IBM logoEnterprise Cloud Management SupportContact Us
ArticlesArticles Most Popular ArticlesMost Popular Articles Most Helpful ArticlesMost Helpful Articles Submit A QuestionSubmit A Question
RSS Feeds
Skip Navigation
DrillDown Icon Table of Contents
DrillDown Icon Enterprise Cloud
DrillDown Icon Release Notes
DrillDown Icon Known Issues
DrillDown Icon Policies
DrillDown Icon Registration and Login
DrillDown Icon Infinicenter Console
DrillDown Icon Enterprise Cloud API
DrillDown Icon Best Practices
DrillDown Icon General
DrillDown Icon Resource Management
DrillDown Icon Processor
DrillDown Icon Memory
DrillDown Icon Networking
DrillDown Icon Timekeeping/Synchronization
DrillDown Icon FAQs
DrillDown Icon Troubleshooting
DrillDown Icon Enterprise Cloud Managed Edition
DrillDown Icon Sales and Support
DrillDown Icon Proprietary Statement
  Email This ArticlePrint PreviewPrint Current Article and All Sub-Articles
VMware Performance Tuning Best Practices - Networking

VMware Performance Tuning Best Practices

Before addressing any network performance optimization or issues, you must understand the physical aspects of the network. The following are some things to keep in mind.

  • What size packets are transmitted through the network?
  • Do the packets need to be fragmented or re-assembled along the transmission path?
  • The default virtual network adapter for guest operating systems are shown in the table.
  • Guest Operating System 32-bit x86 64-bit x64
    Blank Windows Intel E1000 Intel E1000
    Blank Linux® Flexible Intel E1000
    Template Windows VMXNet 3 VMXNet 3
    Template CentOS 5.x Intel E1000 Intel E1000
    Template CentOS 6.x Intel E1000 VMXNet 3
    Template Red Hat 5.x Intel E1000 Intel E1000
    Template Red Hat 6.x Intel E1000 VMXNet 3
    Template Ubuntu N/A VMXNet 3
  • In the configuration and hardware of Enterprise Cloud, the e1000 driver used on 64-bit machines can cause intermittent network performance issues. Contact IBM Global Support Services for any performance issues. If the e1000 driver is found to be the cause or possible cause, Global Support Services will perform this update.
  • The network speeds reported by the guest networking driver on the virtual machine do not necessarily reflect the actual capacity of the underlying physical network interface card.
  • In some cases, low throughput between virtual machines on the same host server may be caused by buffer overflows in the guest driver. Buffer overflows require the sender to retransmit data, thereby limiting bandwidth.
  • IBM suggests disabling TCP Offload (Checksum) due to the hardware and VMware configurations used.
  • IBM suggests disabling TCP Chimney due to the hardware and VMware configurations used.
Related Articles