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
…cores
Automatic merge from submit-queue
Scale kube-proxy conntrack limits by cores (new default behavior)
For large machines we want more conntrack entries than smaller machines.
Commence bike-shedding on names and values and semantics. I'd love to get this in as a patch to 1.3.x since we have had some trouble for users on large machines.
Fixes#28867
This seems like very low-hanging fruit and hugely impactful. 256K might suffice for 4 or 8 core machines, but it's not enough for 32 core machines.
I heard a couple grumbles from people regarding 1.3 - maybe we should make this a patch for 1.3.1 or 1.3.2.
@matchstick @girishkalele @roberthbailey objections? I think this can be pretty surgical.
The text was updated successfully, but these errors were encountered: