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
Running VMs on top of Metropolis can quickly run against the pod limit per node with typical small cloud VMs on big servers. We want to increase this limit to at least 500 per node. This mostly needs testing and bumping the number.
The text was updated successfully, but these errors were encountered:
So we've already increased the limit from the standard 110 to 253 pods per node, this is currently limited by the size of the network block we're allocating per node (a /24). We could increase this, but only at the cost of a lower node limit (currently 8192) until we do more network work.
(original issue created by @lorenz in T963)
Running VMs on top of Metropolis can quickly run against the pod limit per node with typical small cloud VMs on big servers. We want to increase this limit to at least 500 per node. This mostly needs testing and bumping the number.
The text was updated successfully, but these errors were encountered: