JavaScript is required to for searching.
Skip Navigation Links
Exit Print View
Sun ZFS Storage 7000 System Administration Guide
search filter icon
search icon

Document Information

Preface

1.  Introduction

2.  Status

3.  Configuration

4.  Services

5.  Shares

6.  Analytics

Analytics

Introduction

Concepts

Analytics

Drilldown Analysis

Statistics

Datasets

Actions

Worksheets

Statistics

Introduction

Descriptions

Analytics

Advanced Analytics

Default Statistics

Tasks

Statistics Tasks

CPU Percent utilization

CPU: Percent Utilization

Example

When to check

Breakdowns

Further Analysis

Details

Cache ARC accesses

Cache: ARC accesses

When to check

Breakdowns

Details

Metadata

Prefetch

Further Analysis

Cache L2ARC IO bytes

Cache: L2ARC I/O bytes

When to check

Breakdowns

Further Analysis

Cache L2ARC accesses

Cache: L2ARC accesses

When to check

Breakdowns

Further Analysis

Data Movement NDMP bytes transferred tofrom disk

Data Movement: NDMP bytes transferred to/from disk

When to check

Breakdowns

Further Analysis

Data Movement NDMP bytes transferred tofrom tape

Data Movement: NDMP bytes transferred to/from tape

When to check

Breakdowns

Further Analysis

Data Movement Shadow migration bytes

Data Movement: Shadow migration bytes

When to check

Breakdowns

Further Analysis

Data Movement Shadow migration ops

Data Movement: Shadow migration ops

When to check

Breakdowns

Further Analysis

Data Movement Shadow migration requests

Data Movement: Shadow migration requests

When to check

Breakdowns

Further Analysis

Disk Disks

Disk: Disks

When to check

Breakdowns

Interpretation

Further Analysis

Details

Disk IO bytes

Disk: I/O bytes

When to check

Breakdowns

Further Analysis

Disk IO operations

Disk: I/O operations

When to check

Breakdowns

Further Analysis

Network Device bytes

Network: Device bytes

When to check

Breakdowns

Further Analysis

Network Interface bytes

Network: Interface bytes

Example

When to check

Breakdowns

Further Analysis

Protocol SMB operations

Protocol: SMB operations

Example

When to check

Breakdowns

Further Analysis

Protocol Fibre Channel bytes

Protocol: Fibre Channel bytes

Example

When to check

Breakdowns

Further Analysis

Protocol Fibre Channel operations

Protocol: Fibre Channel operations

Example

When to check

Breakdowns

Further Analysis

Protocol FTP bytes

Protocol: FTP bytes

Example

When to check

Breakdowns

Further Analysis

Protocol HTTPWebDAV requests

Protocol: HTTP/WebDAV requests

When to check

Breakdowns

Further Analysis

Protocol iSCSI bytes

Protocol: iSCSI bytes

When to check

Breakdowns

Further Analysis

Protocol iSCSI operations

Protocol: iSCSI operations

When to check

Breakdowns

Further Analysis

Protocol NFSv2 operations

Protocol: NFSv2 operations

Example

When to check

Breakdowns

Further Analysis

Protocol NFSv3 operations

Protocol: NFSv3 operations

When to check

Breakdowns

Further Analysis

Protocol NFSv4 operations

Protocol: NFSv4 operations

Example

When to check

Breakdowns

Further Analysis

Protocol SFTP bytes

Protocol: SFTP bytes

Example

When to check

Breakdowns

Further Analysis

Protocol SRP bytes

Protocol: SRP bytes

Example

When to check

Breakdowns

Further Analysis

Protocol SRP operations

Protocol: SRP operations

Example

When to check

Breakdowns

Further Analysis

CPU CPUs

CPU: CPUs

When to check

Breakdowns

Details

CPU Kernel spins

CPU: Kernel spins

When to check

Breakdowns

Cache ARC adaptive parameter

Cache: ARC adaptive parameter

When to check

Breakdowns

Cache ARC evicted bytes

Cache: ARC evicted bytes

When to check

Breakdowns

Cache ARC size

Cache: ARC size

When to check

Breakdowns

Cache ARC target size

Cache: ARC target size

When to check

Breakdowns

Cache DNLC accesses

Cache: DNLC accesses

When to check

Breakdowns

Cache DNLC entries

Cache: DNLC entries

When to check

Breakdowns

Cache L2ARC errors

Cache: L2ARC errors

When to check

Breakdowns

Cache L2ARC size

Cache: L2ARC size

When to check

Breakdowns

Data Movement NDMP file system operations

Data Movement: NDMP file system operations

When to check

Breakdowns

Data Movement NDMP jobs

Data Movement: NDMP jobs

When to check

Breakdowns

Disk Percent utilization

