Skip to content

#199 - Account for TX transform overhead in MTU sizing#218

Draft
MikesRND wants to merge 1 commit into
NVIDIA:mainfrom
MikesRND:issue-199-tx-transform-mtu
Draft

#199 - Account for TX transform overhead in MTU sizing#218
MikesRND wants to merge 1 commit into
NVIDIA:mainfrom
MikesRND:issue-199-tx-transform-mtu

Conversation

@MikesRND

@MikesRND MikesRND commented Jul 8, 2026

Copy link
Copy Markdown
Contributor

Summary

Closes #199.

This updates raw-engine MTU sizing so configured TX transform overhead is considered alongside RX sizing. It also refreshes the related docs and log wording so MTU behavior is described consistently for RX and TX.

Verification

  • git diff --check
  • git clang-format --diff --style file HEAD -- include/daqiri/types.h src/engines/dpdk/daqiri_dpdk_engine.cpp src/engines/ibverbs/ daqiri_ibverbs_engine.cpp src/engines/ibverbs/daqiri_ibverbs_engine.h
  • Built daqiri_dpdk, daqiri_ibverbs, and daqiri_common in the project container with examples disabled
  • python3 scripts/check_doc_refs.py

Note: the full container image build currently fails before this change is compiled, in examples/pool_ring_bench.cpp, with a DPDK/GCC SIMD flag mismatch around _mm_alignr_epi8 from rte_memcpy.h. The focused container build disables examples and verifies the changed DPDK, ibverbs, and common library targets.
Recommended follow-up on target hardware.

Signed-off-by: MikesRND <6515522+MikesRND@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

[BUG] Account for TX hardware encap/push overhead in raw MTU sizing

1 participant