So I have a server running Centos 6 64bit with cPanel. It's set on eth0 running at 100MB/s full duplex. But, one particular server seems sluggish on its connectivity, despite server load being minimal on CPU and memory. Would like some tips on tracing the cause. I don't think the NIC card is faulty by any means. I tested via wget on 2 different U.S. mirrors for Centos 6 repo (4.4GB DVD), it was about 10M/s which should be a lot faster I'd think.
root@server [~]# ethtool eth0
Settings for eth0:
Supported ports: [ TP ]
Supported link modes: 10baseT/Half 10baseT/Full
100baseT/Half 100baseT/Full
1000baseT/Full
Supported pause frame use: No
Supports auto-negotiation: Yes
Advertised link modes: 10baseT/Half 10baseT/Full
100baseT/Half 100baseT/Full
1000baseT/Full
Advertised pause frame use: No
Advertised auto-negotiation: Yes
Speed: 100Mb/s
Duplex: Full
Port: Twisted Pair
PHYAD: 1
Transceiver: internal
Auto-negotiation: on
MDI-X: off
Supports Wake-on: pumbg
Wake-on: g
Current message level: 0x00000007 (7)
drv probe link
Link detected: yes
As Rex mentioned, the difference there is in bits versus bytes. MB is megabytes, and Mb is megabits. Network speeds are almost always measured in bits. The 10 MB/s performance you're seeing is accurate, as your overall speed is 12.5 MB/s. Factor in dropped packets, error corrections, other services' network usage, etc. and your speed is on par.
A gigbit (1 Gb/s) full duplex link will give you 125 MB/s tops.
User contributions licensed under CC BY-SA 3.0