Compare commits

...

4 Commits

Author SHA1 Message Date
Nagesh Bansal
f605624538 chore: deprecates generator from deploy 2026-02-27 21:51:17 +05:30
Srikanth Chekuri
7605775a38 chore: remove support for non v5 version in rules (#10406) 2026-02-24 23:16:21 +05:30
Vinicius Lourenço
cb1a2a8a13 perf(bundle-size): lazy load pages to reduce main bundle size (#10230)
Some checks failed
build-staging / prepare (push) Has been cancelled
build-staging / js-build (push) Has been cancelled
build-staging / go-build (push) Has been cancelled
build-staging / staging (push) Has been cancelled
Release Drafter / update_release_draft (push) Has been cancelled
2026-02-24 10:41:40 +00:00
Nikhil Soni
1a5d37b25a fix: add missing filtering for ip address for scalar data (#10264)
* fix: add missing filtering for ip address for scalar data

In domain listing api for external api monitoring,
we have option to filter out the IP address but
it only handles timeseries and raw type data while
domain list handler returns scalar data.

* fix: switch to new derived attributes for ip filtering

---------

Co-authored-by: Nityananda Gohain <nityanandagohain@gmail.com>
2026-02-24 10:26:10 +00:00
15 changed files with 343 additions and 543 deletions

View File

@@ -1,38 +0,0 @@
version: "3"
x-common: &common
networks:
- signoz-net
extra_hosts:
- host.docker.internal:host-gateway
logging:
options:
max-size: 50m
max-file: "3"
deploy:
restart_policy:
condition: on-failure
services:
hotrod:
<<: *common
image: jaegertracing/example-hotrod:1.61.0
command: [ "all" ]
environment:
- OTEL_EXPORTER_OTLP_ENDPOINT=http://host.docker.internal:4318 #
load-hotrod:
<<: *common
image: "signoz/locust:1.2.3"
environment:
ATTACKED_HOST: http://hotrod:8080
LOCUST_MODE: standalone
NO_PROXY: standalone
TASK_DELAY_FROM: 5
TASK_DELAY_TO: 30
QUIET_MODE: "${QUIET_MODE:-false}"
LOCUST_OPTS: "--headless -u 10 -r 1"
volumes:
- ../../../common/locust-scripts:/locust
networks:
signoz-net:
name: signoz-net
external: true

View File

@@ -1,69 +0,0 @@
version: "3"
x-common: &common
networks:
- signoz-net
extra_hosts:
- host.docker.internal:host-gateway
logging:
options:
max-size: 50m
max-file: "3"
deploy:
mode: global
restart_policy:
condition: on-failure
services:
otel-agent:
<<: *common
image: otel/opentelemetry-collector-contrib:0.111.0
command:
- --config=/etc/otel-collector-config.yaml
volumes:
- ./otel-agent-config.yaml:/etc/otel-collector-config.yaml
- /:/hostfs:ro
environment:
- SIGNOZ_COLLECTOR_ENDPOINT=http://host.docker.internal:4317 # In case of external SigNoz or cloud, update the endpoint and access token
- OTEL_RESOURCE_ATTRIBUTES=host.name={{.Node.Hostname}},os.type={{.Node.Platform.OS}}
# - SIGNOZ_ACCESS_TOKEN="<your-access-token>"
# Before exposing the ports, make sure the ports are not used by other services
# ports:
# - "4317:4317"
# - "4318:4318"
otel-metrics:
<<: *common
image: otel/opentelemetry-collector-contrib:0.111.0
user: 0:0 # If you have security concerns, you can replace this with your `UID:GID` that has necessary permissions to docker.sock
command:
- --config=/etc/otel-collector-config.yaml
volumes:
- ./otel-metrics-config.yaml:/etc/otel-collector-config.yaml
- /var/run/docker.sock:/var/run/docker.sock
environment:
- SIGNOZ_COLLECTOR_ENDPOINT=http://host.docker.internal:4317 # In case of external SigNoz or cloud, update the endpoint and access token
- OTEL_RESOURCE_ATTRIBUTES=host.name={{.Node.Hostname}},os.type={{.Node.Platform.OS}}
# - SIGNOZ_ACCESS_TOKEN="<your-access-token>"
# Before exposing the ports, make sure the ports are not used by other services
# ports:
# - "4317:4317"
# - "4318:4318"
deploy:
mode: replicated
replicas: 1
placement:
constraints:
- node.role == manager
logspout:
<<: *common
image: "gliderlabs/logspout:v3.2.14"
command: syslog+tcp://otel-agent:2255
user: root
volumes:
- /etc/hostname:/etc/host_hostname:ro
- /var/run/docker.sock:/var/run/docker.sock
depends_on:
- otel-agent
networks:
signoz-net:
name: signoz-net
external: true

