SlideShare a Scribd company logo
Addressing data plane performance measurement on OpenStack clouds using VMTP
OpenStack summit Vancouver is fast approaching and I for one can’t wait to see how
much OpenStack has progressed from Juno to Kilo. I expect to see even more momentum with
new companies being added to the OpenStack community, continuing to drive the industry
acceptance momentum of OpenStack. While a lot of good stuff is happening from a
functionality (features) and new projects standpoint, being able to systematically measure
performance across the major components still remains largely a work in progress. While Nova
(Compute) and Swift (Object Storage) continue to mature rapidly with good work being done by
many in the OpenStack community around performance measurement, Neutron (Networking)
continues to lag.
Prior to the Juno summit in Paris last November, there was intent in the OpenStack
community to move away from Nova networking onto Neutron where there is significantly
more functionality and scale to be had. But there are many challenges that are preventing this
migration from happening. Primary among those challenges is the inability to easily measure
performance on Neutron to ensure that there isn’t significant performance degradation as a
result of the move from Nova networking to Neutron. Cisco is proactively addressing the gap of
performance measurement on Neutron by releasing in Stackforge an open source data plane
performance measurement tool called VMTP (VM Throughput Performance). It is heartening to
see that others in the community are also providing tools for data plane measurement such as
the recently released “shaker”.
VMTP addresses the need for a quick, simple and automatable way to get VM-level or host-
level single-flow throughput and latency numbers from any OpenStack cloud, while also taking
into account various Neutron topologies. VMTP can also easily check whether certain
OpenStack configuration options, Neutron plug-ins perform to expectation or if there is any
data path impact for upgrading to a different OpenStack release.
VMTP is a small python application that will automatically perform ping connectivity, round
trip time measurement (latency) and TCP/UDP throughput measurement for the following
East/West flows on any OpenStack deployment:
 VM to VM same network (private fixed IP, flow #1)
 VM to VM different network using fixed IP (same as intra-tenant L3 fixed IP, flow #2)
 VM to VM different network using floating IP and NAT (same as floating IP inter-tenant
L3, flow #3)
In addition VMTP can also test for the following traffic scenarios
 When an external Linux host is available for testing North/South flows:
 External host/VM download and upload throughput/latency (L3/floating IP, flow #4
and #5)
 Optionally, when SSH login to any Linux host (native or virtual) is available:
o Host to host process-level throughput/latency (intra-node and inter-node)
VMTP can also extract automatically CPU usage from all native hosts in the cloud during the
throughput tests, provided the Ganglia monitoring service (gmond) is installed and enabled on
those hosts.
For VM-related flows, VMTP will automatically create the necessary OpenStack
resources (router, networks, subnets, key pairs, security groups, test VMs) using the public
OpenStack API, install the test tools then orchestrate them to gather the throughput
measurements then cleanup all related resources before exiting. VMTP has been architected to
run independently of Heat as we’ve seen that most deployments in the field don’t have Heat
also installed.
VMTP measures true north/south traffic via a client app that run outside the cloud.
Additional benefits of using VMTP are:
 A hook to Ganglia monitoring to capture host level system metrics during test
 Flow measurement chaining which results in faster runs (e.g. VMTP chains all client
VM positions for different flows with the same server VM, which you can't do with
Heat. With Heat you need to tear down and rebuild the setup/server for each flow)
 Results stored directly in MongoDB
 Auto extraction of OpenStack versions, encapsulation and L2 agent types and
versions
 Select special network interfaces (useful for VMs attached to multiple networks)
 SR-IOV and IPv6 support
 Detailed online documentation @ http://vmtp.readthedocs.org/en/latest/
Finally VMTP also supports a quick way of creating charts from multiple run JSON
results so you can easily view and consume the results of multiple runs. This new
feature (genchart.py) takes one or more VMTP JSON files as input and generates a
static HTML file. The --browser option allows the tool to directly open the generated
HTML file in the user's default browser. There is no need for any additional HTTP
server since the html file is self-contained and the browser will automatically load
the required JavaScript libraries.
I hope you enjoyed learning about what the VMTP tool can offer and hope you
join in making it even better by contributing to the code at:
http://vmtp.readthedocs.org/en/latest/contributing.html#contribute-to-vmtp

