Apica Docs
  • Welcome to Apica Docs!
  • PRODUCT OVERVIEW
    • Ascent Overview
    • Ascent User Interface
  • TECHNOLOGIES
    • Ascent with Kubernetes
      • Kubernetes is a Game-Changer
      • Ascent: Built on Kubernetes
    • Ascent with OpenTelemetry
      • Why Implement OpenTelemetry?
      • Common Use Cases for OpenTelemetry
      • How to Get Started with OpenTelemetry
      • Best Practices for OpenTelemetry Implementations
  • RELEASE NOTES
    • Release Notes
      • Ascent 2.10.3
      • Ascent 2.10.2
      • Ascent 2.9.0
      • Ascent 2.8.1
      • Ascent 2.8.0
      • Ascent 2.7.0
      • Ascent 2.6.0
      • Ascent 2.5.0
      • Ascent 2.4.0
      • Ascent 2.3.0
      • Ascent 2.2.0
      • Ascent 2.1.0
        • Data Fabric
          • Releases-old
        • Synthetic Monitoring
        • Advanced Scripting Engine
        • IRONdb
      • Synthetic Monitoring
  • GETTING STARTED
    • Getting Started with Ascent
      • Getting Started with Metrics
      • Getting Started with Logs
        • OpenTelemetry
    • Ascent Deployment Overview
    • Quickstart with Docker-Compose
    • On-Premise PaaS deployment
      • On-Premise PaaS Deployment Architecture
      • Deploying Apica Ascent PaaS on Kubernetes
      • Deploying Apica Ascent PaaS on MicroK8s
      • Deploying Apica Ascent PaaS on AWS
      • Deploying Apica Ascent EKS on AWS using CloudFormation
      • Deploying Ascent on AWS EKS with Aurora PostgreSQL and ElastiCache Redis using Cloud Formation
        • Deploying Apica Ascent on AWS EKS with Aurora PostgreSQL and ElastiCache Redis using CloudFormation
        • Apica Ascent on AWS EKS (Private Endpoint) with Aurora PostgreSQL and ElastiCache Redis on prod VPC
      • Deploying Apica Ascent EKS on AWS using custom AMI
      • Deploying Apica Ascent EKS with AWS ALB
      • Deploying Apica Ascent PaaS in Azure Kubernetes Service
        • Azure Blob Storage Lifecycle Management
      • Deploying Apica Ascent with OpenShift
    • Boomi RTO Quick Start Guide
      • RTO Dashboarding
      • Alerting on RTO Metrics
      • Alerting on RTO Logs
    • Dashboards & Visualizations
  • DATA SOURCES
    • Data Source Overview
    • API
      • JSON Data source
      • RSS
    • AWS
      • Amazon Athena
      • Amazon CloudWatch ( YAML )
      • Amazon Elasticsearch Service
      • Amazon Redshift
      • MySQL Server (Amazon RDS)
    • NoSQL Data Sources
      • MongoDB
    • OLAP
      • Data Bricks
      • Druid
      • Snowflake
    • SQL Data Sources
      • PostgreSQL
      • Microsoft SQL Server
      • MySQL Server
    • Time Series Databases
      • Prometheus Compatible
      • Elasticsearch
      • InfluxDB
    • Ascent Synthetics
      • Checks
    • Ascent Logs
      • Logs
  • INTEGRATIONS
    • Integrations Overview
      • Generating a secure ingest token
      • Data Ingest Ports
    • List of Integrations
      • Apache Beam
        • Export Metrics to Prometheus
          • Pull Mechanism via Push-Gateway
        • Export Events to Apica Ascent
      • Apica ASM
      • Apica Ascent Observability Data Collector Agent
      • AWS
        • AWS CloudWatch
        • AWS ECS
          • Forwarding AWS ECS logs to Apica Ascent using AWS FireLens
          • ECS prometheus metrics to Apica Ascent
        • AWS S3
      • Azure
        • Azure Databricks
        • Azure Eventhub
        • Azure Event Hubs
      • Docker Compose
      • Docker Swarm logging
      • Docker Syslog log driver
      • F5 Big-Ip System
      • Filebeat
      • Fluent Bit
        • Forwarding Amazon-Linux logs to Apica Ascent using Fluent Bit
        • Fluent Bit installation on Ubuntu
        • Enabling IoT(MQTT) Input (PAAS)
        • IIS Logs on Windows
      • Fluentd
      • FortiNet Firewalls
      • GCP PubSub
      • GCP Cloud Logging
      • IBM QRadar
      • ilert
      • Incident Management
        • Webhooks
      • Jaeger
      • Kafka
      • Kinesis
      • Kubernetes
      • Logstash
      • MQTT
      • Network Packets
      • OpenTelemetry
      • Object store (S3 Compatible)
      • Oracle OCI Infrastructure Audit/Logs
      • Oracle Data Integrator (ODI)
      • OSSEC Variants (OSSEC/WAZUH/ATOMIC)
        • Apica Ascent-OSSEC Agent for Windows
      • Palo Alto Firewall
      • Prometheus
        • Spring Boot
        • Prometheus on Windows
        • Prometheus Remote Write
        • MongoDB Exporter
