Skip to content

Commit c491a4a

Browse files
authored
Merge pull request #3659 from abbas1902/ofi_fix
Hotfix: Boolean logic on when cloud rdma ofi tunables run
2 parents e727f26 + 3d13617 commit c491a4a

File tree

37 files changed

+45
-50
lines changed

37 files changed

+45
-50
lines changed

cmd/root.go

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -53,7 +53,7 @@ HPC deployments on the Google Cloud Platform.`,
5353
logging.Fatal("cmd.Help function failed: %s", err)
5454
}
5555
},
56-
Version: "v1.46.0",
56+
Version: "v1.46.1",
5757
Annotations: annotation,
5858
}
5959
)

community/examples/hpc-slurm-h4d.yaml

Lines changed: 0 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -128,14 +128,8 @@ deployment_groups:
128128
machine_type: n2-standard-4
129129
enable_login_public_ips: true
130130

131-
- id: slurm_controller_startup
132-
source: modules/scripts/startup-script
133-
settings:
134-
set_ofi_cloud_rdma_tunables: true
135-
136131
- id: slurm_controller
137132
source: community/modules/scheduler/schedmd-slurm-gcp-v6-controller
138133
use: [h4d-slurm-net-0, h4d_partition, slurm_login, homefs, appsfs]
139134
settings:
140135
enable_controller_public_ips: true
141-
controller_startup_script: $(slurm_controller_startup.startup_script)

community/modules/compute/htcondor-execute-point/versions.tf

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -25,6 +25,6 @@ terraform {
2525
}
2626

2727
provider_meta "google" {
28-
module_name = "blueprints/terraform/hpc-toolkit:htcondor-execute-point/v1.46.0"
28+
module_name = "blueprints/terraform/hpc-toolkit:htcondor-execute-point/v1.46.1"
2929
}
3030
}

community/modules/compute/mig/versions.tf

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -22,6 +22,6 @@ terraform {
2222
}
2323
}
2424
provider_meta "google" {
25-
module_name = "blueprints/terraform/hpc-toolkit:mig/v1.46.0"
25+
module_name = "blueprints/terraform/hpc-toolkit:mig/v1.46.1"
2626
}
2727
}

community/modules/compute/schedmd-slurm-gcp-v6-nodeset-dynamic/versions.tf

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -24,6 +24,6 @@ terraform {
2424
}
2525
}
2626
provider_meta "google" {
27-
module_name = "blueprints/terraform/hpc-toolkit:schedmd-slurm-gcp-v6-nodeset-dynamic/v1.46.0"
27+
module_name = "blueprints/terraform/hpc-toolkit:schedmd-slurm-gcp-v6-nodeset-dynamic/v1.46.1"
2828
}
2929
}

community/modules/compute/schedmd-slurm-gcp-v6-nodeset-tpu/versions.tf

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -18,6 +18,6 @@ terraform {
1818
required_version = ">= 1.3"
1919

2020
provider_meta "google" {
21-
module_name = "blueprints/terraform/hpc-toolkit:schedmd-slurm-gcp-v6-nodeset-tpu/v1.46.0"
21+
module_name = "blueprints/terraform/hpc-toolkit:schedmd-slurm-gcp-v6-nodeset-tpu/v1.46.1"
2222
}
2323
}

community/modules/compute/schedmd-slurm-gcp-v6-nodeset/versions.tf

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -24,6 +24,6 @@ terraform {
2424
}
2525
}
2626
provider_meta "google" {
27-
module_name = "blueprints/terraform/hpc-toolkit:schedmd-slurm-gcp-v6-nodeset/v1.46.0"
27+
module_name = "blueprints/terraform/hpc-toolkit:schedmd-slurm-gcp-v6-nodeset/v1.46.1"
2828
}
2929
}

community/modules/compute/schedmd-slurm-gcp-v6-partition/versions.tf

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -18,6 +18,6 @@ terraform {
1818
required_version = ">= 1.3"
1919

2020
provider_meta "google" {
21-
module_name = "blueprints/terraform/hpc-toolkit:schedmd-slurm-gcp-v6-partition/v1.46.0"
21+
module_name = "blueprints/terraform/hpc-toolkit:schedmd-slurm-gcp-v6-partition/v1.46.1"
2222
}
2323
}

community/modules/database/slurm-cloudsql-federation/versions.tf

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -26,10 +26,10 @@ terraform {
2626
}
2727
}
2828
provider_meta "google" {
29-
module_name = "blueprints/terraform/hpc-toolkit:slurm-cloudsql-federation/v1.46.0"
29+
module_name = "blueprints/terraform/hpc-toolkit:slurm-cloudsql-federation/v1.46.1"
3030
}
3131
provider_meta "google-beta" {
32-
module_name = "blueprints/terraform/hpc-toolkit:slurm-cloudsql-federation/v1.46.0"
32+
module_name = "blueprints/terraform/hpc-toolkit:slurm-cloudsql-federation/v1.46.1"
3333
}
3434