More Related Content

What's hot

Flink Forward Berlin 2017: Aljoscha Krettek - Talk Python to me: Stream Proce...
Flink Forward Berlin 2017: Aljoscha Krettek - Talk Python to me: Stream Proce...Flink Forward Berlin 2017: Aljoscha Krettek - Talk Python to me: Stream Proce...
Flink Forward Berlin 2017: Aljoscha Krettek - Talk Python to me: Stream Proce...
Flink Forward
 
Weave Cortex: Multi-tenant, horizontally scalable Prometheus as a Service
Weave Cortex: Multi-tenant, horizontally scalable Prometheus as a ServiceWeave Cortex: Multi-tenant, horizontally scalable Prometheus as a Service
Weave Cortex: Multi-tenant, horizontally scalable Prometheus as a Service
Weaveworks
 
Neutron upgrades
Neutron upgradesNeutron upgrades
Neutron upgrades
Victor Morales
 
Prometheus workshop
Prometheus workshopPrometheus workshop
Prometheus workshop
OpsTree solutions
 
OSMC 2019 | Monitoring Cockpit for Kubernetes Clusters by Ulrike Klusik
OSMC 2019 | Monitoring Cockpit for Kubernetes Clusters by Ulrike KlusikOSMC 2019 | Monitoring Cockpit for Kubernetes Clusters by Ulrike Klusik
OSMC 2019 | Monitoring Cockpit for Kubernetes Clusters by Ulrike Klusik
NETWAYS
 
Securing & Enforcing Network Policy and Encryption with Weave Net
Securing & Enforcing Network Policy and Encryption with Weave NetSecuring & Enforcing Network Policy and Encryption with Weave Net
Securing & Enforcing Network Policy and Encryption with Weave Net
Luke Marsden
 
Monitoring on Kubernetes using prometheus
Monitoring on Kubernetes using prometheusMonitoring on Kubernetes using prometheus
Monitoring on Kubernetes using prometheus
Chandresh Pancholi
 
Shaker
ShakerShaker
Shaker
Ilya Shakhat
 
Prometheus - Intro, CNCF, TSDB,PromQL,Grafana
Prometheus - Intro, CNCF, TSDB,PromQL,GrafanaPrometheus - Intro, CNCF, TSDB,PromQL,Grafana
Prometheus - Intro, CNCF, TSDB,PromQL,Grafana
Sridhar Kumar N
 
20171027 モニタリング勉強会
20171027 モニタリング勉強会20171027 モニタリング勉強会
20171027 モニタリング勉強会
Paul Traylor
 
Swift container sync
Swift container syncSwift container sync
Swift container syncOpen Stack
 
OpenNebulaconf2017US: Rapid scaling of research computing to over 70,000 cor...
OpenNebulaconf2017US:  Rapid scaling of research computing to over 70,000 cor...OpenNebulaconf2017US:  Rapid scaling of research computing to over 70,000 cor...
OpenNebulaconf2017US: Rapid scaling of research computing to over 70,000 cor...
OpenNebula Project
 
Slack in the Age of Prometheus
Slack in the Age of PrometheusSlack in the Age of Prometheus
Slack in the Age of Prometheus
George Luong
 
Integrating Bare-metal Provisioning into CERN's Private Cloud
Integrating Bare-metal Provisioning into CERN's Private CloudIntegrating Bare-metal Provisioning into CERN's Private Cloud
Integrating Bare-metal Provisioning into CERN's Private Cloud
Arne Wiebalck
 