        • JMX Exporter
      • Rsyslogd
      • Syslog
      • Syslog-ng
      • Splunk Universal Forwarder
      • Splunk Heavy Forwarder
      • SNMP
      • Splunk Forwarding Proxy
      • Vault
        • Audit Vault Logs - AWS
        • Audit Vault Logs - OCI
        • Audit Vault Metrics
    • Apica API DOCS
  • DATA MANAGEMENT
    • Data Management Overview
    • Data Explorer Overview
      • Query Builder
      • Widget
      • Alerts
      • JSON Import
      • Creating Json Schema
        • Visualization
          • Line chart
          • Bar chart
          • Area chart
          • Scatter chart
          • Status chart
          • Counter chart
          • Stat chart
          • Size chart
          • Dense Status chart
          • Honeycomb chart
          • Gauge chart
          • Pie chart
          • Disk chart
          • Table chart
          • Date time chart
      • Time-Series AI/ML
        • Anomaly Detection
        • Averaging
        • Standard Deviation(STD)
      • Data Explorer Dashboard
        • Create a Dashboard
        • Editing Dashboard
          • Dashboard level filters
    • Timestamp handling
      • Timestamp bookmark
    • Large log/events/metrics/traces
  • OBSERVE
    • Monitoring Overview
      • Connecting Prometheus
      • Connecting Amazon Managed Service for Prometheus
      • Windows Redis Monitoring
      • Writing queries
        • Query Snippets
      • Query API
      • Use Apica API to ingest JSON data
    • Distributed Tracing
      • Traces
      • Spans
      • Native support for OTEL Traces
      • Windows .NET Application Tracing
      • Linux+Java Application Tracing
    • Log Management
      • Terminology
      • Explore Logs
      • Topology
      • Apica Ascent Search Cheat Sheet
      • Share Search Results
      • Severity Metrics
      • Log2Metrics
      • Native support for OTEL Logs
      • Reports
        • Accessing Reports results via API
      • Role-Based Access Control (RBAC)
      • Configuring RBAC
    • AI and LLM Observability
      • AI Agent Deployment
      • Ascent AI Agent Monitoring
      • Ascent Quick Start Guide
    • Synthetic Check Monitoring
      • Map View
      • List View
      • Alerting for Check Results
  • Flow
    • Overview
    • Pipeline Management
      • Configuring Pipelines
      • Visualize Pipelines
      • Pipeline Overview Dashboard
      • Forwarding Data
    • OpenTelemetry Ingest
      • OpenTelemetry Logs / Traces
      • OpenTelemetry Metrics
        • Transforming Metrics through Code Rules
    • Vault
      • Certificates
      • Variables
      • Lookups
    • Rules
      • FILTER
      • EXTRACT
      • SIEM and TAG
      • REWRITE
      • CODE
      • FORWARD
        • Rename Attributes
      • STREAM
    • Functions
      • ascent.encode
      • ascent.decode
      • ascent.persist
      • Ascent.variables
      • ascent.crypto
      • Ascent.mask
      • Ascent.net
      • Ascent.text
      • Ascent.time
      • Ascent.lookups
    • List of Forwarders
    • OpenTelemetry Forwarding
      • Metrics
      • Traces
      • Logs
    • Splunk Forwarding
      • Apica UF Proxy App Extension
        • Standalone Instance
        • List of Indexer Instances
        • Indexer Discovery
      • Metric Indexes
      • Non Metric Indexes
      • Syslog Forwarding
    • Real-Time Stream Forwarding
      • AWS Kinesis
      • Azure Eventhub
      • Google Pub/Sub
    • Security Monitor Forwarding
      • Arc Sight
      • RSA New Witness
    • Forwarding to Monitoring Tools
      • Datadog Forwarding
      • New Relic Forwarding
      • Dynatrace Forwarding
      • Elasticsearch Forwarding
      • Coralogix Forwarding
      • Azure Log Analytics Forwarding
    • Object Store Forwarding
      • S3 Compatible
      • Azure Blob Storage
    • Forwarding to Data Warehouse
      • GCP Bigquery
  • Customized Forwarders
    • JS Code Forwarding
  • LAKE
    • Powered by Instastore™
  • FLEET MANAGEMENT
    • Overview
    • Agents
    • Configurations
    • Packages
    • Fleet Repository Management
    • Advanced Search
    • List of Agents
      • Datadog Agent
      • Fluent-bit Agent
      • Grafana Alloy
      • OpenTelemetry Collector
      • OpenTelemetry Kubernetes
      • Prometheus Agent
  • COMMAND LINE INTERFACE
    • apicactl Documentation
  • AUTONOMOUS INSIGHTS
    • Time Series AI-ML
      • Anomaly Detection
      • Averaging
