Bug 1324594 - keepalived high number of close syscalls
keepalived high number of close syscalls
Status: POST
Product: Red Hat Enterprise Linux 7
Classification: Red Hat
Component: keepalived (Show other bugs)
x86_64 Linux
high Severity high
: rc
: 7.2
Assigned To: Ryan O'Hara
Brandon Perkins
Depends On: 1419049
Blocks: 1394959
  Show dependency treegraph
Reported: 2016-04-06 13:53 EDT by Ryan Howe
Modified: 2017-02-03 11:39 EST (History)
10 users (show)

See Also:
Fixed In Version:
Doc Type: Bug Fix
Doc Text:
Story Points: ---
Clone Of:
Last Closed:
Type: Bug
Regression: ---
Mount Type: ---
Documentation: ---
Verified Versions:
Category: ---
oVirt Team: ---
RHEL 7.3 requirements from Atomic Host:
Cloudforms Team: ---

Attachments (Terms of Use)

External Trackers
Tracker ID Priority Status Summary Last Updated
Red Hat Bugzilla 1323526 None None None 2016-04-13 08:45 EDT

  None (edit)
Description Ryan Howe 2016-04-06 13:53:53 EDT
Description of problem:

keepalived is generating a high number of close syscalls, when a third party agent never drops close events and processing this amount of events is causing the high CPU usage and node to crash

Version-Release number of selected component (if applicable):

How reproducible: Have not reproduced, with 3rd party application.   

Steps to Reproduce:
1.Configure Ipfailover on openshift
2.Configure 3rd party sysdig to openshift

Actual results:
Openshift node crashes 

Expected results:
keepalived to not generate as many syscalls

Additional info:

OpenShift User list

Customer is running sysdig 

 keepalived 1.2.20

"Optimise closure of fds before invoking scripts.
  Every time before a script was invoked, closeall() was called,
  which would spin through 1024 file descriptors closing them, even
  though the vast majority were not open, resulting in 1024 system
  calls. To avoid that, open all sockets and file descriptors
  (except fd 0/1/2) with the CLOEXEC flag set, so that the fds will
  be closed by the kernel when the script is exec'd."
Comment 1 Ryan O'Hara 2016-04-11 11:32:04 EDT
Shouldn't the component for this be keepalived?

The patch in question is upstream commit 480b451a6fb98ee1c1476c3478e366666f87fe15.

Note You need to log in before you can comment on or make changes to this bug.