prometheus/cadvisor
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity
1,111 Commits 1 Branch 39 Tags 50 MiB
ee4bdc2698
Commit Graph

57 Commits

Author SHA1 Message Date
Katie Knister
ee4bdc2698 Improvements to events integration test 2015-04-10 13:33:22 -07:00
Katie Knister
21e96ed61c adding systemd oomparser functionality 2015-03-24 12:33:57 -07:00
Victor Marmol
5eeb6fdd40 Merge pull request #574 from kateknister/master 
Fixed some bugs in oomparser streaming
 2015-03-11 09:14:07 -07:00
Katie Knister
78f3029943 Fixed some bugs in oomparser streaming 2015-03-10 18:18:54 -07:00
Victor Marmol
d357c34f22 Refactor and centralize HTTP registration. 2015-03-10 18:00:10 -07:00
Victor Marmol
563ead3cce Use mux to register HTTP handlers. 
This will allow us to register handlers on the non-default HTTP handler.
 2015-03-10 15:37:16 -07:00
Victor Marmol
54bc33dd2c Lowering log level for frequent events. 
Lowering all frequent normal logs to v=3. Kubelet runs by default on
debug of v=2 and we don't want to log these events in that case.
 2015-03-09 14:53:53 -07:00
Federico Simoncelli
02a3e46996 Add system uuid and machine id information 
Signed-off-by: Federico Simoncelli <fsimonce@redhat.com>
 2015-03-01 15:06:19 -05:00
Rohit Jnagal
872546ba3a Bulk move current info api to info/v1. Making room for info/v2. 2015-03-04 00:47:28 +00:00
Katie Knister
412f27798e Revised oomparser to not use all the cpu 2015-03-02 14:22:53 -08:00
Katie Knister
3856690715 Added an oomwatcher function to manager 2015-02-19 16:22:37 -08:00
Rohit Jnagal
e09f9684e6 Fix cpuset returned in spec on a single core machine. 
Switch from "0-0" to "0".
 2015-02-19 18:54:23 +00:00
Jihoon Chung
09aff7cb92 Filter out non-netdev entries in sysfs/class/net 2015-02-16 16:11:46 +09:00
Rohit Jnagal
48c41ba273 Merge pull request #491 from rjnagal/summary 
WIP: Add utility to calculate derived stats.
 2015-02-13 17:54:49 -08:00
Rohit Jnagal
009a74179d WIP: Add utility to calculate derived stats. 2015-02-13 22:11:58 +00:00
Victor Marmol
58f3cd48d5 Merge pull request #494 from rjnagal/cpu 
Use shared_cpu_map instead of shared_cpu_list to get cache hierarchy.
 2015-02-07 09:38:22 -08:00
Rohit Jnagal
9f9f8ad983 Use shared_cpu_map instead of shared_cpu_list to get cache hierarchy. 2015-02-07 16:24:19 +00:00
Katie Knister
1291347c73 small change to the way time is parsed from the kernel log in oomparser 
small change to the way time is parsed from the kernel log in oomparser
 2015-02-04 18:48:34 -08:00
Katie Knister
c806d603ba Added a test file for oomparser 2015-01-30 10:24:08 -08:00
Rohit Jnagal
0b7e41c991 Fix typo in netlink example. 2015-01-30 16:56:34 +00:00
Rohit Jnagal
62b02a6b94 Set of fixes for cpuload calculations. 
. Remove counting of taskgroups from scheddebug.
. Move monitoring thread 500ms ahead of other containers housekeeping.
. Rely on /proc/loadavg for root load.
. Cover up for scheddebug atomicity issues (WIP)
. Remove counting of monitoring thread.

Getting better, but still a bit farther away from ideal load :(
 2015-01-29 22:27:07 +00:00
Katie Knister
b5609e2942 Made an oomparser that gets oomkill logs from kernel messages 
Made an oomparser that gets oomkill logs from kernel messages

Made an oomparser that gets oomkill logs from kernel messages

Made an oomparser that gets oomkill logs from kernel messages

Made an oomparser that gets oomkill logs from kernel messages

Made an oomparser that gets oomkill logs from kernel messages

Made an oomparser that gets oomkill logs from kernel messages
 2015-01-27 10:26:38 -08:00
Rohit Jnagal
c26ca15cc7 Make cpu load stats hierarchical for scheddebug. 2015-01-26 23:48:39 +00:00
Rohit Jnagal
db3d840a9d Prefer scheddebug over netlink for cpu load. 2015-01-26 20:44:12 +00:00
Rohit Jnagal
67af1a1bbd Add scheddebug based cpuload reader. 
Prefer netlink based reader when available as it provides stats for
processes in state other than running (sleep, diskio, uninterruptible).
 2015-01-26 18:46:29 +00:00
Rohit Jnagal
1375f451b2 Refactor netlink implementation. 
This allows us to plug in a scheddebug based interface.
 2015-01-23 23:07:50 +00:00
Victor Marmol
8f0f2299ab Make network fields signed integers. 
The kernel reports -1 in case of errors so it should be an allowable
returned value.

