X-Ray Performance & Reliability Tests

X-Ray 6.2 marks a bold new chapter for performance benchmarking. This release introduces fresh ways to connect, measure, and share insights across your infrastructure — now smarter, faster, and more connected than ever before.🚀 What’s NewX-Ray ConnectUpload results from your on-premises X-Ray directly to the cloud-based X-Ray as a Service (XRaaS). Authenticate seamlessly through MyNutanix and collaborate across teams with ease. (XRAY-6515)Benchmarking on Nutanix Kubernetes Platform (NKP)Run performance benchmarks natively on NKP clusters for a modern, containerized infrastructure experience. (XRAY-6338)Windows EUC BenchmarkingNew scenario for Windows End-User Computing (EUC) and Virtual Desktop Infrastructure (VDI) Measure desktop performance and scale with precision. (XRAY-6810)Direct Feedback in X-Ray

Hello, I completed the install of the new and shiny X-Ray 5.3Nice addition for the certificate, thank you to the Team in charge.A another new feature I was eager to try is Windows, So A followed the preparation guide, got a golden image and launch a test scenario Peak Performance Microbenchmark.Unfortunately it failed preparing the VMs : group_0: Preparing VMsCause: Cause:fatal: [169.254.217.84]: UNREACHABLE! => {fatal: [169.254.252.231]: UNREACHABLE! => {fatal: [169.254.146.81]: UNREACHABLE! => {fatal: [169.254.122.189]: UNREACHABLE! => {fatal: [169.254.37.135]: UNREACHABLE! => {fatal: [169.254.178.209]: UNREACHABLE! => {fatal: [169.254.54.182]: UNREACHABLE! => {fatal: [169.254.253.253]: UNREACHABLE! => {Impact: Ansible command did not finish cleanly. Final status was 'failed', Ansible return code was 4Corrective Action: NoneI have collected the logs also , b

Hello, Is it possible to replace the default SSL certificate of the X-Ray “appliance”, I didn’t find a procedure for that ? Thank you in advance (hoping this is the correct place to get help on this)PhS

When I attempt to add Nutanix as a target in xray, the validation completes okay but when i click done i get this error:Bad request. ahv.nodes.0.networks.0.switch_id: Ensure this field has no more than 100 characters. ahv.nodes.0.networks.4.switch_id: Ensure this field has no more than 100 characters. ahv.nodes.1.networks.0.switch_id: Ensure this field has no more than 100 characters. ahv.nodes.1.networks.4.switch_id: Ensure this field has no more than 100 characters. ahv.nodes.2.networks.0.switch_id: Ensure this field has no more than 100 characters. ahv.nodes.2.networks.4.switch_id: Ensure this field has no more than 100 characters. ahv.nodes.3.networks.0.switch_id: Ensure this field has no more than 100 characters. ahv.nodes.3.networks.4.switch_id: Ensure this field has no more than 100 characters. ahv.nodes.4.networks.0.switch_id: Ensure this field has no more than 100 characters. ahv.nodes.4.networks.4.switch_id: Ensure this field has no more than 100 characters. ahv.nod

Hi folks, when we go to add a our cluster into XRAY all the validation tests complete however on clicking done it says: Any ideas of what I should check?Our Switch has is called XrayNetwork

All,I ran the VM HA test failover; similar to another user, here Nutanix X-Ray VM High Availability Test timeout I got the 120 seconds timeout. So I raised a ticket. However one issue I did have is the powered off host was not powered back on again. All validation tests when I discovered the targets were good. I have included this in the support ticket for now, but wondering if anyone else has seen this? Older G5 Nutanix, 3 Node cluster, AOS 5.20.3, PC 2022.1.

I used X-Ray to do a performance testing for the Nutanix cluster. After added the target, and I do a Peak Performance Micro benchmark test. All the process has worked well. but when the performance testing is running, there is no I/O performance graph, only display the 3 graphs as cluster CPU usage,cluster network received, and cluster network transmitted. I cannot find the I/O performance information from the graph. I have meet this kind of problem many times. and the x-Ray version is 3.11.As the beginning test, the timezone is not right and I have ever adjust the time of X-Ray VM. 