3535
required_version = ">= 0.13.0"

community/modules/file-system/cloud-storage-bucket/versions.tf

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -30,10 +30,10 @@ terraform {
3030
}
3131
}
3232
provider_meta "google" {
33-
module_name = "blueprints/terraform/hpc-toolkit:cloud-storage-bucket/v1.46.0"
33+
module_name = "blueprints/terraform/hpc-toolkit:cloud-storage-bucket/v1.46.1"
3434
}
3535
provider_meta "google-beta" {
36-
module_name = "blueprints/terraform/hpc-toolkit:cloud-storage-bucket/v1.46.0"
36+
module_name = "blueprints/terraform/hpc-toolkit:cloud-storage-bucket/v1.46.1"
3737
}
3838
required_version = ">= 0.14.0"
3939
}

community/modules/file-system/nfs-server/versions.tf

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -30,7 +30,7 @@ terraform {
3030
}
3131
}
3232
provider_meta "google" {
33-
module_name = "blueprints/terraform/hpc-toolkit:nfs-server/v1.46.0"
33+
module_name = "blueprints/terraform/hpc-toolkit:nfs-server/v1.46.1"
3434
}
3535

3636
required_version = ">= 0.14.0"

community/modules/files/fsi-montecarlo-on-batch/versions.tf

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -35,9 +35,9 @@ terraform {
3535
}
3636
}
3737
provider_meta "google" {
38-
module_name = "blueprints/terraform/hpc-toolkit:fsi-montecarlo-on-batch/v1.46.0"
38+
module_name = "blueprints/terraform/hpc-toolkit:fsi-montecarlo-on-batch/v1.46.1"
3939
}
4040
provider_meta "google-beta" {
41-
module_name = "blueprints/terraform/hpc-toolkit:fsi-montecarlo-on-batch/v1.46.0"
41+
module_name = "blueprints/terraform/hpc-toolkit:fsi-montecarlo-on-batch/v1.46.1"
4242
}
4343
}

community/modules/network/private-service-access/versions.tf

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -30,11 +30,11 @@ terraform {
3030
}
3131
}
3232
provider_meta "google" {
33-
module_name = "blueprints/terraform/hpc-toolkit:private-service-access/v1.46.0"
33+
module_name = "blueprints/terraform/hpc-toolkit:private-service-access/v1.46.1"
3434
}
3535

3636
provider_meta "google-beta" {
37-
module_name = "blueprints/terraform/hpc-toolkit:private-service-access/v1.46.0"
37+
module_name = "blueprints/terraform/hpc-toolkit:private-service-access/v1.46.1"
3838
}
3939

4040
required_version = ">= 1.2"

community/modules/project/service-enablement/versions.tf

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -22,7 +22,7 @@ terraform {
2222
}
2323
}
2424
provider_meta "google" {
25-
module_name = "blueprints/terraform/hpc-toolkit:service-enablement/v1.46.0"
25+
module_name = "blueprints/terraform/hpc-toolkit:service-enablement/v1.46.1"
2626
}
2727

2828
required_version = ">= 0.14.0"

community/modules/pubsub/bigquery-sub/versions.tf

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -26,10 +26,10 @@ terraform {
2626
}
2727
}
2828
provider_meta "google" {
29-
module_name = "blueprints/terraform/hpc-toolkit:bigquery-sub/v1.46.0"
29+
module_name = "blueprints/terraform/hpc-toolkit:bigquery-sub/v1.46.1"
3030
}
3131
provider_meta "google-beta" {
32-
module_name = "blueprints/terraform/hpc-toolkit:bigquery-sub/v1.46.0"
32+
module_name = "blueprints/terraform/hpc-toolkit:bigquery-sub/v1.46.1"
3333
}
3434
required_version = ">= 1.0"
3535
}

community/modules/pubsub/topic/versions.tf

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -27,6 +27,6 @@ terraform {
2727
}
2828
}
2929
provider_meta "google" {
30-
module_name = "blueprints/terraform/hpc-toolkit:topic/v1.46.0"
30+
module_name = "blueprints/terraform/hpc-toolkit:topic/v1.46.1"
3131
}
3232
}

community/modules/scheduler/htcondor-access-point/versions.tf

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -26,7 +26,7 @@ terraform {
2626
}
2727
}
2828
provider_meta "google" {
29-
module_name = "blueprints/terraform/hpc-toolkit:htcondor-access-point/v1.46.0"
29+
module_name = "blueprints/terraform/hpc-toolkit:htcondor-access-point/v1.46.1"
3030
}
3131

