rte_eth_ip...dynfield_t(3)

💅 NAME 💅

rte_eth_ip_reassembly_dynfield_t — the little struct that holds your frags together when IP reassembly goes off the rails, bestie

---

✨ SYNOPSIS ✨

#include <rte_ethdev.h>

🎀 Data Fields 🎀

• struct rte_mbuf * next_frag
• uint16_t time_spent
• uint16_t nb_frags

---

🌸 DESCRIPTION 🌸

Okay so picture this: IP reassembly offload tried its best and failed 😭. Not the vibe. But here's the slay part — the packet doesn't just get thrown away. Instead it gets updated with the dynamic flag RTE_MBUF_DYNFLAG_IP_REASSEMBLY_INCOMPLETE_NAME, and the packets are returned without alteration. Like, untouched. Iconic behavior honestly.

Then your application can go retrieve the attached fragments using the mbuf dynamic field RTE_MBUF_DYNFIELD_IP_REASSEMBLY_NAME. That's your girl right there 🫶.

Fr fr, this is the fallback path — the HW couldn't finish the reassembly, so you get handed the pieces and it's on you to go get them. No cap.

Definition at line 5972 of file rte_ethdev.h.

---

🦋 FIELD DOCUMENTATION 🦋

💜 struct rte_mbuf* next_frag

The next fragment packet, duh. Your app should fetch the dynamic field of each fragment until a NULL is received and nb_frags is 0. Both. At the same time. That's the stopping condition, don't @ me ✋

Definition at line 5977 of file rte_ethdev.h.

⭐ uint16_t time_spent

Time spent (in ms) by the HW waiting around for further fragments. Yes, in milliseconds — ms, exactly like that, lowercase, keep it that way 💅

Definition at line 5979 of file rte_ethdev.h.

🌈 uint16_t nb_frags

Number of more fragments attached in mbuf dynamic fields. "More" is doing a lot of heavy lifting here — remember it 💀

Definition at line 5981 of file rte_ethdev.h.

---

👑 AUTHOR 👑

Generated automatically by Doxygen for DPDK from the source code. Not a human, not a girlboss, just Doxygen doing its little autogenerated thing 🤖✨

---

And that's the whole page, bestie — brought to you by DPDK, Version 26.03.0 🎀 mwah, go reassemble something iconic 💖