Top Banner
Lars Ejskjaer Greg Ferguson TR 1-470 Performance Analysis for Dummies
38

Lars Ejskjaer Greg Ferguson TR 1-470 Performance Analysis for Dummies.

Mar 31, 2015

Download

Documents

Savana Hood
Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Page 1: Lars Ejskjaer Greg Ferguson TR 1-470 Performance Analysis for Dummies.

Lars EjskjaerGreg Ferguson

TR 1-470

Performance Analysis for Dummies

Page 2: Lars Ejskjaer Greg Ferguson TR 1-470 Performance Analysis for Dummies.

2

Understanding Performance Analysis Can Help You Sell

− Gain better understanding of your customers environment

− Grow awareness to possible system bottleneck areas

− Understand changes that can enhance your customers overall satisfaction

Getting Started…

Simple Analysis (1, 2, 3)

Valuable Tools and Resources

Agenda

Page 3: Lars Ejskjaer Greg Ferguson TR 1-470 Performance Analysis for Dummies.

3

”My storage is slow…”

The Customer Problem

Page 4: Lars Ejskjaer Greg Ferguson TR 1-470 Performance Analysis for Dummies.

4

Guide the customer to best practices

Recommend solutions

− Administrative

− Product

Provide advice in the context of their environment

Your Goal

Page 5: Lars Ejskjaer Greg Ferguson TR 1-470 Performance Analysis for Dummies.

5

Understanding of how the customer’s environment was set up

Ability to identify missed best practices

− Administrative

− Performance

Ability to identify common performance issues

What You Will Need To Know

Page 6: Lars Ejskjaer Greg Ferguson TR 1-470 Performance Analysis for Dummies.

6

Getting Started

Page 7: Lars Ejskjaer Greg Ferguson TR 1-470 Performance Analysis for Dummies.

7

Easily Collect Performance Data - Perfstathttps://communities.netapp.com/docs/DOC-16209

Pro Tip:

Perform multiple smaller iterations versus one larger iteration for better visibility

Page 8: Lars Ejskjaer Greg Ferguson TR 1-470 Performance Analysis for Dummies.

8

Loading Data into LatX for Analysis https://latx.netapp.com/

Page 9: Lars Ejskjaer Greg Ferguson TR 1-470 Performance Analysis for Dummies.

9

Find and View the Perfstat

NetApp Confidential – Limited Use

Page 10: Lars Ejskjaer Greg Ferguson TR 1-470 Performance Analysis for Dummies.

10

Finding Specific Data

Pro Tip

Use PRESTATS iteration 1 for configuration information

Use POSTSTATS for performance measurements

Page 11: Lars Ejskjaer Greg Ferguson TR 1-470 Performance Analysis for Dummies.

11

Understand Configuration

− Aggregates

− Volumes

− Look for configuration errors

Analyze Performance

− System

− Disk

− Flash

Make Recommendations

Analysis Strategy

Page 12: Lars Ejskjaer Greg Ferguson TR 1-470 Performance Analysis for Dummies.

12

Disk Configuration

The Simple Analysis Part 1

Page 13: Lars Ejskjaer Greg Ferguson TR 1-470 Performance Analysis for Dummies.

13

Disk Types on the Controller

Pro Tip

Common disk types today: SAS, BSAS, MSATA

Prestats - sysconfig -r

Page 14: Lars Ejskjaer Greg Ferguson TR 1-470 Performance Analysis for Dummies.

14

RAID Groups

Pro Tip

Avoid unbalanced raid-groups in aggregates!

Poststats – statit

Page 15: Lars Ejskjaer Greg Ferguson TR 1-470 Performance Analysis for Dummies.

15

32-bit vs 64-bit Aggregates

Pro Tip

New features work best (require) with 64-bits aggregates Using one aggregate type makes the customer operations easier

Prestats – aggr status -v

Page 16: Lars Ejskjaer Greg Ferguson TR 1-470 Performance Analysis for Dummies.

16

Aggregate UtilizationPoststats - df –A -h

Pro Tip

An aggregate which is 80% full, should be monitored Aggregates over +90% full could impact performance

Page 17: Lars Ejskjaer Greg Ferguson TR 1-470 Performance Analysis for Dummies.

17

Aggregate Snapshot Copies Prestats - df –A –h, snap status -A & aggr status –v

NetApp Confidential – Limited Use

Pro Tip

Only SyncMirror and MetroCluster use aggregate snapshots

If not in use: - Remove schedule- Release space reservation

Page 18: Lars Ejskjaer Greg Ferguson TR 1-470 Performance Analysis for Dummies.

18

Volumes

The Simple Analysis Part 2

Page 19: Lars Ejskjaer Greg Ferguson TR 1-470 Performance Analysis for Dummies.

19

Volume Space UtilizationPoststats - df & lun stat –v all (or vol status –v)

Pro Tip

Databases like Oracle initialize their data files or data could be static so it could be fine that the volume is almost full

Page 20: Lars Ejskjaer Greg Ferguson TR 1-470 Performance Analysis for Dummies.

20

DeduplicationPoststats- stats perfstat_sis

Pro Tip

Savings less than 6-8% are just using resources without a real effect, unless data is static, turn it off and save resources!

Page 21: Lars Ejskjaer Greg Ferguson TR 1-470 Performance Analysis for Dummies.

21

Deduplication RuntimesPoststats - sis status -l

Pro Tip

Deduplication is a low priority process but it still occupies system resourcesWork to understand run times to smooth system scheduling for better performance

Page 22: Lars Ejskjaer Greg Ferguson TR 1-470 Performance Analysis for Dummies.

22

MisalignmentPoststats - nfsstat –d & lun stat –v all

Pro Tip

Understand what is in these files/LUNsLogfiles are often ”misaligned”Verify that virtual machines are aligned

Page 23: Lars Ejskjaer Greg Ferguson TR 1-470 Performance Analysis for Dummies.

23

System Performance

The Simple Analysis Part 3

Page 24: Lars Ejskjaer Greg Ferguson TR 1-470 Performance Analysis for Dummies.

24

ONTAP breaks work into groups of processes called domains

ONTAP schedules work across CPU cores as IT sees best

This can be seen in Sysstat –M

Detailed analysis of this is an advanced topic

What Are Domains In Data ONTAP?

Page 25: Lars Ejskjaer Greg Ferguson TR 1-470 Performance Analysis for Dummies.

25

CPU UtilizationPoststats - sysstatM.out

Pro Tip:

Average CPU utilization >70% depicts a very busy controllerCPU Utilization is a generally poor indicator of performanceLook at AVG CPU – Single CPU (thread) utilization is very informative

Page 26: Lars Ejskjaer Greg Ferguson TR 1-470 Performance Analysis for Dummies.

26

Writing Data to Disk - CP Type & TimePoststats – sysstat_1sec.out

Pro Tip

Deferred Back-to-back CP’s are performance killers (type #)- Data can’t get to disk fast enoughInvestigate (ignoring the CPU utilization):- Mis-alignment- Disk over commitedSolutions:- Move load to another controller/aggregate- Add disks/Flash Cache

Page 27: Lars Ejskjaer Greg Ferguson TR 1-470 Performance Analysis for Dummies.

27

Aggregate Disk UtilizationPoststats - statit

Pro Tip

Analyze performance impact based on drive utilization (by drive type)- SATA drives > 50% = busy- SAS drives > 60% = busyStatit will give clues about where to move load to

Page 28: Lars Ejskjaer Greg Ferguson TR 1-470 Performance Analysis for Dummies.

28

Active VolumesPerfsys Report

Pro Tip

Map volumes to aggregates (aggr status –v) Identify workloads to move

Page 29: Lars Ejskjaer Greg Ferguson TR 1-470 Performance Analysis for Dummies.

29

FlashCachePerfsys Report

Pro Tip

Verify that the system is benefiting from the use of FlashCacheUse PCS and perfstat to verify a customers gains by use of FlashCache

Page 30: Lars Ejskjaer Greg Ferguson TR 1-470 Performance Analysis for Dummies.

30

Latency in the EnvironmentPoststats - stats perfstat_cifs/_nfs/_fcp

Pro Tip

High latency = performance impactLatency requirements vary by applicatonAnalyze the workload and- Add Disk- Add FlashCache- Upgrade the Controllers

Page 31: Lars Ejskjaer Greg Ferguson TR 1-470 Performance Analysis for Dummies.

31

We reviewed

− High disk I/O’s

− Busy volumes

− Disk configuration issues

− Average CPU utilization

− Potential Flash Cache benefits

− Mis-alignments

Review of Findings

Page 32: Lars Ejskjaer Greg Ferguson TR 1-470 Performance Analysis for Dummies.

32

Resolve mis-alignments

Consider moving busy volumes

Add drives and reallocate to even out raid groups

Add Flash Cache

Upgrade Controllers

Add more Controllers within Clustered Data ONTAP

Recommendations

Page 33: Lars Ejskjaer Greg Ferguson TR 1-470 Performance Analysis for Dummies.

33

Don’t be afraid – performance is no longer such a mystery!

Now YOU Can Better Understand System Performance

Have FUN!

Most importantly, monitor disk utilization!

Page 34: Lars Ejskjaer Greg Ferguson TR 1-470 Performance Analysis for Dummies.

34

The Community site

− http://communities.netapp.com

ONTAP documentation (particularly ONTAP Command ref)

− http://support.netapp.com

Latx – your analysis tool

− http://latx.netapp.com

Important Resources

Page 35: Lars Ejskjaer Greg Ferguson TR 1-470 Performance Analysis for Dummies.

35

Complimentary Sessions

TR-1-123 Sizing, Designing, and Presenting a NetApp Solution

TR-2-717 Using NetApp Tech Tools to Create Winning Proposals and Tech Refreshes

TR-2-315 A Field Guide to Sizing - Part 1

TR-3-317 A Field Guide to Sizing – Part 2

Page 36: Lars Ejskjaer Greg Ferguson TR 1-470 Performance Analysis for Dummies.

36

Take an Insight Survey!

1) Click on the session number in your agenda. 2) Click on the Surveys Button. 3) Follow the prompts, complete the survey and submit!

Complete this survey by 7PM and be entered to win one of the following prizes: 1 iPad Mini 16GB Wifi 1 Bose SoundLink Mini Bluetooth 2 Jawbone Up Wristbands (Activity Tracker) 4 NetApp Signature Dry Zone Caps

NEW!

Went to a different session? Need a translated survey? Visit the main survey page in the mobile app to take a daily survey – available in English, Chinese, Japanese and Korean.

Page 37: Lars Ejskjaer Greg Ferguson TR 1-470 Performance Analysis for Dummies.

37

Facebook

www.facebook.com /NetAppInsightAmericas

www.facebook.com /NetAppInsightEMEA

Twitter

www.twitter.com / InsightAmericas

www.twitter.com / InsightEMEA

Tweet friends with #NTAPInsight

Page 38: Lars Ejskjaer Greg Ferguson TR 1-470 Performance Analysis for Dummies.

38

© 2013 NetApp, Inc. All rights reserved. No portions of this document may be reproduced without prior written consent of NetApp, Inc. Specifications are subject to change without notice. NetApp, the NetApp logo, and Go further, faster, are trademarks or registered trademarks of NetApp, Inc. in the United States and/or other countries. All other brands or products are trademarks or registered trademarks of their respective holders and should be treated as such.