Hi everybody,
I'm asking some questions about the quality and transparency of mirroring in VDS.
To begin, the goal of this mirror is to make some performance measurement of the network and applications hosted in the ESX.
In order to be sure about the mirror quality we've done some tests.
Here's the lab. description :
• network card config (default) on the two hosts:
∘ IPv4 checksum offload : rx&tx enabled
∘ Jumbo packet : disabled
∘ Large send offload (ipv4) : enabled
∘ Coalesce buffer : 128
∘ Receive Buffers : 256
∘ TCP Checksum Offload : Rx & Tx Enabled
∘ Transmit Buffers : 512
∘ UDP Chesksum Offload : Rx & Tx Enabled
The test is done with iperf with the following parameters:
Results :
as you can see in this wireshark screenshot
nearly all packets are not in order, ack is coming before data packet.
as you can easily imagine, it complicates in a huge amount the probe behaviour.
>> Have you got other experience return ? Is there others parameters to tweak in advanced parameters ?
You'll find pcap file attached (Source, Destination and mirror)
Interesting post. I am curious if your results are more stable if you set the desired transmission size to 1472 (i.e. on iperf). The reason I ask is I see some packets coming in with a size of 1514 resulting in the "TCP Window Full" message. With that said, I will humbly defer this to the real networking folks here (I'm just a server guy!).
Hi Grasshopper, thanks for feedback
About 1514 Bytes packets seen :
{ Please Note that MTU seats here : 1460 bytes of data + 20 Bytes IP header + 20 Bytes TCP Header = 1500 Bytes carried by Ethernet Layer}
Total packet size : 1460 + 20 + 20 +14 = 1514 Bytes
Hope it's more clear for you now ? Sometimes, MTU and packet size are confusing !
Regards