High CPU usage with em driver RC1

[dotdash]

This happened on a production system, so there was no extensive testing. As a result this is a subjective report, I'm just mentioning it in case anyone has similar issues.
I have a CARP cluster running on boxes that each have four em interfaces. Two WANs, multiple VLANs (two em cards are used for VLAN trunking). The system was working fine on 1.2 and 1.2.2. I upgraded to 1.2.3 RC1 and the CPU usage went crazy. Seemed to be the em taskqueues spiking the box. Performance seemed OK, but the webgui was awful. Updating to a recent 7.2 based (RC2) snap seems to have cleared up the issue, so I suspect something was not right with the 7.1 em driver.

[clarknova]

I believe there was a problem with broadcast storms on CARP setups in 1.2.3-RC1 that has been resolved in the more recent builds. You'll find more info in other posts here in the forum. My guess is that its related. there was also an issue with states not expiring that has been fixed, but I don't think that would cause the symptoms you're reporting.

db

[dotdash]

I spoke too soon. It came back on 7.2 after about a day.
This is top -S:
last pid: 16105;  load averages:  4.61,  5.08,  5.03    up 0+23:57:09  16:24:04
106 processes: 8 running, 82 sleeping, 16 waiting
CPU: 52.2% user,  0.0% nice, 42.9% system,  4.9% interrupt,  0.0% idle
Mem: 59M Active, 11M Inact, 42M Wired, 416K Cache, 26M Buf, 375M Free
Swap: 1024M Total, 1024M Free

PID USERNAME  THR PRI NICE  SIZE    RES STATE    TIME  WCPU COMMAND
13937 root        1  -8    0 40684K 13892K piperd  0:27 12.79% php
  26 root        1 -68    -    0K    8K -      20:05  9.67% em1 taskq
16095 root        1  97    0  3156K  856K RUN      0:00  7.47% tail
16088 root        1  8    0  3492K  1396K wait    0:00  6.88% sh
14832 root        1  -8    0 40684K 13784K piperd  0:16  6.79% php
9109 root        1  -8    0 41708K 15140K piperd  0:58  4.98% php
8421 root        1  4    0 40684K 14364K accept  0:58  4.49% php
  25 root        1 -68    -    0K    8K -      13:07  4.20% em0 taskq
  12 root        1 -44    -    0K    8K WAIT    4:44  2.39% swi1: net
1164 root        1  4    0  7148K  5096K kqread  8:46  0.29% lighttpd
15715 root        1  44    0  3528K  1924K RUN      0:00  0.29% top
  11 root        1 171 ki31    0K    8K RUN    17.9H  0.00% idle: cpu0
  27 root        1 -68    -    0K    8K -      11:07  0.00% em2 taskq
  28 root        1 -68    -    0K    8K -        3:57  0.00% em3 taskq
  13 root        1 -32    -    0K    8K WAIT    3:40  0.00% swi4: clock sio
  23 root        1  8    -    0K    8K -        3:11  0.00% thread taskq
  15 root        1  44    -    0K    8K RUN      3:03  0.00% yarrow