Skip to content

feat(infra): export prometheus metrics to s3 #310

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

Draft
xDarksome wants to merge 21 commits into
base: main
Choose a base branch
from
+205 −109
Draft

feat(infra): export prometheus metrics to s3 #310

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
21 commits
Select commit Hold shift + click to select a range
26f96a3
feat: prom2parquet
xDarksome Jan 7, 2026
c701712
fix: secrets
xDarksome Jan 7, 2026
e494fc4
fix: flatten
xDarksome Jan 7, 2026
c2e1c0d
fix: merge
xDarksome Jan 7, 2026
4d202b8
fix: coalesce
xDarksome Jan 7, 2026
13bdcda
configure container
xDarksome Jan 7, 2026
f530bd0
fix: iam policy
xDarksome Jan 7, 2026
34f80bc
fix: iam policy
xDarksome Jan 7, 2026
ec380f6
fix: min memoryReservation
xDarksome Jan 7, 2026
de49eed
fix: use arm image
xDarksome Jan 8, 2026
1d3c775
fix: update prom2parquet image
xDarksome Jan 8, 2026
a9fc94e
enable prometheus remote write
xDarksome Jan 8, 2026
bbf4c48
fix: prom2parquet url
xDarksome Jan 8, 2026
22aac95
fix: set task role
xDarksome Jan 8, 2026
0137e2d
fix: create task role
xDarksome Jan 8, 2026
1b36840
fix: index
xDarksome Jan 8, 2026
245055e
fix: specify AWS_REGION
xDarksome Jan 8, 2026
785c87b
update metrics prefix
xDarksome Jan 9, 2026
fb1aa77
update s3 permissions
xDarksome Jan 9, 2026
a8e4096
fix: prefix
xDarksome Jan 9, 2026
9930762
change bucket
xDarksome Jan 9, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
206 changes: 127 additions & 79 deletions infra/modules/node-operator/main.tf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,6 +44,10 @@ variable "config" {
cpu_cores = number
memory = number
disk = number

prom2parquet_image = optional(string)
s3_bucket = optional(string)
s3_metrics_prefix = optional(string)
}))

grafana = optional(object({
Expand All @@ -68,6 +72,7 @@ variable "config" {

locals {
create_ec2_instance_connect_endpoint = coalesce(var.config.create_ec2_instance_connect_endpoint, true)
prometheus_s3_export = try(var.config.prometheus.prom2parquet_image, null) != null
}

data "aws_region" "current" {}
Expand Down Expand Up @@ -134,22 +139,25 @@ module "db" {

public_ip = false

ports = [
{ port = local.db_primary_rpc_server_port, protocol = "udp", internal = true },
{ port = local.db_secondary_rpc_server_port, protocol = "udp", internal = true },
{ port = local.db_metrics_server_port, protocol = "tcp", internal = true },
]

environment = {
PRIMARY_RPC_SERVER_PORT = tostring(local.db_primary_rpc_server_port)
SECONDARY_RPC_SERVER_PORT = tostring(local.db_secondary_rpc_server_port)
METRICS_SERVER_PORT = tostring(local.db_metrics_server_port)
ROCKSDB_DIR = "/data"
}
containers = [{
image = var.config.db.image
ports = [
{ port = local.db_primary_rpc_server_port, protocol = "udp", internal = true },
{ port = local.db_secondary_rpc_server_port, protocol = "udp", internal = true },
{ port = local.db_metrics_server_port, protocol = "tcp", internal = true },
]

environment = {
PRIMARY_RPC_SERVER_PORT = tostring(local.db_primary_rpc_server_port)
SECONDARY_RPC_SERVER_PORT = tostring(local.db_secondary_rpc_server_port)
METRICS_SERVER_PORT = tostring(local.db_metrics_server_port)
ROCKSDB_DIR = "/data"
}

secrets = {
SECRET_KEY = module.secret["ed25519_secret_key"]
}
secrets = {
SECRET_KEY = module.secret["ed25519_secret_key"]
}
}]
})
}

Expand All @@ -170,37 +178,41 @@ module "node" {

public_ip = true

ports = [
{ port = local.node_primary_rpc_server_port, protocol = "udp", internal = false },
{ port = local.node_secondary_rpc_server_port, protocol = "udp", internal = false },
{ port = local.node_metrics_server_port, protocol = "tcp", internal = true },
]

environment = {
PRIMARY_RPC_SERVER_PORT = tostring(local.node_primary_rpc_server_port)
SECONDARY_RPC_SERVER_PORT = tostring(local.node_secondary_rpc_server_port)
METRICS_SERVER_PORT = tostring(local.node_metrics_server_port)
DATABASE_RPC_SERVER_ADDRESS = module.db.private_ip
DATABASE_PEER_ID = local.peer_id
DATABASE_PRIMARY_RPC_SERVER_PORT = tostring(local.db_primary_rpc_server_port)
DATABASE_SECONDARY_RPC_SERVER_PORT = tostring(local.db_secondary_rpc_server_port)
SMART_CONTRACT_ADDRESS = local.smart_contract_address
}
containers = [{
image = var.config.nodes[count.index].image
ports = [
{ port = local.node_primary_rpc_server_port, protocol = "udp", internal = false },
{ port = local.node_secondary_rpc_server_port, protocol = "udp", internal = false },
{ port = local.node_metrics_server_port, protocol = "tcp", internal = true },
]

