NageshbansalandGitHub
272a49f57d
#### Fixes
- Render templated per-node macros (`shard`, `replica`) in ClickHouse
`config.yaml` so multi-shard/multi-replica clusters get unique Keeper
paths instead of collisions
- Use the first TelemetryStore TCP address (not comma-joined) for
`SIGNOZ_TELEMETRYSTORE_CLICKHOUSE_DSN` and ingester ClickHouse DSNs
#### Refactors
- `telemetrystore` molding now emits `config-{shard}-{replica}.yaml` per
node (mirrors `telemetrykeeper` per-replica pattern)
Related: https://github.com/SigNoz/platform-pod/issues/1332
646 lines
22 KiB
Plaintext
646 lines
22 KiB
Plaintext
apiVersion: v1alpha1
|
|
kind: Installation
|
|
metadata:
|
|
name: signoz
|
|
spec:
|
|
deployment:
|
|
flavor: helm
|
|
mode: kubernetes
|
|
ingester:
|
|
spec:
|
|
cluster:
|
|
replicas: 1
|
|
config:
|
|
data:
|
|
ingester.yaml: |
|
|
connectors:
|
|
signozmeter:
|
|
metrics_flush_interval: 1h
|
|
dimensions:
|
|
- name: service.name
|
|
- name: deployment.environment
|
|
- name: host.name
|
|
receivers:
|
|
otlp:
|
|
protocols:
|
|
grpc:
|
|
endpoint: "0.0.0.0:4317"
|
|
http:
|
|
endpoint: "0.0.0.0:4318"
|
|
processors:
|
|
batch:
|
|
send_batch_size: 50000
|
|
send_batch_max_size: 55000
|
|
timeout: 5s
|
|
batch/meter:
|
|
send_batch_size: 20000
|
|
send_batch_max_size: 25000
|
|
timeout: 5s
|
|
signozspanmetrics/delta:
|
|
metrics_exporter: signozclickhousemetrics
|
|
metrics_flush_interval: 60s
|
|
latency_histogram_buckets:
|
|
- 100us
|
|
- 1ms
|
|
- 2ms
|
|
- 6ms
|
|
- 10ms
|
|
- 50ms
|
|
- 100ms
|
|
- 250ms
|
|
- 500ms
|
|
- 1000ms
|
|
- 1400ms
|
|
- 2000ms
|
|
- 5s
|
|
- 10s
|
|
- 20s
|
|
- 40s
|
|
- 60s
|
|
dimensions_cache_size: 100000
|
|
aggregation_temporality: AGGREGATION_TEMPORALITY_DELTA
|
|
enable_exp_histogram: true
|
|
dimensions:
|
|
- name: service.namespace
|
|
default: default
|
|
- name: deployment.environment
|
|
default: default
|
|
- name: signoz.collector.id
|
|
- name: service.version
|
|
exporters:
|
|
clickhousetraces:
|
|
datasource: tcp://signoz-telemetrystore-clickhouse:9000/signoz_traces
|
|
low_cardinal_exception_grouping: ${env:LOW_CARDINAL_EXCEPTION_GROUPING}
|
|
use_new_schema: true
|
|
timeout: 45s
|
|
sending_queue:
|
|
enabled: false
|
|
signozclickhousemetrics:
|
|
dsn: tcp://signoz-telemetrystore-clickhouse:9000/signoz_metrics
|
|
timeout: 45s
|
|
sending_queue:
|
|
enabled: false
|
|
clickhouselogsexporter:
|
|
dsn: tcp://signoz-telemetrystore-clickhouse:9000/signoz_logs
|
|
use_new_schema: true
|
|
timeout: 45s
|
|
sending_queue:
|
|
enabled: false
|
|
signozclickhousemeter:
|
|
dsn: tcp://signoz-telemetrystore-clickhouse:9000/signoz_meter
|
|
timeout: 45s
|
|
