VSP1999 esxtop for Advanced Users Name, Title, Company.

Slides:



Advertisements
Similar presentations
Housekeeping Utilities for VMware. 11 June Housekeeping is preparing meals for oneself and family and the managing of other domestic concerns.
Advertisements

Key Metrics for Effective Storage Performance and Capacity Reporting.
Capacity Planning in a Virtual Environment
High Availability Deep Dive What’s New in vSphere 5 David Lane, Virtualization Engineer High Point Solutions.
System Center 2012 R2 Overview
© 2014 VMware Inc. All rights reserved. Characterizing Cloud Management Performance Adarsh Jagadeeshwaran CMG INDIA CONFERENCE, December 12, 2014.
© 2010 VMware Inc. All rights reserved Confidential Performance Tuning for Windows Guest OS IT Pro Camp Presented by: Matthew Mitchell.
Copyright © 2014 EMC Corporation. All Rights Reserved. ESXi Host Installation and Integration for Block Upon completion of this module, you should be able.
© 2009 VMware Inc. All rights reserved vSphere Performance Best Practices Rob Moran Premier Services Engineer – VMware Global Support Services – Cork,
VSphere vs. Hyper-V Metron Performance Showdown. Objectives Architecture Available metrics Challenges in virtual environments Test environment and methods.
Managing the Capacity and Performance of a VMware Cluster environment Presented by: Pete Weilnau CTO PERFMAN
Managing storage requirements in VMware Environments October 2009.
© 2014 VMware Inc. All rights reserved. Performance Management Iwan ‘e1’ Rahabok Staff SE (Strategic Accounts) & CTO Ambassador
RDMA in Virtualized and Cloud Environments #OFADevWorkshop Aaron Blasius, ESXi Product Manager Bhavesh Davda, Office of CTO VMware.
Virtualization Infrastructure Administration Cluster Jakub Yaghob.
VSP3868 VMware vStorage Best Practices Name, Title, Company.
VSP1700 VMware vSphere 5.0 Storage Features Name, Title, Company.
Scalability Module 6.
Virtualization Performance H. Reza Taheri Senior Staff Eng. VMware.
VMware vSphere 4 Introduction. Agenda VMware vSphere Virtualization Technology vMotion Storage vMotion Snapshot High Availability DRS Resource Pools Monitoring.
1 Some Context for This Session…  Performance historically a concern for virtualized applications  By 2009, VMware (through vSphere) and hardware vendors.
Module 18 Monitoring SQL Server 2008 R2. Module Overview Monitoring Activity Capturing and Managing Performance Data Analyzing Collected Performance Data.
Module 10 Configuring and Managing Storage Technologies.
13-1 Veeam Monitor Demo Topic 2: VM Performance Monitoring 3.
John Paul Enterprise Hosting Services Research and Development
How to Resolve Bottlenecks and Optimize your Virtual Environment Chris Chesley, Sr. Systems Engineer
Hands-On Virtual Computing
Microsoft Virtual Academy. 2 Competitive Advantages I - Core VirtualizationII - Private Cloud.
Sources of Performance Problems
Don’t Panic DBAs – Databases On VMware Made Easy Kathy Gibbs Senior Database Administrator, CONFIO Software.
Xangati Summer Blockbuster Launching 8/23/11. © 2011 Xangati, Inc. │ Company Confidential │ Slide 2 What’s New Dramatic enhancements –Xangati Management.
Improving Disk Latency and Throughput with VMware Presented by Raxco Software, Inc. March 11, 2011.
© 2014 VMware Inc. All rights reserved My Slides from VMware vSphere: Optimize and Scale.
Session objectives Discuss whether or not virtualization makes sense for Exchange 2013 Describe supportability of virtualization features Explain sizing.
SRM Technical Presentation Mornay Van Der Walt Sr. Solutions Architect.
The Top 10 Virtual Configurations You SHOULDN'T Implement Tom Howarth Owner PlanetVM.NET Pre-requisites for this presentation: 1) General understanding.
11 MANAGING PERFORMANCE Chapter 16. Chapter 16: MANAGING PERFORMANCE2 OVERVIEW  Optimize memory, disk, and CPU performance  Monitor system performance.
VSP3866 Performance Best Practices and Troubleshooting Name, Title, Company.
VMware vSphere Configuration and Management v6
VMWare Troubleshooting Basics Lewis Talley. Memory ESXi incorporates a number of memory management techniques such as (transparent page sharing, Ballooning,
MEMORY RESOURCE MANAGEMENT IN VMWARE ESX SERVER 김정수
Peter Mattei HP Storage Consultant 16. May 2013
Using Heat to Deploy and Manage Applications in OpenStack Trevor Roberts Jr, VMware, Inc. CNA1763 #CNA1763.
Modeling Virtualized Environments in Simalytic ® Models by Computing Missing Service Demand Parameters CMG2009 Paper 9103, December 11, 2009 Dr. Tim R.
Alignment Overview 1 NetApp Public. What is Misalignment?  Misalignment is a condition where a single client IO operation results in multiple shared.
Deployment options for Fluid Cache for SAN with VMware
What's New in Windows Server Hyper-V
AP02 NFS & iSCSI: Performance Characterization and Best Practices in ESX 3.5 Priti Mishra MTS, VMware Bing Tsai Sr. R&D Manager, VMware.
Capacity Planning in a Virtual Environment Chris Chesley, Sr. Systems Engineer
1 Best Practices for Monitoring Databases on VMware Dean Richards Senior DBA, Confio Software.
REMINDER Check in on the COLLABORATE mobile app Best Practices for Oracle on VMware - Deep Dive Darryl Smith Chief Database Architect Distinguished Engineer.
Module Objectives At the end of the module, you will be able to:
REMINDER Check in on the COLLABORATE mobile app Oracle Performance Management with vCenter Operations Manager and Oracle Enterprise Manager (OEM) Adapter.
1 SQL Server on VMware? Rob Mandeville Senior DBA, Confio Software 1 Virtualizing Our Environment: Lessons Learned Rob Mandeville.
Successfully Virtualizing SQL Server on vSphere
VMware vSphere 4.0 Preventive & Maintenance. Agenda Preventive & Maintenace Storage/Datastore ESX Host Performance Monitoring ESX Maintenance User Access.
1 SQL Server on VMware? Rob Mandeville Senior DBA, Confio Software.
vSphere 6 Foundations Beta Question Answer
VSPHERE 6 FOUNDATIONS BETA Study Guide QUESTION ANSWER
OnCommand Insight Host File System Utilization
Don’t Panic, DBAs! Databases on Vmware made easy Janis Griffin Senior DBA, Confio Software 1.
SQL Server Monitoring Overview
Optimizing SQL Server Performance in a Virtual Environment
Comparison of the Three CPU Schedulers in Xen
Key Metrics and Practices for Monitoring Virtualization Platforms
If vSAN Powered The Matrix
VMware vRealize® Operations™ Management Pack for Pure Storage
Specialized Cloud Architectures
VMware vSphere 4.0 © Capacity Management “Now the Dust is Settling”
Presentation transcript:

