diff options
author | pmikus <peter.mikus@protonmail.ch> | 2023-02-03 11:15:18 +0000 |
---|---|---|
committer | Peter Mikus <peter.mikus@protonmail.ch> | 2023-02-03 11:30:03 +0000 |
commit | 534260730b25b948e350351500ba56441382ff91 (patch) | |
tree | a811c230f63de7b951a227ad74ab33b27b6fd5b3 | |
parent | a80768fb102e01bc6081e343343bfcd3151d6ddb (diff) |
feat(terraform): Optimize ETL execution
Signed-off-by: pmikus <peter.mikus@protonmail.ch>
Change-Id: I11dfe8f642c6d565d39b1e0fbc41361460a42320
(cherry picked from commit a32f6fa10f5a75b59c6b2cc12576161185b738d5)
9 files changed, 699 insertions, 600 deletions
diff --git a/fdio.infra.terraform/terraform-nomad-pyspark-etl/conf/nomad/etl-coverage-rls2302.hcl.tftpl b/fdio.infra.terraform/terraform-nomad-pyspark-etl/conf/nomad/etl-coverage-rls2302.hcl.tftpl new file mode 100644 index 0000000000..042c3bde92 --- /dev/null +++ b/fdio.infra.terraform/terraform-nomad-pyspark-etl/conf/nomad/etl-coverage-rls2302.hcl.tftpl @@ -0,0 +1,215 @@ +job "${job_name}" { + datacenters = "${datacenters}" + type = "${type}" + periodic { + cron = "${cron}" + prohibit_overlap = "${prohibit_overlap}" + time_zone = "${time_zone}" + } + group "${job_name}" { + restart { + mode = "fail" + } + constraint { + attribute = "$${attr.cpu.arch}" + operator = "!=" + value = "arm64" + } + constraint { + attribute = "$${node.class}" + value = "builder" + } + task "${job_name}-device" { + artifact { + source = "git::https://github.com/FDio/csit" + destination = "local/csit" + } + driver = "docker" + config { + image = "${image}" + command = "gluesparksubmit" + args = [ + "--driver-memory", "20g", + "--executor-memory", "20g", + "--executor-cores", "2", + "--master", "local[2]", + "coverage_device_rls2302.py" + ] + work_dir = "/local/csit/csit.infra.etl" + } + env { + AWS_ACCESS_KEY_ID = "${aws_access_key_id}" + AWS_SECRET_ACCESS_KEY = "${aws_secret_access_key}" + AWS_DEFAULT_REGION = "${aws_default_region}" + OUT_AWS_ACCESS_KEY_ID = "${out_aws_access_key_id}" + OUT_AWS_SECRET_ACCESS_KEY = "${out_aws_secret_access_key}" + OUT_AWS_DEFAULT_REGION = "${out_aws_default_region}" + ${ envs } + } + resources { + cpu = ${cpu} + memory = ${memory} + } + } + task "${job_name}-hoststack" { + artifact { + source = "git::https://github.com/FDio/csit" + destination = "local/csit" + } + driver = "docker" + config { + image = "${image}" + command = "gluesparksubmit" + args = [ + "--driver-memory", "20g", + "--executor-memory", "20g", + "--executor-cores", "2", + "--master", "local[2]", + "coverage_hoststack_rls2302.py" + ] + work_dir = "/local/csit/csit.infra.etl" + } + env { + AWS_ACCESS_KEY_ID = "${aws_access_key_id}" + AWS_SECRET_ACCESS_KEY = "${aws_secret_access_key}" + AWS_DEFAULT_REGION = "${aws_default_region}" + OUT_AWS_ACCESS_KEY_ID = "${out_aws_access_key_id}" + OUT_AWS_SECRET_ACCESS_KEY = "${out_aws_secret_access_key}" + OUT_AWS_DEFAULT_REGION = "${out_aws_default_region}" + ${ envs } + } + resources { + cpu = ${cpu} + memory = ${memory} + } + } + task "${job_name}-mrr" { + artifact { + source = "git::https://github.com/FDio/csit" + destination = "local/csit" + } + driver = "docker" + config { + image = "${image}" + command = "gluesparksubmit" + args = [ + "--driver-memory", "20g", + "--executor-memory", "20g", + "--executor-cores", "2", + "--master", "local[2]", + "coverage_mrr_rls2302.py" + ] + work_dir = "/local/csit/csit.infra.etl" + } + env { + AWS_ACCESS_KEY_ID = "${aws_access_key_id}" + AWS_SECRET_ACCESS_KEY = "${aws_secret_access_key}" + AWS_DEFAULT_REGION = "${aws_default_region}" + OUT_AWS_ACCESS_KEY_ID = "${out_aws_access_key_id}" + OUT_AWS_SECRET_ACCESS_KEY = "${out_aws_secret_access_key}" + OUT_AWS_DEFAULT_REGION = "${out_aws_default_region}" + ${ envs } + } + resources { + cpu = ${cpu} + memory = ${memory} + } + } + task "${job_name}-ndrpdr" { + artifact { + source = "git::https://github.com/FDio/csit" + destination = "local/csit" + } + driver = "docker" + config { + image = "${image}" + command = "gluesparksubmit" + args = [ + "--driver-memory", "20g", + "--executor-memory", "20g", + "--executor-cores", "2", + "--master", "local[2]", + "coverage_ndrpdr_rls2302.py" + ] + work_dir = "/local/csit/csit.infra.etl" + } + env { + AWS_ACCESS_KEY_ID = "${aws_access_key_id}" + AWS_SECRET_ACCESS_KEY = "${aws_secret_access_key}" + AWS_DEFAULT_REGION = "${aws_default_region}" + OUT_AWS_ACCESS_KEY_ID = "${out_aws_access_key_id}" + OUT_AWS_SECRET_ACCESS_KEY = "${out_aws_secret_access_key}" + OUT_AWS_DEFAULT_REGION = "${out_aws_default_region}" + ${ envs } + } + resources { + cpu = ${cpu} + memory = ${memory} + } + } + task "${job_name}-reconf" { + artifact { + source = "git::https://github.com/FDio/csit" + destination = "local/csit" + } + driver = "docker" + config { + image = "${image}" + command = "gluesparksubmit" + args = [ + "--driver-memory", "20g", + "--executor-memory", "20g", + "--executor-cores", "2", + "--master", "local[2]", + "coverage_reconf_rls2302.py" + ] + work_dir = "/local/csit/csit.infra.etl" + } + env { + AWS_ACCESS_KEY_ID = "${aws_access_key_id}" + AWS_SECRET_ACCESS_KEY = "${aws_secret_access_key}" + AWS_DEFAULT_REGION = "${aws_default_region}" + OUT_AWS_ACCESS_KEY_ID = "${out_aws_access_key_id}" + OUT_AWS_SECRET_ACCESS_KEY = "${out_aws_secret_access_key}" + OUT_AWS_DEFAULT_REGION = "${out_aws_default_region}" + ${ envs } + } + resources { + cpu = ${cpu} + memory = ${memory} + } + } + task "${job_name}-soak" { + artifact { + source = "git::https://github.com/FDio/csit" + destination = "local/csit" + } + driver = "docker" + config { + image = "${image}" + command = "gluesparksubmit" + args = [ + "--driver-memory", "20g", + "--executor-memory", "20g", + "--executor-cores", "2", + "--master", "local[2]", + "coverage_soak_rls2302.py" + ] + work_dir = "/local/csit/csit.infra.etl" + } + env { + AWS_ACCESS_KEY_ID = "${aws_access_key_id}" + AWS_SECRET_ACCESS_KEY = "${aws_secret_access_key}" + AWS_DEFAULT_REGION = "${aws_default_region}" + OUT_AWS_ACCESS_KEY_ID = "${out_aws_access_key_id}" + OUT_AWS_SECRET_ACCESS_KEY = "${out_aws_secret_access_key}" + OUT_AWS_DEFAULT_REGION = "${out_aws_default_region}" + ${ envs } + } + resources { + cpu = ${cpu} + memory = ${memory} + } + } + } +}
\ No newline at end of file diff --git a/fdio.infra.terraform/terraform-nomad-pyspark-etl/conf/nomad/etl-iterative-rls2302.hcl.tftpl b/fdio.infra.terraform/terraform-nomad-pyspark-etl/conf/nomad/etl-iterative-rls2302.hcl.tftpl new file mode 100644 index 0000000000..3d4e45b06f --- /dev/null +++ b/fdio.infra.terraform/terraform-nomad-pyspark-etl/conf/nomad/etl-iterative-rls2302.hcl.tftpl @@ -0,0 +1,183 @@ +job "${job_name}" { + datacenters = "${datacenters}" + type = "${type}" + periodic { + cron = "${cron}" + prohibit_overlap = "${prohibit_overlap}" + time_zone = "${time_zone}" + } + group "${job_name}" { + restart { + mode = "fail" + } + constraint { + attribute = "$${attr.cpu.arch}" + operator = "!=" + value = "arm64" + } + constraint { + attribute = "$${node.class}" + value = "builder" + } + task "${job_name}-hoststack" { + artifact { + source = "git::https://github.com/FDio/csit" + destination = "local/csit" + } + driver = "docker" + config { + image = "${image}" + command = "gluesparksubmit" + args = [ + "--driver-memory", "20g", + "--executor-memory", "20g", + "--executor-cores", "2", + "--master", "local[2]", + "iterative_hoststack_rls2302.py" + ] + work_dir = "/local/csit/csit.infra.etl" + } + env { + AWS_ACCESS_KEY_ID = "${aws_access_key_id}" + AWS_SECRET_ACCESS_KEY = "${aws_secret_access_key}" + AWS_DEFAULT_REGION = "${aws_default_region}" + OUT_AWS_ACCESS_KEY_ID = "${out_aws_access_key_id}" + OUT_AWS_SECRET_ACCESS_KEY = "${out_aws_secret_access_key}" + OUT_AWS_DEFAULT_REGION = "${out_aws_default_region}" + ${ envs } + } + resources { + cpu = ${cpu} + memory = ${memory} + } + } + task "${job_name}-mrr" { + artifact { + source = "git::https://github.com/FDio/csit" + destination = "local/csit" + } + driver = "docker" + config { + image = "${image}" + command = "gluesparksubmit" + args = [ + "--driver-memory", "20g", + "--executor-memory", "20g", + "--executor-cores", "2", + "--master", "local[2]", + "iterative_mrr_rls2302.py" + ] + work_dir = "/local/csit/csit.infra.etl" + } + env { + AWS_ACCESS_KEY_ID = "${aws_access_key_id}" + AWS_SECRET_ACCESS_KEY = "${aws_secret_access_key}" + AWS_DEFAULT_REGION = "${aws_default_region}" + OUT_AWS_ACCESS_KEY_ID = "${out_aws_access_key_id}" + OUT_AWS_SECRET_ACCESS_KEY = "${out_aws_secret_access_key}" + OUT_AWS_DEFAULT_REGION = "${out_aws_default_region}" + ${ envs } + } + resources { + cpu = ${cpu} + memory = ${memory} + } + } + task "${job_name}-ndrpdr" { + artifact { + source = "git::https://github.com/FDio/csit" + destination = "local/csit" + } + driver = "docker" + config { + image = "${image}" + command = "gluesparksubmit" + args = [ + "--driver-memory", "20g", + "--executor-memory", "20g", + "--executor-cores", "2", + "--master", "local[2]", + "iterative_ndrpdr_rls2302.py" + ] + work_dir = "/local/csit/csit.infra.etl" + } + env { + AWS_ACCESS_KEY_ID = "${aws_access_key_id}" + AWS_SECRET_ACCESS_KEY = "${aws_secret_access_key}" + AWS_DEFAULT_REGION = "${aws_default_region}" + OUT_AWS_ACCESS_KEY_ID = "${out_aws_access_key_id}" + OUT_AWS_SECRET_ACCESS_KEY = "${out_aws_secret_access_key}" + OUT_AWS_DEFAULT_REGION = "${out_aws_default_region}" + ${ envs } + } + resources { + cpu = ${cpu} + memory = ${memory} + } + } + task "${job_name}-reconf" { + artifact { + source = "git::https://github.com/FDio/csit" + destination = "local/csit" + } + driver = "docker" + config { + image = "${image}" + command = "gluesparksubmit" + args = [ + "--driver-memory", "20g", + "--executor-memory", "20g", + "--executor-cores", "2", + "--master", "local[2]", + "iterative_reconf_rls2302.py" + ] + work_dir = "/local/csit/csit.infra.etl" + } + env { + AWS_ACCESS_KEY_ID = "${aws_access_key_id}" + AWS_SECRET_ACCESS_KEY = "${aws_secret_access_key}" + AWS_DEFAULT_REGION = "${aws_default_region}" + OUT_AWS_ACCESS_KEY_ID = "${out_aws_access_key_id}" + OUT_AWS_SECRET_ACCESS_KEY = "${out_aws_secret_access_key}" + OUT_AWS_DEFAULT_REGION = "${out_aws_default_region}" + ${ envs } + } + resources { + cpu = ${cpu} + memory = ${memory} + } + } + task "${job_name}-soak" { + artifact { + source = "git::https://github.com/FDio/csit" + destination = "local/csit" + } + driver = "docker" + config { + image = "${image}" + command = "gluesparksubmit" + args = [ + "--driver-memory", "20g", + "--executor-memory", "20g", + "--executor-cores", "2", + "--master", "local[2]", + "iterative_soak_rls2302.py" + ] + work_dir = "/local/csit/csit.infra.etl" + } + env { + AWS_ACCESS_KEY_ID = "${aws_access_key_id}" + AWS_SECRET_ACCESS_KEY = "${aws_secret_access_key}" + AWS_DEFAULT_REGION = "${aws_default_region}" + OUT_AWS_ACCESS_KEY_ID = "${out_aws_access_key_id}" + OUT_AWS_SECRET_ACCESS_KEY = "${out_aws_secret_access_key}" + OUT_AWS_DEFAULT_REGION = "${out_aws_default_region}" + ${ envs } + } + resources { + cpu = ${cpu} + memory = ${memory} + } + } + } +} diff --git a/fdio.infra.terraform/terraform-nomad-pyspark-etl/conf/nomad/etl-stats.hcl.tftpl b/fdio.infra.terraform/terraform-nomad-pyspark-etl/conf/nomad/etl-stats.hcl.tftpl new file mode 100644 index 0000000000..86ca584de7 --- /dev/null +++ b/fdio.infra.terraform/terraform-nomad-pyspark-etl/conf/nomad/etl-stats.hcl.tftpl @@ -0,0 +1,53 @@ +job "${job_name}" { + datacenters = "${datacenters}" + type = "${type}" + periodic { + cron = "${cron}" + prohibit_overlap = "${prohibit_overlap}" + time_zone = "${time_zone}" + } + group "${job_name}" { + restart { + mode = "fail" + } + constraint { + attribute = "$${attr.cpu.arch}" + operator = "!=" + value = "arm64" + } + constraint { + attribute = "$${node.class}" + value = "builder" + } + task "${job_name}" { + artifact { + source = "git::https://github.com/FDio/csit" + destination = "local/csit" + } + driver = "docker" + config { + image = "${image}" + command = "gluesparksubmit" + args = [ + "--driver-memory", "10g", + "--executor-memory", "10g", + "stats.py" + ] + work_dir = "/local/csit/csit.infra.etl" + } + env { + AWS_ACCESS_KEY_ID = "${aws_access_key_id}" + AWS_SECRET_ACCESS_KEY = "${aws_secret_access_key}" + AWS_DEFAULT_REGION = "${aws_default_region}" + OUT_AWS_ACCESS_KEY_ID = "${out_aws_access_key_id}" + OUT_AWS_SECRET_ACCESS_KEY = "${out_aws_secret_access_key}" + OUT_AWS_DEFAULT_REGION = "${out_aws_default_region}" + ${ envs } + } + resources { + cpu = ${cpu} + memory = ${memory} + } + } + } +} diff --git a/fdio.infra.terraform/terraform-nomad-pyspark-etl/conf/nomad/etl-trending-hoststack.hcl.tftpl b/fdio.infra.terraform/terraform-nomad-pyspark-etl/conf/nomad/etl-trending-hoststack.hcl.tftpl new file mode 100644 index 0000000000..24aa4095d2 --- /dev/null +++ b/fdio.infra.terraform/terraform-nomad-pyspark-etl/conf/nomad/etl-trending-hoststack.hcl.tftpl @@ -0,0 +1,53 @@ +job "${job_name}" { + datacenters = "${datacenters}" + type = "${type}" + periodic { + cron = "${cron}" + prohibit_overlap = "${prohibit_overlap}" + time_zone = "${time_zone}" + } + group "${job_name}" { + restart { + mode = "fail" + } + constraint { + attribute = "$${attr.cpu.arch}" + operator = "!=" + value = "arm64" + } + constraint { + attribute = "$${node.class}" + value = "builder" + } + task "${job_name}" { + artifact { + source = "git::https://github.com/FDio/csit" + destination = "local/csit" + } + driver = "docker" + config { + image = "${image}" + command = "gluesparksubmit" + args = [ + "--driver-memory", "30g", + "--executor-memory", "30g", + "trending_hoststack.py" + ] + work_dir = "/local/csit/csit.infra.etl" + } + env { + AWS_ACCESS_KEY_ID = "${aws_access_key_id}" + AWS_SECRET_ACCESS_KEY = "${aws_secret_access_key}" + AWS_DEFAULT_REGION = "${aws_default_region}" + OUT_AWS_ACCESS_KEY_ID = "${out_aws_access_key_id}" + OUT_AWS_SECRET_ACCESS_KEY = "${out_aws_secret_access_key}" + OUT_AWS_DEFAULT_REGION = "${out_aws_default_region}" + ${ envs } + } + resources { + cpu = ${cpu} + memory = ${memory} + } + } + } +}