View File

@@ -1,102 +0,0 @@
receivers:
hostmetrics:
collection_interval: 30s
root_path: /hostfs
scrapers:
cpu: {}
load: {}
memory: {}
disk: {}
filesystem: {}
network: {}
otlp:
protocols:
grpc:
endpoint: 0.0.0.0:4317
http:
endpoint: 0.0.0.0:4318
prometheus:
config:
global:
scrape_interval: 60s
scrape_configs:
- job_name: otel-agent
static_configs:
- targets:
- localhost:8888
labels:
job_name: otel-agent
tcplog/docker:
listen_address: "0.0.0.0:2255"
operators:
- type: regex_parser
regex: '^<([0-9]+)>[0-9]+ (?P<timestamp>[0-9]{4}-[0-9]{2}-[0-9]{2}T[0-9]{2}:[0-9]{2}:[0-9]{2}(\.[0-9]+)?([zZ]|([\+-])([01]\d|2[0-3]):?([0-5]\d)?)?) (?P<container_id>\S+) (?P<container_name>\S+) [0-9]+ - -( (?P<body>.*))?'
timestamp:
parse_from: attributes.timestamp
layout: '%Y-%m-%dT%H:%M:%S.%LZ'
- type: move
from: attributes["body"]
to: body
- type: remove
field: attributes.timestamp
# please remove names from below if you want to collect logs from them
- type: filter
id: signoz_logs_filter
expr: 'attributes.container_name matches "^(signoz_(logspout|signoz|otel-collector|clickhouse|zookeeper))|(infra_(logspout|otel-agent|otel-metrics)).*"'
processors:
batch:
send_batch_size: 10000
send_batch_max_size: 11000
timeout: 10s
resourcedetection:
# Using OTEL_RESOURCE_ATTRIBUTES envvar, env detector adds custom labels.
detectors:
# - ec2
# - gcp
# - azure
- env
- system
timeout: 2s
extensions:
health_check:
endpoint: 0.0.0.0:13133
pprof:
endpoint: 0.0.0.0:1777
exporters:
otlp:
endpoint: ${env:SIGNOZ_COLLECTOR_ENDPOINT}
tls:
insecure: true
headers:
signoz-access-token: ${env:SIGNOZ_ACCESS_TOKEN}
# debug: {}
service:
telemetry:
logs:
encoding: json
metrics:
address: 0.0.0.0:8888
extensions:
- health_check
- pprof
pipelines:
traces:
receivers: [otlp]
processors: [resourcedetection, batch]
exporters: [otlp]
metrics:
receivers: [otlp]
processors: [resourcedetection, batch]
exporters: [otlp]
metrics/hostmetrics:
receivers: [hostmetrics]
processors: [resourcedetection, batch]
exporters: [otlp]
metrics/prometheus:
receivers: [prometheus]
processors: [resourcedetection, batch]
exporters: [otlp]
logs:
receivers: [otlp, tcplog/docker]
processors: [resourcedetection, batch]
exporters: [otlp]

