Personaly i have never seen them used in a real setting so i am
wondering if i am just watching the wrong networks, or if jumboframes are
generally not used (and then: why? Are devices unable to handle jubo frames
still an issue today?).
Jumbo frames are practically non-existent on the internet at large; however, many companies make heavy use of jumbo frames in private LAN and WANs. The most common application is for database / storage traffic to make the links / servers more efficient.
The max link efficiency at 1500 byte MTUs is about 95% (assuming TCP traffic) vs 99% at 9000 byte MTUs:
- Ethernet includes 20 bytes of framing overhead (Preamble + SFD + IPG)
- The ethernet header is 18 bytes
- IP and TCP transmit an additional 40+ bytes of headers (20 Bytes for IP header and at least 20 bytes for TCP header)
- CRC is 4 bytes
Ethernet payload efficiency at 1500-byte MTUs
The efficiency at 1500 bytes (assuming no Vlan tag) is: 94.93%
(data_size) / (ethernet_frame_size_on_wire)
(1500 - 40) / (18 + 1500 + 4 + 20) = 1460 / 1538 = 0.949284
Ethernet payload efficiency at 9000-byte MTUs
The efficiency at 9000 bytes (assuming no Vlan tag) is: 99.14%
(data_size) / (ethernet_frame_size_on_wire)
(9000 - 40) / (18 + 9000 + 4 + 20) = 8960 / 9038 = 0.99136977
At GigabitEthernet rates you're getting about 42Mbps more with Jumbo frames (assuming the link operates at max capacity).
Why are jumbo frames limited to 9000 Bytes? I think i read something about this being related to limitations of the 32 Bit CRC sum
As you asserted in your question, it's mostly due to the math of a 32-bit CRC. Changing the CRC is pretty radical, since your switches and all NICs would need to use the same CRC calculation.
I would argue that repeaters hardly do exist today.
A repeater amplifies the electric signal but is a completely analogue device and does not in any way interpret the signal. A repeater is the same thing as a 2-port hub although I've seen some companies starting to use the term repeater for equipment that resembles a switch more than a hub.
Contrast this with a switch that receives a frame, interprets it and extracts the destination MAC address which it then acts upon to forward the frame to it's correct destination. A bridge is the same thing as a 2-port switch.
Due to the low cost of switches and their support for higher speeds, the market for hubs/repeaters is slim to none.
Best Answer
This is a matter of DTE vs. DCE -- the role each endpoint takes. The NIC in your desktop is a "user terminal" (DTE). The switch it connects to is "communication equipment" (DCE). All this means is which pins are transmit vs. receive, such that a straight through cable from DTE to DCE works as expected. This is why a crossover cable is(was) required to connect two switches (DCE) or two hosts (DTE) together.
"Auto" really didn't become popular (read: everywhere) until the era of gigabit ethernet. Gig-e uses all four pairs for both TX and RX, so the required logic for auto-mdix is already there. Prior to this, additional logic (read: additional costs) were required.