sending_queue:
|
|
enabled: false
|
|
metadataexporter:
|
|
enabled: true
|
|
dsn: tcp://signoz-telemetrystore-clickhouse:9000/signoz_metadata
|
|
timeout: 45s
|
|
cache:
|
|
provider: in_memory
|
|
extensions:
|
|
signoz_health_check:
|
|
endpoint: "0.0.0.0:13133"
|
|
pprof:
|
|
endpoint: "0.0.0.0:1777"
|
|
service:
|
|
telemetry:
|
|
logs:
|
|
encoding: json
|
|
extensions:
|
|
- signoz_health_check
|
|
- pprof
|
|
pipelines:
|
|
traces:
|
|
receivers:
|
|
- otlp
|
|
processors:
|
|
- signozspanmetrics/delta
|
|
- batch
|
|
exporters:
|
|
- clickhousetraces
|
|
- signozmeter
|
|
- metadataexporter
|
|
metrics:
|
|
receivers:
|
|
- otlp
|
|
processors:
|
|
- batch
|
|
exporters:
|
|
- signozclickhousemetrics
|
|
- signozmeter
|
|
- metadataexporter
|
|
logs:
|
|
receivers:
|
|
- otlp
|
|
processors:
|
|
- batch
|
|
exporters:
|
|
- clickhouselogsexporter
|
|
- signozmeter
|
|
- metadataexporter
|
|
metrics/meter:
|
|
receivers:
|
|
- signozmeter
|
|
processors:
|
|
- batch/meter
|
|
exporters:
|
|
- signozclickhousemeter
|
|
opamp.yaml: |
|
|
server_endpoint: tcp://signoz:4320/v1/opamp
|
|
enabled: true
|
|
env:
|
|
SIGNOZ_OTEL_COLLECTOR_TIMEOUT: 10m
|
|
image: signoz/signoz-otel-collector:latest
|
|
version: latest
|
|
status:
|
|
addresses:
|
|
otlp: null
|
|
config:
|
|
data:
|
|
ingester.yaml: |
|
|
connectors:
|
|
signozmeter:
|
|
metrics_flush_interval: 1h
|
|
dimensions:
|
|
- name: service.name
|
|
- name: deployment.environment
|
|
- name: host.name
|
|
receivers:
|
|
otlp:
|
|
protocols:
|
|
grpc:
|
|
endpoint: "0.0.0.0:4317"
|
|
http:
|
|
endpoint: "0.0.0.0:4318"
|
|
processors:
|
|
batch:
|
|
send_batch_size: 50000
|
|
send_batch_max_size: 55000
|
|
timeout: 5s
|
|
batch/meter:
|
|
send_batch_size: 20000
|
|
send_batch_max_size: 25000
|
|
timeout: 5s
|
|
signozspanmetrics/delta:
|
|
metrics_exporter: signozclickhousemetrics
|
|
metrics_flush_interval: 60s
|
|
latency_histogram_buckets:
|
|
- 100us
|
|
- 1ms
|
|
- 2ms
|
|
- 6ms
|
|
- 10ms
|
|
- 50ms
|
|
- 100ms
|
|
- 250ms
|
|
- 500ms
|
|
- 1000ms
|
|
- 1400ms
|
|
- 2000ms
|
|
- 5s
|
|
- 10s
|
|
- 20s
|
|
- 40s
|
|
- 60s
|
|
dimensions_cache_size: 100000
|
|
aggregation_temporality: AGGREGATION_TEMPORALITY_DELTA
|
|
enable_exp_histogram: true
|
|
dimensions:
|
|
- name: service.namespace
|
|
default: default
|
|
- name: deployment.environment
|
|
default: default
|
|
- name: signoz.collector.id
|
|
- name: service.version
|
|
exporters:
|
|
clickhousetraces:
|
|
datasource: tcp://signoz-telemetrystore-clickhouse:9000/signoz_traces
|
|
low_cardinal_exception_grouping: ${env:LOW_CARDINAL_EXCEPTION_GROUPING}
|
|
use_new_schema: true
|
|
timeout: 45s