\ No newline at end of file diff --git a/fdio.infra.terraform/terraform-nomad-pyspark-etl/conf/nomad/etl-trending-mrr.hcl.tftpl b/fdio.infra.terraform/terraform-nomad-pyspark-etl/conf/nomad/etl-trending-mrr.hcl.tftpl new file mode 100644 index 0000000000..47d6149eed --- /dev/null +++ b/fdio.infra.terraform/terraform-nomad-pyspark-etl/conf/nomad/etl-trending-mrr.hcl.tftpl @@ -0,0 +1,53 @@ +job "${job_name}" { + datacenters = "${datacenters}" + type = "${type}" + periodic { + cron = "${cron}" + prohibit_overlap = "${prohibit_overlap}" + time_zone = "${time_zone}" + } + group "${job_name}" { + restart { + mode = "fail" + } + constraint { + attribute = "$${attr.cpu.arch}" + operator = "!=" + value = "arm64" + } + constraint { + attribute = "$${node.class}" + value = "builder" + } + task "${job_name}" { + artifact { + source = "git::https://github.com/FDio/csit" + destination = "local/csit" + } + driver = "docker" + config { + image = "${image}" + command = "gluesparksubmit" + args = [ + "--driver-memory", "30g", + "--executor-memory", "30g", + "trending_mrr.py" + ] + work_dir = "/local/csit/csit.infra.etl" + } + env { + AWS_ACCESS_KEY_ID = "${aws_access_key_id}" + AWS_SECRET_ACCESS_KEY = "${aws_secret_access_key}" + AWS_DEFAULT_REGION = "${aws_default_region}" + OUT_AWS_ACCESS_KEY_ID = "${out_aws_access_key_id}" + OUT_AWS_SECRET_ACCESS_KEY = "${out_aws_secret_access_key}" + OUT_AWS_DEFAULT_REGION = "${out_aws_default_region}" + ${ envs } + } + resources { + cpu = ${cpu} + memory = ${memory} + } + } + } +}
\ No newline at end of file diff --git a/fdio.infra.terraform/terraform-nomad-pyspark-etl/conf/nomad/etl-trending-ndrpdr.hcl.tftpl b/fdio.infra.terraform/terraform-nomad-pyspark-etl/conf/nomad/etl-trending-ndrpdr.hcl.tftpl new file mode 100644 index 0000000000..797de65944 --- /dev/null +++ b/fdio.infra.terraform/terraform-nomad-pyspark-etl/conf/nomad/etl-trending-ndrpdr.hcl.tftpl @@ -0,0 +1,53 @@ +job "${job_name}" { + datacenters = "${datacenters}" + type = "${type}" + periodic { + cron = "${cron}" + prohibit_overlap = "${prohibit_overlap}" + time_zone = "${time_zone}" + } + group "${job_name}" { + restart { + mode = "fail" + } + constraint { + attribute = "$${attr.cpu.arch}" + operator = "!=" + value = "arm64" + } + constraint { + attribute = "$${node.class}" + value = "builder" + } + task "${job_name}" { + artifact { + source = "git::https://github.com/FDio/csit" + destination = "local/csit" + } + driver = "docker" + config { + image = "${image}" + command = "gluesparksubmit" + args = [ + "--driver-memory", "30g", + "--executor-memory", "30g", + "trending_ndrpdr.py" + ] + work_dir = "/local/csit/csit.infra.etl" + } + env { + AWS_ACCESS_KEY_ID = "${aws_access_key_id}" + AWS_SECRET_ACCESS_KEY = "${aws_secret_access_key}" + AWS_DEFAULT_REGION = "${aws_default_region}" + OUT_AWS_ACCESS_KEY_ID = "${out_aws_access_key_id}" + OUT_AWS_SECRET_ACCESS_KEY = "${out_aws_secret_access_key}" + OUT_AWS_DEFAULT_REGION = "${out_aws_default_region}" + ${ envs } + } + resources { + cpu = ${cpu} + memory = ${memory} + } + } + } +}
\ No newline at end of file diff --git a/fdio.infra.terraform/terraform-nomad-pyspark-etl/conf/nomad/etl.hcl.tftpl b/fdio.infra.terraform/terraform-nomad-pyspark-etl/conf/nomad/etl.hcl.tftpl deleted file mode 100644 index b5b43e5052..0000000000 --- a/fdio.infra.terraform/terraform-nomad-pyspark-etl/conf/nomad/etl.hcl.tftpl +++ /dev/null @@ -1,597 +0,0 @@ -job "${job_name}" { - datacenters = "${datacenters}" - type = "${type}" - periodic { - cron = "${cron}" - prohibit_overlap = "${prohibit_overlap}" - time_zone = "${time_zone}" - } - group "${job_name}-trending" { - restart { - mode = "fail" - } - constraint { - attribute = "$${attr.cpu.arch}" - operator = "!=" - value = "arm64" - } - constraint { - attribute = "$${node.class}" - value = "builder" - } - task "${job_name}-trending-mrr" { - artifact { - source = "git::https://github.com/FDio/csit" - destination = "local/csit" - } - driver = "docker" - config { - image = "${image}" - command = "gluesparksubmit" - args = [ - "--driver-memory", "30g", - "--executor-memory", "30g", - "trending_mrr.py" - ] - work_dir = "/local/csit/csit.infra.etl" - } - env { - AWS_ACCESS_KEY_ID = "${aws_access_key_id}" - AWS_SECRET_ACCESS_KEY = "${aws_secret_access_key}" - AWS_DEFAULT_REGION = "${aws_default_region}" - OUT_AWS_ACCESS_KEY_ID = "${out_aws_access_key_id}" - OUT_AWS_SECRET_ACCESS_KEY = "${out_aws_secret_access_key}" - OUT_AWS_DEFAULT_REGION = "${out_aws_default_region}" - ${ envs } - } - resources { - cpu = ${cpu} - memory = ${memory} - } - } - task "${job_name}-trending-ndrpdr" { - artifact { - source = "git::https://github.com/FDio/csit" - destination = "local/csit" - } - driver = "docker" - config { - image = "${image}" - command = "gluesparksubmit" - args = [ - "--driver-memory", "30g", - "--executor-memory", "30g", - "trending_ndrpdr.py" - ] - work_dir = "/local/csit/csit.infra.etl" - } - env { - AWS_ACCESS_KEY_ID = "${aws_access_key_id}" - AWS_SECRET_ACCESS_KEY = "${aws_secret_access_key}" - AWS_DEFAULT_REGION = "${aws_default_region}" - OUT_AWS_ACCESS_KEY_ID = "${out_aws_access_key_id}" - OUT_AWS_SECRET_ACCESS_KEY = "${out_aws_secret_access_key}" - OUT_AWS_DEFAULT_REGION = "${out_aws_default_region}" - ${ envs } - } - resources { - cpu = ${cpu} - memory = ${memory} - } - } - task "${job_name}-trending-soak" { - artifact { - source = "git::https://github.com/FDio/csit" - destination = "local/csit" - } - driver = "docker" - config { - image = "${image}" - command = "gluesparksubmit" - args = [ - "--driver-memory", "30g", - "--executor-memory", "30g", - "trending_soak.py" - ] - work_dir = "/local/csit/csit.infra.etl" - } - env { - AWS_ACCESS_KEY_ID = "${aws_access_key_id}" - AWS_SECRET_ACCESS_KEY = "${aws_secret_access_key}" - AWS_DEFAULT_REGION = "${aws_default_region}" - OUT_AWS_ACCESS_KEY_ID = "${out_aws_access_key_id}" - OUT_AWS_SECRET_ACCESS_KEY = "${out_aws_secret_access_key}" - OUT_AWS_DEFAULT_REGION = "${out_aws_default_region}" - ${ envs } - } - resources { - cpu = ${cpu} - memory = ${memory} - } - } - task "${job_name}-trending-reconf" { - artifact { - source = "git::https://github.com/FDio/csit" - destination = "local/csit" - } - driver = "docker" - config { - image = "${image}" - command = "gluesparksubmit" - args = [ - "--driver-memory", "30g", - "--executor-memory", "30g", - "trending_reconf.py" - ] - work_dir = "/local/csit/csit.infra.etl" - } - env { - AWS_ACCESS_KEY_ID = "${aws_access_key_id}" - AWS_SECRET_ACCESS_KEY = "${aws_secret_access_key}" - AWS_DEFAULT_REGION = "${aws_default_region}" - OUT_AWS_ACCESS_KEY_ID = "${out_aws_access_key_id}" - OUT_AWS_SECRET_ACCESS_KEY = "${out_aws_secret_access_key}" - OUT_AWS_DEFAULT_REGION = "${out_aws_default_region}" - ${ envs } - } - resources { - cpu = ${cpu} - memory = ${memory} - } - } - task "${job_name}-trending-hoststack" { - artifact { - source = "git::https://github.com/FDio/csit" - destination = "local/csit" - } - driver = "docker" - config { - image = "${image}" - command = "gluesparksubmit" - args = [ - "--driver-memory", "30g", - "--executor-memory", "30g", - "trending_hoststack.py" - ] - work_dir = "/local/csit/csit.infra.etl" - } - env { - AWS_ACCESS_KEY_ID = "${aws_access_key_id}" - AWS_SECRET_ACCESS_KEY = "${aws_secret_access_key}" - AWS_DEFAULT_REGION = "${aws_default_region}" - OUT_AWS_ACCESS_KEY_ID = "${out_aws_access_key_id}" - OUT_AWS_SECRET_ACCESS_KEY = "${out_aws_secret_access_key}" - OUT_AWS_DEFAULT_REGION = "${out_aws_default_region}" - ${ envs } - } - resources { - cpu = ${cpu} - memory = ${memory} - } - } - } - group "${job_name}-stats" { - restart { - mode = "fail" - } - constraint { - attribute = "$${attr.cpu.arch}" - operator = "!=" - value = "arm64" - } - constraint { - attribute = "$${node.class}" - value = "builder" - } - task "${job_name}-stats" { - artifact { - source = "git::https://github.com/FDio/csit" - destination = "local/csit" - } - driver = "docker" - config { - image = "${image}" - command = "gluesparksubmit" - args = [ - "--driver-memory", "10g", - "--executor-memory", "10g", - "stats.py" - ] - work_dir = "/local/csit/csit.infra.etl" - } - env { - AWS_ACCESS_KEY_ID = "${aws_access_key_id}" - AWS_SECRET_ACCESS_KEY = "${aws_secret_access_key}" - AWS_DEFAULT_REGION = "${aws_default_region}" - OUT_AWS_ACCESS_KEY_ID = "${out_aws_access_key_id}" - OUT_AWS_SECRET_ACCESS_KEY = "${out_aws_secret_access_key}" - OUT_AWS_DEFAULT_REGION = "${out_aws_default_region}" - ${ envs } - } - resources { - cpu = ${cpu} - memory = ${memory} - } - } - } - group "${job_name}-coverage-rls2302" { - restart { - mode = "fail" - } - constraint { - attribute = "$${attr.cpu.arch}" - operator = "!