      • Standard Deviation(STD)
      • Forecasting
      • AI-ML on PromQL Query Data Set
      • Statistical Data Description
    • Pattern-Signature (PS)
      • Log PS Explained
        • Unstructured Logs
        • Semi-structured JSON
        • Reduce Logs Based on PS
        • Log PS Use Cases
          • Log Outlier Isolation
          • Log Trending Analysis
          • Simple Log Compare
      • Config PS
        • Config JSON PS
    • ALIVE Log Visualization
      • ALIVE Pattern Signature Summary
      • ALIVE Log Compare
    • Log Explained using Generative AI
      • Configuring Generative AI Access
      • GenAI Example Using Log Explain
    • Alerts
    • Alerts (Simple/Anomaly)
    • Alerts On Logs
    • Rule Packs
    • AI-powered Search
  • PLATFORM DOCS
    • Synthetic Monitoring Overview
      • Getting Started with ASM
        • Achieving 3 Clicks to Issue Resolution via ASM
        • FAQ - Frequently Asked Questions
        • Creating A New Check
          • Creating a New Real Browser Check
      • Explore the Platform
        • API Details
        • Check Types
          • Android Check
          • Command Check
          • Compound Check
          • Browser Check
          • Desktop Application Check
          • AWS Lambda Check
          • DNS Resolver Check
          • DNS Security Check
          • Domain Availability Check
          • Domain Delegation Check
          • Domain Expiration Date Check
          • Hostname Integrity Check
          • iPad Check
          • iPhone Check
          • Ping Check
          • Port Check
          • Postman Check
          • Response Time Check
          • SSL Certificate Expiration Check
          • Scripted Check
        • Dashboards
        • Integrations
          • DynaTrace Integration
          • Google Analytics Integration
          • Akamai Integration
          • Centrify Integration
          • AppDynamics Integration
          • PagerDuty Integration
          • ServiceNow Integration
          • Splunk Integration
        • Metrics
          • Analyze Site
          • Result Values
          • Trends
          • Analyze Metrics
        • Monitoring
          • Integrating ASM Metrics into Grafana Using Apica Panels
            • Understanding the ASM Imported Dashboards
            • Using the Apica Panels Dashboards
          • Understanding ASM Check Host Locations
        • Navigation
          • Manage Menu
        • Reports
        • Use Cases
      • Configurations
        • Configuring Checks
          • Understanding Check Results
            • Understanding ZebraTester Check Results
            • Understanding Browser Check Results
            • Understanding Check Details
          • Editing Checks
            • Editing Browser Checks
            • Editing ZebraTester Checks
          • Using Regular Expressions Within the ASM Platform
          • Understanding the Edit Scenario Page
          • Comparing Selenium IDE Scripts to ASM Scenarios
          • Configuring Apica DNS Check Types
          • Implementing Tags Effectively Within ASM
          • Storing and Retrieving Information Using the ASM Dictionary
        • Configuring Users
          • Configuring SSO Within ASM
        • Configuring Alerts
          • Configuring Webhook Alerts
      • How-To Articles
        • ASM Monitoring Best Practices
        • API Monitoring Guide
        • IT Monitoring Guide
        • Monitor Mission-Critical Applications through the Eyes of Your Users
        • How To Mask Sensitive Data in ASM
        • How to Mask Sensitive Data When Using Postman Checks
        • How to Handle URL Errors in a Check
        • How To Set Up SSO Using Azure AD
        • How to Set Up SSO Using Centrify
        • ASM Scenarios How-To
          • How To Pace a Selenium Script
          • How to Utilize XPath Within a Selenium Script
          • How to Mask Sensitive Information Within an ASM Scenario
          • Handling Elements Which Do Not Appear Consistently
          • How to Handle HTML Windows in ASM Scenarios
    • ZebraTester Scripting
      • ZebraTester Overview
      • Install ZebraTester
        • Download ZebraTester
          • Core ZebraTester V7.5-A Documentation
          • Core ZebraTester V7.0-B Documentation
          • Core ZebraTester V7.0-A Documentation
          • Core ZebraTester V5.5-Z Documentation
          • Core ZebraTester V5.5-F Documentation
