FM / examples

/usr/share/doc/bpftrace/examples

Name	Size	Mode	Actions
bashreadline_example.txt	722	0644	edit dl rm
biolatency_example.txt	1790	0644	edit dl rm
biosnoop_example.txt	2056	0644	edit dl rm
biostacks_example.txt	1914	0644	edit dl rm
bitesize_example.txt	3003	0644	edit dl rm
capable_example.txt	2659	0644	edit dl rm
cpuwalk_example.txt	4919	0644	edit dl rm
dcsnoop_example.txt	4612	0644	edit dl rm
execsnoop_example.txt	1535	0644	edit dl rm
gethostlatency_example.txt	923	0644	edit dl rm
killsnoop_example.txt	846	0644	edit dl rm
loads_example.txt	864	0644	edit dl rm
mdflush_example.txt	1866	0644	edit dl rm
naptime_example.txt	844	0644	edit dl rm
oomkill_example.txt	1668	0644	edit dl rm
opensnoop_example.txt	2528	0644	edit dl rm
pidpersec_example.txt	1504	0644	edit dl rm
runqlat_example.txt	8632	0644	edit dl rm
runqlen_example.txt	980	0644	edit dl rm
setuids_example.txt	2441	0644	edit dl rm
ssllatency_example.txt	4510	0644	edit dl rm
sslsnoop_example.txt	1916	0644	edit dl rm
statsnoop_example.txt	2738	0644	edit dl rm
swapin_example.txt	549	0644	edit dl rm
syncsnoop_example.txt	541	0644	edit dl rm
syscount_example.txt	1144	0644	edit dl rm
tcpaccept_example.txt	1350	0644	edit dl rm
tcpconnect_example.txt	1085	0644	edit dl rm
tcpdrop_example.txt	1256	0644	edit dl rm
tcplife_example.txt	1597	0644	edit dl rm
tcpretrans_example.txt	1153	0644	edit dl rm
tcpsynbl_example.txt	940	0644	edit dl rm
threadsnoop_example.txt	1182	0644	edit dl rm
undump_example.txt	680	0644	edit dl rm
vfscount_example.txt	1199	0644	edit dl rm
vfsstat_example.txt	929	0644	edit dl rm
writeback_example.txt	1962	0644	edit dl rm
xfsdist_example.txt	3419	0644	edit dl rm

Edit: /usr/share/doc/bpftrace/examples/oomkill_example.txt (1668B)

Demonstrations of oomkill, the Linux bpftrace/eBPF version.

oomkill is a simple program that traces the Linux out-of-memory (OOM) killer,
and shows basic details on one line per OOM kill:

# ./oomkill.bt
Tracing oom_kill_process()... Ctrl-C to end.
21:03:39 Triggered by PID 3297 ("ntpd"), OOM kill of PID 22516 ("perl"), 3850642 pages, loadavg: 0.99 0.39 0.30 3/282 22724
21:03:48 Triggered by PID 22517 ("perl"), OOM kill of PID 22517 ("perl"), 3850642 pages, loadavg: 0.99 0.41 0.30 2/282 22932

The first line shows that PID 22516, with process name "perl", was OOM killed
when it reached 3850642 pages (usually 4 Kbytes per page). This OOM kill
happened to be triggered by PID 3297, process name "ntpd", doing some memory
allocation.

The system log (dmesg) shows pages of details and system context about an OOM
kill. What it currently lacks, however, is context on how the system had been
changing over time. I've seen OOM kills where I wanted to know if the system
was at steady state at the time, or if there had been a recent increase in
workload that triggered the OOM event. oomkill provides some context: at the
end of the line is the load average information from /proc/loadavg. For both
of the oomkills here, we can see that the system was getting busier at the
time (a higher 1 minute "average" of 0.99, compared to the 15 minute "average"
of 0.30).

oomkill can also be the basis of other tools and customizations. For example,
you can edit it to include other task_struct details from the target PID at
the time of the OOM kill, or to run other commands from the shell.

There is another version of this tool in bcc: https://github.com/iovisor/bcc

cmd: