Torch Log Service
Torch Log Service
Torch Log Service
Document
Product News
Product Overview
Product Billing
User Guide
TLS Agent
AgentLoop
Resource management
Host group
Data collection
LogCollector collection
Introduction to LogCollector
Installation and upgrade
Collect host logs
Collect container logs
LogCollector plugins
Manage LogCollector
general reference
Data import
Cloud product log collection
TOS log collection
DBW log collection
VPN Log collection
VKE log collection
CLB log collection
CloudTrail log collection
CFW log collection
NTA log collection
ALB log collection
APMPlus log collection
veFaaS log collection
VPC log collection
veImageX log collection
TrafficRoute DNS log collection
DDoS log collection
WAF log collection
DCDN log collection
Multi-cloud security platform log collection
APIG log collection
Machine learning task log collection
CR log collection
Volcano Ark application lab log collection
FileNAS log collection
LLM Application Firewall Service log collection
vePFS log collection
Cloud security center log collection
EFS log collection
Data storage
Query and analysis
Configure log indexes
Query log
Analyze logs
Query and analyze logs using third-party tools
Associate external data source for log query
SQL function
SQL syntax
Visualization
Query and analysis charts
Summaries of query and analysis charts
Create dashboard
Use dashboard
Add dashboard filters and variables
Use other systems to analyze logs
Log application
Log applications for product observability
Log applications for large models observability
Coding Agent log app
ModelProvider log app
No-coding Agent log app
Log applications for basic service monitoring
Data processing
Data transformation
Syntax and functions
Global operation function
expression function
Data processing best practices
general reference
Data write processor
Data consumer processor
Data consumption and shipping
Ship logs to TOS
Ship logs to Kafka
Ship logs to Splunk
Alarm
Alarm policy
Alarm notification content
Alarm notification content template
alarm notification channel
Tracing service
Monitor Log Service
API reference
Project management API
Topic management API
Shard management API
Index management API
Log management API
Host group management API
Collection configuration management API
Data import API
Data processor API
Data transformation API
Data backflow API
SQL analysis API
Alarm management API
Consumer group management API
Kafka protocol consumption API
Tag management API
Trace storage API
Account management API
SDK reference
Go SDK
Java SDK
Python SDK
iOS SDK
C++ SDK
CLI reference
Best practices
Data collection
Query and analysis
permission management
Consumption and delivery
Visualization
Alarm
FAQs
Billing and cost FAQ
Data collection FAQ
Data storage FAQ
Index configuration FAQ
Query and analysis FAQ
Scheduled SQL tasks FAQ
Alarm FAQ
- Documentation
Torch Log ServiceUser GuideQuery and analysisMachine learning functionThreshold recommendation function
Copy page
Download PDFMachine learning function
Threshold recommendation function
Copy pageDownload PDFThreshold recommendation function
This topic introduces the syntax of threshold functions supported by TLS and usage examples for common scenarios.
Notice
Currently, machine learning functions are in public beta.
ts_threshold_recommendation
When monitoring SLA-related metrics with traditional manual alarm rule configuration, issues may exist in the results, including insufficient metric coverage and inaccurate alarm thresholds. If anomaly detection thresholds are set too loosely, it reduces active fault detection rate, leading to increased user loss and compensation. If anomaly detection thresholds are set too strictly, it results in a large number of false alarms. Consequently, the operation team may short of time to handle the actual exceptions.
The ts_threshold_recommendation function enables clustering analysis of historical time series data, quickly identifies the distribution of normal data, and automatically recommends exception detection thresholds. It is suitable for alarm threshold settings and similar scenarios.
Function syntax
- Syntax format
- select ts_threshold_recommendation(x, y，metricType)
- Parameters description
- ParametersData typeDescriptionParametersData typeDescriptionxdoubleTime column, sorted in ascending order. Format: Unix time timestamp; unit: second.ydoubleValue column. It represents values for each corresponding time. The array length must match x, and contain at least 500 elements.metricTypevarchar
- SuccessRate: success rate. The input range for y is 0 to 1. If the success rate is below recommended threshold, exception exists.
- SuccessRate100: success rate. The input range for y is 0 to 100. If the success rate is below recommended threshold, exception exists.
- ErrorRate: error rate. The input range for y is 0 to 1. If the error rate exceeds recommended threshold, exception exists.
- ErrorRate100: error rate. The input range for y is 0 to 100. If the error rate exceeds recommended threshold, exception exists.
- Count: count statistics. The input range for y is integers. If the count is below recommended threshold, exception exists.
- ErrorCount: indicates error count statistics. The input range for y is integers. If the count exceeds recommended threshold, exception exists.
- Latency: latency in milliseconds. The input type for y is a floating-point number in milliseconds. If the latency exceeds the recommended threshold, exception exists.
- LatencySecond: latency in seconds. The input type for y is a floating-point number in seconds. If the latency exceeds the recommended threshold, exception exists.
- ResourceUtilizationRate: resource utilization rate. The input range for y is 0 to 1. If the rate exceeds the recommended threshold.
- ResourceUtilizationRate100: Resource utilization rate. The input value for y must be within the range 0–100. If the values is above recommended threshold, exception exists.
- Throughput: The input type for y must be a floating point number. If the values is above recommended threshold, exception exists.
NoticeHow to choose between xxxRate and xxxRate100: if the data contains decimals, choose xxxRate; if the data contains integers, choose xxxRate100.
- Return values
- The return value is of Double type.
Function examples
- Scenarios
- Calculate the millisecond delay threshold based on time and request size.
- Query and analysis statements
- *|select ts_threshold_recommendation(stamp, value, 'Latency') from (select __time__ as stamp, ReqSize as value limit 1000)
- Query and analysis results
-
Last updated: 2026.05.08 14:32:46
All rights reserved © Beijing Volcano Engine Technology Co., Ltd2024