View File

@@ -1,103 +0,0 @@
receivers:
prometheus:
config:
global:
scrape_interval: 60s
scrape_configs:
- job_name: otel-metrics
static_configs:
- targets:
- localhost:8888
labels:
job_name: otel-metrics
# For Docker daemon metrics to be scraped, it must be configured to expose
# Prometheus metrics, as documented here: https://docs.docker.com/config/daemon/prometheus/
# - job_name: docker-daemon
# dockerswarm_sd_configs:
# - host: unix:///var/run/docker.sock
# role: nodes
# relabel_configs:
# - source_labels: [__meta_dockerswarm_node_address]
# target_label: __address__
# replacement: $1:9323
- job_name: "dockerswarm"
dockerswarm_sd_configs:
- host: unix:///var/run/docker.sock
role: tasks
relabel_configs:
- action: keep
regex: running
source_labels:
- __meta_dockerswarm_task_desired_state
- action: keep
regex: true
source_labels:
- __meta_dockerswarm_service_label_signoz_io_scrape
- regex: ([^:]+)(?::\d+)?
replacement: $1
source_labels:
- __address__
target_label: swarm_container_ip
- separator: .
source_labels:
- __meta_dockerswarm_service_name
- __meta_dockerswarm_task_slot
- __meta_dockerswarm_task_id
target_label: swarm_container_name
- target_label: __address__
source_labels:
- swarm_container_ip
- __meta_dockerswarm_service_label_signoz_io_port
separator: ":"
- source_labels:
- __meta_dockerswarm_service_label_signoz_io_path
target_label: __metrics_path__
- source_labels:
- __meta_dockerswarm_service_label_com_docker_stack_namespace
target_label: namespace
- source_labels:
- __meta_dockerswarm_service_name
target_label: service_name
- source_labels:
- __meta_dockerswarm_task_id
target_label: service_instance_id
- source_labels:
- __meta_dockerswarm_node_hostname
target_label: host_name
processors:
batch:
send_batch_size: 10000
send_batch_max_size: 11000
timeout: 10s
resourcedetection:
detectors:
- env
- system
timeout: 2s
extensions:
health_check:
endpoint: 0.0.0.0:13133
pprof:
endpoint: 0.0.0.0:1777
exporters:
otlp:
endpoint: ${env:SIGNOZ_COLLECTOR_ENDPOINT}
tls:
insecure: true
headers:
signoz-access-token: ${env:SIGNOZ_ACCESS_TOKEN}
# debug: {}
service:
telemetry:
logs:
encoding: json
metrics:
address: 0.0.0.0:8888
extensions:
- health_check
- pprof
pipelines:
metrics:
receivers: [prometheus]
processors: [resourcedetection, batch]
exporters: [otlp]

View File

@@ -1,39 +0,0 @@
version: "3"
x-common: &common
networks:
- signoz-net
extra_hosts:
- host.docker.internal:host-gateway
logging:
options:
max-size: 50m
max-file: "3"
restart: unless-stopped
services:
hotrod:
<<: *common
image: jaegertracing/example-hotrod:1.61.0
container_name: hotrod
command: [ "all" ]
environment:
- OTEL_EXPORTER_OTLP_ENDPOINT=http://host.docker.internal:4318 # In case of external SigNoz or cloud, update the endpoint and access token
# - OTEL_OTLP_HEADERS=signoz-access-token=<your-access-token>
load-hotrod:
<<: *common
image: "signoz/locust:1.2.3"
container_name: load-hotrod
environment:
ATTACKED_HOST: http://hotrod:8080
LOCUST_MODE: standalone
NO_PROXY: standalone
TASK_DELAY_FROM: 5
TASK_DELAY_TO: 30
QUIET_MODE: "${QUIET_MODE:-false}"
LOCUST_OPTS: "--headless -u 10 -r 1"
volumes:
- ../../../common/locust-scripts:/locust
networks:
signoz-net:
name: signoz-net
external: true

View File

@@ -1,43 +0,0 @@
version: "3"
x-common: &common
networks:
- signoz-net
extra_hosts:
- host.docker.internal:host-gateway
logging:
options:
max-size: 50m
max-file: "3"
restart: unless-stopped
services:
otel-agent:
<<: *common
image: otel/opentelemetry-collector-contrib:0.111.0
command:
- --config=/etc/otel-collector-config.yaml
volumes:
- ./otel-collector-config.yaml:/etc/otel-collector-config.yaml
- /:/hostfs:ro
- /var/run/docker.sock:/var/run/docker.sock
environment:
- SIGNOZ_COLLECTOR_ENDPOINT=http://host.docker.internal:4317 # In case of external SigNoz or cloud, update the endpoint and access token
- OTEL_RESOURCE_ATTRIBUTES=host.name=signoz-host,os.type=linux # Replace signoz-host with the actual hostname
# - SIGNOZ_ACCESS_TOKEN="<your-access-token>"
# Before exposing the ports, make sure the ports are not used by other services
# ports:
# - "4317:4317"
# - "4318:4318"
logspout:
<<: *common
image: "gliderlabs/logspout:v3.2.14"
volumes:
- /etc/hostname:/etc/host_hostname:ro
- /var/run/docker.sock:/var/run/docker.sock
command: syslog+tcp://otel-agent:2255
depends_on:
- otel-agent
networks:
signoz-net:
name: signoz-net
external: true

View File

@@ -1,139 +0,0 @@
receivers:
hostmetrics:
collection_interval: 30s
root_path: /hostfs
scrapers:
cpu: {}
load: {}
memory: {}
disk: {}
filesystem: {}
network: {}
otlp:
protocols:
grpc:
endpoint: 0.0.0.0:4317
http:
endpoint: 0.0.0.0:4318
prometheus:
config:
global:
scrape_interval: 60s
scrape_configs:
- job_name: otel-collector
static_configs:
- targets:
- localhost:8888
labels:
job_name: otel-collector
# For Docker daemon metrics to be scraped, it must be configured to expose
# Prometheus metrics, as documented here: https://docs.docker.com/config/daemon/prometheus/
# - job_name: docker-daemon
# static_configs:
# - targets:
# - host.docker.internal:9323
# labels:
# job_name: docker-daemon
- job_name: docker-container
docker_sd_configs:
- host: unix:///var/run/docker.sock
relabel_configs:
- action: keep
regex: true
source_labels:
- __meta_docker_container_label_signoz_io_scrape
- regex: true
source_labels:
- __meta_docker_container_label_signoz_io_path
target_label: __metrics_path__
- regex: (.+)
source_labels:
- __meta_docker_container_label_signoz_io_path
target_label: __metrics_path__
- separator: ":"
source_labels:
- __meta_docker_network_ip
- __meta_docker_container_label_signoz_io_port
target_label: __address__
- regex: '/(.*)'
replacement: '$1'
source_labels:
- __meta_docker_container_name
target_label: container_name
- regex: __meta_docker_container_label_signoz_io_(.+)
action: labelmap
replacement: $1
tcplog/docker:
listen_address: "0.0.0.0:2255"
operators:
- type: regex_parser
regex: '^<([0-9]+)>[0-9]+ (?P<timestamp>[0-9]{4}-[0-9]{2}-[0-9]{2}T[0-9]{2}:[0-9]{2}:[0-9]{2}(\.[0-9]+)?([zZ]|([\+-])([01]\d|2[0-3]):?([0-5]\d)?)?) (?P<container_id>\S+) (?P<container_name>\S+) [0-9]+ - -( (?P<body>.*))?'
timestamp:
parse_from: attributes.timestamp
layout: '%Y-%m-%dT%H:%M:%S.%LZ'
- type: move
from: attributes["body"]
to: body
- type: remove
field: attributes.timestamp
# please remove names from below if you want to collect logs from them
- type: filter
id: signoz_logs_filter
expr: 'attributes.container_name matches "^signoz|(signoz-(|otel-collector|clickhouse|zookeeper))|(infra-(logspout|otel-agent)-.*)"'
processors:
batch:
send_batch_size: 10000
send_batch_max_size: 11000
timeout: 10s
resourcedetection:
# Using OTEL_RESOURCE_ATTRIBUTES envvar, env detector adds custom labels.
detectors:
# - ec2
# - gcp
# - azure
- env
- system
timeout: 2s
extensions:
health_check:
endpoint: 0.0.0.0:13133
pprof:
endpoint: 0.0.0.0:1777
exporters:
otlp:
endpoint: ${env:SIGNOZ_COLLECTOR_ENDPOINT}
tls:
insecure: true
headers:
signoz-access-token: ${env:SIGNOZ_ACCESS_TOKEN}
# debug: {}
service:
telemetry:
logs:
encoding: json
metrics:
address: 0.0.0.0:8888
extensions:
- health_check
- pprof
pipelines:
traces:
receivers: [otlp]
processors: [resourcedetection, batch]
exporters: [otlp]
metrics:
receivers: [otlp]
processors: [resourcedetection, batch]
exporters: [otlp]
metrics/hostmetrics:
receivers: [hostmetrics]
processors: [resourcedetection, batch]
exporters: [otlp]
metrics/prometheus:
receivers: [prometheus]
processors: [resourcedetection, batch]
exporters: [otlp]
logs:
receivers: [otlp, tcplog/docker]
processors: [resourcedetection, batch]
exporters: [otlp]

View File

@@ -308,3 +308,15 @@ export const PublicDashboardPage = Loadable(
/* webpackChunkName: "Public Dashboard Page" */ 'pages/PublicDashboard'
),
);
export const AlertTypeSelectionPage = Loadable(
() =>
import(
/* webpackChunkName: "Alert Type Selection Page" */ 'pages/AlertTypeSelection'
),
);
export const MeterExplorerPage = Loadable(
() =>
import(/* webpackChunkName: "Meter Explorer Page" */ 'pages/MeterExplorer'),
);

