Bug ID 720569: Disaggregation algorithm distributing traffic unequally across CPU cores on Virtual Edition

Last Modified: Nov 22, 2021

Bug Tracker

Affected Product:  See more info
BIG-IP All(all modules)

Known Affected Versions:
12.1.0, 12.1.0 HF1, 12.1.0 HF2, 12.1.1, 12.1.1 HF1, 12.1.1 HF2, 12.1.2, 12.1.2 HF1, 12.1.2 HF2, 12.1.3, 12.1.3.1, 12.1.3.2, 12.1.3.3, 12.1.3.4, 12.1.3.5, 12.1.3.6, 12.1.3.7, 12.1.4, 12.1.4.1, 12.1.5, 12.1.5.1, 12.1.5.2, 13.0.0, 13.0.0 HF1, 13.0.0 HF2, 13.0.0 HF3, 13.0.1, 13.1.0, 13.1.0.1, 13.1.0.2, 13.1.0.3, 13.1.0.4, 13.1.0.5, 13.1.0.6, 13.1.0.7, 13.1.0.8, 13.1.1, 13.1.1.2, 13.1.1.3, 13.1.1.4, 13.1.1.5, 13.1.3, 13.1.3.1, 13.1.3.2, 13.1.3.3, 13.1.3.4, 14.0.0, 14.0.0.1, 14.0.0.2, 14.0.0.3, 14.0.0.4, 14.0.0.5, 14.0.1, 14.0.1.1

Fixed In:
14.1.0, 13.1.3.5, 12.1.5.3

Opened: May 17, 2018
Severity: 3-Major

Symptoms

After a period of time, Inet port exhaustion error messages begin to be reported, and traffic starts to fail: crit tmm1[17985]: 01010201:2: Inet port exhaustion on <ip_address> to <ip_address>. CPU cores are unevenly loaded by the tmm process. Typically odd cores will have a more loaded tmm thread.

Impact

The system reports Inet port exhaustion error messages, and traffic starts to fail. Where CPU use by the tmm process is very uneven as the busiest cores reach near maximum connections will be offloaded at an early stage to less used tmm threads on quieter cores. This means the uneven CPU usually has a minimal impact itself.

Conditions

BIG-IP system uses unic, sock or virtIO drivers

Workaround

None.

Fix Information

Disaggregation algorithm has been improved to avoid unequal distribution.

Behavior Change