3232
required_version = ">= 1.1"

community/modules/scheduler/htcondor-central-manager/versions.tf

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -22,7 +22,7 @@ terraform {
2222
}
2323
}
2424
provider_meta "google" {
25-
module_name = "blueprints/terraform/hpc-toolkit:htcondor-central-manager/v1.46.0"
25+
module_name = "blueprints/terraform/hpc-toolkit:htcondor-central-manager/v1.46.1"
2626
}
2727

2828
required_version = ">= 1.1.0"

community/modules/scheduler/htcondor-pool-secrets/versions.tf

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -26,7 +26,7 @@ terraform {
2626
}
2727
}
2828
provider_meta "google" {
29-
module_name = "blueprints/terraform/hpc-toolkit:htcondor-pool-secrets/v1.46.0"
29+
module_name = "blueprints/terraform/hpc-toolkit:htcondor-pool-secrets/v1.46.1"
3030
}
3131

3232
required_version = ">= 1.3.0"

community/modules/scheduler/schedmd-slurm-gcp-v6-controller/versions.tf

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -24,6 +24,6 @@ terraform {
2424
}
2525
}
2626
provider_meta "google" {
27-
module_name = "blueprints/terraform/hpc-toolkit:schedmd-slurm-gcp-v6-controller/v1.46.0"
27+
module_name = "blueprints/terraform/hpc-toolkit:schedmd-slurm-gcp-v6-controller/v1.46.1"
2828
}
2929
}

community/modules/scheduler/schedmd-slurm-gcp-v6-login/versions.tf

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -24,6 +24,6 @@ terraform {
2424
}
2525
}
2626
provider_meta "google" {
27-
module_name = "blueprints/terraform/hpc-toolkit:schedmd-slurm-gcp-v6-login/v1.46.0"
27+
module_name = "blueprints/terraform/hpc-toolkit:schedmd-slurm-gcp-v6-login/v1.46.1"
2828
}
2929
}

community/modules/scripts/wait-for-startup/versions.tf

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -22,7 +22,7 @@ terraform {
2222
}
2323
}
2424
provider_meta "google" {
25-
module_name = "blueprints/terraform/hpc-toolkit:wait-for-startup/v1.46.0"
25+
module_name = "blueprints/terraform/hpc-toolkit:wait-for-startup/v1.46.1"
2626
}
2727

2828
required_version = ">= 0.14.0"

community/modules/scripts/windows-startup-script/versions.tf

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -16,7 +16,7 @@
1616

1717
terraform {
1818
provider_meta "google" {
19-
module_name = "blueprints/terraform/hpc-toolkit:windows-startup-script/v1.46.0"
19+
module_name = "blueprints/terraform/hpc-toolkit:windows-startup-script/v1.46.1"
2020
}
2121

2222
required_version = ">= 0.14.0"

modules/compute/gke-node-pool/versions.tf

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -30,6 +30,6 @@ terraform {
3030
}
3131
}
3232
provider_meta "google" {
33-
module_name = "blueprints/terraform/hpc-toolkit:gke-node-pool/v1.46.0"
33+
module_name = "blueprints/terraform/hpc-toolkit:gke-node-pool/v1.46.1"
3434
}
3535
}

modules/compute/vm-instance/versions.tf

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -31,10 +31,10 @@ terraform {
3131
}
3232
}
3333
provider_meta "google" {
34-
module_name = "blueprints/terraform/hpc-toolkit:vm-instance/v1.46.0"
34+
module_name = "blueprints/terraform/hpc-toolkit:vm-instance/v1.46.1"
3535
}
3636
provider_meta "google-beta" {
37-
module_name = "blueprints/terraform/hpc-toolkit:vm-instance/v1.46.0"
37+
module_name = "blueprints/terraform/hpc-toolkit:vm-instance/v1.46.1"
3838
}
3939

4040
required_version = ">= 1.3.0"

modules/file-system/filestore/versions.tf

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -26,10 +26,10 @@ terraform {
2626
}
2727
}
2828
provider_meta "google" {
29-
module_name = "blueprints/terraform/hpc-toolkit:filestore/v1.46.0"
29+
module_name = "blueprints/terraform/hpc-toolkit:filestore/v1.46.1"
3030
}
3131
provider_meta "google-beta" {
32-
module_name = "blueprints/terraform/hpc-toolkit:filestore/v1.46.0"
32+
module_name = "blueprints/terraform/hpc-toolkit:filestore/v1.46.1"
3333
}
3434

3535
required_version = ">= 1.3.0"

modules/file-system/gke-persistent-volume/versions.tf

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -29,6 +29,6 @@ terraform {
2929
}
3030
}
3131
provider_meta "google" {
32-
module_name = "blueprints/terraform/hpc-toolkit:gke-persistent-volume/v1.46.0"
32+
module_name = "blueprints/terraform/hpc-toolkit:gke-persistent-volume/v1.46.1"
3333
}
3434
}

modules/file-system/gke-storage/versions.tf

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -16,6 +16,6 @@ terraform {
1616
required_version = ">= 1.5"
1717