View File

@@ -1,12 +1,10 @@
import { RouteProps } from 'react-router-dom';
import ROUTES from 'constants/routes';
import AlertTypeSelectionPage from 'pages/AlertTypeSelection';
import MessagingQueues from 'pages/MessagingQueues';
import MeterExplorer from 'pages/MeterExplorer';
import {
AlertHistory,
AlertOverview,
AlertTypeSelectionPage,
AllAlertChannels,
AllErrors,
ApiMonitoring,
@@ -29,6 +27,8 @@ import {
LogsExplorer,
LogsIndexToFields,
LogsSaveViews,
MessagingQueuesMainPage,
MeterExplorerPage,
MetricsExplorer,
OldLogsExplorer,
Onboarding,
@@ -399,28 +399,28 @@ const routes: AppRoutes[] = [
{
path: ROUTES.MESSAGING_QUEUES_KAFKA,
exact: true,
component: MessagingQueues,
component: MessagingQueuesMainPage,
key: 'MESSAGING_QUEUES_KAFKA',
isPrivate: true,
},
{
path: ROUTES.MESSAGING_QUEUES_CELERY_TASK,
exact: true,
component: MessagingQueues,
component: MessagingQueuesMainPage,
key: 'MESSAGING_QUEUES_CELERY_TASK',
isPrivate: true,
},
{
path: ROUTES.MESSAGING_QUEUES_OVERVIEW,
exact: true,
component: MessagingQueues,
component: MessagingQueuesMainPage,
key: 'MESSAGING_QUEUES_OVERVIEW',
isPrivate: true,
},
{
path: ROUTES.MESSAGING_QUEUES_KAFKA_DETAIL,
exact: true,
component: MessagingQueues,
component: MessagingQueuesMainPage,
key: 'MESSAGING_QUEUES_KAFKA_DETAIL',
isPrivate: true,
},
@@ -463,21 +463,21 @@ const routes: AppRoutes[] = [
{
path: ROUTES.METER,
exact: true,
component: MeterExplorer,
component: MeterExplorerPage,
key: 'METER',
isPrivate: true,
},
{
path: ROUTES.METER_EXPLORER,
exact: true,
component: MeterExplorer,
component: MeterExplorerPage,
key: 'METER_EXPLORER',
isPrivate: true,
},
{
path: ROUTES.METER_EXPLORER_VIEWS,
exact: true,
component: MeterExplorer,
component: MeterExplorerPage,
key: 'METER_EXPLORER_VIEWS',
isPrivate: true,
},

View File

@@ -120,6 +120,8 @@ func FilterResponse(results []*qbtypes.QueryRangeResponse) []*qbtypes.QueryRange
}
}
resultData.Rows = filteredRows
case *qbtypes.ScalarData:
resultData.Data = filterScalarDataIPs(resultData.Columns, resultData.Data)
}
filteredData = append(filteredData, result)
@@ -145,6 +147,39 @@ func shouldIncludeSeries(series *qbtypes.TimeSeries) bool {
return true
}
func filterScalarDataIPs(columns []*qbtypes.ColumnDescriptor, data [][]any) [][]any {
// Find column indices for server address fields
serverColIndices := make([]int, 0)
for i, col := range columns {
if col.Name == derivedKeyHTTPHost {
serverColIndices = append(serverColIndices, i)
}
}
if len(serverColIndices) == 0 {
return data
}
filtered := make([][]any, 0, len(data))
for _, row := range data {
includeRow := true
for _, colIdx := range serverColIndices {
if colIdx < len(row) {
if strVal, ok := row[colIdx].(string); ok {
if net.ParseIP(strVal) != nil {
includeRow = false
break
}
}
}
}
if includeRow {
filtered = append(filtered, row)
}
}
return filtered
}
func shouldIncludeRow(row *qbtypes.RawRow) bool {
if row.Data != nil {
if domainVal, ok := row.Data[derivedKeyHTTPHost]; ok {

