On Tue, 13 Jan 2026 15:13:24 +0000 Haiyang Zhang wrote:

quoted

quoted

I get that. What is the logic for combining 4 packets into a single
completion? How does it work? Your commit message mentions "regression
on latency" - what is the bound on that regression?  

When we received CQE type CQE_RX_COALESCED_4, it's a coalesced CQE. And in
the CQE OOB, there is an array with 4 PPI elements, with each pkt's length:
oob->ppi[i].pkt_len.

So we read the related WQE and the DMA buffers for the RX pkt payloads, up
to 4.
But, if the coalesced pkts <4, the pkt_len will be 0 after the last pkt,
so we know when to stop reading the WQEs.  

And, the coalescing can add up to 2 microseconds into one-way latency.

I am asking you how the _device_ (hypervisor?) decides when to coalesce
and when to send a partial CQE (<4 packets in 4 pkt CQE). You are using
the coalescing uAPI, so I'm trying to make sure this is the correct API.
CQE configuration can also be done via ringparam.