I had
one user complain about their HTTP traffic to one specific Google appliance
really being slow. Turns out the interface had a ton of CRC and Runt errors. At
first I thought this was cable related because of the CRC errors but the Runts
took away from that notion. I still had them replace the cable but Runts are Ethernet packets that are less than 64 bytes. Most
operating systems and devices don’t process Runts. The issue turned out to be
duplex mismatch on the server side as the switch was already set to 100Mb/Full.
Good Cisco article about this is below.
https://supportforums.cisco.com/docs/DOC-2809
6509E#show int fa4/36
FastEthernet4/36 is up, line
protocol is up (connected)
Hardware is C6k 100Mb
802.3, address is 0011.bb28.0d23 (bia 0011.bb28.0d23)
Description: Google Appliance
MTU 1500 bytes, BW 100000
Kbit, DLY 100 usec,
reliability 221/255, txload 22/255, rxload 1/255
Encapsulation ARPA,
loopback not set
Keepalive set (10 sec)
Full-duplex, 100Mb/s
input flow-control is
off, output flow-control is unsupported
ARP type: ARPA, ARP
Timeout 04:00:00
Last input never, output
never, output hang never
Last clearing of
"show interface" counters 04:37:32
Input queue: 0/2000/0/0
(size/max/drops/flushes); Total output drops: 0
Queueing strategy: fifo
Output queue: 0/40
(size/max)
5 minute input rate
435000 bits/sec, 736 packets/sec
5 minute output rate
8837000 bits/sec, 796 packets/sec
12677713 packets input, 894017675 bytes, 0 no buffer
Received 362263 broadcasts (362262 multicasts)
451875 runts, 0 giants, 0
throttles
3591374 input errors, 20316 CRC,
0 frame, 0 overrun, 0 ignored
0
watchdog, 0 multicast, 0 pause input
0 input
packets with dribble condition detected
13181204 packets output, 18277208769 bytes, 0 underruns
0 output
errors, 0 collisions, 0 interface resets
0
babbles, 0 late collision, 0 deferred
0 lost
carrier, 0 no carrier, 0 PAUSE output
0
output buffer failures, 0 output buffers swapped out
Server Side
eth0 Link
encap:Ethernet HWaddr 78:2B:CB:19:3A:79
inet
addr:192.168.232.49 Bcast:192.168.232.255 Mask:255.255.255.0
UP
BROADCAST RUNNING MULTICAST MTU:1500 Metric:1
RX
packets:8606244989 errors:3 dropped:24215 overruns:0 frame:3
TX
packets:5810977239 errors:15811579 dropped:0 overruns:0 carrier:15811579
collisions:2206833034 txqueuelen:1000
RX
bytes:11961560341542 (10.8 TiB) TX bytes:510772576280 (475.6 GiB)
Interrupt:36 Memory:d6000000-d6012700
Duplex settings were changed on the server side since the switch was already set to 100Mb/Full. Issue disappears.
6509E#show int fa4/36
FastEthernet4/36 is up, line
protocol is up (connected)
Hardware is C6k 100Mb
802.3, address is 0011.bb28.0d23 (bia 0011.bb28.0d23)
Description: Google Appliance
MTU 1500 bytes, BW 100000
Kbit, DLY 100 usec,
reliability 255/255, txload 12/255, rxload 1/255
Encapsulation ARPA,
loopback not set
Keepalive set (10 sec)
Full-duplex, 100Mb/s
input flow-control is
off, output flow-control is unsupported
ARP type: ARPA, ARP
Timeout 04:00:00
Last input never, output
never, output hang never
Last clearing of
"show interface" counters 03:43:09
Input queue: 0/2000/0/0
(size/max/drops/flushes); Total output drops: 0
Queueing strategy: fifo
Output queue: 0/40
(size/max)
5 minute input rate 305000
bits/sec, 375 packets/sec
5 minute output rate
4863000 bits/sec, 459 packets/sec
7917902
packets input, 741546238 bytes, 0 no buffer
Received 0 broadcasts (0 multicasts)
0 runts, 0 giants, 0 throttles
0 input errors, 0 CRC, 0 frame, 0 overrun, 0
ignored
0
watchdog, 0 multicast, 0 pause input
0 input
packets with dribble condition detected
11120155 packets output, 15401101799 bytes, 0 underruns
0
output errors, 0 collisions, 0 interface resets
0
babbles, 0 late collision, 0 deferred
0 lost
carrier, 0 no carrier, 0 PAUSE output
0
output buffer failures, 0 output buffers swapped out
No comments:
Post a Comment