Tek-Tips is the largest IT community on the Internet today!
Members share and learn making Tek-Tips Forums the best source of peer-reviewed technical information on the Internet!
-
Congratulations Mike Lewis on being selected by the Tek-Tips community for having the most helpful posts in the forums last week. Way to Go!
bottle neck
- Thread starter cellspam
- Start date
Annihilannic
MIS
A physical examination of the server should help, but you shouldn't really allow people to drink in your data centre! 
But seriously... collect some throughput statistics and see if they are approaching the theoretical limit of the NIC in question. You can do this by running something like ifconfig eth0 or ethtool -S eth0 once every, say, 10 seconds, and calculating the differences between the TX bytes/RX bytes values.
For a 100Mbit NIC, you can devide that value by 10 to get an approximate theoretical limit in bytes per second.
Also check the stats reported by the above for high collision rates and TX/RX errors/retries which may indicate network problems or a misconfiguration (speed mismatch between NIC and port or similar).
Annihilannic.
But seriously... collect some throughput statistics and see if they are approaching the theoretical limit of the NIC in question. You can do this by running something like ifconfig eth0 or ethtool -S eth0 once every, say, 10 seconds, and calculating the differences between the TX bytes/RX bytes values.
For a 100Mbit NIC, you can devide that value by 10 to get an approximate theoretical limit in bytes per second.
Also check the stats reported by the above for high collision rates and TX/RX errors/retries which may indicate network problems or a misconfiguration (speed mismatch between NIC and port or similar).
Annihilannic.
- Status