1818
provider_meta "google" {
19-
module_name = "blueprints/terraform/hpc-toolkit:gke-storage/v1.46.0"
19+
module_name = "blueprints/terraform/hpc-toolkit:gke-storage/v1.46.1"
2020
}
2121
}

modules/monitoring/dashboard/versions.tf

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -22,7 +22,7 @@ terraform {
2222
}
2323
}
2424
provider_meta "google" {
25-
module_name = "blueprints/terraform/hpc-toolkit:dashboard/v1.46.0"
25+
module_name = "blueprints/terraform/hpc-toolkit:dashboard/v1.46.1"
2626
}
2727

2828
required_version = ">= 0.14.0"

modules/network/firewall-rules/versions.tf

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -22,7 +22,7 @@ terraform {
2222
}
2323
}
2424
provider_meta "google" {
25-
module_name = "blueprints/terraform/hpc-toolkit:firewall-rules/v1.46.0"
25+
module_name = "blueprints/terraform/hpc-toolkit:firewall-rules/v1.46.1"
2626
}
2727

2828
required_version = ">= 1.5"

modules/network/pre-existing-subnetwork/versions.tf

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -22,7 +22,7 @@ terraform {
2222
}
2323
}
2424
provider_meta "google" {
25-
module_name = "blueprints/terraform/hpc-toolkit:pre-existing-subnetwork/v1.46.0"
25+
module_name = "blueprints/terraform/hpc-toolkit:pre-existing-subnetwork/v1.46.1"
2626
}
2727

2828
required_version = ">= 1.5"

modules/network/pre-existing-vpc/versions.tf

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -22,7 +22,7 @@ terraform {
2222
}
2323
}
2424
provider_meta "google" {
25-
module_name = "blueprints/terraform/hpc-toolkit:pre-existing-vpc/v1.46.0"
25+
module_name = "blueprints/terraform/hpc-toolkit:pre-existing-vpc/v1.46.1"
2626
}
2727

2828
required_version = ">= 1.5"

modules/scheduler/batch-login-node/versions.tf

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -22,7 +22,7 @@ terraform {
2222
}
2323
}
2424
provider_meta "google" {
25-
module_name = "blueprints/terraform/hpc-toolkit:batch-login-node/v1.46.0"
25+
module_name = "blueprints/terraform/hpc-toolkit:batch-login-node/v1.46.1"
2626
}
2727

2828
required_version = ">= 0.14.0"

modules/scheduler/gke-cluster/versions.tf

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -30,6 +30,6 @@ terraform {
3030
}
3131
}
3232
provider_meta "google" {
33-
module_name = "blueprints/terraform/hpc-toolkit:gke-cluster/v1.46.0"
33+
module_name = "blueprints/terraform/hpc-toolkit:gke-cluster/v1.46.1"
3434
}
3535
}

modules/scheduler/pre-existing-gke-cluster/versions.tf

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -23,7 +23,7 @@ terraform {
2323
}
2424

2525
provider_meta "google" {
26-
module_name = "blueprints/terraform/hpc-toolkit:pre-existing-gke-cluster/v1.46.0"
26+
module_name = "blueprints/terraform/hpc-toolkit:pre-existing-gke-cluster/v1.46.1"
2727
}
2828

2929
required_version = ">= 1.3"

modules/scripts/startup-script/main.tf

Lines changed: 3 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -93,7 +93,7 @@ locals {
9393
}
9494
]
9595

96-
ofi_runner = var.set_ofi_cloud_rdma_tunables == "" ? [] : [
96+
ofi_runner = !var.set_ofi_cloud_rdma_tunables ? [] : [
9797
{
9898
type = "data"
9999
destination = "/etc/profile.d/set_ofi_cloud_rdma_tunables.sh"
@@ -102,7 +102,8 @@ locals {
102102
export FI_PROVIDER="verbs;ofi_rxm"
103103
export FI_OFI_RXM_USE_RNDV_WRITE=1
104104
export FI_VERBS_INLINE_SIZE=39
105-
export I_MPI_FABRICS="shm:rxm"
105+
export I_MPI_FABRICS="shm:ofi"
106+
export FI_UNIVERSE_SIZE=3072
106107
EOT
107108
},
108109
]

modules/scripts/startup-script/versions.tf

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -30,7 +30,7 @@ terraform {
3030
}
3131
}
3232
provider_meta "google" {
33-
module_name = "blueprints/terraform/hpc-toolkit:startup-script/v1.46.0"
33+
module_name = "blueprints/terraform/hpc-toolkit:startup-script/v1.46.1"
3434
}
3535

3636
required_version = ">= 1.5"

0 commit comments

Comments
 (0)