Kubermatic How to Migrate 100 Clusters from On-Prem to Google Cloud Without D...
Kubermatic How to Migrate 100 Clusters from On-Prem to Google Cloud Without D...Kubermatic How to Migrate 100 Clusters from On-Prem to Google Cloud Without D...
Kubermatic How to Migrate 100 Clusters from On-Prem to Google Cloud Without D...
Tobias Schneck
 
KubeOne
KubeOne KubeOne
KubeOne
loodse
 
Operational War Stories from 5 Years of Running OpenStack in Production
Operational War Stories from 5 Years of Running OpenStack in ProductionOperational War Stories from 5 Years of Running OpenStack in Production
Operational War Stories from 5 Years of Running OpenStack in Production
Arne Wiebalck
 
Understanding and Extending Prometheus AlertManager
Understanding and Extending Prometheus AlertManagerUnderstanding and Extending Prometheus AlertManager
Understanding and Extending Prometheus AlertManager
Lee Calcote
 
Prometheus Training
Prometheus TrainingPrometheus Training
Prometheus Training
Tim Tyler
 

What's hot (19)

Flink Forward Berlin 2017: Aljoscha Krettek - Talk Python to me: Stream Proce...
Flink Forward Berlin 2017: Aljoscha Krettek - Talk Python to me: Stream Proce...Flink Forward Berlin 2017: Aljoscha Krettek - Talk Python to me: Stream Proce...
Flink Forward Berlin 2017: Aljoscha Krettek - Talk Python to me: Stream Proce...
 
Weave Cortex: Multi-tenant, horizontally scalable Prometheus as a Service
Weave Cortex: Multi-tenant, horizontally scalable Prometheus as a ServiceWeave Cortex: Multi-tenant, horizontally scalable Prometheus as a Service
Weave Cortex: Multi-tenant, horizontally scalable Prometheus as a Service
 
Neutron upgrades
Neutron upgradesNeutron upgrades
Neutron upgrades
 
Prometheus workshop
Prometheus workshopPrometheus workshop
Prometheus workshop
 
OSMC 2019 | Monitoring Cockpit for Kubernetes Clusters by Ulrike Klusik
OSMC 2019 | Monitoring Cockpit for Kubernetes Clusters by Ulrike KlusikOSMC 2019 | Monitoring Cockpit for Kubernetes Clusters by Ulrike Klusik
OSMC 2019 | Monitoring Cockpit for Kubernetes Clusters by Ulrike Klusik
 
Securing & Enforcing Network Policy and Encryption with Weave Net
Securing & Enforcing Network Policy and Encryption with Weave NetSecuring & Enforcing Network Policy and Encryption with Weave Net
Securing & Enforcing Network Policy and Encryption with Weave Net
 
Monitoring on Kubernetes using prometheus
Monitoring on Kubernetes using prometheusMonitoring on Kubernetes using prometheus
Monitoring on Kubernetes using prometheus
 
Shaker
ShakerShaker
Shaker
 
Prometheus - Intro, CNCF, TSDB,PromQL,Grafana
Prometheus - Intro, CNCF, TSDB,PromQL,GrafanaPrometheus - Intro, CNCF, TSDB,PromQL,Grafana
Prometheus - Intro, CNCF, TSDB,PromQL,Grafana
 
20171027 モニタリング勉強会
20171027 モニタリング勉強会20171027 モニタリング勉強会
20171027 モニタリング勉強会
 
Swift container sync
Swift container syncSwift container sync
Swift container sync
 
OpenNebulaconf2017US: Rapid scaling of research computing to over 70,000 cor...
OpenNebulaconf2017US:  Rapid scaling of research computing to over 70,000 cor...OpenNebulaconf2017US:  Rapid scaling of research computing to over 70,000 cor...
OpenNebulaconf2017US: Rapid scaling of research computing to over 70,000 cor...
 
Slack in the Age of Prometheus
Slack in the Age of PrometheusSlack in the Age of Prometheus
Slack in the Age of Prometheus
 
Integrating Bare-metal Provisioning into CERN's Private Cloud
Integrating Bare-metal Provisioning into CERN's Private CloudIntegrating Bare-metal Provisioning into CERN's Private Cloud
Integrating Bare-metal Provisioning into CERN's Private Cloud
 
Kubermatic How to Migrate 100 Clusters from On-Prem to Google Cloud Without D...
Kubermatic How to Migrate 100 Clusters from On-Prem to Google Cloud Without D...Kubermatic How to Migrate 100 Clusters from On-Prem to Google Cloud Without D...
Kubermatic How to Migrate 100 Clusters from On-Prem to Google Cloud Without D...
 
KubeOne
KubeOne KubeOne
KubeOne
 
Operational War Stories from 5 Years of Running OpenStack in Production
Operational War Stories from 5 Years of Running OpenStack in ProductionOperational War Stories from 5 Years of Running OpenStack in Production
Operational War Stories from 5 Years of Running OpenStack in Production
 
Understanding and Extending Prometheus AlertManager
Understanding and Extending Prometheus AlertManagerUnderstanding and Extending Prometheus AlertManager
Understanding and Extending Prometheus AlertManager
 
Prometheus Training
Prometheus TrainingPrometheus Training
Prometheus Training
 

Similar to Addressing data plane performance measurement on OpenStack clouds using VMTP

151121 e openstack-api-nfv
151121 e openstack-api-nfv151121 e openstack-api-nfv
151121 e openstack-api-nfv
Amanda Espíndola Raymundi
 
OpenStack Collaboration made in heaven with Heat, Mistral, Neutron and more..
OpenStack Collaboration made in heaven with Heat, Mistral, Neutron and more..OpenStack Collaboration made in heaven with Heat, Mistral, Neutron and more..
OpenStack Collaboration made in heaven with Heat, Mistral, Neutron and more..
Trinath Somanchi
 
Basic concepts for_clustered_data_ontap_8.3_v1.1-lab_guide
Basic concepts for_clustered_data_ontap_8.3_v1.1-lab_guideBasic concepts for_clustered_data_ontap_8.3_v1.1-lab_guide
Basic concepts for_clustered_data_ontap_8.3_v1.1-lab_guide
Vikas Sharma
 
OpenNebulaconf2017US: Paying down technical debt with "one" dollar bills by ...
OpenNebulaconf2017US:  Paying down technical debt with "one" dollar bills by ...OpenNebulaconf2017US:  Paying down technical debt with "one" dollar bills by ...
OpenNebulaconf2017US: Paying down technical debt with "one" dollar bills by ...
OpenNebula Project
 
OpenFlow as a Service from research institute
OpenFlow as a Service from research instituteOpenFlow as a Service from research institute
OpenFlow as a Service from research institute
Vijayaguru Jayaram
 
GMOインターネット様 発表「OpenStackのモデルの最適化とConoHa, Z.comとGMOアプリクラウドへの適用」 - OpenStack最新情...
GMOインターネット様 発表「OpenStackのモデルの最適化とConoHa, Z.comとGMOアプリクラウドへの適用」 - OpenStack最新情...GMOインターネット様 発表「OpenStackのモデルの最適化とConoHa, Z.comとGMOアプリクラウドへの適用」 - OpenStack最新情...
GMOインターネット様 発表「OpenStackのモデルの最適化とConoHa, Z.comとGMOアプリクラウドへの適用」 - OpenStack最新情...
VirtualTech Japan Inc.
 
OpenStack at NTT Resonant: Lessons Learned in Web Infrastructure
OpenStack at NTT Resonant: Lessons Learned in Web InfrastructureOpenStack at NTT Resonant: Lessons Learned in Web Infrastructure
OpenStack at NTT Resonant: Lessons Learned in Web Infrastructure
Tomoya Hashimoto
 
NFV Open Source projects
NFV Open Source projectsNFV Open Source projects
NFV Open Source projects
Marie-Paule Odini
 
Design and Performance Characteristics of Tap-as-a-Service
Design and Performance Characteristics of Tap-as-a-ServiceDesign and Performance Characteristics of Tap-as-a-Service
Design and Performance Characteristics of Tap-as-a-Service
soichi shigeta
 
Using Agilio SmartNICs for OpenStack Networking Acceleration
Using Agilio SmartNICs for OpenStack Networking AccelerationUsing Agilio SmartNICs for OpenStack Networking Acceleration
Using Agilio SmartNICs for OpenStack Networking Acceleration
Netronome
 
The advantages of Arista/OVH configurations, and the technologies behind buil...
The advantages of Arista/OVH configurations, and the technologies behind buil...The advantages of Arista/OVH configurations, and the technologies behind buil...
The advantages of Arista/OVH configurations, and the technologies behind buil...
OVHcloud
 
Red Hat presentatie: Open stack Latest Pure Tech
Red Hat presentatie: Open stack Latest Pure TechRed Hat presentatie: Open stack Latest Pure Tech
Red Hat presentatie: Open stack Latest Pure Tech
ProxyServices
 
Monitoring in Big Data Platform - Albert Lewandowski, GetInData
Monitoring in Big Data Platform - Albert Lewandowski, GetInDataMonitoring in Big Data Platform - Albert Lewandowski, GetInData
Monitoring in Big Data Platform - Albert Lewandowski, GetInData
GetInData
 
OpenStack Networking and Automation
OpenStack Networking and AutomationOpenStack Networking and Automation
OpenStack Networking and Automation
Adam Johnson
 
Survey of open source cloud architectures
Survey of open source cloud architecturesSurvey of open source cloud architectures
Survey of open source cloud architecturesabhinav vedanbhatla
 
Openstack starter-guide-diablo
Openstack starter-guide-diabloOpenstack starter-guide-diablo
Openstack starter-guide-diablo锐 张
 
Openstack starter-guide-diablo
Openstack starter-guide-diabloOpenstack starter-guide-diablo
Openstack starter-guide-diablo
babycat_feifei
 
OpenStack - An Overview
OpenStack - An OverviewOpenStack - An Overview
OpenStack - An Overview
graziol
 
Support of containerized workloads in ONAP
Support of containerized workloads in ONAPSupport of containerized workloads in ONAP
Support of containerized workloads in ONAP
Victor Morales
 
What's new in OpenStack Liberty
What's new in OpenStack LibertyWhat's new in OpenStack Liberty
What's new in OpenStack Liberty
Michael Solberg
 

Similar to Addressing data plane performance measurement on OpenStack clouds using VMTP (20)

151121 e openstack-api-nfv
151121 e openstack-api-nfv151121 e openstack-api-nfv
151121 e openstack-api-nfv
 
OpenStack Collaboration made in heaven with Heat, Mistral, Neutron and more..
OpenStack Collaboration made in heaven with Heat, Mistral, Neutron and more..OpenStack Collaboration made in heaven with Heat, Mistral, Neutron and more..
OpenStack Collaboration made in heaven with Heat, Mistral, Neutron and more..
 
Basic concepts for_clustered_data_ontap_8.3_v1.1-lab_guide
Basic concepts for_clustered_data_ontap_8.3_v1.1-lab_guideBasic concepts for_clustered_data_ontap_8.3_v1.1-lab_guide
Basic concepts for_clustered_data_ontap_8.3_v1.1-lab_guide
 
OpenNebulaconf2017US: Paying down technical debt with "one" dollar bills by ...
OpenNebulaconf2017US:  Paying down technical debt with "one" dollar bills by ...OpenNebulaconf2017US:  Paying down technical debt with "one" dollar bills by ...
OpenNebulaconf2017US: Paying down technical debt with "one" dollar bills by ...
 
OpenFlow as a Service from research institute
OpenFlow as a Service from research instituteOpenFlow as a Service from research institute
OpenFlow as a Service from research institute
 
GMOインターネット様 発表「OpenStackのモデルの最適化とConoHa, Z.comとGMOアプリクラウドへの適用」 - OpenStack最新情...
GMOインターネット様 発表「OpenStackのモデルの最適化とConoHa, Z.comとGMOアプリクラウドへの適用」 - OpenStack最新情...GMOインターネット様 発表「OpenStackのモデルの最適化とConoHa, Z.comとGMOアプリクラウドへの適用」 - OpenStack最新情...
GMOインターネット様 発表「OpenStackのモデルの最適化とConoHa, Z.comとGMOアプリクラウドへの適用」 - OpenStack最新情...
 
OpenStack at NTT Resonant: Lessons Learned in Web Infrastructure
OpenStack at NTT Resonant: Lessons Learned in Web InfrastructureOpenStack at NTT Resonant: Lessons Learned in Web Infrastructure
OpenStack at NTT Resonant: Lessons Learned in Web Infrastructure
 
NFV Open Source projects
NFV Open Source projectsNFV Open Source projects
NFV Open Source projects
 
Design and Performance Characteristics of Tap-as-a-Service
Design and Performance Characteristics of Tap-as-a-ServiceDesign and Performance Characteristics of Tap-as-a-Service
Design and Performance Characteristics of Tap-as-a-Service
 
Using Agilio SmartNICs for OpenStack Networking Acceleration
Using Agilio SmartNICs for OpenStack Networking AccelerationUsing Agilio SmartNICs for OpenStack Networking Acceleration
Using Agilio SmartNICs for OpenStack Networking Acceleration
 
The advantages of Arista/OVH configurations, and the technologies behind buil...
The advantages of Arista/OVH configurations, and the technologies behind buil...The advantages of Arista/OVH configurations, and the technologies behind buil...
The advantages of Arista/OVH configurations, and the technologies behind buil...
 
Red Hat presentatie: Open stack Latest Pure Tech
Red Hat presentatie: Open stack Latest Pure TechRed Hat presentatie: Open stack Latest Pure Tech
Red Hat presentatie: Open stack Latest Pure Tech
 
Monitoring in Big Data Platform - Albert Lewandowski, GetInData
Monitoring in Big Data Platform - Albert Lewandowski, GetInDataMonitoring in Big Data Platform - Albert Lewandowski, GetInData
Monitoring in Big Data Platform - Albert Lewandowski, GetInData
 
OpenStack Networking and Automation
OpenStack Networking and AutomationOpenStack Networking and Automation
OpenStack Networking and Automation
 
Survey of open source cloud architectures
Survey of open source cloud architecturesSurvey of open source cloud architectures
Survey of open source cloud architectures
 
Openstack starter-guide-diablo
Openstack starter-guide-diabloOpenstack starter-guide-diablo
Openstack starter-guide-diablo
 
Openstack starter-guide-diablo
Openstack starter-guide-diabloOpenstack starter-guide-diablo
Openstack starter-guide-diablo
 
OpenStack - An Overview
OpenStack - An OverviewOpenStack - An Overview
OpenStack - An Overview
 
Support of containerized workloads in ONAP
Support of containerized workloads in ONAPSupport of containerized workloads in ONAP
Support of containerized workloads in ONAP
 
What's new in OpenStack Liberty
What's new in OpenStack LibertyWhat's new in OpenStack Liberty
What's new in OpenStack Liberty
 