HiI used X-Ray 4.1.3 to do a test of VM High Availability in a cluste which includes 6 Lenovo HX nodes installed ESXi 7.0 U2, I tested several times and all are failed. The test failed in the phase of after poweroff the Host and reestablish the workload in 120 seconds. All are time out in 120 secs. I checked the VM which has already HA to another host, and the VM is already restated and the IP already obtained. So this is the timeout issue. seems if the timeout  value is larger, the test will be successfully. but I cannot find the place to adjust the 120 secs value.My question  is “ Is there any way to adjust the 120 sec value for the VM high Availability test”? 

When no DHCP server is available, or where creating a scope large enough for X-Ray VMs is not possible, use zero-configuration for self-assigned IP addressing. Zero-configuration networking is a standard for IP addressing where a host self-assigns an IP address. X-Ray uses IPv4. which uses the reserved addresses 169.254.0.0/16. This feature eliminates the need for manual IP address configuration or DHCP. 

Hello All, When attempting to run any test we receive one error: Prism Error 500 - This happens when it attempts to communicate with node 2 of our Nutanix cluster (we have 3 nodes)  or when Deleting images (Kclusterapierror) I’ve checked all the configuration and can pass the validation, so I am unsure what could be the cause of the error. Any advice would be appreciated.  

X-Ray is an automated testing framework and benchmarking application for enterprise-grade data centers. The X-ray application is a downloadable virtual machine (VM) with a user interface and complete documentation. Once installed, X-ray can test and analyze several different systems and report comparable information for your use. X-ray provides test scenarios for hype converged platforms that demonstrate variations in areas such as performance, data integrity and availability. Note: X-Ray is a tool for test environments and not intended for production environments.X-ray runs one test scenario per target at a time.

Petter Glenstrup shows you what you can do with X-Ray, the performance benchmarking and scenario based testing tool from Nutanix. 

Nutanix X-Ray is a free way to evaluate a variety of hyperconvergence scenarios. Compare configs and automate testing. X-ray your infrastructure and see if HCI is right for you.Move beyond peak-performance benchmarking to make informed decisions on hyperconverged infrastructure (HCI) evaluations. X-Ray is an automated testing framework and benchmarking solution that offers comprehensive 360° assessments of major hyperconverged infrastructure solutions. 

This was a blog by Josh Odgers posted on March 5, 2021For a while now I’ve been working on building new X-ray scenarios for both internal engineering/QA and for customers to quickly/easily and repeatably test more granular functionality of Nutanix.The HCI Platform Availability, Resiliency and Integrity series covers how the test functions on both Nutanix AOS and VMware vSAN and highlights that AOS has a major advantage over vSAN as it always maintains data integrity (both Availability and Integrity) even during failures on the minimum 3 node configurations.vSAN on the other hand suffers I/O errors even with much higher I/O timeouts, larger clusters and even with 3 copies of data (FTT2).But don’t take my word for it, you can now run the tests yourself.Read the complete blog:

X-Ray 3.10.2 is an automated testing framework and benchmarking application for enterprise-grade data centers.X-Ray is packaged as a VM and uses realistic workloads paired with real-world test scenarios to simulate various workflows and events that typically occur during datacenter HCI life-cycles.New FeaturesData locality scenario: X-Ray 3.10.2 adds a scenario to test resiliency during unplanned system events.Resolved IssuesCurie variables not available on vSAN: Fixed an issue where scenarios did not correctly process CURIE_HCI variables on vSAN targets. IPMI discovery failing: Fixed an issue where X-Ray discovery failed when you added a target with the IPMI configuration set to None. Cannot add AWS cluster as a target: Fix

I am using the newest version of X-ray (3.10.0) to connect to a vCenter (6.5U1d) to have some performance tests for my cluster. At the step 4 (Validation) of creating the target cluster, it failed to validate the cluster.Error: Target cannot be verified.After looking into the log, in the HTTP Response body, it contains the 500 Internal Server Error. Still cannot get what it means as everything seems fine and the connection from X-ray VM to cluster still has no problem at all.

