Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Allocate all GPU resources POC #1

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Allocate all GPU resources POC #1

wants to merge 1 commit into from

Conversation

XIAZY
Copy link

@XIAZY XIAZY commented Sep 11, 2023 

$ terraform plan -var project_id="zeet-demo" -var region="us-west1" -var zone="us-west1-b" -var cluster_id="zeet-zeet-example-gcp" -var cluster_name="zeet-zeet-example-gcp" -var cluster_domain="random.app" -var user_id="random" -var enable_l4="true" -var enable_tpu="true" -var enable_a100="true" -no-color > out

>>>

  # module.gke.google_container_node_pool.pools["n1-standard-4-nvidia-v100"] will be created
  + resource "google_container_node_pool" "pools" {
      + cluster                     = "zeet-zeet-zeet-example-gcp"
      + id                          = (known after apply)
      + initial_node_count          = 0
      + instance_group_urls         = (known after apply)
      + location                    = "us-west1-b"
      + managed_instance_group_urls = (known after apply)
      + max_pods_per_node           = (known after apply)
      + name                        = "n1-standard-4-nvidia-v100"
      + name_prefix                 = (known after apply)
      + node_count                  = (known after apply)
      + node_locations              = [
          + "us-west1-b",
        ]
      + operation                   = (known after apply)
      + project                     = "zeet-demo"
      + version                     = (known after apply)

      + autoscaling {
          + max_node_count = 20
          + min_node_count = 0
        }

      + management {
          + auto_repair  = true
          + auto_upgrade = true
        }

      + node_config {
          + disk_size_gb      = 200
          + disk_type         = "pd-standard"
          + guest_accelerator = [
              + {
                  + count = 1
                  + type  = "nvidia-tesla-v100"
                },
            ]
          + image_type        = "COS_CONTAINERD"
          + labels            = {
              + "ZeetClusterId"                    = "zeet-zeet-example-gcp"
              + "ZeetUserId"                       = "random"
              + "cloud.google.com/gke-accelerator" = "nvidia-tesla-v100"
              + "cluster_name"                     = "zeet-zeet-zeet-example-gcp"
              + "node_pool"                        = "n1-standard-4-nvidia-v100"
              + "zeet.co/dedicated"                = "dedicated"
            }
          + local_ssd_count   = 0
          + machine_type      = "n1-standard-4"
          + metadata          = {
              + "ZeetClusterId"            = "zeet-zeet-example-gcp"
              + "ZeetUserId"               = "random"
              + "cluster_name"             = "zeet-zeet-zeet-example-gcp"
              + "disable-legacy-endpoints" = "true"
              + "node_pool"                = "n1-standard-4-nvidia-v100"
            }
          + oauth_scopes      = [
              + "https://www.googleapis.com/auth/cloud-platform",
              + "https://www.googleapis.com/auth/logging.write",
              + "https://www.googleapis.com/auth/monitoring",
            ]
          + preemptible       = false
          + service_account   = (known after apply)
          + spot              = false
          + tags              = [
              + "gke-zeet-zeet-zeet-example-gcp",
              + "gke-zeet-zeet-zeet-example-gcp-n1-standard-4-nvidia-v100",
            ]
          + taint             = (known after apply)

          + shielded_instance_config {
              + enable_integrity_monitoring = true
              + enable_secure_boot          = false
            }

          + workload_metadata_config {
              + mode = "GKE_METADATA"
            }
        }

      + timeouts {
          + create = "45m"
          + delete = "45m"
          + update = "45m"
        }

      + upgrade_settings {
          + max_surge       = 1
          + max_unavailable = 0
        }
    }

  # module.gke.google_container_node_pool.pools["n1-standard-8-nvidia-k80"] will be created
  + resource "google_container_node_pool" "pools" {
      + cluster                     = "zeet-zeet-zeet-example-gcp"
      + id                          = (known after apply)
      + initial_node_count          = 0
      + instance_group_urls         = (known after apply)
      + location                    = "us-west1-b"
      + managed_instance_group_urls = (known after apply)
      + max_pods_per_node           = (known after apply)
      + name                        = "n1-standard-8-nvidia-k80"
      + name_prefix                 = (known after apply)
      + node_count                  = (known after apply)
      + node_locations              = [
          + "us-west1-b",
        ]
      + operation                   = (known after apply)
      + project                     = "zeet-demo"
      + version                     = (known after apply)

      + autoscaling {
          + max_node_count = 20
          + min_node_count = 0
        }

      + management {
          + auto_repair  = true
          + auto_upgrade = true
        }

      + node_config {
          + disk_size_gb      = 200
          + disk_type         = "pd-standard"
          + guest_accelerator = [
              + {
                  + count = 1
                  + type  = "nvidia-tesla-k80"
                },
            ]
          + image_type        = "COS_CONTAINERD"
          + labels            = {
              + "ZeetClusterId"                    = "zeet-zeet-example-gcp"
              + "ZeetUserId"                       = "random"
              + "cloud.google.com/gke-accelerator" = "nvidia-tesla-k80"
              + "cluster_name"                     = "zeet-zeet-zeet-example-gcp"
              + "node_pool"                        = "n1-standard-8-nvidia-k80"
              + "zeet.co/dedicated"                = "dedicated"
            }
          + local_ssd_count   = 0
          + machine_type      = "n1-standard-8"
          + metadata          = {
              + "ZeetClusterId"            = "zeet-zeet-example-gcp"
              + "ZeetUserId"               = "random"
              + "cluster_name"             = "zeet-zeet-zeet-example-gcp"
              + "disable-legacy-endpoints" = "true"
              + "node_pool"                = "n1-standard-8-nvidia-k80"
            }
          + oauth_scopes      = [
              + "https://www.googleapis.com/auth/cloud-platform",
              + "https://www.googleapis.com/auth/logging.write",
              + "https://www.googleapis.com/auth/monitoring",
            ]
          + preemptible       = false
          + service_account   = (known after apply)
          + spot              = false
          + tags              = [
              + "gke-zeet-zeet-zeet-example-gcp",
              + "gke-zeet-zeet-zeet-example-gcp-n1-standard-8-nvidia-k80",
            ]
          + taint             = (known after apply)

          + shielded_instance_config {
              + enable_integrity_monitoring = true
              + enable_secure_boot          = false
            }

          + workload_metadata_config {
              + mode = "GKE_METADATA"
            }
        }

      + timeouts {
          + create = "45m"
          + delete = "45m"
          + update = "45m"
        }

      + upgrade_settings {
          + max_surge       = 1
          + max_unavailable = 0
        }
    }

  # module.gke.google_container_node_pool.pools["n1-standard-8-nvidia-p100"] will be created
  + resource "google_container_node_pool" "pools" {
      + cluster                     = "zeet-zeet-zeet-example-gcp"
      + id                          = (known after apply)
      + initial_node_count          = 0
      + instance_group_urls         = (known after apply)
      + location                    = "us-west1-b"
      + managed_instance_group_urls = (known after apply)
      + max_pods_per_node           = (known after apply)
      + name                        = "n1-standard-8-nvidia-p100"
      + name_prefix                 = (known after apply)
      + node_count                  = (known after apply)
      + node_locations              = [
          + "us-west1-b",
        ]
      + operation                   = (known after apply)
      + project                     = "zeet-demo"
      + version                     = (known after apply)

      + autoscaling {
          + max_node_count = 20
          + min_node_count = 0
        }

      + management {
          + auto_repair  = true
          + auto_upgrade = true
        }

      + node_config {
          + disk_size_gb      = 200
          + disk_type         = "pd-standard"
          + guest_accelerator = [
              + {
                  + count = 1
                  + type  = "nvidia-tesla-p100"
                },
            ]
          + image_type        = "COS_CONTAINERD"
          + labels            = {
              + "ZeetClusterId"                    = "zeet-zeet-example-gcp"
              + "ZeetUserId"                       = "random"
              + "cloud.google.com/gke-accelerator" = "nvidia-tesla-p100"
              + "cluster_name"                     = "zeet-zeet-zeet-example-gcp"
              + "node_pool"                        = "n1-standard-8-nvidia-p100"
              + "zeet.co/dedicated"                = "dedicated"
            }
          + local_ssd_count   = 0
          + machine_type      = "n1-standard-8"
          + metadata          = {
              + "ZeetClusterId"            = "zeet-zeet-example-gcp"
              + "ZeetUserId"               = "random"
              + "cluster_name"             = "zeet-zeet-zeet-example-gcp"
              + "disable-legacy-endpoints" = "true"
              + "node_pool"                = "n1-standard-8-nvidia-p100"
            }
          + oauth_scopes      = [
              + "https://www.googleapis.com/auth/cloud-platform",
              + "https://www.googleapis.com/auth/logging.write",
              + "https://www.googleapis.com/auth/monitoring",
            ]
          + preemptible       = false
          + service_account   = (known after apply)
          + spot              = false
          + tags              = [
              + "gke-zeet-zeet-zeet-example-gcp",
              + "gke-zeet-zeet-zeet-example-gcp-n1-standard-8-nvidia-p100",
            ]
          + taint             = (known after apply)

          + shielded_instance_config {
              + enable_integrity_monitoring = true
              + enable_secure_boot          = false
            }

          + workload_metadata_config {
              + mode = "GKE_METADATA"
            }
        }

      + timeouts {
          + create = "45m"
          + delete = "45m"
          + update = "45m"
        }

      + upgrade_settings {
          + max_surge       = 1
          + max_unavailable = 0
        }
    }

  # module.gke.google_container_node_pool.pools["n1-standard-8-nvidia-t4"] will be created
  + resource "google_container_node_pool" "pools" {
      + cluster                     = "zeet-zeet-zeet-example-gcp"
      + id                          = (known after apply)
      + initial_node_count          = 0
      + instance_group_urls         = (known after apply)
      + location                    = "us-west1-b"
      + managed_instance_group_urls = (known after apply)
      + max_pods_per_node           = (known after apply)
      + name                        = "n1-standard-8-nvidia-t4"
      + name_prefix                 = (known after apply)
      + node_count                  = (known after apply)
      + node_locations              = [
          + "us-west1-b",
        ]
      + operation                   = (known after apply)
      + project                     = "zeet-demo"
      + version                     = (known after apply)

      + autoscaling {
          + max_node_count = 20
          + min_node_count = 0
        }

      + management {
          + auto_repair  = true
          + auto_upgrade = true
        }

      + node_config {
          + disk_size_gb      = 200
          + disk_type         = "pd-standard"
          + guest_accelerator = [
              + {
                  + count = 1
                  + type  = "nvidia-tesla-t4"
                },
            ]
          + image_type        = "COS_CONTAINERD"
          + labels            = {
              + "ZeetClusterId"                    = "zeet-zeet-example-gcp"
              + "ZeetUserId"                       = "random"
              + "cloud.google.com/gke-accelerator" = "nvidia-tesla-t4"
              + "cluster_name"                     = "zeet-zeet-zeet-example-gcp"
              + "node_pool"                        = "n1-standard-8-nvidia-t4"
              + "zeet.co/dedicated"                = "dedicated"
            }
          + local_ssd_count   = 0
          + machine_type      = "n1-standard-8"
          + metadata          = {
              + "ZeetClusterId"            = "zeet-zeet-example-gcp"
              + "ZeetUserId"               = "random"
              + "cluster_name"             = "zeet-zeet-zeet-example-gcp"
              + "disable-legacy-endpoints" = "true"
              + "node_pool"                = "n1-standard-8-nvidia-t4"
            }
          + oauth_scopes      = [
              + "https://www.googleapis.com/auth/cloud-platform",
              + "https://www.googleapis.com/auth/logging.write",
              + "https://www.googleapis.com/auth/monitoring",
            ]
          + preemptible       = false
          + service_account   = (known after apply)
          + spot              = false
          + tags              = [
              + "gke-zeet-zeet-zeet-example-gcp",
              + "gke-zeet-zeet-zeet-example-gcp-n1-standard-8-nvidia-t4",
            ]
          + taint             = (known after apply)