Fixes #454.
 2015-01-20 22:34:10 -08:00
Rohit Jnagal
efa8890132 Add error checks for netlink read. 2015-01-20 06:53:57 +00:00
Victor Marmol
90e5dc9b08 Merge pull request #446 from rjnagal/diskinfo 
Add scheduler type to disk info.
 2015-01-16 16:10:52 -08:00
Rohit Jnagal
aa398c800a Add scheduler type to disk info. 
Type can be one of "none", "noop", "deadline", "cfq".
For block devices that don't use scheduler (like dm), the type will be "none".
We'll also report "none" for partitions when we start reporting those.
 2015-01-17 00:09:07 +00:00
Victor Marmol
909fa133e1 Merge pull request #445 from rjnagal/docker 
Add task load stats to containers.
 2015-01-16 16:00:50 -08:00
Rohit Jnagal
cbdd96a554 Add task load stats to containers. 
The stats are only populated when cAdvisor is running outside network namespaces.
We'll add a different backend to retrieve the same data from within namespaces.
 2015-01-16 23:25:22 +00:00
Victor Marmol
ffa108f148 Merge pull request #439 from rjnagal/docs 
Handle root network device names other than eth.
 2015-01-14 14:43:42 -08:00
Rohit Jnagal
3780075bad Handle root network device names other than eth. 
New logic ignores veth, docker, and loopback devices.
 2015-01-14 22:28:59 +00:00
Rohit Jnagal
aeee52161c Add a utility to read cpu load stats. 2015-01-14 00:41:53 +00:00
Rohit Jnagal
14844dbedd Remove sched stats scraping utils. 
sched_debug is getting the wrong load information. Runnable tasks list
in the output include running and sleeping tasks. We only need to look
at nr_running for each scheduling entity to figure out load. We also
don't need per-core stats.

I am going to redo these to derive per-cgroup load from nr_running.
 2015-01-10 07:08:35 +00:00
Rohit Jnagal
de0e8e28eb Add percentiles utility methods. 
This is copied verbatim for our older prototype. We'll use it as
a starting point for building stats summary.
 2015-01-09 17:36:51 +00:00
Vish Kannan
54834156eb Merge pull request #407 from rjnagal/diskinfo 
Add network stats to root container.
 2015-01-02 10:06:11 -08:00
Rohit Jnagal
aee5c36313 Fix vet errors 2015-01-01 22:41:55 +00:00
Rohit Jnagal
45334c6f71 Add network stats to root container. Provides machine-level networking stats. 2014-12-30 17:12:42 +00:00
Rohit Jnagal
3836d1e2ec Refactor common methods out of sysfs package and add tests. 2014-12-29 17:09:27 +00:00
Rohit Jnagal
04fef734d2 Merge pull request #402 from rjnagal/diskinfo 
Add ethernet devices information to machine endpoint.
 2014-12-26 09:47:11 -08:00
Rohit Jnagal
496ee65cc2 Add ethernet devices information to machine endpoint. 2014-12-25 21:15:21 +00:00
Vish Kannan
2d58ee4643 Merge pull request #401 from rjnagal/docs 
Skip ROM devices in disk map.
 2014-12-25 12:41:07 -08:00
Rohit Jnagal
1f23693de8 Skip ROM devices in disk map. 2014-12-25 19:01:27 +00:00
Rohit Jnagal
5994c17b1e Add cache info to machine topology 2014-12-22 17:54:36 +00:00
Rohit Jnagal
e5200948f5 Add a disk map to machine info. 
This is read once at start of cAdvisor. We can use this to report
machine state as well as return logical name for block devices in UI.

Signed-off-by: Rohit Jnagal <jnagal@google.com> (github: rjnagal)
 2014-12-17 00:15:50 +00:00
Vishnu Kannan
3e390e0f33 Use glog instead of 'log' library. 
Docker-DCO-1.1-Signed-off-by: Vishnu Kannan <vishnuk@google.com> (github: vishh)
 2014-08-07 18:38:58 +00:00
Nan Deng
324874411d the unit in /proc/<pid>/schedstat should be ns 2014-08-06 11:03:40 -07:00
Nan Deng
b804ceac30 read core loads from /proc/sched_debug 2014-07-30 17:30:01 -07:00