |
560 | ffffffff | |
1da177e4 | 561 | |
18404756 MK |
562 | The default_smp_affinity mask applies to all non-active IRQs, which are the |
563 | IRQs which have not yet been allocated/activated, and hence which lack a | |
564 | /proc/irq/[0-9]* directory. | |
1da177e4 | 565 | |
18404756 MK |
566 | prof_cpu_mask specifies which CPUs are to be profiled by the system wide |
567 | profiler. Default value is ffffffff (all cpus). | |
1da177e4 LT |
568 | |
569 | The way IRQs are routed is handled by the IO-APIC, and it's Round Robin | |
570 | between all the CPUs which are allowed to handle it. As usual the kernel has | |
571 | more info than you and does a better job than you, so the defaults are the | |
572 | best choice for almost everyone. | |
573 | ||
574 | There are three more important subdirectories in /proc: net, scsi, and sys. | |
575 | The general rule is that the contents, or even the existence of these | |
576 | directories, depend on your kernel configuration. If SCSI is not enabled, the | |
577 | directory scsi may not exist. The same is true with the net, which is there | |
578 | only when networking support is present in the running kernel. | |
579 | ||
580 | The slabinfo file gives information about memory usage at the slab level. | |
581 | Linux uses slab pools for memory management above page level in version 2.2. | |
582 | Commonly used objects have their own slab pool (such as network buffers, | |
583 | directory cache, and so on). | |
584 | ||
585 | .............................................................................. | |
586 | ||
587 | > cat /proc/buddyinfo | |
588 | ||
589 | Node 0, zone DMA 0 4 5 4 4 3 ... | |
590 | Node 0, zone Normal 1 0 0 1 101 8 ... | |
591 | Node 0, zone HighMem 2 0 0 1 1 0 ... | |
592 | ||
593 | Memory fragmentation is a problem under some workloads, and buddyinfo is a | |
594 | useful tool for helping diagnose these problems. Buddyinfo will give you a | |
595 | clue as to how big an area you can safely allocate, or why a previous | |
596 | allocation failed. | |
597 | ||
598 | Each column represents the number of pages of a certain order which are | |
599 | available. In this case, there are 0 chunks of 2^0*PAGE_SIZE available in | |
600 | ZONE_DMA, 4 chunks of 2^1*PAGE_SIZE in ZONE_DMA, 101 chunks of 2^4*PAGE_SIZE | |
601 | available in ZONE_NORMAL, etc... | |
602 | ||
603 | .............................................................................. | |
604 | ||
605 | meminfo: | |
606 | ||
607 | Provides information about distribution and utilization of memory. This | |
608 | varies by architecture and compile options. The following is from a | |
609 | 16GB PIII, which has highmem enabled. You may not have all of these fields. | |
610 | ||
611 | > cat /proc/meminfo | |
612 | ||
613 | ||
614 | MemTotal: 16344972 kB | |
615 | MemFree: 13634064 kB | |
616 | Buffers: 3656 kB | |
617 | Cached: 1195708 kB | |
618 | SwapCached: 0 kB | |
619 | Active: 891636 kB | |
620 | Inactive: 1077224 kB | |
621 | HighTotal: 15597528 kB | |
622 | HighFree: 13629632 kB | |
623 | LowTotal: 747444 kB | |
624 | LowFree: 4432 kB | |
625 | SwapTotal: 0 kB | |
626 | SwapFree: 0 kB | |
627 | Dirty: 968 kB | |
628 | Writeback: 0 kB | |
b88473f7 | 629 | AnonPages: 861800 kB |
1da177e4 | 630 | Mapped: 280372 kB |
b88473f7 MS |
631 | Slab: 284364 kB |
632 | SReclaimable: 159856 kB | |
633 | SUnreclaim: 124508 kB | |
634 | PageTables: 24448 kB | |
635 | NFS_Unstable: 0 kB | |
636 | Bounce: 0 kB | |
637 | WritebackTmp: 0 kB | |
1da177e4 LT |
638 | CommitLimit: 7669796 kB |
639 | Committed_AS: 100056 kB | |
1da177e4 LT |
640 | VmallocTotal: 112216 kB |
641 | VmallocUsed: 428 kB | |
642 | VmallocChunk: 111088 kB | |
643 | ||
644 | MemTotal: Total usable ram (i.e. physical ram minus a few reserved | |
645 | bits and the kernel binary code) | |
646 | MemFree: The sum of LowFree+HighFree | |
647 | Buffers: Relatively temporary storage for raw disk blocks | |
648 | shouldn't get tremendously large (20MB or so) | |
649 | Cached: in-memory cache for files read from the disk (the | |
650 | pagecache). Doesn't include SwapCached | |
651 | SwapCached: Memory that once was swapped out, is swapped back in but | |
652 | still also is in the swapfile (if memory is needed it | |
653 | doesn't need to be swapped out AGAIN because it is already | |
654 | in the swapfile. This saves I/O) | |
655 | Active: Memory that has been used more recently and usually not | |
656 | reclaimed unless absolutely necessary. | |
657 | Inactive: Memory which has been less recently used. It is more | |
658 | eligible to be reclaimed for other purposes | |
659 | HighTotal: | |
660 | HighFree: Highmem is all memory above ~860MB of physical memory | |
661 | Highmem areas are for use by userspace programs, or | |
662 | for the pagecache. The kernel must use tricks to access | |
663 | this memory, making it slower to access than lowmem. | |
664 | LowTotal: | |
665 | LowFree: Lowmem is memory which can be used for everything that | |
3f6dee9b | 666 | highmem can be used for, but it is also available for the |
1da177e4 LT |
667 | kernel's use for its own data structures. Among many |
668 | other things, it is where everything from the Slab is | |
669 | allocated. Bad things happen when you're out of lowmem. | |
670 | SwapTotal: total amount of swap space available | |
671 | SwapFree: Memory which has been evicted from RAM, and is temporarily | |