|
|
sending_queue:
|
|
enabled: false
|
|
signozclickhousemetrics:
|
|
dsn: tcp://signoz-telemetrystore-clickhouse:9000/signoz_metrics
|
|
timeout: 45s
|
|
sending_queue:
|
|
enabled: false
|
|
clickhouselogsexporter:
|
|
dsn: tcp://signoz-telemetrystore-clickhouse:9000/signoz_logs
|
|
use_new_schema: true
|
|
timeout: 45s
|
|
sending_queue:
|
|
enabled: false
|
|
signozclickhousemeter:
|
|
dsn: tcp://signoz-telemetrystore-clickhouse:9000/signoz_meter
|
|
timeout: 45s
|
|
sending_queue:
|
|
enabled: false
|
|
metadataexporter:
|
|
enabled: true
|
|
dsn: tcp://signoz-telemetrystore-clickhouse:9000/signoz_metadata
|
|
timeout: 45s
|
|
cache:
|
|
provider: in_memory
|
|
extensions:
|
|
signoz_health_check:
|
|
endpoint: "0.0.0.0:13133"
|
|
pprof:
|
|
endpoint: "0.0.0.0:1777"
|
|
service:
|
|
telemetry:
|
|
logs:
|
|
encoding: json
|
|
extensions:
|
|
- signoz_health_check
|
|
- pprof
|
|
pipelines:
|
|
traces:
|
|
receivers:
|
|
- otlp
|
|
processors:
|
|
- signozspanmetrics/delta
|
|
- batch
|
|
exporters:
|
|
- clickhousetraces
|
|
- signozmeter
|
|
- metadataexporter
|
|
metrics:
|
|
receivers:
|
|
- otlp
|
|
processors:
|
|
- batch
|
|
exporters:
|
|
- signozclickhousemetrics
|
|
- signozmeter
|
|
- metadataexporter
|
|
logs:
|
|
receivers:
|
|
- otlp
|
|
processors:
|
|
- batch
|
|
exporters:
|
|
- clickhouselogsexporter
|
|
- signozmeter
|
|
- metadataexporter
|
|
metrics/meter:
|
|
receivers:
|
|
- signozmeter
|
|
processors:
|
|
- batch/meter
|
|
exporters:
|
|
- signozclickhousemeter
|
|
opamp.yaml: |
|
|
server_endpoint: tcp://signoz:4320/v1/opamp
|
|
env:
|
|
SIGNOZ_OTEL_COLLECTOR_TIMEOUT: 10m
|
|
metastore:
|
|
kind: postgres
|
|
spec:
|
|
cluster:
|
|
replicas: 1
|
|
config: {}
|
|
enabled: true
|
|
env:
|
|
POSTGRES_DB: signoz
|
|
POSTGRES_PASSWORD: signoz
|
|
POSTGRES_USER: signoz
|
|
image: postgres:16
|
|
version: "16"
|
|
status:
|
|
addresses:
|
|
dsn:
|
|
- postgres://signoz-metastore-postgres:5432
|
|
config: {}
|
|
env:
|
|
POSTGRES_DB: signoz
|
|
POSTGRES_PASSWORD: signoz
|
|
POSTGRES_USER: signoz
|
|
signoz:
|
|
spec:
|
|
cluster:
|
|
replicas: 1
|
|
config: {}
|
|
enabled: true
|
|
env:
|
|
SIGNOZ_SQLSTORE_POSTGRES_DSN: postgres://signoz:signoz@signoz-metastore-postgres:5432/signoz?sslmode=disable
|
|
SIGNOZ_SQLSTORE_PROVIDER: postgres
|
|
SIGNOZ_TELEMETRYSTORE_CLICKHOUSE_DSN: tcp://signoz-telemetrystore-clickhouse:9000
|
|
SIGNOZ_TELEMETRYSTORE_PROVIDER: clickhouse
|
|
image: signoz/signoz:latest
|
|
version: latest
|
|
status:
|
|
addresses:
|
|
apiserver: null
|
|
opamp:
|
|
- tcp://signoz:4320
|
|
config: {}
|
|
env:
|
|