          + shielded_instance_config {
              + enable_integrity_monitoring = true
              + enable_secure_boot          = false
            }

          + workload_metadata_config {
              + mode = "GKE_METADATA"
            }
        }

      + timeouts {
          + create = "45m"
          + delete = "45m"
          + update = "45m"
        }

      + upgrade_settings {
          + max_surge       = 1
          + max_unavailable = 0
        }
    }

  # module.gke.google_container_node_pool.pools["n1-standard-8-nvidia-v100"] will be created
  + resource "google_container_node_pool" "pools" {
      + cluster                     = "zeet-zeet-zeet-example-gcp"
      + id                          = (known after apply)
      + initial_node_count          = 0
      + instance_group_urls         = (known after apply)
      + location                    = "us-west1-b"
      + managed_instance_group_urls = (known after apply)
      + max_pods_per_node           = (known after apply)
      + name                        = "n1-standard-8-nvidia-v100"
      + name_prefix                 = (known after apply)
      + node_count                  = (known after apply)
      + node_locations              = [
          + "us-west1-b",
        ]
      + operation                   = (known after apply)
      + project                     = "zeet-demo"
      + version                     = (known after apply)

      + autoscaling {
          + max_node_count = 20
          + min_node_count = 0
        }

      + management {
          + auto_repair  = true
          + auto_upgrade = true
        }

      + node_config {
          + disk_size_gb      = 200
          + disk_type         = "pd-standard"
          + guest_accelerator = [
              + {
                  + count = 1
                  + type  = "nvidia-tesla-v100"
                },
            ]
          + image_type        = "COS_CONTAINERD"
          + labels            = {
              + "ZeetClusterId"                    = "zeet-zeet-example-gcp"
              + "ZeetUserId"                       = "random"
              + "cloud.google.com/gke-accelerator" = "nvidia-tesla-v100"
              + "cluster_name"                     = "zeet-zeet-zeet-example-gcp"
              + "node_pool"                        = "n1-standard-8-nvidia-v100"
              + "zeet.co/dedicated"                = "dedicated"
            }
          + local_ssd_count   = 0
          + machine_type      = "n1-standard-8"
          + metadata          = {
              + "ZeetClusterId"            = "zeet-zeet-example-gcp"
              + "ZeetUserId"               = "random"
              + "cluster_name"             = "zeet-zeet-zeet-example-gcp"
              + "disable-legacy-endpoints" = "true"
              + "node_pool"                = "n1-standard-8-nvidia-v100"
            }
          + oauth_scopes      = [
              + "https://www.googleapis.com/auth/cloud-platform",
              + "https://www.googleapis.com/auth/logging.write",
              + "https://www.googleapis.com/auth/monitoring",
            ]
          + preemptible       = false
          + service_account   = (known after apply)
          + spot              = false
          + tags              = [
              + "gke-zeet-zeet-zeet-example-gcp",
              + "gke-zeet-zeet-zeet-example-gcp-n1-standard-8-nvidia-v100",
            ]
          + taint             = (known after apply)

          + shielded_instance_config {
              + enable_integrity_monitoring = true
              + enable_secure_boot          = false
            }

          + workload_metadata_config {
              + mode = "GKE_METADATA"
            }
        }

      + timeouts {
          + create = "45m"
          + delete = "45m"
          + update = "45m"
        }

      + upgrade_settings {
          + max_surge       = 1
          + max_unavailable = 0
        }
    }

…

@XIAZY
Copy link
Author

XIAZY commented Sep 11, 2023

https://linear.app/zeet/issue/ZEET-3307/poc-create-a-proof-of-concept-that-works-for-creating-cloud-resources

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

None yet
1 participant
@XIAZY