672 | on the disk | |
673 | Dirty: Memory which is waiting to get written back to the disk | |
674 | Writeback: Memory which is actively being written back to the disk | |
b88473f7 | 675 | AnonPages: Non-file backed pages mapped into userspace page tables |
1da177e4 | 676 | Mapped: files which have been mmaped, such as libraries |
e82443c0 | 677 | Slab: in-kernel data structures cache |
b88473f7 MS |
678 | SReclaimable: Part of Slab, that might be reclaimed, such as caches |
679 | SUnreclaim: Part of Slab, that cannot be reclaimed on memory pressure | |
680 | PageTables: amount of memory dedicated to the lowest level of page | |
681 | tables. | |
682 | NFS_Unstable: NFS pages sent to the server, but not yet committed to stable | |
683 | storage | |
684 | Bounce: Memory used for block device "bounce buffers" | |
685 | WritebackTmp: Memory used by FUSE for temporary writeback buffers | |
1da177e4 LT |
686 | CommitLimit: Based on the overcommit ratio ('vm.overcommit_ratio'), |
687 | this is the total amount of memory currently available to | |
688 | be allocated on the system. This limit is only adhered to | |
689 | if strict overcommit accounting is enabled (mode 2 in | |
690 | 'vm.overcommit_memory'). | |
691 | The CommitLimit is calculated with the following formula: | |
692 | CommitLimit = ('vm.overcommit_ratio' * Physical RAM) + Swap | |
693 | For example, on a system with 1G of physical RAM and 7G | |
694 | of swap with a `vm.overcommit_ratio` of 30 it would | |
695 | yield a CommitLimit of 7.3G. | |
696 | For more details, see the memory overcommit documentation | |
697 | in vm/overcommit-accounting. | |
698 | Committed_AS: The amount of memory presently allocated on the system. | |
699 | The committed memory is a sum of all of the memory which | |
700 | has been allocated by processes, even if it has not been | |
701 | "used" by them as of yet. A process which malloc()'s 1G | |
702 | of memory, but only touches 300M of it will only show up | |
703 | as using 300M of memory even if it has the address space | |
704 | allocated for the entire 1G. This 1G is memory which has | |
705 | been "committed" to by the VM and can be used at any time | |
706 | by the allocating application. With strict overcommit | |
707 | enabled on the system (mode 2 in 'vm.overcommit_memory'), | |
708 | allocations which would exceed the CommitLimit (detailed | |
709 | above) will not be permitted. This is useful if one needs | |
710 | to guarantee that processes will not fail due to lack of | |
711 | memory once that memory has been successfully allocated. | |
1da177e4 LT |
712 | VmallocTotal: total size of vmalloc memory area |
713 | VmallocUsed: amount of vmalloc area which is used | |
19f59460 | 714 | VmallocChunk: largest contiguous block of vmalloc area which is free |
1da177e4 | 715 | |
a47a126a ED |
716 | .............................................................................. |
717 | ||
718 | vmallocinfo: | |
719 | ||
720 | Provides information about vmalloced/vmaped areas. One line per area, | |
721 | containing the virtual address range of the area, size in bytes, | |
722 | caller information of the creator, and optional information depending | |
723 | on the kind of area : | |
724 | ||
725 | pages=nr number of pages | |
726 | phys=addr if a physical address was specified | |
727 | ioremap I/O mapping (ioremap() and friends) | |
728 | vmalloc vmalloc() area | |
729 | vmap vmap()ed pages | |
730 | user VM_USERMAP area | |
731 | vpages buffer for pages pointers was vmalloced (huge area) | |
732 | N<node>=nr (Only on NUMA kernels) | |
733 | Number of pages allocated on memory node <node> | |
734 | ||
735 | > cat /proc/vmallocinfo | |
736 | 0xffffc20000000000-0xffffc20000201000 2101248 alloc_large_system_hash+0x204 ... | |
737 | /0x2c0 pages=512 vmalloc N0=128 N1=128 N2=128 N3=128 | |
738 | 0xffffc20000201000-0xffffc20000302000 1052672 alloc_large_system_hash+0x204 ... | |
739 | /0x2c0 pages=256 vmalloc N0=64 N1=64 N2=64 N3=64 | |
740 | 0xffffc20000302000-0xffffc20000304000 8192 acpi_tb_verify_table+0x21/0x4f... | |
741 | phys=7fee8000 ioremap | |
742 | 0xffffc20000304000-0xffffc20000307000 12288 acpi_tb_verify_table+0x21/0x4f... | |
743 | phys=7fee7000 ioremap | |
744 | 0xffffc2000031d000-0xffffc2000031f000 8192 init_vdso_vars+0x112/0x210 | |
745 | 0xffffc2000031f000-0xffffc2000032b000 49152 cramfs_uncompress_init+0x2e ... | |
746 | /0x80 pages=11 vmalloc N0=3 N1=3 N2=2 N3=3 | |
747 | 0xffffc2000033a000-0xffffc2000033d000 12288 sys_swapon+0x640/0xac0 ... | |
748 | pages=2 vmalloc N1=2 | |
749 | 0xffffc20000347000-0xffffc2000034c000 20480 xt_alloc_table_info+0xfe ... | |
750 | /0x130 [x_tables] pages=4 vmalloc N0=4 | |
751 | 0xffffffffa0000000-0xffffffffa000f000 61440 sys_init_module+0xc27/0x1d00 ... | |
752 | pages=14 vmalloc N2=14 | |
753 | 0xffffffffa000f000-0xffffffffa0014000 20480 sys_init_module+0xc27/0x1d00 ... | |
754 | pages=4 vmalloc N1=4 | |
755 | 0xffffffffa0014000-0xffffffffa0017000 12288 sys_init_module+0xc27/0x1d00 ... | |
756 | pages=2 vmalloc N1=2 | |
757 | 0xffffffffa0017000-0xffffffffa0022000 45056 sys_init_module+0xc27/0x1d00 ... | |
758 | pages=10 vmalloc N0=10 | |
1da177e4 | 759 | |
d3d64df2 KK |
760 | .............................................................................. |
761 | ||
762 | softirqs: | |
763 | ||
764 | Provides counts of softirq handlers serviced since boot time, for each cpu. | |
