Tag Archives: vCenter

Oracle performance on HPE Synergy, vSAN and Intel Optane

Image result for hpe synergy

I had the privilege recently to work with a customer who had asked HPE to perform some performance benchmarks not just with HCI Bench, but because they run quite a lot of Oracle workloads they wanted to determine if the performance of vSAN on HPe Synergy would be sufficient in order to run their workloads.

Whilst agreeing on the hardware specification, the customer had referenced my previous post on Optane™ Performance and had asked HPE to perform the tests using Optane™ as the cache tier in the Synergy configuration, this was not only to provide a superior performance experience, but it also would free up two capacity slots in the disk tray of the chassis per Synergy compute node meaning the customer could have more capacity.

Synergy Specification:

  • HPE Virtual Connect SE 40Gb F8 Module for Synergy
  • HPE Synergy D3940 Storage Module with SAS expanders
  • 3x HPE Synergy 480 Gen10 nodes, each equipped with:
  • 2x Intel® Xeon® Gold 6154 CPU @ 3.00GHz
  • 2x Intel® Optane™ 750 GB SSD DC P4800X Series PCIe (x4)
  • 768 GB Memory (24x 32 GB RDIMM @ 2666 MHz)
  • 2x Disk Group config with 1x Optane + 3x 800GB SAS per Disk Group
  • LACP based 40GbE interconnection between Compute Nodes

Please note: At the time of writing the 750GB U.2 Optane drives were undergoing certification for HPE Synergy.

In order to perform the Oracle workload testing HPE engaged with their own internal Oracle specialists to determine the correct workloads that needed to be performed, and with a target of <2ms specified by the customer they decided to use Kevin Closson’s SLOB tool, SLOB was configured in the following way:

  • 128 SLOB Schemas
  • Each Schema was 8GB in Size
  • Total of 1TB Test data

For the purpose of testing HPE decided that they would perform different tests in the following way:

  • (A) Single Oracle VM Instance with 128 Schemas, 70% Read, 30% Write
  • (B) Single Oracle VM Instance with 128 Schemas, 50% Read, 50% Write
  • (C&D) Single Oracle VM Instance with Heavy REDO activity and Large SGA and REDO_STRESS=Heavy, 50% Read, 50% Write, with 128 Schemas and 32 Schemas
  • (E) Single Oracle VM Instance
  • (F & G) 2 Parallel Oracle VM Instances with 64 / 128 Schemas Each, 70% Read, 30% Write
TestSGAPGASchemasScaleREDO_STRESS
A5G1G1288GLite
B5G1G1288GLite
C256G100G1288GHeavy
D256G100G328GHeavy
E5G1G1288GLite
F5G1G648GLite
G5G1G1288GLite

Before the tests were performed, and Oracle I/O Calibration was performed which is a feature of Oracle Databases and is used to assess the performance of the I/O subsystem by issuing an I/O intensive read-only workload in order to determine the maximum IOPS and throughput whilst maintaining close to 0ms latency.

Each test ran for 60 minutes in order to ensure enough data was filling up the write buffer, so let’s take a look at the results:

As you can see from the results, the target of <2ms was achieved successfully and at one point with two oracle VMs achieveing a staggering 250k IOPS at 1.305ms latency is very impressive across a 3-Node cluster, not only was the customer pleased with the results, but the Oracle Specialist within HPE said that the results exceeded their expectations also.

So as you can see, a composable infrastructure deployment of vSAN such as HPE Synergy with Intel Optane™ can still deliver the same levels of performance as standard rack mount servers, combined with VMware Cloud Foundation delivering a full SDDC package from both a hardware and software perspective.

Day-2 Operations – vSphere built in vROPS dashboards

At VMworld I ran a few sessions on Day-2 Operations which I also covered the new built in dashboards for vROPS which were introduced with the fully baked HTML5 client in vSAN/vSphere 6.7.  Many people were not aware of the dashboards and moreso were not aware that these vSAN specific dashboards continue to work even after the 90 day trial period has expired.  Not only that but VMware has done a great job in automating a deployment of vROPS if you have not already got an appliance deployed.  So let’s take a look at these new dashboards in a bit more detail.

Firstly the three vSphere operations Dashboards, the default one that loads up is an overview dashboard of all your clusters:

Then there is the Cluster Level View where you pick a specific cluster:

And finally is the Alerts view…Great timing, I have a physical disk failure in the vSAN Cluster:Now the above three dashboards will no longer be available after the 90 day trial period has expired, and also the link to the vRealize Operations appliance will not be functional either, but after the 90 day trial period has expired, the following three vSAN Dashboards will still be fully functional and available, so let’s look at those in a bit more detail:

The vSAN Overview dashboard, like the vSphere overview dashboard, displays information at a holistic level for all of your vSAN Clusters within this particular vCenter server, you will see that the dashboard provides information on how many clusters are running dedupe/compression, or how many of the clusters are a Stretched Cluster for example.  The dashboard also shows if you need to investigate any current alerts (yes I cleaned up the failed disk before grabbing this screenshot).

The next dashboard we choose a specific cluster to look at in more detail:
In this dashboard we see information pertaining to a specific cluster, we can see that I have 6 critical alerts which we will take a look at next, but there are some key metrics here that from an operational perspective are pretty important from a day-2 operations standpoint:

  • Remaining Capacity
  • Component Limit
  • IOPS, Throughput and Latency statistics
  • Read versus Write latency

The last dashboard is alerts:
Here we can see the current alerts that have been triggered for each cluster which may need to be addressed, the critical alerts previously highlighted in the cluster view were all related to a network redundancy lost when I was troubleshooting packet loss on the physical switch.

