THE IMPACT OF QOS NETWORK TRAFFIC ON VM PERFORMANCE
A lot of interesting material is written about configuring Quality of Service (QoS) on 10GB (converged) networks in Virtual Infrastructures. With the release of vSphere 4.1, VMware introduced a network QoS mechanism called Network I/O Control (NetIOC). The two most popular Blade systems; HP with Flex10 technology and Cisco UCS both offer traffic shaping mechanisms at hardware level. Both NetIOC and Cisco UCS approach network Quality of Service with a sharing perspective, guaranteeing a minimum amount of bandwidth opposed to the HP Flex-10 technology, which isolates the available bandwidth and dedicate an X amount of bandwidth to a specified NIC. When allocating bandwidths to the various network traffic streams most admins try to stay on the safe side and over-allocate bandwidth to virtual machine traffic. Obviously it is essential to guarantee enough bandwidth to virtual machines but bandwidth is finite, resulting in less bandwidth available to other types of traffic such as vMotion. Unfortunately by reducing the available bandwidth used for vMotion traffic can ultimately have negative effect on the performance of the virtual machines. MaxMovesPerHost In vSphere 4.1 DRS uses an adaptive technique called MaxMovesPerHost. This technique allows DRS to decide the optimum concurrent vMotions per ESX host for Load-Balancing operations. DRS will adapt the maximum concurrent vMotions per host (8) based upon the average migration time observed from previous migrations. Decreasing bandwidth available for vMotion traffic can result in a lower number of allowed concurrent vMotions.In turn the amount of allowed concurrent vMotions affects the number of migration recommendations generated by DRS. DRS will only calculate and generate the amount of migration recommendation is believes it can complete before the next DRS invocation. It limits the amount of generated migration recommendations, as there is no advantage in generating recommending migrations that cannot be complement before the next DRS invocation. During the next re-evaluation cycle, virtual machine resource demand can have changed rendering the previous recommendations obsolete By limiting the amount of bandwidth available to vMotion, it can decrease the maximum amount of concurrent vMotions per host and could risk leaving the cluster imbalanced for a longer period of time. Both NetIOC and Cisco UCS Class of Service (COS) Quality of Service can be used to guarantee a minimum amount of bandwidth available to vMotion during contention. Both techniques allow vMotion traffic to use all the available bandwidth if no contention occurs. HP uses a different approach, isolating and dedicating a specific amount of bandwidth to an adapter and thereby possible restricting specific workloads. Bred Hedlund wrote an article explaining the fundamental differences in how bandwidth is handled between HP Flex-10 and Cisco UCS. Cisco UCS intelligent QoS vs. HP Virtual Connect rate limiting Recommendations for Flex-10 Due to the restrictive behavior of Flex-10, it is recommended to specifically take the adaptive nature of DRS into account and not restricting vMotion traffic too much when shaping network bandwidth for the configured FlexNics. It is recommended to monitor the bandwidth requirements of the virtual machines and adjust the rate limit for virtual machine traffic and vMotion traffic accordingly, reducing the possibility of delaying DRS to reach a steady state when a significant load imbalance in the cluster exits. Recommendations for NetIOC and UCS QoS Fortunately the sharing nature of NetIOC and UCS allow other network streams allocate bandwidth during periods without bandwidth contention. Despite this “plays well with other” nature, it is recommended to assign a minimum guarantee amount of bandwidth for vMotion traffic (NetIOC) or a custom Class of Service to the vMotion vNICs (UCS). Chances are that if virtual machines saturate the network, virtual machines are experiencing a high workload and DRS will try to provide the resources the virtual machines are entitled to.