765 | ||
766 | > cat /proc/softirqs | |
767 | CPU0 CPU1 CPU2 CPU3 | |
768 | HI: 0 0 0 0 | |
769 | TIMER: 27166 27120 27097 27034 | |
770 | NET_TX: 0 0 0 17 | |
771 | NET_RX: 42 0 0 39 | |
772 | BLOCK: 0 0 107 1121 | |
773 | TASKLET: 0 0 0 290 | |
774 | SCHED: 27035 26983 26971 26746 | |
775 | HRTIMER: 0 0 0 0 | |
776 | RCU: 1678 1769 2178 2250 | |
777 | ||
778 | ||
1da177e4 LT |
779 | 1.3 IDE devices in /proc/ide |
780 | ---------------------------- | |
781 | ||
782 | The subdirectory /proc/ide contains information about all IDE devices of which | |
783 | the kernel is aware. There is one subdirectory for each IDE controller, the | |
784 | file drivers and a link for each IDE device, pointing to the device directory | |
785 | in the controller specific subtree. | |
786 | ||
787 | The file drivers contains general information about the drivers used for the | |
788 | IDE devices: | |
789 | ||
790 | > cat /proc/ide/drivers | |
791 | ide-cdrom version 4.53 | |
792 | ide-disk version 1.08 | |
793 | ||
794 | More detailed information can be found in the controller specific | |
795 | subdirectories. These are named ide0, ide1 and so on. Each of these | |
349888ee | 796 | directories contains the files shown in table 1-6. |
1da177e4 LT |
797 | |
798 | ||
349888ee | 799 | Table 1-6: IDE controller info in /proc/ide/ide? |
1da177e4 LT |
800 | .............................................................................. |
801 | File Content | |
802 | channel IDE channel (0 or 1) | |
803 | config Configuration (only for PCI/IDE bridge) | |
804 | mate Mate name | |
805 | model Type/Chipset of IDE controller | |
806 | .............................................................................. | |
807 | ||
808 | Each device connected to a controller has a separate subdirectory in the | |
349888ee | 809 | controllers directory. The files listed in table 1-7 are contained in these |
1da177e4 LT |
810 | directories. |
811 | ||
812 | ||
349888ee | 813 | Table 1-7: IDE device information |
1da177e4 LT |
814 | .............................................................................. |
815 | File Content | |
816 | cache The cache | |
817 | capacity Capacity of the medium (in 512Byte blocks) | |
818 | driver driver and version | |
819 | geometry physical and logical geometry | |
820 | identify device identify block | |
821 | media media type | |
822 | model device identifier | |
823 | settings device setup | |
824 | smart_thresholds IDE disk management thresholds | |
825 | smart_values IDE disk management values | |
826 | .............................................................................. | |
827 | ||
828 | The most interesting file is settings. This file contains a nice overview of | |
829 | the drive parameters: | |
830 | ||
831 | # cat /proc/ide/ide0/hda/settings | |
832 | name value min max mode | |
833 | ---- ----- --- --- ---- | |
834 | bios_cyl 526 0 65535 rw | |
835 | bios_head 255 0 255 rw | |
836 | bios_sect 63 0 63 rw | |
837 | breada_readahead 4 0 127 rw | |
838 | bswap 0 0 1 r | |
839 | file_readahead 72 0 2097151 rw | |
840 | io_32bit 0 0 3 rw | |
841 | keepsettings 0 0 1 rw | |
842 | max_kb_per_request 122 1 127 rw | |
843 | multcount 0 0 8 rw | |
844 | nice1 1 0 1 rw | |
845 | nowerr 0 0 1 rw | |
846 | pio_mode write-only 0 255 w | |
847 | slow 0 0 1 rw | |
848 | unmaskirq 0 0 1 rw | |
849 | using_dma 0 0 1 rw | |
850 | ||
851 | ||
852 | 1.4 Networking info in /proc/net | |
853 | -------------------------------- | |
854 | ||
349888ee | 855 | The subdirectory /proc/net follows the usual pattern. Table 1-8 shows the |
1da177e4 | 856 | additional values you get for IP version 6 if you configure the kernel to |
349888ee | 857 | support this. Table 1-9 lists the files and their meaning. |
1da177e4 LT |
858 | |
859 | ||
349888ee | 860 | Table 1-8: IPv6 info in /proc/net |
1da177e4 LT |
861 | .............................................................................. |
862 | File Content | |
863 | udp6 UDP sockets (IPv6) | |
864 | tcp6 TCP sockets (IPv6) | |
865 | raw6 Raw device statistics (IPv6) | |
866 | igmp6 IP multicast addresses, which this host joined (IPv6) | |
867 | if_inet6 List of IPv6 interface addresses | |
868 | ipv6_route Kernel routing table for IPv6 | |
869 | rt6_stats Global IPv6 routing tables statistics | |
870 | sockstat6 Socket statistics (IPv6) | |
871 | snmp6 Snmp data (IPv6) | |
872 | .............................................................................. | |
873 | ||
874 | ||
349888ee | 875 | Table 1-9: Network info in /proc/net |
1da177e4 LT |
876 | .............................................................................. |
877 | File Content | |
878 | arp Kernel ARP table | |
879 | dev network devices with statistics | |
880 | dev_mcast the Layer2 multicast groups a device is listening too | |
881 | (interface index, label, number of references, number of bound | |
882 | addresses). | |
883 | dev_stat network device status | |
884 | ip_fwchains Firewall chain linkage | |
885 | ip_fwnames Firewall chain names | |
886 | ip_masq Directory containing the masquerading tables | |
887 | ip_masquerade Major masquerading table | |
888 | netstat Network statistics | |
889 | raw raw device statistics | |
890 | route Kernel routing table | |
891 | rpc Directory containing rpc info | |
892 | rt_cache Routing cache | |
893 | snmp SNMP data | |