        • Download the ZebraTester Recorder Extension
        • Windows Installation
          • ZebraTester on Windows
          • Generate Private CA Root Certificate
          • Windows System Tuning
          • Install a new ZT version on Windows Server
          • Install/Uninstall ZT Windows Installer Silently
        • macOS Installation
          • macOS Preinstallation Instructions
          • Generate Private CA Root Cert (macOS X)
          • System Tuning (macOS)
          • Import a CA Root Certificate to an iOS device
          • Memory Configuration Guidelines for ZebraTester Agents
      • ZebraTester User Guide
        • Menu and Navigation Overview
        • 1. Get a Load Test Session
          • Recording Web Surfing Sessions with ZebraTester
            • Further Hints for Recording Web Surfing Sessions
            • Recording Extension
              • Record Web Session
              • Cookies and Cache
              • Proxy
              • Page Breaks
              • Recording Extension Introduction
              • Troubleshooting
            • Add URL to ZebraTester
            • Page Scanner
          • Next Steps after Recording a Web Surfing Session
        • 2. Scripting the Load Test Session
          • 1. Assertions - HTTP Response Verificaton
          • 2. Correlation - Dynamic Session Parameters
            • 2b. Configuring Variable Rules
            • 2a. Var Finder
          • 3. Parameterization: Input Fields, ADR and Input Files
            • ADR
          • 4. Execution Control - Inner Loops
          • 5. Execution Control - URL Loops
          • 6. Execution Control -User-Defined Transactions And Page Breaks
          • 7. Custom Scripting - Inline Scripts
          • 8. Custom Scripting - Load Test Plug-ins
            • ZebraTester Plug-in Handbooks
          • Modular Scripting Support
        • 3. Recording Session Replay
        • 4. Execute the Load Test
          • Executing a First Load Test
          • Executing Load Test Programs
            • Project Navigator
              • Configuration of the Project Navigator Main Directory
            • Real-Time Load Test Actions
            • Real-Time Error Analysis
            • Acquiring the Load Test Result
            • More Tips for Executing Load Tests
          • Distributed Load Tests
            • Exec Agents
            • Exec Agent Clusters
          • Multiple Client IP Addresses
            • Sending Email And Alerts
            • Using Multiple Client IP Addresses per Load-Releasing System
        • 5. Analyzing Results
          • Detail Results
          • Load Test Result Detail-Statistics and Diagrams
          • Enhanced HTTP Status Codes
          • Error Snapshots
          • Load Curve Diagrams
          • URL Exec Step
          • Comparison Diagrams
            • Analysis Load Test Response Time Comparison
            • Performance Overview
            • Session Failures
        • Programmatic Access to Measured Data
          • Extracting Error Snapshots
          • Extracting Performance Data
        • Web Tools
        • Advanced Topics
          • Execute a JMeter Test Plan in ZebraTester
          • Credentials Manager for ZebraTester
          • Wildcard Edition
          • Execution Plan in ZebraTester
          • Log rotation settings for ZebraTester Processes
          • Modify Session
          • Modular Scripting Support
          • Understanding Pacing
          • Integrating ZebraTester with GIT
            • GitHub Integration Manual V5.4.1
      • ZebraTester FAQ
      • ZebraTester How-to articles
        • How to Combine Multiple ZebraTester Scripts Into One
        • Inline Scripting
        • How to Configure a ZebraTester Script to Fetch Credentials from CyberArk
        • How to Configure a ZebraTester Scenario to Fetch Credentials from CyberArk
        • How to Convert a HAR file into a ZebraTester Script
        • How to Convert a LoadRunner Script to ZebraTester
        • How to Import the ZT Root Certificate to an iOS device
        • How to iterate over JSON objects in ZebraTester using Inline Scripts
        • How to round a number to a certain number of decimal points within a ZebraTester Inline Script
        • How to Use a Custom DNS Host File Within a ZebraTester Script
        • How to Move a ZebraTester Script to an Older Format
        • API Plugin Version