VSWITCH FAILBACK AND HIGH AVAILABILITY
One setting most admins get caught off-guard is vSwitch Failback setting in combination with HA. If the management network vSwitch is configured with Active/Standby NICs and the HA isolation response is set to “Shutdown” VM or “Power-off” VM it is advised to set the vSwitch Failback mode to No. If left at default (Yes), all the ESX hosts in the cluster or entire virtual infrastructure might issue an Isolation response if one of the management network physical switches is rebooted. Here’s why: Just a quick rehash: Active\Standby One NIC (vmnic0) is assigned as active to the management\service console portgroup, the second NIC (vmnic1) is configured as standby. The vMotion portgroup is configured with the first NIC (vmnic0) in standby mode and the second NIC as Active (vmnic1). [caption id=“attachment_1344” align=“aligncenter” width=“316” caption=“Active Standby setup management network vSwitch0”][/caption] Failback The Failback setting determines if the VMkernel will return the uplink (NIC) to active duty after recovery of a downed link or failed NIC. If the Failback setting is set to Yes the NIC will return to active duty, when Failback is set to No the failed NIC is assigned the Standby role and the administrator must manually reconfigure the NIC to the active state. Effect of Failback yes setting on environment When using the default setting of Failback unexpected behavior can occur during maintenance of a physical switch. Most switches, like those from Cisco, initiate the port after boot, so called Lights on. The port is active but is still unable to receive or transmitting data. The process from Lights-on to forwarding mode can take up to 50 seconds; unfortunately ESX is not able to distinguish between Lights-on status and forwarding mode, there for treating the link as usable and will return the NIC to active status again. High Availability will proceed to transmit heartbeats and expect to receive heartbeats, after missing 13 seconds of heartbeats HA will try to ping its Isolation Address, due to the specified Isolation respond it will shut down or power-off the virtual machines two seconds later to allow other ESX hosts to power-up the virtual machines. But because it is common – recommended even – to configure each host in the cluster in an identical manner, each active NIC used by the management network of every ESX host connect to the same physical switch. Due to this design, once the switch is booted, a cluster wide Isolation response occurs resulting in a cluster wide outage. To allow switch maintenance, it’s better to set the vSwitch failback mode to No. Selecting this setting introduces an increase of manual operations after failure or certain maintenance operations, but will reduce the change of “false positives” and cluster-wide isolation responses.
BEST PRACTICES
Last week at VMworld and the VCDX defense panels I heard the term “Best Practices” a lot. The term best practice makes me feel happy, shudder and laugh at the same time. Now when it comes to applying best practice I always use the analogy of crossing the road: I am born and raised in the Netherlands and best practice is to look left first, then to the right and finally check left again before crossing the road. This best practice served me well and it helped me avoid being hit by a car/truck/crazy people on bikes and even trams and trolleys. But I ask you does this best practice still apply when I try to cross the street in London? Don’t get me wrong, best practice are useful and very valuable, but to apply a best practice blindly won’t be as lethal as my analogy but it can get you into a lot of trouble.
VMWORLD VCLOUD DIRECTOR LABS
Yesterday the VMworld Labs opened up to the public and if you want to take vCloud Director for a spin I’m recommending doing the following labs: Private cloud – Management: Lab 13 VMware vCloud Director Install and Config Lab 18 VMware vCloud Director Networking Private Cloud - Security: Lab20 VMware vShield Its best to complete Lab 18 vCloud Director Networking before doing VMware vShield Lab (Lab 20) because the terms and knowledge gained in Lab 18 will prepare you for Lab 20. Today the VMworld 2010 speaker sessions started and I strongly recommend Duncan’s session “BC7803 - Planning and Designing an HA Cluster that Maximizes VM Uptime” and Kit Colbert’s “ TA7750 - Understanding Virtualization Memory Management Concepts”. Go check it out.
NUMA, HYPERTHREADING AND NUMA.PREFERHT
I received a lot of questions about Hyperthreading and NUMA in ESX 4.1 after writing the ESX 4.1 NUMA scheduling article. A common misconception is that Hyperthreading is ignored and therefore not used on a NUMA system. This is not entirely true and due to the improved Hyperthreading code on Nehalems, the CPU scheduler is programmed to use the HT feature more aggressively than the previous releases of ESX. The main reason why I think this misconception exists is the way the NUMA load balancer handles vCPU placement of vSMP virtual machine. Before continuing, let’s get our CPU elements nomenclature aligned, I’ve created a diagram showing all the elements:
VM SETTINGS: PREFER PARTIALLY AUTOMATED OVER DISABLED
Due to requirements or constraints it might be necessary to exclude a virtual machine from automatic migration and stop it from moving around by DRS. Use the “Partially automated” setting instead of “Disabled” at the individual virtual machine automation level. Partially automated blocks automated migration by DRS, but keep the initial placement function. During startup, DRS is still able to select the most optimal host for the virtual machine. By selecting the “Disabled” function, the virtual machine is started on the ESX server it is registered and chances of getting an optimal placement are low(er). An exception for this recommendation might be a virtualized vCenter server, most admins like to keep track of the vCenter server in case a disaster happens. After a disaster occurs, for example a datacenter-wide power-outage, they only need to power-up the ESX host on which the vCenter VM is registered and manually power-up the vCenter VM. An alternative to this method is to keep track of the datastore vCenter is placed on and register and power-on the VM on a (random) ESX host after a disaster. Slightly more work than disabling DRS for vCenter, but offers probably better performance of the vCenter Virtual Machine during normal operations. Due to expanding virtual infrastructures and new additional features, vCenter is becoming more and more important for day-to-day operational management today. Assuring good performance outweighs any additional effort necessary after a (hopefully) rare occasion, but both methods have merits.