894 | sockstat Socket statistics | |
895 | tcp TCP sockets | |
896 | tr_rif Token ring RIF routing table | |
897 | udp UDP sockets | |
898 | unix UNIX domain sockets | |
899 | wireless Wireless interface data (Wavelan etc) | |
900 | igmp IP multicast addresses, which this host joined | |
901 | psched Global packet scheduler parameters. | |
902 | netlink List of PF_NETLINK sockets | |
903 | ip_mr_vifs List of multicast virtual interfaces | |
904 | ip_mr_cache List of multicast routing cache | |
905 | .............................................................................. | |
906 | ||
907 | You can use this information to see which network devices are available in | |
908 | your system and how much traffic was routed over those devices: | |
909 | ||
910 | > cat /proc/net/dev | |
911 | Inter-|Receive |[... | |
912 | face |bytes packets errs drop fifo frame compressed multicast|[... | |
913 | lo: 908188 5596 0 0 0 0 0 0 [... | |
914 | ppp0:15475140 20721 410 0 0 410 0 0 [... | |
915 | eth0: 614530 7085 0 0 0 0 0 1 [... | |
916 | ||
917 | ...] Transmit | |
918 | ...] bytes packets errs drop fifo colls carrier compressed | |
919 | ...] 908188 5596 0 0 0 0 0 0 | |
920 | ...] 1375103 17405 0 0 0 0 0 0 | |
921 | ...] 1703981 5535 0 0 0 3 0 0 | |
922 | ||
923 | In addition, each Channel Bond interface has it's own directory. For | |
924 | example, the bond0 device will have a directory called /proc/net/bond0/. | |
925 | It will contain information that is specific to that bond, such as the | |
926 | current slaves of the bond, the link status of the slaves, and how | |
927 | many times the slaves link has failed. | |
928 | ||
929 | 1.5 SCSI info | |
930 | ------------- | |
931 | ||
932 | If you have a SCSI host adapter in your system, you'll find a subdirectory | |
933 | named after the driver for this adapter in /proc/scsi. You'll also see a list | |
934 | of all recognized SCSI devices in /proc/scsi: | |
935 | ||
936 | >cat /proc/scsi/scsi | |
937 | Attached devices: | |
938 | Host: scsi0 Channel: 00 Id: 00 Lun: 00 | |
939 | Vendor: IBM Model: DGHS09U Rev: 03E0 | |
940 | Type: Direct-Access ANSI SCSI revision: 03 | |
941 | Host: scsi0 Channel: 00 Id: 06 Lun: 00 | |
942 | Vendor: PIONEER Model: CD-ROM DR-U06S Rev: 1.04 | |
943 | Type: CD-ROM ANSI SCSI revision: 02 | |
944 | ||
945 | ||
946 | The directory named after the driver has one file for each adapter found in | |
947 | the system. These files contain information about the controller, including | |
948 | the used IRQ and the IO address range. The amount of information shown is | |
949 | dependent on the adapter you use. The example shows the output for an Adaptec | |
950 | AHA-2940 SCSI adapter: | |
951 | ||
952 | > cat /proc/scsi/aic7xxx/0 | |
953 | ||
954 | Adaptec AIC7xxx driver version: 5.1.19/3.2.4 | |
955 | Compile Options: | |
956 | TCQ Enabled By Default : Disabled | |
957 | AIC7XXX_PROC_STATS : Disabled | |
958 | AIC7XXX_RESET_DELAY : 5 | |
959 | Adapter Configuration: | |
960 | SCSI Adapter: Adaptec AHA-294X Ultra SCSI host adapter | |
961 | Ultra Wide Controller | |
962 | PCI MMAPed I/O Base: 0xeb001000 | |
963 | Adapter SEEPROM Config: SEEPROM found and used. | |
964 | Adaptec SCSI BIOS: Enabled | |
965 | IRQ: 10 | |
966 | SCBs: Active 0, Max Active 2, | |
967 | Allocated 15, HW 16, Page 255 | |
968 | Interrupts: 160328 | |
969 | BIOS Control Word: 0x18b6 | |
970 | Adapter Control Word: 0x005b | |
971 | Extended Translation: Enabled | |
972 | Disconnect Enable Flags: 0xffff | |
973 | Ultra Enable Flags: 0x0001 | |
974 | Tag Queue Enable Flags: 0x0000 | |
975 | Ordered Queue Tag Flags: 0x0000 | |
976 | Default Tag Queue Depth: 8 | |
977 | Tagged Queue By Device array for aic7xxx host instance 0: | |
978 | {255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255} | |
979 | Actual queue depth per device for aic7xxx host instance 0: | |
980 | {1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1} | |
981 | Statistics: | |
982 | (scsi0:0:0:0) | |
983 | Device using Wide/Sync transfers at 40.0 MByte/sec, offset 8 | |
984 | Transinfo settings: current(12/8/1/0), goal(12/8/1/0), user(12/15/1/0) | |
985 | Total transfers 160151 (74577 reads and 85574 writes) | |
986 | (scsi0:0:6:0) | |
987 | Device using Narrow/Sync transfers at 5.0 MByte/sec, offset 15 | |
988 | Transinfo settings: current(50/15/0/0), goal(50/15/0/0), user(50/15/0/0) | |
989 | Total transfers 0 (0 reads and 0 writes) | |
990 | ||
991 | ||
992 | 1.6 Parallel port info in /proc/parport | |
993 | --------------------------------------- | |
994 | ||
995 | The directory /proc/parport contains information about the parallel ports of | |
996 | your system. It has one subdirectory for each port, named after the port | |
997 | number (0,1,2,...). | |
998 | ||
349888ee | 999 | These directories contain the four files shown in Table 1-10. |
1da177e4 LT |
1000 | |
1001 | ||
349888ee | 1002 | Table 1-10: Files in /proc/parport |
1da177e4 LT |
1003 | .............................................................................. |
1004 | File Content | |
1005 | autoprobe Any IEEE-1284 device ID information that has been acquired. | |
1006 | devices list of the device drivers using that port. A + will appear by the | |
1007 | name of the device currently using the port (it might not appear | |
1008 | against any). | |
1009 | hardware Parallel port's base address, IRQ line and DMA channel. | |