SIGNOZ_SQLSTORE_POSTGRES_DSN: postgres://signoz:signoz@signoz-metastore-postgres:5432/signoz?sslmode=disable
|
|
SIGNOZ_SQLSTORE_PROVIDER: postgres
|
|
SIGNOZ_TELEMETRYSTORE_CLICKHOUSE_DSN: tcp://signoz-telemetrystore-clickhouse:9000
|
|
SIGNOZ_TELEMETRYSTORE_PROVIDER: clickhouse
|
|
telemetrykeeper:
|
|
kind: clickhousekeeper
|
|
spec:
|
|
cluster:
|
|
replicas: 1
|
|
config:
|
|
data:
|
|
keeper-0.yaml: |
|
|
listen_host: 0.0.0.0
|
|
logger:
|
|
level: information
|
|
console: true
|
|
keeper_server:
|
|
four_letter_word_white_list: "*"
|
|
coordination_settings:
|
|
operation_timeout_ms: 10000
|
|
raft_logs_level: warning
|
|
session_timeout_ms: 30000
|
|
force_sync: false
|
|
snapshot_distance: 100000
|
|
snapshots_to_keep: 3
|
|
log_storage_path: /var/lib/clickhouse/coordination/log
|
|
raft_configuration:
|
|
server:
|
|
- hostname: signoz-telemetrykeeper-zookeeper-0
|
|
port: 9234
|
|
id: 0
|
|
server_id: 0
|
|
snapshot_storage_path: /var/lib/clickhouse/coordination/snapshots
|
|
tcp_port: 9181
|
|
enabled: true
|
|
image: clickhouse/clickhouse-keeper:25.5.6
|
|
version: 25.5.6
|
|
status:
|
|
addresses:
|
|
client:
|
|
- tcp://signoz-telemetrykeeper-zookeeper-0:9181
|
|
raft:
|
|
- tcp://signoz-telemetrykeeper-zookeeper-0:9234
|
|
config:
|
|
data:
|
|
keeper-0.yaml: |
|
|
listen_host: 0.0.0.0
|
|
logger:
|
|
level: information
|
|
console: true
|
|
keeper_server:
|
|
four_letter_word_white_list: "*"
|
|
coordination_settings:
|
|
operation_timeout_ms: 10000
|
|
raft_logs_level: warning
|
|
session_timeout_ms: 30000
|
|
force_sync: false
|
|
snapshot_distance: 100000
|
|
snapshots_to_keep: 3
|
|
log_storage_path: /var/lib/clickhouse/coordination/log
|
|
raft_configuration:
|
|
server:
|
|
- hostname: signoz-telemetrykeeper-zookeeper-0
|
|
port: 9234
|
|
id: 0
|
|
server_id: 0
|
|
snapshot_storage_path: /var/lib/clickhouse/coordination/snapshots
|
|
tcp_port: 9181
|
|
telemetrystore:
|
|
kind: clickhouse
|
|
spec:
|
|
cluster:
|
|
replicas: 0
|
|
shards: 1
|
|
config:
|
|
data:
|
|
config-0-0.yaml: |
|
|
path: /var/lib/clickhouse/
|
|
tmp_path: /var/lib/clickhouse/tmp/
|
|
user_files_path: /var/lib/clickhouse/user_files/
|
|
format_schema_path: /var/lib/clickhouse/format_schemas/
|
|
dictionaries_config: '*_dictionary.xml'
|
|
display_name: cluster
|
|
distributed_ddl:
|
|
path: /clickhouse/task_queue/ddl
|
|
http_port: 8123
|
|
interserver_http_port: 9009
|
|
listen_host: 0.0.0.0
|
|
logger:
|
|
console: 1
|
|
count: 10
|
|
formatting:
|
|
type: console
|
|
level: information
|
|
size: 1000M
|
|
macros:
|
|
replica: "00"
|
|
shard: "00"
|
|
profiles:
|
|
default:
|
|
allow_simdjson: 0
|
|
load_balancing: random
|
|
log_queries: 1
|
|
quotas:
|
|
