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

feat: add support for gpu_sharing_config on nodepool #1874

Merged
merged 9 commits into from
May 24, 2024
Merged

feat: add support for gpu_sharing_config on nodepool #1874

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
0317fd8
feat: add support for gpu_sharing_config on nodepool
jimgus Feb 13, 2024
5ce48f7
Merge branch 'master' into gpu_sharing_config
apeabody Mar 13, 2024
5ec2da1
Revert example changes
jimgus Mar 13, 2024
f5a4959
Merge branch 'master' into gpu_sharing_config
apeabody May 15, 2024
3c987d6
Merge branch 'master' into gpu_sharing_config
apeabody May 22, 2024
ecdfc78
Add GPU sharing config to readme
jimgus May 23, 2024
c760869
Add node pool re-creation at value change
jimgus May 23, 2024
dfe844f
Merge branch 'master' into gpu_sharing_config
apeabody May 23, 2024
554ae9c
Merge branch 'master' into gpu_sharing_config
apeabody May 23, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
41 changes: 23 additions & 18 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,24 +54,29 @@ module "gke" {
node_pools = [
{
name = "default-node-pool"
machine_type = "e2-medium"
node_locations = "us-central1-b,us-central1-c"
min_count = 1
max_count = 100
local_ssd_count = 0
spot = false
disk_size_gb = 100
disk_type = "pd-standard"
image_type = "COS_CONTAINERD"
enable_gcfs = false
enable_gvnic = false
logging_variant = "DEFAULT"
auto_repair = true
auto_upgrade = true
service_account = "project-service-account@<PROJECT ID>.iam.gserviceaccount.com"
preemptible = false
initial_node_count = 80
name = "default-node-pool"
machine_type = "e2-medium"
node_locations = "us-central1-b,us-central1-c"
min_count = 1
max_count = 100
local_ssd_count = 0
spot = false
disk_size_gb = 100
disk_type = "pd-standard"
image_type = "COS_CONTAINERD"
enable_gcfs = false
enable_gvnic = false
logging_variant = "DEFAULT"
auto_repair = true
auto_upgrade = true
service_account = "project-service-account@<PROJECT ID>.iam.gserviceaccount.com"
preemptible = false
initial_node_count = 80
accelerator_count = 1
accelerator_type = "nvidia-l4"
gpu_driver_version = "LATEST"
gpu_sharing_strategy = "TIME_SHARING"
max_shared_clients_per_gpu = 2
},
]
Expand Down
43 changes: 24 additions & 19 deletions autogen/main/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -96,27 +96,32 @@ module "gke" {
{% if autopilot_cluster != true %}
node_pools = [
{
name = "default-node-pool"
machine_type = "e2-medium"
node_locations = "us-central1-b,us-central1-c"
min_count = 1
max_count = 100
local_ssd_count = 0
spot = false
name = "default-node-pool"
machine_type = "e2-medium"
node_locations = "us-central1-b,us-central1-c"
min_count = 1
max_count = 100
local_ssd_count = 0
spot = false
{% if beta_cluster %}
local_ssd_ephemeral_count = 0
local_ssd_ephemeral_count = 0
{% endif %}
disk_size_gb = 100
disk_type = "pd-standard"
image_type = "COS_CONTAINERD"
enable_gcfs = false
enable_gvnic = false
logging_variant = "DEFAULT"
auto_repair = true
auto_upgrade = true
service_account = "project-service-account@<PROJECT ID>.iam.gserviceaccount.com"
preemptible = false
initial_node_count = 80
disk_size_gb = 100
disk_type = "pd-standard"
image_type = "COS_CONTAINERD"
enable_gcfs = false
enable_gvnic = false
logging_variant = "DEFAULT"
auto_repair = true
auto_upgrade = true
service_account = "project-service-account@<PROJECT ID>.iam.gserviceaccount.com"
preemptible = false
initial_node_count = 80
accelerator_count = 1
accelerator_type = "nvidia-l4"
gpu_driver_version = "LATEST"
gpu_sharing_strategy = "TIME_SHARING"
max_shared_clients_per_gpu = 2
},
]
Expand Down
10 changes: 10 additions & 0 deletions autogen/main/cluster.tf.tmpl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -643,6 +643,8 @@ locals {
"accelerator_type",
"gpu_partition_size",
"gpu_driver_version",
"gpu_sharing_strategy",
"max_shared_clients_per_gpu",
"enable_secure_boot",
"enable_integrity_monitoring",
"local_ssd_count",
Expand Down Expand Up @@ -927,6 +929,14 @@ resource "google_container_node_pool" "windows_pools" {
gpu_driver_version = lookup(each.value, "gpu_driver_version", "")
}
}

dynamic "gpu_sharing_config" {
for_each = lookup(each.value, "gpu_sharing_strategy", "") != "" ? [1] : []
apeabody marked this conversation as resolved.
Show resolved Hide resolved
content {
gpu_sharing_strategy = lookup(each.value, "gpu_sharing_strategy", "")
max_shared_clients_per_gpu = lookup(each.value, "max_shared_clients_per_gpu", 2)
apeabody marked this conversation as resolved.
Show resolved Hide resolved
}
}
}
}