        • Setting up the Memu Player for ZebraTester Recording
        • Inline Script Version
      • Apica Data Repository (ADR) aka Apica Table Server
        • ADR related inline functions available in ZT
        • Apica Data Repository Release Notes
        • REST Endpoint Examples
        • Accessing the ADR with Inline Scripts
      • ZebraTester Plugin Repository
      • Apica YAML
        • Installing and Using the ApicaYAML CLI Tool
        • Understanding ApicaYAML Scripting and Syntax
    • Load Testing Overview
      • Getting Started with ALT
      • Creating / Running a Single Load Test
      • Running Multiple Tests Concurrently
      • Understanding Loadtest Results
    • Test Data Orchestrator (TDO)
      • Technical Guides
        • Hardware / Environment Requirements
        • IP Forwarding Instructions (Linux)
        • Self-Signed Certificate
        • Windows Server Install
        • Linux Server Install
        • User Maintenance
        • LDAP Setup
        • MongoDB Community Server Setup
        • TDX Installation Guide
      • User Documentation
        • End User Guide for TDO
          • Connecting to Orson
          • Coverage Sets and Business Rules
          • Data Assembly
          • Downloading Data
        • User Guide for TDX
          • Connecting to TDX
          • Setting up a Data Profile
          • Extracting Data
          • Analyzing Data Patterns
          • Performing Table Updates
        • API Guide
          • API Structure and Usage
          • Determining Attribute APIs
            • Create Determining Attribute (Range-based)
            • Create Determining Attribute (Value-based)
            • Update Determining Attributes
            • Get Determining Attribute Details
            • Delete a Determining Attribute
          • Coverage Set API’s
            • Create Coverage Set
            • Update Coverage Set
            • Get All Coverage Set Details
            • Get Single Coverage Set Details
            • Lock Coverage Set
            • Unlock Coverage Set
            • Delete Coverage Set
          • Business Rule API’s
            • Create Business Rule
            • Update Business Rule
            • Get Business Rule Details
            • Get All Business Rules
            • Delete Business Rule
          • Workset API's
            • Create Workset
            • Update Workset
            • Get All Worksets
            • Get Workset Details
            • Unlock Workset
            • Clone Workset
            • Delete Workset
          • Data Assembly API's
            • Assemble Data
            • Check Assembly Process
          • Data Movement API's
            • Ingest (Upload) Data Files
            • Download Data Files
              • HTML Download
              • CSV Download
              • Comma Delimited with Sequence Numbers Download
              • Pipe Delimited Download
              • Tab Delimited with Sequence Numbers Download
              • EDI X12 834 Download
              • SQL Lite db Download
              • Alight File Format Download
          • Reporting API's
            • Session Events
            • Rules Events
            • Coverage Events
            • Retrieve Data Block Contents
            • Data Assembly Summary
        • Workflow Guide
      • Release Notes
        • Build 1.0.2.0-20250213-1458
  • IRONdb
    • Getting Started
      • Installation
      • Configuration
      • Cluster Sizing
      • Command Line Options
      • ZFS Guide
    • Administration
      • Activity Tracking
      • Compacting Numeric Rollups
      • Migrating To A New Cluster
      • Monitoring
      • Operations
      • Rebuilding IRONdb Nodes
      • Resizing Clusters
    • API
      • API Specs
      • Data Deletion
      • Data Retrieval
      • Data Submission
      • Rebalance
      • State and Topology
    • Integrations
      • Graphite
      • Prometheus
      • OpenTSDB
    • Tools
      • Grafana Data Source
      • Graphite Plugin
      • IRONdb Relay
      • IRONdb Relay Release Notes
    • Metric Names and Tags
    • Release Notes
    • Archived Release Notes
  • Administration
    • E-Mail Configuration
    • Single Sign-On with SAML
    • Port Management
    • Audit Trail
      • Events Trail
      • Alerts Trail
Powered by GitBook
On this page
  • Key Terminology
  • Rules of Thumb
  • Storage Space
  • Sizing Example
  • Hardware Choices
  • Hardware Profiles

