net/mlx5: Avoid payload in skb's linear part for better GRO-processing
Status from this message: This series was applied to netdev/net-next.git (main)
Get series with b4
b4 am [email protected]Versions newest first · linked by author and title
- v7 Latest2 patches 0 repliesApplied 2/2
- v63 patches 14 repliesSuperseded
Changes in v7 from the cover letter
- Drop cache aligned memcpy patch as it no longer shows benefits on further testing on other hosts.
- For XDP, pull at most ETH_HLEN bytes into linear part.
- Fix skb pull length calculation for XDP (Amery Hung).
- Switched from min_t() to min() to avoid skb->data_len 16 bit truncation (David Laigh).
- Improved commit message for last patch to make it clear that the benchmark is not on native XDP (Sashiko).
Patches in v7 All 2 applied
| # | Subject and files | Size | Replies | Applied |
|---|---|---|---|---|
| 1/2 | net/mlx5e: DMA-sync earlier in mlx5e_skb_from_cqe_mpwrq_nonlineardrivers/ | +15 | 0 replies | Applied |
| 2/2 | net/mlx5e: Avoid copying payload to the skb's linear partdrivers/ | +7 | 0 replies | Applied |
Reviews trailers per patch
All 2 patches have a Reviewed-by or Acked-by.
| Patch | Eric Dumazet | Saeed Mahameed |
|---|---|---|
| 1/2 | R-b | R-b |
| 2/2 | R-b | R-b |
Trailers given in replies are filled; those carried in the patches from earlier versions are outlined with dashes.
Cover letter [PATCH net-next V7 0/2] net/mlx5: Avoid payload in skb's linear part for better GRO-processing
Hi,
This is V7 of a series originally submitted by Christoph.
When LRO is enabled on the MLX, mlx5e_skb_from_cqe_mpwrq_nonlinear copies parts of the payload to the linear part of the skb.
This triggers suboptimal processing in GRO, causing slow throughput.
This patch series addresses this by using eth_get_headlen to compute the size of the protocol headers and only copy those bits. This results in a significant throughput improvement (detailed results in the specific patch).
Regards,
Tariq
---
V7:
- Drop cache aligned memcpy patch as it no longer shows benefits on further testing on other hosts.
- For XDP, pull at most ETH_HLEN bytes into linear part.
- Fix skb pull length calculation for XDP (Amery Hung).
- Switched from min_t() to min() to avoid skb->data_len 16 bit truncation (David Laigh).
- Improved commit message for last patch to make it clear that the benchmark is not on native XDP (Sashiko).
V6:
https://lore.kernel.org/all/[email protected]/
Christoph Paasch (2):
net/mlx5e: DMA-sync earlier in mlx5e_skb_from_cqe_mpwrq_nonlinear net/mlx5e: Avoid copying payload to the skb's linear part
.../net/ethernet/mellanox/mlx5/core/en_rx.c | 33 ++++++++++++------- 1 file changed, 22 insertions(+), 11 deletions(-)
base-commit: 8415598365503ced2e3d019491b0a2756c85c494
Signature · 1 line
2.44.0