VSP1999 esxtop for Advanced Users Name, Title, Company

2 Disclaimer  This session may contain product features that are currently under development.  This session/overview of the new technology represents no commitment from VMware to deliver these features in any generally available product.  Features are subject to change, and must not be included in contracts, purchase orders, or sales agreements of any kind.  Technical feasibility and market demand will affect final delivery.  Pricing and packaging for any new technologies or features discussed or presented have not been determined.

3 Before we dive in…

4 vSphere Performance Management Tools (1 of 2)  vCenter Alarms Relies on static thresholds Alarm trigger may not always indicate an actual performance problem  vCenter Operations Aggregates metrics into workload, capacity and health scores Relies on dynamic thresholds  vCenter Charts Historical trends Post mortem analysis, comparing metrics

5 vSphere Performance Management Tools (2 of 2)  esxtop/resxtop For live troubleshooting and root cause analysis esxplot, perfmon and other tools can be used for offline analysis

6 Performance Snapshot  For complicated problems Technical support may ask you for a performance snapshot for offline analysis

7 About This Talk This talk will focus on the esxtop counters using illustrative examples esxtop manual: Interpreting esxtop statistics Previous vmworld talks: VMworld VMworld VMworld

8 esxtop Screens Screens c: cpu (default) m: memory n: network d: disk adapter u: disk device (added in ESX 3.5) v: disk VM (added in ESX 3.5) i: Interrupts (added in ESX 4.0) p: power management (added in ESX 4.1) VMkernel CPU Scheduler Memory Scheduler Virtual Switch vSCSI c, i, pmd, u, vn VM

9 New counters in ESX 5.0

10 vCPU and VM Count World, VM and vCPU count

11 VMWAIT %WAIT - %IDLE More about this later…

12 CPU Clock Frequency in Different P-states CPU clock frequency in different P-states P-states are visible to ESX only when power management setting in the BIOS is set to “OS Controlled” More about this later…

13 Failed Disk IOs Failed IOs are now accounted separately from successful IOs

14 VAAI: Block Deletion Operations New set of VAAI stats for tracking block deletion VAAI : vStorage API for Array Integration

15 Low-Latency Swap (Host Cache) Low-Latency (SSD) Swap

16 Understanding CPU counters

17 CPU State Times IDLE WAIT SWPWT blocked VMWAIT RUN RDY MLMTD Elapsed Time CSTP Guest I/O

18 CPU Usage Accounting USED = RUN RUN SYS OVRLP System Service USED could be < RUN if the CPU is not running at its rated clock frequency + SYS - OVRLP

19 Impact of P-States P-States%RUN%UTIL%USED P0 (2400 Mhz)100% P1 (1700 Mhz)100% 70% P2 (1200 Mhz)100% 50% P3 (800 Mhz)100% 33% %USED: CPU usage with reference to rated base clock frequency %UTIL: CPU utilization with reference to current clock frequency %RUN: CPU occupancy time

20 Factors That Affect VM CPU Usage Accounting  Chargeback %SYS time  CPU frequency scaling Turbo boost USED > (RUN – SYS) Power management USED < (RUN – SYS)  Hyperthreading

21 Poor performance due to power management

22 CPU Usage: With CPU Clock Frequency Scaling VM is running all the time but uses only 75% of the clock frequency. Power savings enabled in BIOS.

23 Poor performance due to core sharing

24 Hyperthreading PCPU Core HT Off HT On ESX scheduler tries to avoid sharing the same core

25 CPU Usage: Without Core Sharing Two VMs running on different cores USED is > 100 due to Turbo Boost

26 CPU Usage: With Core Sharing Two VMs sharing the same core %LAT_C counter shows the CPU time unavailable to due to core sharing

27 Performance Impact of Swapping

28 Performance Impact of Swapping Some swapping activity Time spent in blocked state due to swapping

29 How to identify storage connectivity issues

30 NFS Connectivity Issue (1 of 2) I/O activity to NFS datastore System time charged for NFS activity

31 NFS Connectivity Issue (2 of 2) VM blocked, connectivity lost to NFS datastore No I/O activity on the NFS datastore VM is not using CPU

32 Poor performance during snapshot revert

33 Snapshot Revert Reads in MB from VM check point file Not accounted in VM disk I/O traffic But can be seen in adapter view

34 Wide-NUMA behavior in ESX 5.0

35 Wide-NUMA Support in ESX x 16G NUMA Nodes 24G vRAM exceeds one NUMA node 1 home NUMA node assigned 1 vCPU VM

36 Wide-NUMA Support in ESX vCPUs, exceeds one NUMA node 2 x 16G NUMA Nodes 24G vRAM exceeds one NUMA node 2 Home NUMA nodes assigned

37 Network packet drops due to CPU resource issue

38 Network Packet Drops Max CPU limited Excessive Ready time Packet drops at the vSwitch

39 Understanding esxtop disk counters

40 Disk I/O Latencies Application Guest OS Application Guest OS ESX Storage Stack ESX Storage Stack VMM Driver KAVG iostat/perfmon DAVG GAVG QAVG KAVG = GAVG – DAVG Array SP Fabric vSCSI HBA Time spent in ESX storage stack is minimal, for all practical purposes KAVG ~= QAVG In a well configured system QAVG should be zero

41 Disk I/O Queuing GQLEN – Guest Queue AQLEN – Adapter Queue WQLEN – World Queue D(/L)QLEN – LUN Queue SQLEN – Array SP Queue DQLEN AQLEN SQLEN GQLEN D(/L)QLEN can change dynamically when SIOC is enabled Reported in esxtop Application Guest OS Application Guest OS VMM Driver Array SP Fabric vSCSI HBA WQLEN ESX Storage Stack ESX Storage Stack

Max IOPS = Max Outstanding IOs / Latency For example, with 64 outstanding IOs and 4msec average latency Max IOPS = 64/4ms = 16,000

43 Identifying Queue bottlenecks

44 Disk I/O Queuing – Device Queue Device Queue length, modifiable via driver parameter IO commands in Flight IO commands waiting in Queue

45 Disk I/O Queuing – World Queue World ID World Queue Length – modifiable Disk.SchedNumReq uestOutstanding

46 Device Queue Full KAVG is non-zero Queuing issue LUN Queue depth is IOs in flight and 32 Queued

47 Disk I/O Queuing – Adapter Queue Different adapters have different queue size Adapter Queue can come into play if the total outstanding IOs exceeds the adapter queue

48 A few takeaways…

49 Takeaways  esxtop is great for troubleshooting a diverse set of problems  You can do root-cause analysis by co-relating statistics from different screens  Good understanding of the counters is essential for accurate troubleshooting  esxtop is not designed for performance management  There are various other tools for vSphere performance management

50 Thank You!