1010 | irq IRQ that parport is using for that port. This is in a separate | |
1011 | file to allow you to alter it by writing a new value in (IRQ | |
1012 | number or none). | |
1013 | .............................................................................. | |
1014 | ||
1015 | 1.7 TTY info in /proc/tty | |
1016 | ------------------------- | |
1017 | ||
1018 | Information about the available and actually used tty's can be found in the | |
1019 | directory /proc/tty.You'll find entries for drivers and line disciplines in | |
349888ee | 1020 | this directory, as shown in Table 1-11. |
1da177e4 LT |
1021 | |
1022 | ||
349888ee | 1023 | Table 1-11: Files in /proc/tty |
1da177e4 LT |
1024 | .............................................................................. |
1025 | File Content | |
1026 | drivers list of drivers and their usage | |
1027 | ldiscs registered line disciplines | |
1028 | driver/serial usage statistic and status of single tty lines | |
1029 | .............................................................................. | |
1030 | ||
1031 | To see which tty's are currently in use, you can simply look into the file | |
1032 | /proc/tty/drivers: | |
1033 | ||
1034 | > cat /proc/tty/drivers | |
1035 | pty_slave /dev/pts 136 0-255 pty:slave | |
1036 | pty_master /dev/ptm 128 0-255 pty:master | |
1037 | pty_slave /dev/ttyp 3 0-255 pty:slave | |
1038 | pty_master /dev/pty 2 0-255 pty:master | |
1039 | serial /dev/cua 5 64-67 serial:callout | |
1040 | serial /dev/ttyS 4 64-67 serial | |
1041 | /dev/tty0 /dev/tty0 4 0 system:vtmaster | |
1042 | /dev/ptmx /dev/ptmx 5 2 system | |
1043 | /dev/console /dev/console 5 1 system:console | |
1044 | /dev/tty /dev/tty 5 0 system:/dev/tty | |
1045 | unknown /dev/tty 4 1-63 console | |
1046 | ||
1047 | ||
1048 | 1.8 Miscellaneous kernel statistics in /proc/stat | |
1049 | ------------------------------------------------- | |
1050 | ||
1051 | Various pieces of information about kernel activity are available in the | |
1052 | /proc/stat file. All of the numbers reported in this file are aggregates | |
1053 | since the system first booted. For a quick look, simply cat the file: | |
1054 | ||
1055 | > cat /proc/stat | |
c574358e ED |
1056 | cpu 2255 34 2290 22625563 6290 127 456 0 0 |
1057 | cpu0 1132 34 1441 11311718 3675 127 438 0 0 | |
1058 | cpu1 1123 0 849 11313845 2614 0 18 0 0 | |
1da177e4 LT |
1059 | intr 114930548 113199788 3 0 5 263 0 4 [... lots more numbers ...] |
1060 | ctxt 1990473 | |
1061 | btime 1062191376 | |
1062 | processes 2915 | |
1063 | procs_running 1 | |
1064 | procs_blocked 0 | |
d3d64df2 | 1065 | softirq 183433 0 21755 12 39 1137 231 21459 2263 |
1da177e4 LT |
1066 | |
1067 | The very first "cpu" line aggregates the numbers in all of the other "cpuN" | |
1068 | lines. These numbers identify the amount of time the CPU has spent performing | |
1069 | different kinds of work. Time units are in USER_HZ (typically hundredths of a | |
1070 | second). The meanings of the columns are as follows, from left to right: | |
1071 | ||
1072 | - user: normal processes executing in user mode | |
1073 | - nice: niced processes executing in user mode | |
1074 | - system: processes executing in kernel mode | |
1075 | - idle: twiddling thumbs | |
1076 | - iowait: waiting for I/O to complete | |
1077 | - irq: servicing interrupts | |
1078 | - softirq: servicing softirqs | |
b68f2c3a | 1079 | - steal: involuntary wait |
ce0e7b28 RO |
1080 | - guest: running a normal guest |
1081 | - guest_nice: running a niced guest | |
1da177e4 LT |
1082 | |
1083 | The "intr" line gives counts of interrupts serviced since boot time, for each | |
1084 | of the possible system interrupts. The first column is the total of all | |
1085 | interrupts serviced; each subsequent column is the total for that particular | |
1086 | interrupt. | |
1087 | ||
1088 | The "ctxt" line gives the total number of context switches across all CPUs. | |
1089 | ||
1090 | The "btime" line gives the time at which the system booted, in seconds since | |
1091 | the Unix epoch. | |
1092 | ||
1093 | The "processes" line gives the number of processes and threads created, which | |
1094 | includes (but is not limited to) those created by calls to the fork() and | |
1095 | clone() system calls. | |
1096 | ||
e3cc2226 LGE |
1097 | The "procs_running" line gives the total number of threads that are |
1098 | running or ready to run (i.e., the total number of runnable threads). | |
1da177e4 LT |
1099 | |
1100 | The "procs_blocked" line gives the number of processes currently blocked, | |
1101 | waiting for I/O to complete. | |
1102 | ||
d3d64df2 KK |
1103 | The "softirq" line gives counts of softirqs serviced since boot time, for each |
1104 | of the possible system softirqs. The first column is the total of all | |
1105 | softirqs serviced; each subsequent column is the total for that particular | |
1106 | softirq. | |
1107 | ||
37515fac | 1108 | |
c9de560d AT |
1109 | 1.9 Ext4 file system parameters |
1110 | ------------------------------ | |
37515fac TT |
1111 | |
1112 | Information about mounted ext4 file systems can be found in | |
1113 | /proc/fs/ext4. Each mounted filesystem will have a directory in | |
1114 | /proc/fs/ext4 based on its device name (i.e., /proc/fs/ext4/hdc or | |
1115 | /proc/fs/ext4/dm-0). The files in each per-device directory are shown | |
349888ee | 1116 | in Table 1-12, below. |