Expand Down
16 changes: 16 additions & 0 deletions cluster.tf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -644,6 +644,14 @@ resource "google_container_node_pool" "pools" {
gpu_driver_version = lookup(each.value, "gpu_driver_version", "")
}
}

dynamic "gpu_sharing_config" {
for_each = lookup(each.value, "gpu_sharing_strategy", "") != "" ? [1] : []
content {
gpu_sharing_strategy = lookup(each.value, "gpu_sharing_strategy", "")
max_shared_clients_per_gpu = lookup(each.value, "max_shared_clients_per_gpu", 2)
}
}
}
}

Expand Down Expand Up @@ -882,6 +890,14 @@ resource "google_container_node_pool" "windows_pools" {
gpu_driver_version = lookup(each.value, "gpu_driver_version", "")
}
}

dynamic "gpu_sharing_config" {
for_each = lookup(each.value, "gpu_sharing_strategy", "") != "" ? [1] : []
content {
gpu_sharing_strategy = lookup(each.value, "gpu_sharing_strategy", "")
max_shared_clients_per_gpu = lookup(each.value, "max_shared_clients_per_gpu", 2)
}
}
}
}

Expand Down
43 changes: 24 additions & 19 deletions modules/beta-private-cluster-update-variant/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -84,25 +84,30 @@ module "gke" {
node_pools = [
{
name = "default-node-pool"
machine_type = "e2-medium"
node_locations = "us-central1-b,us-central1-c"
min_count = 1
max_count = 100
local_ssd_count = 0
spot = false
local_ssd_ephemeral_count = 0
disk_size_gb = 100
disk_type = "pd-standard"
image_type = "COS_CONTAINERD"
enable_gcfs = false
enable_gvnic = false
logging_variant = "DEFAULT"
auto_repair = true
auto_upgrade = true
service_account = "project-service-account@<PROJECT ID>.iam.gserviceaccount.com"
preemptible = false
initial_node_count = 80
name = "default-node-pool"
machine_type = "e2-medium"
node_locations = "us-central1-b,us-central1-c"
min_count = 1
max_count = 100
local_ssd_count = 0
spot = false
local_ssd_ephemeral_count = 0
disk_size_gb = 100
disk_type = "pd-standard"
image_type = "COS_CONTAINERD"
enable_gcfs = false
enable_gvnic = false
logging_variant = "DEFAULT"
auto_repair = true
auto_upgrade = true
service_account = "project-service-account@<PROJECT ID>.iam.gserviceaccount.com"
preemptible = false
initial_node_count = 80
accelerator_count = 1
accelerator_type = "nvidia-l4"
gpu_driver_version = "LATEST"
gpu_sharing_strategy = "TIME_SHARING"
max_shared_clients_per_gpu = 2
},
]
Expand Down
18 changes: 18 additions & 0 deletions modules/beta-private-cluster-update-variant/cluster.tf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -552,6 +552,8 @@ locals {
"accelerator_type",
"gpu_partition_size",
"gpu_driver_version",
"gpu_sharing_strategy",
"max_shared_clients_per_gpu",
"enable_secure_boot",
"enable_integrity_monitoring",
"local_ssd_count",
Expand Down Expand Up @@ -811,6 +813,14 @@ resource "google_container_node_pool" "pools" {
gpu_driver_version = lookup(each.value, "gpu_driver_version", "")
}
}

dynamic "gpu_sharing_config" {
for_each = lookup(each.value, "gpu_sharing_strategy", "") != "" ? [1] : []
content {
gpu_sharing_strategy = lookup(each.value, "gpu_sharing_strategy", "")
max_shared_clients_per_gpu = lookup(each.value, "max_shared_clients_per_gpu", 2)
}
}
}
}

Expand Down Expand Up @@ -1075,6 +1085,14 @@ resource "google_container_node_pool" "windows_pools" {
gpu_driver_version = lookup(each.value, "gpu_driver_version", "")
}
}

dynamic "gpu_sharing_config" {
for_each = lookup(each.value, "gpu_sharing_strategy", "") != "" ? [1] : []
content {
gpu_sharing_strategy = lookup(each.value, "gpu_sharing_strategy", "")
max_shared_clients_per_gpu = lookup(each.value, "max_shared_clients_per_gpu", 2)
}
}
}
}

