You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The wireguard module in kernel (or even a cpp implementation) has far better performance than singbox's embedded one. I think it might be possible to create a virtual interface for wireguard and config the "bypass" or "freedom" output to go through it.
The text was updated successfully, but these errors were encountered:
Using the wg module in the kernel introduces many non-portable changes to the machine. Also, there needs to be a mechanism to ensure that the tunnel is always up and to manage changes in its configuration.
If there is a portable, Docker-compatible solution for it, we can implement it. Do you have any benchmarks regarding the performance of "CF Warp" with the wg module and single-box?
Actually there's a dockerized version of Wireguard, would you please take a look at it?
And since it's relevant, being able to use custom a Wireguard configuration would be great.
As for the benchmark, I'm afraid I don't have one, but it's considered "general knowledge" in singbox/xray community that the implemented Wireguard module doesn't perform as well as a kernel module or a "lower-level" client.
The wireguard module in kernel (or even a cpp implementation) has far better performance than singbox's embedded one. I think it might be possible to create a virtual interface for wireguard and config the "bypass" or "freedom" output to go through it.
The text was updated successfully, but these errors were encountered: