PACKET_MMAP version 1/2 improvements

[kevinGC]

Description

The fdbased LinkEndpoint supports PACKET_MMAP, but is missing a few useful improvements:

• TX: we TX using sendmmsg, but should use PACKET_MMAP buffers.
• RX: the PACKET_MMAP dispatcher seems to return 1-3 packets at a time, while the recvmmsg dispatcher often returns 8. We should investigate this, as PACKET_MMAP should return many packets at once and ultimately be faster than recvmmsg.

This is specific to PACKET_MMAP TPACKET_V1 and TPACKET_V2, not V3. V3 is unsuitable as a dispatcher because it markedly increases latency (by O(milliseconds)) in order to reduce CPU usage.

Is this feature related to a specific bug?

No

Do you have a specific solution in mind?

I believe we only have 32 slots (tpFrameNR) in the dispatcher. Could that be limiting the number of returned packets?

[manninglucas]

Earlier this year I ran experiments across lots of different frame/block sizes with tPACKET v3. The conclusion I came to was that PACKET_MMAP trades off raw packet throughput for CPU efficiency. This is in line with its stated goal of being a "more efficient way to capture packets", not necessarily tx/rx packets like we want it to. Waiting for a block to fill up was always slower than getting them from rcvmmsg. Feel free to take a crack at it, totally possible I missed something. But just a warning: HOURS_WASTED_HERE=~100.

[kevinGC]

IIUC that's specific to V3. I am thinking that PACKET_MMAP improvements would be for the existing V2 interface we use.

[manninglucas]

Yeah could be. I definitely did less testing on V2 since I thought v3 would be the answer. FWIW when I tried to increase the number of frames (in v2) I didn't see any effect.

[hbhasker]

V3 is not going to work.v3 has a hard coded block time of 8ms? It's optimized for bulk packet capture (aka tcpdump). That's the reason I used v2. If you do a simple ping with V3 you will see the latency spike all over the place.

[kevinGC]

I've updated the title and description to make it clear that this issue is not related to use of V3, but rather is about improving the dispatcher using V1 or V2.