Addressing data plane performance measurement on OpenStack clouds using VMTP

  • 1. Addressing data plane performance measurement on OpenStack clouds using VMTP OpenStack summit Vancouver is fast approaching and I for one can’t wait to see how much OpenStack has progressed from Juno to Kilo. I expect to see even more momentum with new companies being added to the OpenStack community, continuing to drive the industry acceptance momentum of OpenStack. While a lot of good stuff is happening from a functionality (features) and new projects standpoint, being able to systematically measure performance across the major components still remains largely a work in progress. While Nova (Compute) and Swift (Object Storage) continue to mature rapidly with good work being done by many in the OpenStack community around performance measurement, Neutron (Networking) continues to lag. Prior to the Juno summit in Paris last November, there was intent in the OpenStack community to move away from Nova networking onto Neutron where there is significantly more functionality and scale to be had. But there are many challenges that are preventing this migration from happening. Primary among those challenges is the inability to easily measure performance on Neutron to ensure that there isn’t significant performance degradation as a result of the move from Nova networking to Neutron. Cisco is proactively addressing the gap of performance measurement on Neutron by releasing in Stackforge an open source data plane performance measurement tool called VMTP (VM Throughput Performance). It is heartening to see that others in the community are also providing tools for data plane measurement such as the recently released “shaker”. VMTP addresses the need for a quick, simple and automatable way to get VM-level or host- level single-flow throughput and latency numbers from any OpenStack cloud, while also taking into account various Neutron topologies. VMTP can also easily check whether certain OpenStack configuration options, Neutron plug-ins perform to expectation or if there is any data path impact for upgrading to a different OpenStack release. VMTP is a small python application that will automatically perform ping connectivity, round trip time measurement (latency) and TCP/UDP throughput measurement for the following East/West flows on any OpenStack deployment:  VM to VM same network (private fixed IP, flow #1)  VM to VM different network using fixed IP (same as intra-tenant L3 fixed IP, flow #2)  VM to VM different network using floating IP and NAT (same as floating IP inter-tenant L3, flow #3) In addition VMTP can also test for the following traffic scenarios  When an external Linux host is available for testing North/South flows:
  • 2.  External host/VM download and upload throughput/latency (L3/floating IP, flow #4 and #5)  Optionally, when SSH login to any Linux host (native or virtual) is available: o Host to host process-level throughput/latency (intra-node and inter-node) VMTP can also extract automatically CPU usage from all native hosts in the cloud during the throughput tests, provided the Ganglia monitoring service (gmond) is installed and enabled on those hosts. For VM-related flows, VMTP will automatically create the necessary OpenStack resources (router, networks, subnets, key pairs, security groups, test VMs) using the public OpenStack API, install the test tools then orchestrate them to gather the throughput measurements then cleanup all related resources before exiting. VMTP has been architected to run independently of Heat as we’ve seen that most deployments in the field don’t have Heat also installed. VMTP measures true north/south traffic via a client app that run outside the cloud. Additional benefits of using VMTP are:  A hook to Ganglia monitoring to capture host level system metrics during test  Flow measurement chaining which results in faster runs (e.g. VMTP chains all client VM positions for different flows with the same server VM, which you can't do with Heat. With Heat you need to tear down and rebuild the setup/server for each flow)
  • 3.  Results stored directly in MongoDB  Auto extraction of OpenStack versions, encapsulation and L2 agent types and versions  Select special network interfaces (useful for VMs attached to multiple networks)  SR-IOV and IPv6 support  Detailed online documentation @ http://vmtp.readthedocs.org/en/latest/ Finally VMTP also supports a quick way of creating charts from multiple run JSON results so you can easily view and consume the results of multiple runs. This new feature (genchart.py) takes one or more VMTP JSON files as input and generates a static HTML file. The --browser option allows the tool to directly open the generated HTML file in the user's default browser. There is no need for any additional HTTP server since the html file is self-contained and the browser will automatically load the required JavaScript libraries. I hope you enjoyed learning about what the VMTP tool can offer and hope you join in making it even better by contributing to the code at: http://vmtp.readthedocs.org/en/latest/contributing.html#contribute-to-vmtp