Disk: Percent utilization

When to check

Breakdowns

Notes

Disk ZFS DMU operations

Disk: ZFS DMU operations

When to check

Breakdowns

Disk ZFS logical IO bytes

Disk: ZFS logical I/O bytes

When to check

Breakdowns

Disk ZFS logical IO operations

Disk: ZFS logical I/O operations

When to check

Breakdowns

Memory Dynamic memory usage

Memory: Dynamic memory usage

When to check

Breakdowns

Memory Kernel memory

Memory: Kernel memory

When to check

Breakdowns

Memory Kernel memory in use

Memory: Kernel memory in use

When to check

Breakdowns

Memory Kernel memory lost to fragmentation

Memory: Kernel memory lost to fragmentation

When to check

Breakdowns

Network IP bytes

Network: IP bytes

When to check

Breakdowns

Network IP packets

Network: IP packets

When to check

Breakdowns

Network TCP bytes

Network: TCP bytes

When to check

Breakdowns

Network TCP packets

Network: TCP packets

When to check

Breakdowns

System NSCD backend requests

System: NSCD backend requests

When to check

Breakdowns

System NSCD operations

System: NSCD operations

When to check

Breakdowns

Open Worksheets

Worksheets

Graph

Quantize Plot

Show Hierarchy

Common

Background Patterns

Saving a Worksheet

Toolbar Reference

CLI

Tips

Tasks

BUI

Saved Worksheets

Introduction

Properties

BUI

CLI

Datasets

Introduction

BUI

CLI

Viewing available datasets

Reading datasets

Suspending and Resuming all datasets

Discarding Data in a Dataset

7.  Integration

Glossary

CPU Percent utilization

CPU: Percent Utilization

This shows the average utilization of the appliance CPUs. A CPU may be a core on a socket or a hardware thread; the number and type can be seen under Hardware. For example, a system may have four sockets of quad-core CPUs, meaning there are 16 CPUs available to the appliance. The utilization shown by this statistic is the average across all CPUs.

The appliance CPUs can reach 100% utilization, which may or may not be a problem. For some performance tests the appliance is delibrately driven to 100% CPU utilization to measure it at peak performance.

Example

This example shows CPU: Percent utilization broken down by CPU mode, while the appliance served over 2 Gbytes/sec of cached data over NFSv3:

image

An average of 82% utilization suggests that there could be more headroom available, and that appliance may be able to serve more than 2 Gbytes/sec (it can). (The breakdowns only add to 81%; the extra 1% is due to rounding.)

The high level of CPU utilization does mean that overall latency of NFS operations may increase, which can be measured by Protocol: NFSv3 operations broken down by latency, as operations may be waiting for CPU resources more often.

When to check

When searching for system bottlenecks. This may also be checked when enabling features that consume CPU, such as compression, to gauge the CPU cost of that feature.

Breakdowns

Available breakdowns of CPU Percent utilization:

Breakdown
Description
CPU mode
Either user or kernel. See the CPU modes table below.
CPU identifier
Numeric operating system identifier of the CPU.
application name
Name of the application which is on-CPU.
process identifier
Operating system process ID (PID).
user name
Name of the user who owns the process or thread which is consuming CPU.

The CPU modes are:

CPU mode
Description
user
This is a user-land process. The most common user-land process consuming CPU is akd, the appliance kit daemon, which provides administrative control of the appliance.
kernel
This is a kernel-based thread which is consuming CPU. Many of the appliance services are kernel-based, such as NFS and SMB.

Further Analysis

A problem with this CPU utilization average is that it can hide issues when a single CPU is at 100% utilization, which may happen if a single software thread is saturated with work. Use the Advanced Analytic CPU: CPUs broken down by percent utilization, which represents utilization as a heat map of CPUs, allowing a single CPU at 100% to be easily identified.

Details

CPU utilization represents the time spent processing CPU instructions in user and kernel code, that are not part of the idle thread. Instruction time includes stall cycles on the memory bus, so high utilization can be caused by the I/O movement of data.