37515fac | 1117 | |
349888ee | 1118 | Table 1-12: Files in /proc/fs/ext4/<devname> |
37515fac TT |
1119 | .............................................................................. |
1120 | File Content | |
1121 | mb_groups details of multiblock allocator buddy cache of free blocks | |
37515fac TT |
1122 | .............................................................................. |
1123 | ||
1da177e4 LT |
1124 | |
1125 | ------------------------------------------------------------------------------ | |
1126 | Summary | |
1127 | ------------------------------------------------------------------------------ | |
1128 | The /proc file system serves information about the running system. It not only | |
1129 | allows access to process data but also allows you to request the kernel status | |
1130 | by reading files in the hierarchy. | |
1131 | ||
1132 | The directory structure of /proc reflects the types of information and makes | |
1133 | it easy, if not obvious, where to look for specific data. | |
1134 | ------------------------------------------------------------------------------ | |
1135 | ||
1136 | ------------------------------------------------------------------------------ | |
1137 | CHAPTER 2: MODIFYING SYSTEM PARAMETERS | |
1138 | ------------------------------------------------------------------------------ | |
1139 | ||
1140 | ------------------------------------------------------------------------------ | |
1141 | In This Chapter | |
1142 | ------------------------------------------------------------------------------ | |
1143 | * Modifying kernel parameters by writing into files found in /proc/sys | |
1144 | * Exploring the files which modify certain parameters | |
1145 | * Review of the /proc/sys file tree | |
1146 | ------------------------------------------------------------------------------ | |
1147 | ||
1148 | ||
1149 | A very interesting part of /proc is the directory /proc/sys. This is not only | |
1150 | a source of information, it also allows you to change parameters within the | |
1151 | kernel. Be very careful when attempting this. You can optimize your system, | |
1152 | but you can also cause it to crash. Never alter kernel parameters on a | |
1153 | production system. Set up a development machine and test to make sure that | |
1154 | everything works the way you want it to. You may have no alternative but to | |
1155 | reboot the machine once an error has been made. | |
1156 | ||
1157 | To change a value, simply echo the new value into the file. An example is | |
1158 | given below in the section on the file system data. You need to be root to do | |
1159 | this. You can create your own boot script to perform this every time your | |
1160 | system boots. | |
1161 | ||
1162 | The files in /proc/sys can be used to fine tune and monitor miscellaneous and | |
1163 | general things in the operation of the Linux kernel. Since some of the files | |
1164 | can inadvertently disrupt your system, it is advisable to read both | |
1165 | documentation and source before actually making adjustments. In any case, be | |
1166 | very careful when writing to any of these files. The entries in /proc may | |
1167 | change slightly between the 2.1.* and the 2.2 kernel, so if there is any doubt | |
1168 | review the kernel documentation in the directory /usr/src/linux/Documentation. | |
1169 | This chapter is heavily based on the documentation included in the pre 2.2 | |
1170 | kernels, and became part of it in version 2.2.1 of the Linux kernel. | |
1171 | ||
760df93e | 1172 | Please see: Documentation/sysctls/ directory for descriptions of these |
db0fb184 | 1173 | entries. |
9d0243bc | 1174 | |
760df93e SF |
1175 | ------------------------------------------------------------------------------ |
1176 | Summary | |
1177 | ------------------------------------------------------------------------------ | |
1178 | Certain aspects of kernel behavior can be modified at runtime, without the | |
1179 | need to recompile the kernel, or even to reboot the system. The files in the | |
1180 | /proc/sys tree can not only be read, but also modified. You can use the echo | |
1181 | command to write value into these files, thereby changing the default settings | |
1182 | of the kernel. | |
1183 | ------------------------------------------------------------------------------ | |
9d0243bc | 1184 | |
760df93e SF |
1185 | ------------------------------------------------------------------------------ |
1186 | CHAPTER 3: PER-PROCESS PARAMETERS | |
1187 | ------------------------------------------------------------------------------ | |
1da177e4 | 1188 | |
760df93e | 1189 | 3.1 /proc/<pid>/oom_adj - Adjust the oom-killer score |
d7ff0dbf JFM |
1190 | ------------------------------------------------------ |
1191 | ||
0753ba01 KM |
1192 | This file can be used to adjust the score used to select which processes |
1193 | should be killed in an out-of-memory situation. Giving it a high score will | |
1194 | increase the likelihood of this process being killed by the oom-killer. Valid | |
1195 | values are in the range -16 to +15, plus the special value -17, which disables | |
1196 | oom-killing altogether for this process. | |
d7ff0dbf | 1197 | |
9e9e3cbc EP |
1198 | The process to be killed in an out-of-memory situation is selected among all others |
1199 | based on its badness score. This value equals the original memory size of the process | |
