Large number of TIME_WAIT connections from haproxy cause stalled API service requests
Bug #1413104 reported by
Dmitry Borodaenko
This bug affects 2 people
Affects | Status | Importance | Assigned to | Milestone | |
---|---|---|---|---|---|
Fuel for OpenStack |
Fix Released
|
Critical
|
Bartłomiej Piotrowski | ||
5.0.x |
Fix Committed
|
Critical
|
Bartłomiej Piotrowski | ||
5.1.x |
Fix Committed
|
Critical
|
Bartłomiej Piotrowski | ||
6.0.x |
Fix Committed
|
Critical
|
Bartłomiej Piotrowski | ||
6.1.x |
Fix Released
|
Critical
|
Bartłomiej Piotrowski |
Bug Description
At load, haproxy begins accumulating a large number of connections to backend services stuck in TIME_WAIT state. Eventually, this leads to stalled requests to OpenStack API services.
Setting the http-server-close option:
https:/
makes the problem disappear.
tags: | added: on-verification |
To post a comment you must log in.
Should the http-server-close option be propagated to customers experiencing the issue? I know 1 for sure