Multi-process support

[heiher]

Summary

Improve CPU utilization on Linux systems by implementing multi-process support.

Motivation

To address the limitations of the current single-threaded mode, and to fully utilize the multi-core CPU resources of the system, enhancing transfer throughput by enabling multi-process mode.

Description

The multi-process mode will be supported on Linux systems, and a configuration option will be added to control the toggle of multi-process mode. When multi-process mode is enabled, the multi-queue function of the TUN device will be activated, allowing multiple processes to work on the same TUN device, with data flows distributed across multiple processes.

[heiher]

Enable multi-process (multi-queue) on Linux systems:

tunnel:
  name: tun0
  mtu: 9000
  multi-queue: true
  ipv4: 198.18.0.1
  ipv6: 'fc00::1'

Run 4 processes:

# Process 1
hev-socks5-tunnel conf.yml
# Process 2
hev-socks5-tunnel conf.yml
# Process 3
hev-socks5-tunnel conf.yml
# Process 4
hev-socks5-tunnel conf.yml

[heiher]

Benchmarks (single-process vs multi-process)

• commit id: ee96124
• testing environment: same as basic benchmarks
• maximum processes: 4

Speed

CPU Usage

Memory Usage

Upload

$ iperf3 -c 192.168.0.8
- - - - - - - - - - - - - - - - - - - - - - - - -
[  5]   0.00-10.00  sec  23.0 GBytes  19.8 Gbits/sec    0             sender
[  5]   0.00-10.04  sec  23.0 GBytes  19.7 Gbits/sec                  receiver
CPU usage: 76%
MEM usage: 2.7M

$ iperf3 -c 192.168.0.8 -P 10
- - - - - - - - - - - - - - - - - - - - - - - - -
[SUM]   0.00-10.00  sec  21.1 GBytes  18.1 Gbits/sec    0             sender
[SUM]   0.00-10.50  sec  21.1 GBytes  17.3 Gbits/sec                  receiver
CPU usage: 90%
MEM usage: 3.3M

$ iperf3 -c 192.168.0.8 -P 10
- - - - - - - - - - - - - - - - - - - - - - - - -
[SUM]   0.00-10.00  sec  51.3 GBytes  44.1 Gbits/sec    0             sender
[SUM]   0.00-10.04  sec  51.3 GBytes  43.9 Gbits/sec                  receiver
CPU usage 1: 68%
CPU usage 2: 64%
CPU usage 3: 42%
CPU usage 4: 28%
MEM usage 1: 2.7M
MEM usage 2: 2.7M
MEM usage 3: 2.5M
MEM usage 4: 2.7M

Download

$ iperf3 -c 192.168.0.8 -R
- - - - - - - - - - - - - - - - - - - - - - - - -
[  5]   0.00-10.04  sec  24.8 GBytes  21.2 Gbits/sec    0             sender
[  5]   0.00-10.00  sec  24.7 GBytes  21.3 Gbits/sec                  receiver
CPU usage: 90%
MEM usage: 2.7M

$ iperf3 -c 192.168.0.8 -R -P 10
- - - - - - - - - - - - - - - - - - - - - - - - -
[SUM]   0.00-10.04  sec  24.7 GBytes  21.1 Gbits/sec    0             sender
[SUM]   0.00-10.00  sec  24.5 GBytes  21.1 Gbits/sec                  receiver
CPU usage: 90%
MEM usage: 3.2M

$ iperf3 -c 192.168.0.8 -R -P 10
- - - - - - - - - - - - - - - - - - - - - - - - -
[SUM]   0.00-10.04  sec  61.4 GBytes  52.6 Gbits/sec    0             sender
[SUM]   0.00-10.00  sec  61.3 GBytes  52.6 Gbits/sec                  receiver
CPU usage 1: 90%
CPU usage 2: 90%
CPU usage 3: 50%
CPU usage 4: 50%
MEM usage 1: 2.7M
MEM usage 2: 2.7M
MEM usage 3: 2.7M
MEM usage 4: 2.7M