1200 | and is then updated according to its CPU time (utime + stime) and the | |
1201 | run time (uptime - start time). The longer it runs the smaller is the score. | |
1202 | Badness score is divided by the square root of the CPU time and then by | |
1203 | the double square root of the run time. | |
1204 | ||
1205 | Swapped out tasks are killed first. Half of each child's memory size is added to | |
1206 | the parent's score if they do not share the same memory. Thus forking servers | |
1207 | are the prime candidates to be killed. Having only one 'hungry' child will make | |
1208 | parent less preferable than the child. | |
1209 | ||
1210 | /proc/<pid>/oom_score shows process' current badness score. | |
1211 | ||
1212 | The following heuristics are then applied: | |
1213 | * if the task was reniced, its score doubles | |
1214 | * superuser or direct hardware access tasks (CAP_SYS_ADMIN, CAP_SYS_RESOURCE | |
1215 | or CAP_SYS_RAWIO) have their score divided by 4 | |
495789a5 | 1216 | * if oom condition happened in one cpuset and checked process does not belong |
9e9e3cbc EP |
1217 | to it, its score is divided by 8 |
1218 | * the resulting score is multiplied by two to the power of oom_adj, i.e. | |
1219 | points <<= oom_adj when it is positive and | |
1220 | points >>= -(oom_adj) otherwise | |
1221 | ||
1222 | The task with the highest badness score is then selected and its children | |
1223 | are killed, process itself will be killed in an OOM situation when it does | |
1224 | not have children or some of them disabled oom like described above. | |
1225 | ||
760df93e | 1226 | 3.2 /proc/<pid>/oom_score - Display current oom-killer score |
d7ff0dbf JFM |
1227 | ------------------------------------------------------------- |
1228 | ||
d7ff0dbf JFM |
1229 | This file can be used to check the current score used by the oom-killer is for |
1230 | any given <pid>. Use it together with /proc/<pid>/oom_adj to tune which | |
1231 | process should be killed in an out-of-memory situation. | |
1da177e4 | 1232 | |
f9c99463 | 1233 | |
760df93e | 1234 | 3.3 /proc/<pid>/io - Display the IO accounting fields |
f9c99463 RK |
1235 | ------------------------------------------------------- |
1236 | ||
1237 | This file contains IO statistics for each running process | |
1238 | ||
1239 | Example | |
1240 | ------- | |
1241 | ||
1242 | test:/tmp # dd if=/dev/zero of=/tmp/test.dat & | |
1243 | [1] 3828 | |
1244 | ||
1245 | test:/tmp # cat /proc/3828/io | |
1246 | rchar: 323934931 | |
1247 | wchar: 323929600 | |
1248 | syscr: 632687 | |
1249 | syscw: 632675 | |
1250 | read_bytes: 0 | |
1251 | write_bytes: 323932160 | |
1252 | cancelled_write_bytes: 0 | |
1253 | ||
1254 | ||
1255 | Description | |
1256 | ----------- | |
1257 | ||
1258 | rchar | |
1259 | ----- | |
1260 | ||
1261 | I/O counter: chars read | |
1262 | The number of bytes which this task has caused to be read from storage. This | |
1263 | is simply the sum of bytes which this process passed to read() and pread(). | |
1264 | It includes things like tty IO and it is unaffected by whether or not actual | |
1265 | physical disk IO was required (the read might have been satisfied from | |
1266 | pagecache) | |
1267 | ||
1268 | ||
1269 | wchar | |
1270 | ----- | |
1271 | ||
1272 | I/O counter: chars written | |
1273 | The number of bytes which this task has caused, or shall cause to be written | |
1274 | to disk. Similar caveats apply here as with rchar. | |
1275 | ||
1276 | ||
1277 | syscr | |
1278 | ----- | |
1279 | ||
1280 | I/O counter: read syscalls | |
1281 | Attempt to count the number of read I/O operations, i.e. syscalls like read() | |
1282 | and pread(). | |
1283 | ||
1284 | ||
1285 | syscw | |
1286 | ----- | |
1287 | ||
1288 | I/O counter: write syscalls | |
1289 | Attempt to count the number of write I/O operations, i.e. syscalls like | |
1290 | write() and pwrite(). | |
1291 | ||
1292 | ||
1293 | read_bytes | |
1294 | ---------- | |
1295 | ||
1296 | I/O counter: bytes read | |
1297 | Attempt to count the number of bytes which this process really did cause to | |
1298 | be fetched from the storage layer. Done at the submit_bio() level, so it is | |
1299 | accurate for block-backed filesystems. <please add status regarding NFS and | |
1300 | CIFS at a later time> | |
1301 | ||
1302 | ||
1303 | write_bytes | |
1304 | ----------- | |
1305 | ||
1306 | I/O counter: bytes written | |
1307 | Attempt to count the number of bytes which this process caused to be sent to | |
1308 | the storage layer. This is done at page-dirtying time. | |
1309 | ||
1310 | ||
1311 | cancelled_write_bytes | |
1312 | --------------------- | |
1313 | ||
1314 | The big inaccuracy here is truncate. If a process writes 1MB to a file and | |
1315 | then deletes the file, it will in fact perform no writeout. But it will have | |
1316 | been accounted as having caused 1MB of write. | |
1317 | In other words: The number of bytes which this process caused to not happen, | |
1318 | by truncating pagecache. A task can cause "negative" IO too. If this task | |
1319 | truncates some dirty pagecache, some IO which another task has been accounted | |
1320 | for (in it's write_bytes) will not be happening. We _could_ just subtract that | |
1321 | from the truncating task's write_bytes, but there is information loss in doing | |
1322 | that. | |
1323 | ||
1324 | ||
1325 | Note | |
1326 | ---- | |
