3750G stacked - slow file copy speed cross-stack :(

paul.thomas · ‎03-26-2012

Hi All

I have a number of Catalyst 3750G switches, a combination of Gb and 10/100 POE models all stacked together.

I am not a Cisco expert so they are pretty much installed as plug and play with one management switch assigned an IP address. No other tweaking/config done.

They have been in situ for a number of years.

I am just performing some performance testing on our file server in advance of getting a replacement model (Its now 3 years old).

When copying a 3.5Gb file from my C:\ to the Windows 2008 R2 server share I get a slow speed of approx 11.5Mb/s.

I have tried this from a number of different clients and to 2 different servers.

If both the client and server are plugged into the same physical switch then speeds of > 100mb/s are achieved.

As soon as I move the client to another switch it slows down again. I have tried this with sifferent clients, servers and switches as well as making sure both server and clients are negotiating 1Gb network connections ok.

I have tried a smaller file and get similar results, the only common denominator seems to be when it is cross-stack. The fact I can achieve significantly faster speeds when plugged intot he same switch at least means the server etc is capable of it.

So it appears I am not getting very good performance cross-stack.

Any ideas or suggestions on what I can do to resolve this? or other testing I can do to narrow down the problem?

Additional Info:-

Clients are Windows 7. No VLAN's in place.

Tests done using windows copy/paste and looking at the speed shown by Windows while copying.

viswamin · ‎03-26-2012

Paul,

What kind of cable that you use to connect between the switches? can you share the show int of the following ports.

1. Port where the client is connected to.

2. if the connection spans across switches can you share the interface output of both ports in both the switches.

3. also can you share the output of show conn status on the switch just to see what speed does your devices operate on?

-Vijay

paul.thomas · ‎03-26-2012

Gigastack cable on the back of the units, cascade between them and back from last to first.

1.:-

Client

FastEthernet1/0/10 is up, line protocol is up (connected)

Hardware is Fast Ethernet, address is 001a.e3e0.140c (bia 001a.e3e0.140c)

MTU 1500 bytes, BW 100000 Kbit, DLY 100 usec,

reliability 255/255, txload 1/255, rxload 1/255

Encapsulation ARPA, loopback not set

Keepalive set (10 sec)

Full-duplex, 100Mb/s, media type is 10/100BaseTX

input flow-control is off, output flow-control is unsupported

ARP type: ARPA, ARP Timeout 04:00:00

Last input never, output 00:00:52, output hang never

Last clearing of "show interface" counters never

Input queue: 0/75/0/0 (size/max/drops/flushes); Total output drops: 0

Queueing strategy: fifo

Output queue: 0/40 (size/max)

5 minute input rate 0 bits/sec, 0 packets/sec

5 minute output rate 2000 bits/sec, 2 packets/sec

0 packets input, 0 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

16309 packets output, 1860810 bytes, 0 underruns

0 output errors, 0 collisions, 1 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

FastEthernet1/0/14 is up, line protocol is up (connected)

Hardware is Fast Ethernet, address is 001a.e3e0.1410 (bia 001a.e3e0.1410)

MTU 1500 bytes, BW 100000 Kbit, DLY 100 usec,

reliability 255/255, txload 1/255, rxload 1/255

Encapsulation ARPA, loopback not set

Keepalive set (10 sec)

Full-duplex, 100Mb/s, media type is 10/100BaseTX

input flow-control is off, output flow-control is unsupported

ARP type: ARPA, ARP Timeout 04:00:00

Last input never, output 00:00:14, output hang never

Last clearing of "show interface" counters never

Input queue: 0/75/0/0 (size/max/drops/flushes); Total output drops: 0

Queueing strategy: fifo

Output queue: 0/40 (size/max)

5 minute input rate 0 bits/sec, 0 packets/sec

5 minute output rate 1000 bits/sec, 1 packets/sec

2507 packets input, 1776293 bytes, 0 no buffer

Received 71 broadcasts (0 multicasts)

0 runts, 0 giants, 0 throttles

0 input errors, 0 CRC, 0 frame, 0 overrun, 0 ignored

0 watchdog, 7 multicast, 0 pause input

0 input packets with dribble condition detected

5078 packets output, 541787 bytes, 0 underruns

0 output errors, 0 collisions, 1 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

Both are currently left plugged into 10/100 POE switches after I have been swapping cables to test things. These are on 2 different switches.

Hope that helps?

paul.thomas · ‎03-26-2012

ok, please ignore this post. It seems one of the switches is not in the stack properly.

I will have to re-connect the stack cables and restart the stack to see if it resolves the problem.

Thanks anyway.