environment = {
PRIMARY_RPC_SERVER_PORT = tostring(local.node_primary_rpc_server_port)
SECONDARY_RPC_SERVER_PORT = tostring(local.node_secondary_rpc_server_port)
METRICS_SERVER_PORT = tostring(local.node_metrics_server_port)
DATABASE_RPC_SERVER_ADDRESS = module.db.private_ip
DATABASE_PEER_ID = local.peer_id
DATABASE_PRIMARY_RPC_SERVER_PORT = tostring(local.db_primary_rpc_server_port)
DATABASE_SECONDARY_RPC_SERVER_PORT = tostring(local.db_secondary_rpc_server_port)
SMART_CONTRACT_ADDRESS = local.smart_contract_address
}

secrets = merge({
SECRET_KEY = module.secret["ed25519_secret_key"]
SMART_CONTRACT_ENCRYPTION_KEY = module.secret["smart_contract_encryption_key"]
RPC_PROVIDER_URL = module.secret["rpc_provider_url"]
},
# configure pk only for the primary node
count.index != 0 ? {} : {
SMART_CONTRACT_SIGNER_PRIVATE_KEY = module.secret["ecdsa_private_key"]
})
secrets = merge({
SECRET_KEY = module.secret["ed25519_secret_key"]
SMART_CONTRACT_ENCRYPTION_KEY = module.secret["smart_contract_encryption_key"]
RPC_PROVIDER_URL = module.secret["rpc_provider_url"]
},
# configure pk only for the primary node
count.index != 0 ? {} : {
SMART_CONTRACT_SIGNER_PRIVATE_KEY = module.secret["ecdsa_private_key"]
})
}]
})
}

locals {
prometheus_port = 3000
prom2parquet_port = 4000
prometheus_domain_name = try("prometheus.${local.region_prefix}.${var.config.route53_zone.name}", null)
}

Expand All @@ -219,6 +231,10 @@ module "prometheus_config" {
targets = ["${module.node[0].private_ip}:${local.node_metrics_server_port}"]
}]
}]
remote_write = local.prometheus_s3_export ? [{
url = "http://localhost:${local.prom2parquet_port}/receive"
remote_timeout = "30s"
}] : []
})
}

Expand Down Expand Up @@ -250,27 +266,56 @@ module "prometheus" {

public_ip = false

ports = [
{ port = local.prometheus_port, protocol = "tcp", internal = true },
]

environment = {}
secrets = {
CONFIG = module.prometheus_config[0]
WEB_CONFIG = module.prometheus_web_config[0]
}

entry_point = ["/bin/sh", "-c"]
command = [<<-CMD
printenv CONFIG > /tmp/prometheus.yml && \
printenv WEB_CONFIG > /tmp/web.yml && \
exec /bin/prometheus \
--config.file=/tmp/prometheus.yml \
--web.config.file=/tmp/web.yml \
--web.listen-address=:${local.prometheus_port} \
--storage.tsdb.path=/data
CMD
]
containers = concat(
[{
name = "prometheus"
image = var.config.prometheus.image
ports = [
{ port = local.prometheus_port, protocol = "tcp", internal = true },
]

environment = {}
secrets = {
CONFIG = module.prometheus_config[0]
WEB_CONFIG = module.prometheus_web_config[0]
}

entry_point = ["/bin/sh", "-c"]
command = [<<-CMD
printenv CONFIG > /tmp/prometheus.yml && \
printenv WEB_CONFIG > /tmp/web.yml && \
exec /bin/prometheus \
--config.file=/tmp/prometheus.yml \
--web.config.file=/tmp/web.yml \
--web.listen-address=:${local.prometheus_port} \
--storage.tsdb.path=/data
CMD
]
}],
local.prometheus_s3_export ? [{
name = "prom2parquet"
image = var.config.prometheus.prom2parquet_image
essential = false
ports = [
{ port = local.prom2parquet_port, protocol = "tcp", internal = true },
]

environment = {
AWS_REGION = local.region
}
secrets = {}

entry_point = ["/prom2parquet"]
command = [
"--backend", "s3",
"--backend-root", "${var.config.prometheus.s3_bucket}",
"--prefix", "${var.config.prometheus.s3_metrics_prefix}/${local.region}",
"--server-port", tostring(local.prom2parquet_port),
]
}] : []
)

s3_buckets = var.config.prometheus.s3_bucket == null ? [] : [var.config.prometheus.s3_bucket]
})
}

Expand Down Expand Up @@ -318,27 +363,30 @@ module "grafana" {

public_ip = false

ports = [
{ port = local.grafana_port, protocol = "tcp", internal = true },
]
containers = [{
image = var.config.grafana.image
ports = [
{ port = local.grafana_port, protocol = "tcp", internal = true },
]

environment = {
GF_SERVER_HTTP_PORT = tostring(local.grafana_port)
GF_PATHS_DATA = "/data"
GF_SECURITY_ADMIN_USER = "admin"
}
environment = {
GF_SERVER_HTTP_PORT = tostring(local.grafana_port)
GF_PATHS_DATA = "/data"
GF_SECURITY_ADMIN_USER = "admin"
}

secrets = {
GF_SECURITY_ADMIN_PASSWORD = module.secret["grafana_admin_password"]
PROMETHEUS_DATASOURCE_CONFIG = module.grafana_prometheus_datasource_config[0]
}
secrets = {
GF_SECURITY_ADMIN_PASSWORD = module.secret["grafana_admin_password"]
PROMETHEUS_DATASOURCE_CONFIG = module.grafana_prometheus_datasource_config[0]
}

entry_point = ["/bin/sh", "-c"]
command = [<<-CMD
printenv PROMETHEUS_DATASOURCE_CONFIG > /etc/grafana/provisioning/datasources/prometheus.yaml && \
exec /run.sh
CMD
]
entry_point = ["/bin/sh", "-c"]
command = [<<-CMD
printenv PROMETHEUS_DATASOURCE_CONFIG > /etc/grafana/provisioning/datasources/prometheus.yaml && \
exec /run.sh
CMD
]
}]
})
}

Expand Down
Loading