1327 | ||
1328 | At its current implementation state, this is a bit racy on 32-bit machines: if | |
1329 | process A reads process B's /proc/pid/io while process B is updating one of | |
1330 | those 64-bit counters, process A could see an intermediate result. | |
1331 | ||
1332 | ||
1333 | More information about this can be found within the taskstats documentation in | |
1334 | Documentation/accounting. | |
1335 | ||
760df93e | 1336 | 3.4 /proc/<pid>/coredump_filter - Core dump filtering settings |
bb90110d KH |
1337 | --------------------------------------------------------------- |
1338 | When a process is dumped, all anonymous memory is written to a core file as | |
1339 | long as the size of the core file isn't limited. But sometimes we don't want | |
1340 | to dump some memory segments, for example, huge shared memory. Conversely, | |
1341 | sometimes we want to save file-backed memory segments into a core file, not | |
1342 | only the individual files. | |
1343 | ||
1344 | /proc/<pid>/coredump_filter allows you to customize which memory segments | |
1345 | will be dumped when the <pid> process is dumped. coredump_filter is a bitmask | |
1346 | of memory types. If a bit of the bitmask is set, memory segments of the | |
1347 | corresponding memory type are dumped, otherwise they are not dumped. | |
1348 | ||
e575f111 | 1349 | The following 7 memory types are supported: |
bb90110d KH |
1350 | - (bit 0) anonymous private memory |
1351 | - (bit 1) anonymous shared memory | |
1352 | - (bit 2) file-backed private memory | |
1353 | - (bit 3) file-backed shared memory | |
b261dfea HK |
1354 | - (bit 4) ELF header pages in file-backed private memory areas (it is |
1355 | effective only if the bit 2 is cleared) | |
e575f111 KM |
1356 | - (bit 5) hugetlb private memory |
1357 | - (bit 6) hugetlb shared memory | |
bb90110d KH |
1358 | |
1359 | Note that MMIO pages such as frame buffer are never dumped and vDSO pages | |
1360 | are always dumped regardless of the bitmask status. | |
1361 | ||
e575f111 KM |
1362 | Note bit 0-4 doesn't effect any hugetlb memory. hugetlb memory are only |
1363 | effected by bit 5-6. | |
1364 | ||
1365 | Default value of coredump_filter is 0x23; this means all anonymous memory | |
1366 | segments and hugetlb private memory are dumped. | |
bb90110d KH |
1367 | |
1368 | If you don't want to dump all shared memory segments attached to pid 1234, | |
e575f111 | 1369 | write 0x21 to the process's proc file. |
bb90110d | 1370 | |
e575f111 | 1371 | $ echo 0x21 > /proc/1234/coredump_filter |
bb90110d KH |
1372 | |
1373 | When a new process is created, the process inherits the bitmask status from its | |
1374 | parent. It is useful to set up coredump_filter before the program runs. | |
1375 | For example: | |
1376 | ||
1377 | $ echo 0x7 > /proc/self/coredump_filter | |
1378 | $ ./some_program | |
1379 | ||
760df93e | 1380 | 3.5 /proc/<pid>/mountinfo - Information about mounts |
2d4d4864 RP |
1381 | -------------------------------------------------------- |
1382 | ||
1383 | This file contains lines of the form: | |
1384 | ||
1385 | 36 35 98:0 /mnt1 /mnt2 rw,noatime master:1 - ext3 /dev/root rw,errors=continue | |
1386 | (1)(2)(3) (4) (5) (6) (7) (8) (9) (10) (11) | |
1387 | ||
1388 | (1) mount ID: unique identifier of the mount (may be reused after umount) | |
1389 | (2) parent ID: ID of parent (or of self for the top of the mount tree) | |
1390 | (3) major:minor: value of st_dev for files on filesystem | |
1391 | (4) root: root of the mount within the filesystem | |
1392 | (5) mount point: mount point relative to the process's root | |
1393 | (6) mount options: per mount options | |
1394 | (7) optional fields: zero or more fields of the form "tag[:value]" | |
1395 | (8) separator: marks the end of the optional fields | |
1396 | (9) filesystem type: name of filesystem of the form "type[.subtype]" | |
1397 | (10) mount source: filesystem specific information or "none" | |
1398 | (11) super options: per super block options | |
1399 | ||
1400 | Parsers should ignore all unrecognised optional fields. Currently the | |
1401 | possible optional fields are: | |
1402 | ||
1403 | shared:X mount is shared in peer group X | |
1404 | master:X mount is slave to peer group X | |
97e7e0f7 | 1405 | propagate_from:X mount is slave and receives propagation from peer group X (*) |
2d4d4864 RP |
1406 | unbindable mount is unbindable |
1407 | ||
97e7e0f7 MS |
1408 | (*) X is the closest dominant peer group under the process's root. If |
1409 | X is the immediate master of the mount, or if there's no dominant peer | |
1410 | group under the same root, then only the "master:X" field is present | |
1411 | and not the "propagate_from:X" field. | |
1412 | ||
2d4d4864 RP |
1413 | For more information on mount propagation see: |
1414 | ||
1415 | Documentation/filesystems/sharedsubtree.txt | |
1416 | ||
4614a696 JS |
1417 | |
1418 | 3.6 /proc/<pid>/comm & /proc/<pid>/task/<tid>/comm | |
1419 | -------------------------------------------------------- | |
1420 | These files provide a method to access a tasks comm value. It also allows for | |
1421 | a task to set its own or one of its thread siblings comm value. The comm value | |
1422 | is limited in size compared to the cmdline value, so writing anything longer | |
1423 | then the kernel's TASK_COMM_LEN (currently 16 chars) will result in a truncated | |
1424 | comm value. |