=" - value = "arm64" - } - constraint { - attribute = "$${node.class}" - value = "builder" - } - task "${job_name}-coverage-device" { - artifact { - source = "git::https://github.com/FDio/csit" - destination = "local/csit" - } - driver = "docker" - config { - image = "${image}" - command = "gluesparksubmit" - args = [ - "--driver-memory", "20g", - "--executor-memory", "20g", - "--executor-cores", "2", - "--master", "local[2]", - "coverage_device_rls2302.py" - ] - work_dir = "/local/csit/csit.infra.etl" - } - env { - AWS_ACCESS_KEY_ID = "${aws_access_key_id}" - AWS_SECRET_ACCESS_KEY = "${aws_secret_access_key}" - AWS_DEFAULT_REGION = "${aws_default_region}" - OUT_AWS_ACCESS_KEY_ID = "${out_aws_access_key_id}" - OUT_AWS_SECRET_ACCESS_KEY = "${out_aws_secret_access_key}" - OUT_AWS_DEFAULT_REGION = "${out_aws_default_region}" - ${ envs } - } - resources { - cpu = ${cpu} - memory = ${memory} - } - } - task "${job_name}-coverage-hoststack" { - artifact { - source = "git::https://github.com/FDio/csit" - destination = "local/csit" - } - driver = "docker" - config { - image = "${image}" - command = "gluesparksubmit" - args = [ - "--driver-memory", "20g", - "--executor-memory", "20g", - "--executor-cores", "2", - "--master", "local[2]", - "coverage_hoststack_rls2302.py" - ] - work_dir = "/local/csit/csit.infra.etl" - } - env { - AWS_ACCESS_KEY_ID = "${aws_access_key_id}" - AWS_SECRET_ACCESS_KEY = "${aws_secret_access_key}" - AWS_DEFAULT_REGION = "${aws_default_region}" - OUT_AWS_ACCESS_KEY_ID = "${out_aws_access_key_id}" - OUT_AWS_SECRET_ACCESS_KEY = "${out_aws_secret_access_key}" - OUT_AWS_DEFAULT_REGION = "${out_aws_default_region}" - ${ envs } - } - resources { - cpu = ${cpu} - memory = ${memory} - } - } - task "${job_name}-coverage-mrr" { - artifact { - source = "git::https://github.com/FDio/csit" - destination = "local/csit" - } - driver = "docker" - config { - image = "${image}" - command = "gluesparksubmit" - args = [ - "--driver-memory", "20g", - "--executor-memory", "20g", - "--executor-cores", "2", - "--master", "local[2]", - "coverage_mrr_rls2302.py" - ] - work_dir = "/local/csit/csit.infra.etl" - } - env { - AWS_ACCESS_KEY_ID = "${aws_access_key_id}" - AWS_SECRET_ACCESS_KEY = "${aws_secret_access_key}" - AWS_DEFAULT_REGION = "${aws_default_region}" - OUT_AWS_ACCESS_KEY_ID = "${out_aws_access_key_id}" - OUT_AWS_SECRET_ACCESS_KEY = "${out_aws_secret_access_key}" - OUT_AWS_DEFAULT_REGION = "${out_aws_default_region}" - ${ envs } - } - resources { - cpu = ${cpu} - memory = ${memory} - } - } - task "${job_name}-coverage-ndrpdr" { - artifact { - source = "git::https://github.com/FDio/csit" - destination = "local/csit" - } - driver = "docker" - config { - image = "${image}" - command = "gluesparksubmit" - args = [ - "--driver-memory", "20g", - "--executor-memory", "20g", - "--executor-cores", "2", - "--master", "local[2]", - "coverage_ndrpdr_rls2302.py" - ] - work_dir = "/local/csit/csit.infra.etl" - } - env { - AWS_ACCESS_KEY_ID = "${aws_access_key_id}" - AWS_SECRET_ACCESS_KEY = "${aws_secret_access_key}" - AWS_DEFAULT_REGION = "${aws_default_region}" - OUT_AWS_ACCESS_KEY_ID = "${out_aws_access_key_id}" - OUT_AWS_SECRET_ACCESS_KEY = "${out_aws_secret_access_key}" - OUT_AWS_DEFAULT_REGION = "${out_aws_default_region}" - ${ envs } - } - resources { - cpu = ${cpu} - memory = ${memory} - } - } - task "${job_name}-coverage-reconf" { - artifact { - source = "git::https://github.com/FDio/csit" - destination = "local/csit" - } - driver = "docker" - config { - image = "${image}" - command = "gluesparksubmit" - args = [ - "--driver-memory", "20g", - "--executor-memory", "20g", - "--executor-cores", "2", - "--master", "local[2]", - "coverage_reconf_rls2302.py" - ] - work_dir = "/local/csit/csit.infra.etl" - } - env { - AWS_ACCESS_KEY_ID = "${aws_access_key_id}" - AWS_SECRET_ACCESS_KEY = "${aws_secret_access_key}" - AWS_DEFAULT_REGION = "${aws_default_region}" - OUT_AWS_ACCESS_KEY_ID = "${out_aws_access_key_id}" - OUT_AWS_SECRET_ACCESS_KEY = "${out_aws_secret_access_key}" - OUT_AWS_DEFAULT_REGION = "${out_aws_default_region}" - ${ envs } - } - resources { - cpu = ${cpu} - memory = ${memory} - } - } - task "${job_name}-coverage-soak" { - artifact { - source = "git::https://github.com/FDio/csit" - destination = "local/csit" - } - driver = "docker" - config { - image = "${image}" - command = "gluesparksubmit" - args = [ - "--driver-memory", "20g", - "--executor-memory", "20g", - "--executor-cores", "2", - "--master", "local[2]", - "coverage_soak_rls2302.py" - ] - work_dir = "/local/csit/csit.infra.etl" - } - env { - AWS_ACCESS_KEY_ID = "${aws_access_key_id}" - AWS_SECRET_ACCESS_KEY = "${aws_secret_access_key}" - AWS_DEFAULT_REGION = "${aws_default_region}" - OUT_AWS_ACCESS_KEY_ID = "${out_aws_access_key_id}" - OUT_AWS_SECRET_ACCESS_KEY = "${out_aws_secret_access_key}" - OUT_AWS_DEFAULT_REGION = "${out_aws_default_region}" - ${ envs } - } - resources { - cpu = ${cpu} - memory = ${memory} - } - } - } - group "${job_name}-iterative-rls2302" { - restart { - mode = "fail" - } - constraint { - attribute = "$${attr.cpu.arch}" - operator = "!