default:
|
|
interval:
|
|
duration: 3600
|
|
errors: 0
|
|
execution_time: 0
|
|
queries: 0
|
|
read_rows: 0
|
|
result_rows: 0
|
|
user_directories:
|
|
users_xml:
|
|
path: users.xml
|
|
remote_servers:
|
|
cluster:
|
|
shard:
|
|
- replica:
|
|
- host: signoz-telemetrystore-clickhouse
|
|
port: 9000
|
|
zookeeper:
|
|
node:
|
|
- host: signoz-telemetrykeeper-zookeeper-0
|
|
port: 9181
|
|
query_log:
|
|
flush_interval_milliseconds: 30000
|
|
partition_by: toYYYYMM(event_date)
|
|
ttl: "event_date + INTERVAL 1 DAY DELETE"
|
|
query_thread_log:
|
|
ttl: "event_date + INTERVAL 1 DAY DELETE"
|
|
query_metric_log:
|
|
ttl: "event_date + INTERVAL 1 DAY DELETE"
|
|
query_views_log:
|
|
ttl: "event_date + INTERVAL 1 DAY DELETE"
|
|
part_log:
|
|
ttl: "event_date + INTERVAL 1 DAY DELETE"
|
|
metric_log:
|
|
flush_interval_milliseconds: 30000
|
|
ttl: "event_date + INTERVAL 1 DAY DELETE"
|
|
asynchronous_metric_log:
|
|
ttl: "event_date + INTERVAL 1 DAY DELETE"
|
|
trace_log:
|
|
flush_interval_milliseconds: 30000
|
|
ttl: "event_date + INTERVAL 1 DAY DELETE"
|
|
error_log:
|
|
ttl: "event_date + INTERVAL 1 DAY DELETE"
|
|
latency_log:
|
|
ttl: "event_date + INTERVAL 1 DAY DELETE"
|
|
processors_profile_log:
|
|
flush_interval_milliseconds: 30000
|
|
ttl: "event_date + INTERVAL 1 DAY DELETE"
|
|
session_log:
|
|
ttl: "event_date + INTERVAL 1 DAY DELETE"
|
|
text_log:
|
|
flush_interval_milliseconds: 30000
|
|
ttl: "event_date + INTERVAL 1 DAY DELETE"
|
|
zookeeper_log:
|
|
ttl: "event_date + INTERVAL 1 DAY DELETE"
|
|
tcp_port: 9000
|
|
user_defined_executable_functions_config: '*function.yaml'
|
|
user_scripts_path: /var/lib/clickhouse/user_scripts/
|
|
users:
|
|
default:
|
|
access_management: 1
|
|
named_collection_control: 1
|
|
networks:
|
|
ip: ::/0
|
|
password: ""
|
|
profile: default
|
|
quota: default
|
|
show_named_collection: 1
|
|
show_named_collection_secrets: 1
|
|
functions.yaml: |
|
|
functions:
|
|
argument:
|
|
- name: buckets
|
|
type: Array(Float64)
|
|
- name: counts
|
|
type: Array(Float64)
|
|
- name: quantile
|
|
type: Array(Float64)
|
|
command: ./histogramQuantile
|
|
format: CSV
|
|
name: histogramQuantile
|
|
return_type: Float64
|
|
type: executable
|
|
enabled: true
|
|
image: clickhouse/clickhouse-server:25.5.6
|
|
version: 25.5.6
|
|
status:
|
|
addresses:
|
|
tcp:
|
|
- tcp://signoz-telemetrystore-clickhouse:9000
|
|
config:
|
|
data:
|
|
config-0-0.yaml: |
|
|
path: /var/lib/clickhouse/
|
|
tmp_path: /var/lib/clickhouse/tmp/
|
|
user_files_path: /var/lib/clickhouse/user_files/
|
|
format_schema_path: /var/lib/clickhouse/format_schemas/
|
|
dictionaries_config: '*_dictionary.xml'