Was this helpful?

Edit on GitHub
Export as PDF
  1. IRONdb
  2. Getting Started

Cluster Sizing

PreviousConfigurationNextCommand Line Options

Last updated 22 days ago

Was this helpful?

This is intended as a general guide to determining how many nodes and how much storage space per node you require for your workload. Please if you have questions arising from your specific needs.

Key Terminology

  • T is the number of unique metric streams.

  • N is the number of nodes participating in the cluster.

  • W is the number of times a given measurement is stored across the cluster.

    • For example, if you have 1 GB of metric data, you must have W GB of storage space across the cluster.

The value of W determines the number of nodes that can be unavailable before metric data become inaccessible. A cluster with W write copies can survive W-1 node failures before a partial data outage will occur.

Metric streams are distributed approximately evenly across the nodes in the cluster. In other words, each node is responsible for storing approximately (T*W)/N metric streams. For example, a cluster of 4 nodes with 100K streams and W=2 would store about 50K streams per node.

Rules of Thumb

  • Nodes should be operated at no more than 70% capacity.

  • Favor ZFS striped mirrors over other pool layouts. This provides the highest performance in IOPS.

  • W must be >= 2

  • N must be >= W

  • W should be >= 3 when N >= 6

  • W should be >= 4 when N >= 100

Storage Space

The default configuration for the raw database is to collect data into shards (time buckets) of 1 week, and to retain those shards for 4 weeks before rolling them up into long-term storage. At 1-minute collection frequency, a single numeric stream would require approximately 118 KiB per 1-week shard, or 472 KiB total, before being rolled up to long-term storage.

These numbers represent uncompressed data. With our default LZ4 compression setting in ZFS, we see 3.5x-4x compression ratios for numeric data.

The following modeling is based on an observed distribution of all data types, in long-term storage, across many clients and may be adjusted from time to time. This would be in addition to the raw database storage above.

Minimum Resolution
Storage Space / Day
Storage Space / Year

10 seconds

120,000 bytes

43,020,000 bytes

1 minute

20,000 bytes

7,170,000 bytes

5 minute

3,800 bytes

1,386,000 bytes

All sizing above represents uncompressed data.

Sizing Example

Suppose we want to store 100,000 metric streams at 1-minute resolution for 5 years. We'd like to build a 4-node cluster with a W value of 2.

T=100,000
N=4
W=2

T * 7,170,000 (bytes/year/stream) * 5 years = 3,585,000,000,000 bytes

3,585,000,000,000 bytes / (1024^3) = 3338 GiB

T * 483,840 (bytes/4 weeks raw/stream) / (1024^3) = 45 GiB

( (3338+45) * W) / N = 1692 GiB per node

1692 GiB / 70% utilization = 2417 GiB of usable space per node

2417 GiB * 2 = 4834 GiB of raw attached storage in ZFS mirrors per node

Hardware Choices

Apica recommends server-class hardware for all production deployments. This includes, but is not limited to, features like ECC memory and hot-swappable hard drives.

In addition to the overall storage space requirements above, consideration must be given to the IOPS requirements. The minimum IOPS required is the primary write load of ingesting metric data (approximately 12 bytes per measurement point), but there is additional internal work such as parsing and various database accounting operations that can induce disk reads beyond the pure writing of measurement data. After initial ingestion there are other operations, such as searching, rollups, and maintenance activity like reconstitution and ZFS scrubbing that require additional IOPS. Ensure that the hardware you choose for your nodes has the capacity to allow for these operations without significantly impacting ongoing ingestion.

Hardware Profiles

The following are sample profiles to guide you in selecting the right combination of hardware and cluster topology for your needs.

Assumptions:

  • 10-second collection frequency

  • 4 weeks of near-term (full-resolution) storage

  • 2 years of historical data at 1-minute resolution

  • striped-mirror ZFS pool layout

Streams per 10sec
Write Copies
Total Streams
Node Count
Streams per Node
Physical CPU cores
RAM (GB)
7200rpm spindles

1MM

3

3MM

5

600K

12

128

6x 2T

10MM

3

30MM

15

2MM

24

256

24x 4T

100MM

3

300MM

75

4MM

36

384

45x 4T

The system stores three types of data: text, numeric (statistical aggregates), and histograms. Additionally there are two tiers of data storage: near-term and long-term. Near-term storage is called the and stores at full resolution (however frequently measurements were collected.) Long-term resolution is determined by the .

See for general advice.

Specifically, hardware RAID should be . ZFS should be given access to raw hard drive devices whenever possible.

ZFS's helps by absorbing some portion of the read load, so the more RAM available to the system, the better.

contact Apica
OpenZFS guidelines
avoided
ARC
raw database
rollup configuration