View File

@@ -117,6 +117,59 @@ func TestFilterResponse(t *testing.T) {
},
},
},
{
name: "should filter out IP addresses from scalar data",
input: []*qbtypes.QueryRangeResponse{
{
Data: qbtypes.QueryData{
Results: []any{
&qbtypes.ScalarData{
QueryName: "endpoints",
Columns: []*qbtypes.ColumnDescriptor{
{
TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{Name: derivedKeyHTTPHost},
Type: qbtypes.ColumnTypeGroup,
},
{
TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{Name: "endpoints"},
Type: qbtypes.ColumnTypeAggregation,
},
},
Data: [][]any{
{"192.168.1.1", 10},
{"example.com", 20},
{"10.0.0.1", 5},
},
},
},
},
},
},
expected: []*qbtypes.QueryRangeResponse{
{
Data: qbtypes.QueryData{
Results: []any{
&qbtypes.ScalarData{
QueryName: "endpoints",
Columns: []*qbtypes.ColumnDescriptor{
{
TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{Name: derivedKeyHTTPHost},
Type: qbtypes.ColumnTypeGroup,
},
{
TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{Name: "endpoints"},
Type: qbtypes.ColumnTypeAggregation,
},
},
Data: [][]any{
{"example.com", 20},
},
},
},
},
},
},
},
}
for _, tt := range tests {

View File

@@ -169,6 +169,7 @@ func NewSQLMigrationProviderFactories(
sqlmigration.NewAddAnonymousPublicDashboardTransactionFactory(sqlstore),
sqlmigration.NewAddRootUserFactory(sqlstore, sqlschema),
sqlmigration.NewAddUserEmailOrgIDIndexFactory(sqlstore, sqlschema),
sqlmigration.NewMigrateRulesV4ToV5Factory(sqlstore, telemetryStore),
)
}

View File

@@ -0,0 +1,209 @@
package sqlmigration
import (
"context"
"database/sql"
"encoding/json"
"log/slog"
"github.com/SigNoz/signoz/pkg/factory"
"github.com/SigNoz/signoz/pkg/sqlstore"
"github.com/SigNoz/signoz/pkg/telemetrystore"
"github.com/SigNoz/signoz/pkg/transition"
"github.com/uptrace/bun"
"github.com/uptrace/bun/migrate"
)
type migrateRulesV4ToV5 struct {
store sqlstore.SQLStore
telemetryStore telemetrystore.TelemetryStore
logger *slog.Logger
}
func NewMigrateRulesV4ToV5Factory(
store sqlstore.SQLStore,
telemetryStore telemetrystore.TelemetryStore,
) factory.ProviderFactory[SQLMigration, Config] {
return factory.NewProviderFactory(
factory.MustNewName("migrate_rules_post_deprecation"),
func(ctx context.Context, ps factory.ProviderSettings, c Config) (SQLMigration, error) {
return &migrateRulesV4ToV5{
store: store,
telemetryStore: telemetryStore,
logger: ps.Logger,
}, nil
})
}
func (migration *migrateRulesV4ToV5) Register(migrations *migrate.Migrations) error {
if err := migrations.Register(migration.Up, migration.Down); err != nil {
return err
}
return nil
}
func (migration *migrateRulesV4ToV5) getLogDuplicateKeys(ctx context.Context) ([]string, error) {
query := `
SELECT name
FROM (
SELECT DISTINCT name FROM signoz_logs.distributed_logs_attribute_keys
INTERSECT
SELECT DISTINCT name FROM signoz_logs.distributed_logs_resource_keys
)
ORDER BY name
`
rows, err := migration.telemetryStore.ClickhouseDB().Query(ctx, query)
if err != nil {
migration.logger.WarnContext(ctx, "failed to query log duplicate keys", "error", err)
return nil, nil
}
defer rows.Close()
var keys []string
for rows.Next() {
var key string
if err := rows.Scan(&key); err != nil {
migration.logger.WarnContext(ctx, "failed to scan log duplicate key", "error", err)
continue
}
keys = append(keys, key)
}
return keys, nil
}
func (migration *migrateRulesV4ToV5) getTraceDuplicateKeys(ctx context.Context) ([]string, error) {
query := `
SELECT tagKey
FROM signoz_traces.distributed_span_attributes_keys
WHERE tagType IN ('tag', 'resource')
GROUP BY tagKey
HAVING COUNT(DISTINCT tagType) > 1
ORDER BY tagKey
`
rows, err := migration.telemetryStore.ClickhouseDB().Query(ctx, query)
if err != nil {
migration.logger.WarnContext(ctx, "failed to query trace duplicate keys", "error", err)
return nil, nil
}
defer rows.Close()
var keys []string
for rows.Next() {
var key string
if err := rows.Scan(&key); err != nil {
migration.logger.WarnContext(ctx, "failed to scan trace duplicate key", "error", err)
continue
}
keys = append(keys, key)
}
return keys, nil
}
func (migration *migrateRulesV4ToV5) Up(ctx context.Context, db *bun.DB) error {
logsKeys, err := migration.getLogDuplicateKeys(ctx)
if err != nil {
return err
}
tracesKeys, err := migration.getTraceDuplicateKeys(ctx)
if err != nil {
return err
}
tx, err := db.BeginTx(ctx, nil)
if err != nil {
return err
}
defer func() {
_ = tx.Rollback()
}()
var rules []struct {
ID string `bun:"id"`
Data map[string]any `bun:"data"`
}
err = tx.NewSelect().
Table("rule").
Column("id", "data").
Scan(ctx, &rules)
if err != nil {
if err == sql.ErrNoRows {
return nil
}
return err
}
alertsMigrator := transition.NewAlertMigrateV5(migration.logger, logsKeys, tracesKeys)
count := 0
for _, rule := range rules {
version, _ := rule.Data["version"].(string)
if version == "v5" {
continue
}
if version == "" {
migration.logger.WarnContext(ctx, "unexpected empty version for rule", "rule_id", rule.ID)
}
migration.logger.InfoContext(ctx, "migrating rule v4 to v5", "rule_id", rule.ID, "current_version", version)
// Check if the queries envelope already exists and is non-empty
hasQueriesEnvelope := false
if condition, ok := rule.Data["condition"].(map[string]any); ok {
if compositeQuery, ok := condition["compositeQuery"].(map[string]any); ok {
if queries, ok := compositeQuery["queries"].([]any); ok && len(queries) > 0 {
hasQueriesEnvelope = true
}
}
}
if hasQueriesEnvelope {
// already has queries envelope, just bump version
// this is because user made a mistake of choosing version
migration.logger.InfoContext(ctx, "rule already has queries envelope, bumping version", "rule_id", rule.ID)
rule.Data["version"] = "v5"
} else {
// old format, run full migration
migration.logger.InfoContext(ctx, "rule has old format, running full migration", "rule_id", rule.ID)
updated := alertsMigrator.Migrate(ctx, rule.Data)
if !updated {
migration.logger.WarnContext(ctx, "expected updated to be true but got false", "rule_id", rule.ID)
continue
}
rule.Data["version"] = "v5"
}
dataJSON, err := json.Marshal(rule.Data)
if err != nil {
return err
}
_, err = tx.NewUpdate().
Table("rule").
Set("data = ?", string(dataJSON)).
Where("id = ?", rule.ID).
Exec(ctx)
if err != nil {
return err
}
count++
}
if count != 0 {
migration.logger.InfoContext(ctx, "migrate v4 alerts", "count", count)
}
return tx.Commit()
}
func (migration *migrateRulesV4ToV5) Down(ctx context.Context, db *bun.DB) error {
return nil
}

