Google Patches Linux kernel with ~40% TCP performance

· 369 words · 2 minute read

I watched a video from Hussein Nasser on YouTube about a patch from Google to get better performance at scale.

Coco Li (from Google) explained of their cachline optimization effort to the networking code:

“Currently, variable-heavy structs in the networking stack is organized chronologically, logically and sometimes by cache line access. This patch series attempts to reorganize the core networking stack variables to minimize cacheline consumption during the phase of data transfer. Specifically, we looked at the TCP/IP stack and the fast path definition in TCP.” — Coco Li | Googler

The performance optimization done - simply - by the variables placements to achieve better caching. The performance is gets better with more requests, with average of 40% better performance on AMD CPUs. Here is all performance wins.

Our tests were run with neper tcp_rr using tcp traffic. The tests have $cpu
number of threads and variable number of flows (see below).

Tests were run on 6.5-rc1

Efficiency is computed as cpu seconds / throughput (one tcp_rr round trip).
The following result shows efficiency delta before and after the patch
series is applied.

On AMD platforms with 100Gb/s NIC and 256Mb L3 cache:
Flows   with patches    clean kernel      Percent reduction
30k     0.0001736538065 0.0002741191042 -36.65%
20k     0.0001583661752 0.0002712559158 -41.62%
10k     0.0001639148817 0.0002951800751 -44.47%
5k      0.0001859683866 0.0003320642536 -44.00%
1k      0.0002035190546 0.0003152056382 -35.43%

Flows   with patches  clean kernel    Percent reduction
30k     0.000202535503  0.0003275329163 -38.16%
20k     0.0002020654777 0.0003411304786 -40.77%
10k     0.0002122427035 0.0003803674705 -44.20%
5k      0.0002348776729 0.0004030403953 -41.72%
1k      0.0002237384583 0.0002813646157 -20.48%

On Intel platforms with 200Gb/s NIC and 105Mb L3 cache:
Flows   with patches    clean kernel    Percent reduction
30k     0.0006296537873 0.0006370427753 -1.16%
20k     0.0003451029365 0.0003628016076 -4.88%
10k     0.0003187646958 0.0003346835645 -4.76%
5k      0.0002954676348 0.000311807592  -5.24%
1k      0.0001909169342 0.0001848069709 3.31%

This performance optimization is coming in Linux 6.8 release.

If you want to read more details, read Phoronix post . If you need even more information, here is the patch itself .

I hope this post helps you. If you know a person who can benefit from this information, send them a link of this post. If you want to get notified about new posts, follow me on YouTube , Twitter (x) , LinkedIn , Facebook , Telegram and GitHub .