Expand Down
43 changes: 24 additions & 19 deletions modules/beta-private-cluster/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,25 +62,30 @@ module "gke" {
node_pools = [
{
name = "default-node-pool"
machine_type = "e2-medium"
node_locations = "us-central1-b,us-central1-c"
min_count = 1
max_count = 100
local_ssd_count = 0
spot = false
local_ssd_ephemeral_count = 0
disk_size_gb = 100
disk_type = "pd-standard"
image_type = "COS_CONTAINERD"
enable_gcfs = false
enable_gvnic = false
logging_variant = "DEFAULT"
auto_repair = true
auto_upgrade = true
service_account = "project-service-account@<PROJECT ID>.iam.gserviceaccount.com"
preemptible = false
initial_node_count = 80
name = "default-node-pool"
machine_type = "e2-medium"
node_locations = "us-central1-b,us-central1-c"
min_count = 1
max_count = 100
local_ssd_count = 0
spot = false
local_ssd_ephemeral_count = 0
disk_size_gb = 100
disk_type = "pd-standard"
image_type = "COS_CONTAINERD"
enable_gcfs = false
enable_gvnic = false
logging_variant = "DEFAULT"
auto_repair = true
auto_upgrade = true
service_account = "project-service-account@<PROJECT ID>.iam.gserviceaccount.com"
preemptible = false
initial_node_count = 80
accelerator_count = 1
accelerator_type = "nvidia-l4"
gpu_driver_version = "LATEST"
gpu_sharing_strategy = "TIME_SHARING"
max_shared_clients_per_gpu = 2
},
]
Expand Down
16 changes: 16 additions & 0 deletions modules/beta-private-cluster/cluster.tf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -735,6 +735,14 @@ resource "google_container_node_pool" "pools" {
gpu_driver_version = lookup(each.value, "gpu_driver_version", "")
}
}

dynamic "gpu_sharing_config" {
for_each = lookup(each.value, "gpu_sharing_strategy", "") != "" ? [1] : []
content {
gpu_sharing_strategy = lookup(each.value, "gpu_sharing_strategy", "")
max_shared_clients_per_gpu = lookup(each.value, "max_shared_clients_per_gpu", 2)
}
}
}
}

Expand Down Expand Up @@ -998,6 +1006,14 @@ resource "google_container_node_pool" "windows_pools" {
gpu_driver_version = lookup(each.value, "gpu_driver_version", "")
}
}

dynamic "gpu_sharing_config" {
for_each = lookup(each.value, "gpu_sharing_strategy", "") != "" ? [1] : []
content {
gpu_sharing_strategy = lookup(each.value, "gpu_sharing_strategy", "")
max_shared_clients_per_gpu = lookup(each.value, "max_shared_clients_per_gpu", 2)
}
}
}
}

Expand Down
43 changes: 24 additions & 19 deletions modules/beta-public-cluster-update-variant/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -78,25 +78,30 @@ module "gke" {
node_pools = [
{
name = "default-node-pool"
machine_type = "e2-medium"
node_locations = "us-central1-b,us-central1-c"
min_count = 1
max_count = 100
local_ssd_count = 0
spot = false
local_ssd_ephemeral_count = 0
disk_size_gb = 100
disk_type = "pd-standard"
image_type = "COS_CONTAINERD"
enable_gcfs = false
enable_gvnic = false
logging_variant = "DEFAULT"
auto_repair = true
auto_upgrade = true
service_account = "project-service-account@<PROJECT ID>.iam.gserviceaccount.com"
preemptible = false
initial_node_count = 80
name = "default-node-pool"
machine_type = "e2-medium"
node_locations = "us-central1-b,us-central1-c"
min_count = 1
max_count = 100
local_ssd_count = 0
spot = false
local_ssd_ephemeral_count = 0
disk_size_gb = 100
disk_type = "pd-standard"
image_type = "COS_CONTAINERD"
enable_gcfs = false
enable_gvnic = false
logging_variant = "DEFAULT"
auto_repair = true
auto_upgrade = true
service_account = "project-service-account@<PROJECT ID>.iam.gserviceaccount.com"
preemptible = false
initial_node_count = 80
accelerator_count = 1
accelerator_type = "nvidia-l4"
gpu_driver_version = "LATEST"
gpu_sharing_strategy = "TIME_SHARING"
max_shared_clients_per_gpu = 2
},
]
Expand Down