=" - value = "arm64" - } - constraint { - attribute = "$${node.class}" - value = "builder" - } - task "${job_name}-iterative-hoststack" { - artifact { - source = "git::https://github.com/FDio/csit" - destination = "local/csit" - } - driver = "docker" - config { - image = "${image}" - command = "gluesparksubmit" - args = [ - "--driver-memory", "20g", - "--executor-memory", "20g", - "--executor-cores", "2", - "--master", "local[2]", - "iterative_hoststack_rls2302.py" - ] - work_dir = "/local/csit/csit.infra.etl" - } - env { - AWS_ACCESS_KEY_ID = "${aws_access_key_id}" - AWS_SECRET_ACCESS_KEY = "${aws_secret_access_key}" - AWS_DEFAULT_REGION = "${aws_default_region}" - OUT_AWS_ACCESS_KEY_ID = "${out_aws_access_key_id}" - OUT_AWS_SECRET_ACCESS_KEY = "${out_aws_secret_access_key}" - OUT_AWS_DEFAULT_REGION = "${out_aws_default_region}" - ${ envs } - } - resources { - cpu = ${cpu} - memory = ${memory} - } - } - task "${job_name}-iterative-mrr" { - artifact { - source = "git::https://github.com/FDio/csit" - destination = "local/csit" - } - driver = "docker" - config { - image = "${image}" - command = "gluesparksubmit" - args = [ - "--driver-memory", "20g", - "--executor-memory", "20g", - "--executor-cores", "2", - "--master", "local[2]", - "iterative_mrr_rls2302.py" - ] - work_dir = "/local/csit/csit.infra.etl" - } - env { - AWS_ACCESS_KEY_ID = "${aws_access_key_id}" - AWS_SECRET_ACCESS_KEY = "${aws_secret_access_key}" - AWS_DEFAULT_REGION = "${aws_default_region}" - OUT_AWS_ACCESS_KEY_ID = "${out_aws_access_key_id}" - OUT_AWS_SECRET_ACCESS_KEY = "${out_aws_secret_access_key}" - OUT_AWS_DEFAULT_REGION = "${out_aws_default_region}" - ${ envs } - } - resources { - cpu = ${cpu} - memory = ${memory} - } - } - task "${job_name}-iterative-ndrpdr" { - artifact { - source = "git::https://github.com/FDio/csit" - destination = "local/csit" - } - driver = "docker" - config { - image = "${image}" - command = "gluesparksubmit" - args = [ - "--driver-memory", "20g", - "--executor-memory", "20g", - "--executor-cores", "2", - "--master", "local[2]", - "iterative_ndrpdr_rls2302.py" - ] - work_dir = "/local/csit/csit.infra.etl" - } - env { - AWS_ACCESS_KEY_ID = "${aws_access_key_id}" - AWS_SECRET_ACCESS_KEY = "${aws_secret_access_key}" - AWS_DEFAULT_REGION = "${aws_default_region}" - OUT_AWS_ACCESS_KEY_ID = "${out_aws_access_key_id}" - OUT_AWS_SECRET_ACCESS_KEY = "${out_aws_secret_access_key}" - OUT_AWS_DEFAULT_REGION = "${out_aws_default_region}" - ${ envs } - } - resources { - cpu = ${cpu} - memory = ${memory} - } - } - task "${job_name}-iterative-reconf" { - artifact { - source = "git::https://github.com/FDio/csit" - destination = "local/csit" - } - driver = "docker" - config { - image = "${image}" - command = "gluesparksubmit" - args = [ - "--driver-memory", "20g", - "--executor-memory", "20g", - "--executor-cores", "2", - "--master", "local[2]", - "iterative_reconf_rls2302.py" - ] - work_dir = "/local/csit/csit.infra.etl" - } - env { - AWS_ACCESS_KEY_ID = "${aws_access_key_id}" - AWS_SECRET_ACCESS_KEY = "${aws_secret_access_key}" - AWS_DEFAULT_REGION = "${aws_default_region}" - OUT_AWS_ACCESS_KEY_ID = "${out_aws_access_key_id}" - OUT_AWS_SECRET_ACCESS_KEY = "${out_aws_secret_access_key}" - OUT_AWS_DEFAULT_REGION = "${out_aws_default_region}" - ${ envs } - } - resources { - cpu = ${cpu} - memory = ${memory} - } - } - task "${job_name}-iterative-soak" { - artifact { - source = "git::https://github.com/FDio/csit" - destination = "local/csit" - } - driver = "docker" - config { - image = "${image}" - command = "gluesparksubmit" - args = [ - "--driver-memory", "20g", - "--executor-memory", "20g", - "--executor-cores", "2", - "--master", "local[2]", - "iterative_soak_rls2302.py" - ] - work_dir = "/local/csit/csit.infra.etl" - } - env { - AWS_ACCESS_KEY_ID = "${aws_access_key_id}" - AWS_SECRET_ACCESS_KEY = "${aws_secret_access_key}" - AWS_DEFAULT_REGION = "${aws_default_region}" - OUT_AWS_ACCESS_KEY_ID = "${out_aws_access_key_id}" - OUT_AWS_SECRET_ACCESS_KEY = "${out_aws_secret_access_key}" - OUT_AWS_DEFAULT_REGION = "${out_aws_default_region}" - ${ envs } - } - resources { - cpu = ${cpu} - memory = ${memory} - } - } - } -} diff --git