Bug ID 882557: TMM restart loop if virtio platform specifies RX or TX queue sizes that are too large (4096 or higher)

Last Modified: Mar 18, 2020

Bug Tracker

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

Known Affected Versions:
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, 13.1.1.4, 13.1.1.5, 13.1.3, 13.1.3.1, 13.1.3.2, 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, 14.1.0, 14.1.0.1, 14.1.0.2, 14.1.0.3, 14.1.0.4, 14.1.0.5, 14.1.0.6, 14.1.2, 14.1.2.1, 14.1.2.2, 14.1.2.3, 15.0.0, 15.0.1, 15.0.1.1, 15.0.1.2, 15.1.0

Opened: Feb 19, 2020
Severity: 1-Blocking

Symptoms

If the underlying virtio platform specifies RX and/or TX queue sizes that are 4096 or larger, the BIG-IP system cannot allocate enough contiguous memory space to accommodate this. Errors similar to these are seen in the tmm log files: ndal Error: Failed to allocate 2232336 (2228224 + 4096 + 16) bytes virtio[0:7.0]: Error: Failed to allocate descriptor chain virtio[0:7.0]: Error: Failed allocate indirect rx buffers

Impact

TMM continually restarts.

Conditions

-- Using a BIG-IP Virtual Edition (VE) with virtio drivers. -- The underlying platform specifies RX and/or TX queue sizes of 4096 or larger.

Workaround

Use the sock driver instead of virtio. In your BIG-IP VE VM execute the lspci command to determine which virtio driver is present: # lspci -nn | grep -i eth | grep -i virtio 00:03.0 Ethernet controller [0200]: Red Hat, Inc Virtio network device [1af4:1000] 00:04.0 Ethernet controller [0200]: Red Hat, Inc Virtio network device [1af4:1000] 00:0b.0 Ethernet controller [0200]: Red Hat, Inc Virtio network device [1af4:1000] Configure a socket driver: echo "device driver vendor_dev 1af4:1000 sock" > /config/tmm_init.tcl Reboot the instance

Fix Information

None

Behavior Change