Command line and full screen utilities for browsing procfs, a "pseudo" file system dynamically generated by Linux to provide information about the status of entries in its process table.
e9c101edcb
Long ago, in a galaxy far away (when top was in charge of library FILL flgs) /proc/status was to be preferred over /proc/stat if a field could be satisfied by both. This was done to avoid costly 64-bit math emulation in a 32-bit application due to 'unsigned long long' data. Well it's time to acknowledge the prevalence of 64-bit platforms. And in such an environment the cost picture has shifted significantly. It now costs 14 times (wow) as much to access /proc/status compared to /proc/stat. In other words, even with '%llu' variables, a sscanf() call in stat2proc() beats the pants off that home brew gperf based hashing employed by the status2proc() guy. In fact, status2proc incurs higher costs than found in the most expensive aspect of top's forest view option. Here's a gprof extract to illustrate the costs. It was produced with an rcfile requiring fields from both the /proc/stat & /proc/status pseudo files (among others). There were 5000 iterations in each of 4 separate gprof runs subsequently merged into 1 gmon.sum for analysis. % self self time seconds calls us/call name ----- ------- ------- ------- ----------- 28.65 4.10 4689423 0.87 status2proc 26.14 3.74 40000 93.50 forest_adds ... 01.96 0.28 4689427 0.06 stat2proc [ since forest_adds is recursive, the calls value is ] [ the non-recursive #, its 'call graph' shows totals ] Anyway, now that such cost is known this patch becomes what is euphemistically known as the usual no-brainer. [ jeeze, was it really this long between profilings? ] Signed-off-by: Jim Warner <james.warner@comcast.net> |
||
|---|---|---|
| contrib | ||
| doc | ||
| Documentation | ||
| include | ||
| lib | ||
| man-po | ||
| misc | ||
| po | ||
| proc | ||
| ps | ||
| testsuite | ||
| top | ||
| .gitignore | ||
| .gitlab-ci.yml | ||
| AUTHORS | ||
| autogen.sh | ||
| ChangeLog | ||
| configure.ac | ||
| COPYING | ||
| COPYING.LIB | ||
| create-man-pot.sh | ||
| free.1 | ||
| free.c | ||
| INSTALL.md | ||
| kill.1 | ||
| kill.c | ||
| Makefile.am | ||
| NEWS | ||
| pgrep.1 | ||
| pgrep.c | ||
| pidof.1 | ||
| pidof.c | ||
| pkill.1 | ||
| pmap.1 | ||
| pmap.c | ||
| pwdx.1 | ||
| pwdx.c | ||
| README.md | ||
| skill.1 | ||
| skill.c | ||
| slabtop.1 | ||
| slabtop.c | ||
| snice.1 | ||
| sysctl.8 | ||
| sysctl.c | ||
| sysctl.conf | ||
| sysctl.conf.5 | ||
| tload.1 | ||
| tload.c | ||
| translate-man.sh | ||
| uptime.1 | ||
| uptime.c | ||
| vmstat.8 | ||
| vmstat.c | ||
| w.1 | ||
| w.c | ||
| watch.1 | ||
| watch.c | ||
procps
procps is a set of command line and full-screen utilities that provide information out of the pseudo-filesystem most commonly located at /proc. This filesystem provides a simple interface to the kernel data structures. The programs of procps generally concentrate on the structures that describe the processess running on the system.
The following programs are found in procps:
- free - Report the amount of free and used memory in the system
- kill - Send a signal to a process based on PID
- pgrep - List processes based on name or other attributes
- pkill - Send a signal to a process based on name or other attributes
- pmap - Report memory map of a process
- ps - Report information of processes
- pwdx - Report current directory of a process
- skill - Obsolete version of pgrep/pkill
- slabtop - Display kernel slab cache information in real time
- snice - Renice a process
- sysctl - Read or Write kernel parameters at run-time
- tload - Graphical representation of system load average
- top - Dynamic real-time view of running processes
- uptime - Display how long the system has been running
- vmstat - Report virtual memory statistics
- w - Report logged in users and what they are doing
- watch - Execute a program periodically, showing output fullscreen
Reporting Bugs
There are a few ways of reporting bugs or feature requests:
- Your distributions bug reporter. If you are using a distribution your first port of call is their bug tracker. This is because each distribution has their own patches and way of dealing with bugs. Also bug reporting often does not need any subscription to websites.
- GitLab Issues - To the left of this page is the issue tracker. You can report bugs here.
- Email list - We have an email list (see below) where you can report bugs. The problem with this method is bug reports often get lost and cannot be tracked. This is especially a big problem when its something that will take time to resolve.
If you need to report bugs, there is more details on the Bug Reporting page.
Email List
The email list for the developers and users of procps is found at http://www.freelists.org/archive/procps/ This email list discusses the development of procps and is used by distributions to also forward or discuss bugs.