a/fdio.infra.terraform/terraform-nomad-pyspark-etl/fdio/main.tf b/fdio.infra.terraform/terraform-nomad-pyspark-etl/fdio/main.tf index 3d2026f0f9..f9422e7cef 100644 --- a/fdio.infra.terraform/terraform-nomad-pyspark-etl/fdio/main.tf +++ b/fdio.infra.terraform/terraform-nomad-pyspark-etl/fdio/main.tf @@ -6,7 +6,7 @@ data "vault_generic_secret" "fdio_docs" { path = "kv/secret/data/etl/fdio_docs" } -module "etl" { +module "etl-stats" { providers = { nomad = nomad.yul1 } @@ -20,4 +20,90 @@ module "etl" { out_aws_default_region = data.vault_generic_secret.fdio_docs.data["region"] cron = "@daily" datacenters = ["yul1"] + job_name = "etl-stats" } + +module "etl-trending-hoststack" { + providers = { + nomad = nomad.yul1 + } + source = "../" + + aws_access_key_id = data.vault_generic_secret.fdio_logs.data["access_key"] + aws_secret_access_key = data.vault_generic_secret.fdio_logs.data["secret_key"] + aws_default_region = data.vault_generic_secret.fdio_logs.data["region"] + out_aws_access_key_id = data.vault_generic_secret.fdio_docs.data["access_key"] + out_aws_secret_access_key = data.vault_generic_secret.fdio_docs.data["secret_key"] + out_aws_default_region = data.vault_generic_secret.fdio_docs.data["region"] + cron = "@daily" + datacenters = ["yul1"] + job_name = "etl-trending-hoststack" +} + +module "etl-trending-mrr" { + providers = { + nomad = nomad.yul1 + } + source = "../" + + aws_access_key_id = data.vault_generic_secret.fdio_logs.data["access_key"] + aws_secret_access_key = data.vault_generic_secret.fdio_logs.data["secret_key"] + aws_default_region = data.vault_generic_secret.fdio_logs.data["region"] + out_aws_access_key_id = data.vault_generic_secret.fdio_docs.data["access_key"] + out_aws_secret_access_key = data.vault_generic_secret.fdio_docs.data["secret_key"] + out_aws_default_region = data.vault_generic_secret.fdio_docs.data["region"] + cron = "@daily" + datacenters = ["yul1"] + job_name = "etl-trending-mrr" +} + +module "etl-trending-ndrpdr" { + providers = { + nomad = nomad.yul1 + } + source = "../" + + aws_access_key_id = data.vault_generic_secret.fdio_logs.data["access_key"] + aws_secret_access_key = data.vault_generic_secret.fdio_logs.data["secret_key"] + aws_default_region = data.vault_generic_secret.fdio_logs.data["region"] + out_aws_access_key_id = data.vault_generic_secret.fdio_docs.data["access_key"] + out_aws_secret_access_key = data.vault_generic_secret.fdio_docs.data["secret_key"] + out_aws_default_region = data.vault_generic_secret.fdio_docs.data["region"] + cron = "@daily" + datacenters = ["yul1"] + job_name = "etl-trending-ndrpdr" +} + +module "etl-iterative-rls2302" { + providers = { + nomad = nomad.yul1 + } + source = "../" + + aws_access_key_id = data.vault_generic_secret.fdio_logs.data["access_key"] + aws_secret_access_key = data.vault_generic_secret.fdio_logs.data["secret_key"] + aws_default_region = data.vault_generic_secret.fdio_logs.data["region"] + out_aws_access_key_id = data.vault_generic_secret.fdio_docs.data["access_key"] + out_aws_secret_access_key = data.vault_generic_secret.fdio_docs.data["secret_key"] + out_aws_default_region = data.vault_generic_secret.fdio_docs.data["region"] + cron = "@daily" + datacenters = ["yul1"] + job_name = "etl-iterative-rls2302" +} + +module "etl-coverage-rls2302" { + providers = { + nomad = nomad.yul1 + } + source = "../" + + aws_access_key_id = data.vault_generic_secret.fdio_logs.data["access_key"] + aws_secret_access_key = data.vault_generic_secret.fdio_logs.data["secret_key"] + aws_default_region = data.vault_generic_secret.fdio_logs.data["region"] + out_aws_access_key_id = data.vault_generic_secret.fdio_docs.data["access_key"] + out_aws_secret_access_key = data.vault_generic_secret.fdio_docs.data["secret_key"] + out_aws_default_region = data.vault_generic_secret.fdio_docs.data["region"] + cron = "@daily" + datacenters = ["yul1"] + job_name = "etl-coverage-rls2302" +}
\ No newline at end of file diff --git a/fdio.infra.terraform/terraform-nomad-pyspark-etl/main.tf b/fdio.infra.terraform/terraform-nomad-pyspark-etl/main.tf index c477da81a8..cd6a9a52ff 100644 --- a/fdio.infra.terraform/terraform-nomad-pyspark-etl/main.tf +++ b/fdio.infra.terraform/terraform-nomad-pyspark-etl/main.tf @@ -3,9 +3,9 @@ locals { envs = join("\n", concat([], var.envs)) } -resource "nomad_job" "nomad_job_etl" { +resource "nomad_job" "nomad_job" { jobspec = templatefile( - "${path.module}/conf/nomad/etl.hcl.tftpl", + "${path.module}/conf/nomad/${var.job_name}.hcl.tftpl", { aws_access_key_id = var.aws_access_key_id, aws_secret_access_key = var.aws_secret_access_key, |