02/09/2021 Update: 3.10.1 has been released and contains the fix for this problemAn attempt to add a cluster with NVMe drives in the X-Ray 3.10.0 fails immediately.While checking the log on the X-Ray VM the following can be observed in the xray.log:ERROR Error occurred while performing final discovery - Invalid value for `type` (SSD-PCIe), must be one of ['HDD', 'SSD', 'Unknown'] That issue is specific to the version 3.10.0 of X-Ray and affects only the clusters with NVMe drives. It is a software bug that is going to be fixed in the upcoming release 3.10.1.The workaround is currently to use the earlier versions. X-Ray 3.8 is validated to work correctly.Earlier versions of X-Ray can be downloaded from the following page: http

The latest release of X-Ray 3.10 has now been published and made available for download on the Nutanix portal here. Check out the latest updates to the Release Notes and Guide.X-Ray is a comprehensive infrastructure assessment solution, testing both the performance and resilience of hyperconverged infrastructure solutions.X-Ray is packaged as an easily deployable VM and uses realistic workloads paired with real-world scenarios to simulate the various workflows and events that typically occur during datacenter infrastructur

Hi All,Just after some advice.  I’ve run the default ‘Four Corners Microbenchmark’ against 2 x identical All Flash clusters and I get very different results and not sure why.The average random read IOPS differ by around 60k, and the random write IOPS around 10k. I know running the test on both clusters will not provide an exact match, but these results appear very different.  Please note these are both 2-node clusters, both are identical in specification so not sure if this matters.I also get the same on 2 x identical 6-node Hybrid arrays, random read IOPS differ by 200k and random write IOPS by 40k!The same X-Ray appliance was used on all clusters, using the default settings in the test itself.Just after a possible explanation to these queries, if somebody could be so helpful.Thanks very much.

Hi.I’ve been trying to find out if I can use X-Ray to test other platforms (VMware and Hyper-V) or if I need to export the test (the “Four corners” in my case) and then use Curie to test the other platforms.There isn’t a lot of information on X-Ray and other platforms to be found though.Thanks.

Would anyone have X-Ray Four Corners Microbenchmark results for the following scenarios:2-node Nutanix cluster, 1 GB uplinks 2-node Nutanix cluster, 10 GB uplinks 3-node Nutanix cluster, 1 GB uplinks 3-node Nutanix cluster, 10 GB uplinksI'm testing some scenarios against Cisco Hyperflex and HPE SimpliVity (which I currently have environments to test against), but don't have access to any Nutanix hardware.BTW...X-Ray is a GREAT product!

Hi,Is it possible to install X-Ray machine in a host outside of Nutanix Cluster nodes?

Hi everyone, The X-Ray new UI just got released last month. The redesign of the tool mainly focused on improving the user experience and better aligning with user’s business needs. Yini talks about the effort behind the scene and explore why we redesigned X-Ray, explain how we approached the redesign, and look at the features and benefits that this redesign enabled. Check out the article 👉 Redesign a data heavy application Be the first to reply and share your thoughts!

Hi there, I'm trying to use X-RAY for our purpose and I faced an error without more logs/messages than: "A timeout occurred waiting for VM(s) in VM Group 'Cluster Check' to become responsive within 120 seconds." I configured both vNIC of the X-RAY VM: eth0: for communication with the API eth1: for communication with VMs workload eth1 is configured with a specific subnet (I didn't find too much documentation for zero configuration). On my Nutanix cluster, I added this specific network and let it to give addresses to VMs deployed by X-RAY (98 IPs available in this subnet) During the cluster check, 4 VMs are deployed, powered up and IPs are assigned. The X-RAY VM can communicate with these 4 VMs. The problem is for the last one, the 5th VM doesn't start and the cluster check fail.

Has anyone experienced the X-Ray tests going to 0% but staying 'open'? For the last few days our X-Ray tests have been running to completion but not finishing. As a result the additional tests do not get run. The curie log indicates "exiting _cluster_results_loop" but the tests hang open at 0% and they have to be cancelled.