View File

@@ -355,6 +355,10 @@ func (r *PostableRule) validate() error {
errs = append(errs, signozError.NewInvalidInputf(signozError.CodeInvalidInput, "composite query is required"))
}
if r.Version != "v5" {
errs = append(errs, signozError.NewInvalidInputf(signozError.CodeInvalidInput, "only version v5 is supported, got %q", r.Version))
}
if isAllQueriesDisabled(r.RuleCondition.CompositeQuery) {
errs = append(errs, signozError.NewInvalidInputf(signozError.CodeInvalidInput, "all queries are disabled in rule condition"))
}

View File

@@ -108,6 +108,7 @@ func TestParseIntoRule(t *testing.T) {
"ruleType": "threshold_rule",
"evalWindow": "5m",
"frequency": "1m",
"version": "v5",
"condition": {
"compositeQuery": {
"queryType": "builder",
@@ -150,6 +151,7 @@ func TestParseIntoRule(t *testing.T) {
content: []byte(`{
"alert": "DefaultsRule",
"ruleType": "threshold_rule",
"version": "v5",
"condition": {
"compositeQuery": {
"queryType": "builder",
@@ -187,6 +189,7 @@ func TestParseIntoRule(t *testing.T) {
initRule: PostableRule{},
content: []byte(`{
"alert": "PromQLRule",
"version": "v5",
"condition": {
"compositeQuery": {
"queryType": "promql",
@@ -256,6 +259,7 @@ func TestParseIntoRuleSchemaVersioning(t *testing.T) {
content: []byte(`{
"alert": "SeverityLabelTest",
"schemaVersion": "v1",
"version": "v5",
"condition": {
"compositeQuery": {
"queryType": "builder",
@@ -344,6 +348,7 @@ func TestParseIntoRuleSchemaVersioning(t *testing.T) {
content: []byte(`{
"alert": "NoLabelsTest",
"schemaVersion": "v1",
"version": "v5",
"condition": {
"compositeQuery": {
"queryType": "builder",
@@ -384,6 +389,7 @@ func TestParseIntoRuleSchemaVersioning(t *testing.T) {
content: []byte(`{
"alert": "OverwriteTest",
"schemaVersion": "v1",
"version": "v5",
"condition": {
"compositeQuery": {
"queryType": "builder",
@@ -474,6 +480,7 @@ func TestParseIntoRuleSchemaVersioning(t *testing.T) {
content: []byte(`{
"alert": "V2Test",
"schemaVersion": "v2",
"version": "v5",
"condition": {
"compositeQuery": {
"queryType": "builder",
@@ -517,6 +524,7 @@ func TestParseIntoRuleSchemaVersioning(t *testing.T) {
initRule: PostableRule{},
content: []byte(`{
"alert": "DefaultSchemaTest",
"version": "v5",
"condition": {
"compositeQuery": {
"queryType": "builder",
@@ -569,6 +577,7 @@ func TestParseIntoRuleSchemaVersioning(t *testing.T) {
func TestParseIntoRuleThresholdGeneration(t *testing.T) {
content := []byte(`{
"alert": "TestThresholds",
"version": "v5",
"condition": {
"compositeQuery": {
"queryType": "builder",
@@ -639,6 +648,7 @@ func TestParseIntoRuleMultipleThresholds(t *testing.T) {
"schemaVersion": "v2",
"alert": "MultiThresholdAlert",
"ruleType": "threshold_rule",
"version": "v5",
"condition": {
"compositeQuery": {
"queryType": "builder",
@@ -732,6 +742,7 @@ func TestAnomalyNegationEval(t *testing.T) {
ruleJSON: []byte(`{
"alert": "AnomalyBelowTest",
"ruleType": "anomaly_rule",
"version": "v5",
"condition": {
"compositeQuery": {
"queryType": "builder",
@@ -766,6 +777,7 @@ func TestAnomalyNegationEval(t *testing.T) {
ruleJSON: []byte(`{
"alert": "AnomalyBelowTest",
"ruleType": "anomaly_rule",
"version": "v5",
"condition": {
"compositeQuery": {
"queryType": "builder",
@@ -799,6 +811,7 @@ func TestAnomalyNegationEval(t *testing.T) {
ruleJSON: []byte(`{
"alert": "AnomalyAboveTest",
"ruleType": "anomaly_rule",
"version": "v5",
"condition": {
"compositeQuery": {
"queryType": "builder",
@@ -833,6 +846,7 @@ func TestAnomalyNegationEval(t *testing.T) {
ruleJSON: []byte(`{
"alert": "AnomalyAboveTest",
"ruleType": "anomaly_rule",
"version": "v5",
"condition": {
"compositeQuery": {
"queryType": "builder",
@@ -866,6 +880,7 @@ func TestAnomalyNegationEval(t *testing.T) {
ruleJSON: []byte(`{
"alert": "AnomalyBelowAllTest",
"ruleType": "anomaly_rule",
"version": "v5",
"condition": {
"compositeQuery": {
"queryType": "builder",
@@ -901,6 +916,7 @@ func TestAnomalyNegationEval(t *testing.T) {
ruleJSON: []byte(`{
"alert": "AnomalyBelowAllTest",
"ruleType": "anomaly_rule",
"version": "v5",
"condition": {
"compositeQuery": {
"queryType": "builder",
@@ -935,6 +951,7 @@ func TestAnomalyNegationEval(t *testing.T) {
ruleJSON: []byte(`{
"alert": "AnomalyOutOfBoundsTest",
"ruleType": "anomaly_rule",
"version": "v5",
"condition": {
"compositeQuery": {
"queryType": "builder",
@@ -969,6 +986,7 @@ func TestAnomalyNegationEval(t *testing.T) {
ruleJSON: []byte(`{
"alert": "ThresholdTest",
"ruleType": "threshold_rule",
"version": "v5",
"condition": {
"compositeQuery": {
"queryType": "builder",
@@ -1003,6 +1021,7 @@ func TestAnomalyNegationEval(t *testing.T) {
ruleJSON: []byte(`{
"alert": "ThresholdTest",
"ruleType": "threshold_rule",
"version": "v5",
"condition": {
"compositeQuery": {
"queryType": "builder",