|
|
display_name: cluster
|
|
distributed_ddl:
|
|
path: /clickhouse/task_queue/ddl
|
|
http_port: 8123
|
|
interserver_http_port: 9009
|
|
listen_host: 0.0.0.0
|
|
logger:
|
|
console: 1
|
|
count: 10
|
|
formatting:
|
|
type: console
|
|
level: information
|
|
size: 1000M
|
|
macros:
|
|
replica: "00"
|
|
shard: "00"
|
|
profiles:
|
|
default:
|
|
allow_simdjson: 0
|
|
load_balancing: random
|
|
log_queries: 1
|
|
quotas:
|
|
default:
|
|
interval:
|
|
duration: 3600
|
|
errors: 0
|
|
execution_time: 0
|
|
queries: 0
|
|
read_rows: 0
|
|
result_rows: 0
|
|
user_directories:
|
|
users_xml:
|
|
path: users.xml
|
|
remote_servers:
|
|
cluster:
|
|
shard:
|
|
- replica:
|
|
- host: signoz-telemetrystore-clickhouse
|
|
port: 9000
|
|
zookeeper:
|
|
node:
|
|
- host: signoz-telemetrykeeper-zookeeper-0
|
|
port: 9181
|
|
query_log:
|
|
flush_interval_milliseconds: 30000
|
|
partition_by: toYYYYMM(event_date)
|
|
ttl: "event_date + INTERVAL 1 DAY DELETE"
|
|
query_thread_log:
|
|
ttl: "event_date + INTERVAL 1 DAY DELETE"
|
|
query_metric_log:
|
|
ttl: "event_date + INTERVAL 1 DAY DELETE"
|
|
query_views_log:
|
|
ttl: "event_date + INTERVAL 1 DAY DELETE"
|
|
part_log:
|
|
ttl: "event_date + INTERVAL 1 DAY DELETE"
|
|
metric_log:
|
|
flush_interval_milliseconds: 30000
|
|
ttl: "event_date + INTERVAL 1 DAY DELETE"
|
|
asynchronous_metric_log:
|
|
ttl: "event_date + INTERVAL 1 DAY DELETE"
|
|
trace_log:
|
|
flush_interval_milliseconds: 30000
|
|
ttl: "event_date + INTERVAL 1 DAY DELETE"
|
|
error_log:
|
|
ttl: "event_date + INTERVAL 1 DAY DELETE"
|
|
latency_log:
|
|
ttl: "event_date + INTERVAL 1 DAY DELETE"
|
|
processors_profile_log:
|
|
flush_interval_milliseconds: 30000
|
|
ttl: "event_date + INTERVAL 1 DAY DELETE"
|
|
session_log:
|
|
ttl: "event_date + INTERVAL 1 DAY DELETE"
|
|
text_log:
|
|
flush_interval_milliseconds: 30000
|
|
ttl: "event_date + INTERVAL 1 DAY DELETE"
|
|
zookeeper_log:
|
|
ttl: "event_date + INTERVAL 1 DAY DELETE"
|
|
tcp_port: 9000
|
|
user_defined_executable_functions_config: '*function.yaml'
|
|
user_scripts_path: /var/lib/clickhouse/user_scripts/
|
|
users:
|
|
default:
|
|
access_management: 1
|
|
named_collection_control: 1
|
|
networks:
|
|
ip: ::/0
|
|
password: ""
|
|
profile: default
|
|
quota: default
|
|
show_named_collection: 1
|
|
show_named_collection_secrets: 1
|
|
functions.yaml: |
|
|
functions:
|
|
argument:
|
|
- name: buckets
|
|
type: Array(Float64)
|
|
- name: counts
|
|
type: Array(Float64)
|
|
- name: quantile
|
|
type: Array(Float64)
|
|
command: ./histogramQuantile
|
|
format: CSV
|
|
name: histogramQuantile
|
|
return_type: Float64
|
|
type: executable
|