VOTED NUMBER 6 OF TOP 25 VMWARE BLOGS, WOW!
Eric Siebert of vSphere-land, together with David Davis, Simon Seagrave and John Troyer announced the results of the Top 25 blogs election this week. Using vChat is in my opinion a very cool format and I had the feeling that I was watching the academy awards for Bloggers. Gentlemen, thank you for taking the time and effort to create this entertaining show. Next time I will be viewing this from my TV instead of my 13" laptop screen and making sure I’ll have the popcorn ready. But most of all I want to thank everyone who voted for me. According to you my blog belongs in the top 10 and I’m very proud and honored to be ranked up that high. Thank you very much!
PROVIDER VDC: CLUSTER OR RESOURCE POOL?
Duncan’s article on vCloud Allocation models states that: a provider vDC can be a VMware vSphere Cluster or a Resource Pool … Although vCloud Director offers the ability to map Provider vDCs to Clusters or Resource Pool, it might be better to choose for the less complex solution. This article zooms in on the compute resource management constructs and particularly on making the choice between assigning a VMware Cluster or a Resource Pool to a Provider vDC and placement of Organization vDCs. I strongly suggest visiting Yellow Bricks to read all vCloud Director posts, these posts explain the new environment / cloud model used by VMware very thoroughly.
RESOURCE POOLS AND SIMULTANEOUS VMOTIONS
Many organizations have the bad habit to use resource pools to create a folder structure in the host and cluster view of vCenter. Virtual machines are being placed inside a resource pool to show some kind of relation or sorting order like operating system or types of application. This is not reason why VMware invented resource pools. Resource pools are meant to prioritize virtual machine workloads, guarantee and/or limit the amount of resources available to a group of virtual machines. During design workshops I always try to convince the customer why resource pools should not to be used to create a folder structure. The main object I have for this is the sibling share level of resource pools and virtual machines. Shares specify the priority for the virtual machine or resource pool relative to other resource pools and/or virtual machines with the same parent in the resource hierarchy. The key point is that shares values can be compared directly only among siblings: the ratios of shares of VM6:VM7 tells which VM is higher priority, but the shares of VM4:VM6 does not tell which VM has higher priority. Many articles have been written about this, such as: “The resource pool priority-pie paradox”, (Craig Risinger) “Resource pools and shares” (Duncan Epping), “Don’t add resource pools for fun” (Eric Sloof) and “Resource pools caveats” (Bouke Groenescheij). But another reason not to use resource pools as a folder structure is the limitation resource pools inflict on vMotion operations. Depending on the network speed, vSphere 4.1 allows 8 simultaneous vMotion operations, however simultaneous migrations with vMotion can only occur if the virtual machine is moving between hosts in the same cluster and is not changing its resource pool. This is recently confirmed in Knowledge Base article [1026102](http://kb.vmware.com/selfservice/microsites/search.do?cmd=displayKC&docType=kc&externalId=1026102&sliceId=1&docTypeID=DT_KB_1_1&dialogID=111208416&stateId=0 0 116148556). Fortunately simultaneous cross-resource-pool vMotions can occur if the virtual machines are migrating to different resource pools, but still one vMotion operation per target resource pool. Because clusters are actually implicit resource pools (the root resource pool), migrations between clusters are also limited to a single concurrent vMotion operation. Using resource pools to create a folder structure can not only impact the availability of resources for the virtual machines, but can also hinder your daily (maintenance) operations if batches of virtual machines are being migrated to other resource pools.
2 DAYS LEFT TO VOTE
Eric Siebert owner of vSphere-land.com started the second round of the bi-annual top 25 VMware virtualization blogs voting. The last voting was back in January and this is your chance to vote for your favorite virtualization bloggers and help determining the top 25 blogs of 2010. This year my blog got nominated for the first time and entered the top 25 (no. 14) and I hope to stay in the top 25 after this voting round. My articles tend to focus primarily on resource management and cover topics such as DRS, CPU and memory scheduler to help you make an informed decision when designing or managing a virtual infrastructure. As noble as this may sound I know that these kinds of topics are not mainstream and I can understand that not everybody is interested to read about these topics week in week out. Fortunately I’ve managed to get a blog post listed in the Top 5 Planet V12n blog post list at least once every month and referred on a regular basis by sites like Yellow-bricks.com (Duncan Epping), Scott Lowe, NTpro.nl (Eric Sloof) and Chad Sakac and of course many others. So it seems I’m doing something right. This is my list of top 10 articles I’ve created this year: