Bug ID 700827: B2250 blades may lose efficiency when source ports form an arithmetic sequence.

Last Modified: Oct 09, 2019

Bug Tracker

Affected Product:  See more info
BIG-IP TMOS(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, 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, 13.1.1.1, 13.1.1.2, 13.1.1.3, 14.0.0, 14.0.0.1, 14.0.0.2, 14.0.0.3, 14.0.0.4

Fixed In:
14.1.0, 14.0.0.5, 13.1.1.4, 12.1.4

Opened: Jan 04, 2018
Severity: 3-Major

Symptoms

Traffic imbalance between tmm threads. You might see the traffic imbalance by running the following command: tmsh show sys tmm-traffic

Impact

Traffic imbalance between tmm threads may result in sub-optimal performance.

Conditions

Source ports used to connect to B2250 blade form an arithmetic sequence. For example, some servers always use randomly selected even source port numbers. This means the 'stride' of the ports selected is '2'. Because a sorted list of the ports yields a list like 2, 4, 6, 8... 32002, 32004. It is 'striding' over the odd ports; thus, a port stride of 2.

Workaround

Randomize source ports when connecting via a BIG-IP system.

Fix Information

This release introduces a new variable you can use to mitigate the issue: mhdag.pu.table.size.multiplier 1. Set the variable to to 2 or 3 on the host. 2. Restart tmm on all blades. 3. Restart tmm on the host. 4. Restart tmm on all guests. Note: Restarting tmm on the guests only does nothing; restarting on the host only means that the guests still use old DAG settings and have high inter-TMM forwarding traffic, resulting in a worse condition than originally experienced.

Behavior Change

This release introduces a new variable to mitigate this issue: mhdag.pu.table.size.multiplier. You must set the variable to 2 or 3 on the host, and then restart tmm on all host blades and then all guests to mitigate the issue.