So as you can see there’s a really good amount of detail in the vSphere UI relating to vROPS making the day-2 operations a lot easier to perform.

 

 

 

 

Day-2 Operations – Performance Monitoring in the vSAN UI

Performance reporting or Performance Monitoring is something of a must in any storage environment today, I remember many times when I was in VMware Support when facing a customer storage performance issue that metrics were not there to capture the event, and most storage performance tools required enabling, obviously this meant that the issue had to be occurring at the time of the performance metrics grab, vSAN in the early days was no different, vSAN Observer whilst being a detailed tool and provided a lot of information, was not a historical tool, it was enabled to troubleshoot a performance issue that was happening at that particular time.

In the later releases of vSAN the UI came equipped with more performance metrics than you could shake a stick at, which from a performance troubleshooting and monitoring perspective is the dogs danglies, but what does this mean from an every day perspective?  Before we take a look at the UI, there are three areas where vSAN Performance metrics can be displayed

  • Cluster level – This is the performance metrics aggregated for the whole cluster and allow you to have the high level view of how your cluster is performing as a whole
  • Host Level – This allows you to look at how vSAN is performing on a host by host perspective and contains further information drilling down through things like Disk Groups, Physical Disks, Network Controllers, VMkernel interfaces.
  • VM Level – This focuses on a specific virtual machine and the objects associated with it.

So what information do we have exactly for a given observation level?  Well let’s first of all take a look at the cluster level performance information, there are three options under the performance tab for vSAN

  • vSAN – Virtual Machine Consumption
  • vSAN – Backend
  • vSAN – iSCSI

I have met many customers that immediately notice there is a big difference between the Virtual Machine Consumption and the Backend graphs, so before we go any further let’s talk about what each of these specific areas mean.

Virtual Machine Consumption
These graphs represent the values that objects residing on the vSAN Datastore are seeing, now remember everything that exists on vSAN is an object, so consumers that are counted in these graphs are Virtual Machines, Stats Objects etc

Backend
These graphs represent the backend disks associated with vSAN, cache and capacity

Both sets of graphs cover the statistics for:

  • IOPS
  • Throughput
  • Latency
  • Congestion
  • Outstanding I/O

iSCSI
The iSCSI Performance graphs contain all the graphs above with the exception of Congestion, these graphs are in relation to each iSCSI Target/LUN created and each one is selected in turn to review the performance graphs associated.

If we move our focus to a host level, in here we have a number of options in addition to the three we also see at a cluster level, however there is some additional metrics we get at a host level for Virtual Machine Consumption and Backend, in the Virtual Machine Consumption graph we have Local Client Cache Hit IOPS and Local Client Cache Hit Rate

And under Backend we also have some additional graphs for Resync IOPS, Resync Throughput and Resync LatencyThe resync metrics are extremely important if vSAN is recovering from a failure of some sort and performing a resync of degraded components, it is also important if you are performing a pro-active rebalance, policy change or a full data migration during host or disk/diskgroup evacuation.

The other options listed under host vSAN performance are:

  • Disk Group – Shows the performance graphs for the disk groups, I will cover this below as this is one of the most interesting set of metrics with a lot of detail.
  • Disk – Shows the physical disks in the host reporting on IOPS, Throughput and  Latency
  • Physical Adapters – Shows the network stats for each vmnic associated with vSAN, stats include Packet Loss Rate which is good for troubleshooting networking issues
  • VMkernel Adapters – Shows the statistics for each VMkernel configured for vSAN, this also includes a Packet Loss Rate which you can then use to troubleshoot the software network stack
  • VMkernel Adapters Aggregation – This is an aggregation of all VMkernel interfaces being used for vSAN on the host

Now let’s go back to the Disk Group performance graphs, as I said earlier this is a very interesting group of metrics to explore, so what do we have in this group?  The first section is all about Frontend (Guest) IOPS, Throughput and Latency

The frontend statistics are maybe as you have guessed already, they are related to vSAN Object I/O being generated from guests running within the vSAN cluster.  If we scroll down a little further we can see statistics relating to Overhead IO,  Read Cache Hit Rate (for hybrid) and Evictions:

Further down we have statistics relating to the vSAN Write Buffer and De-stage rate clearly showing how much of the write buffer is free and also how quickly data is being de-staged from cache to capacity, now we also have resync metrics under disk groups, however this differs slightly against the Cluster Wide Backend statistics, in the disk group graphs we actually have values that represent various aspects of the Resync Operations, the graph differentiates between:

  • Policy Changes
  • Repairs
  • Rebalance

So you can easily distinguish what resync operations are happening by the statistics within the disk group stats.

Collection Interval
The vSAN Performance metrics collect the sample every five minutes, and this is an average over that five minute period, if your cluster is hardly doing anything (like my cluster for the screenshots) then this can throw out some of the latency numbers, in my own cluster I have noticed it shows higher latency when doing practically nothing than it does when I start putting load on the cluster.  I have spoken to many customers about this, it is no concern, it just means that during the collection sample maybe a few “Large” IO operations returned a larger Latency and because of the low number of samples, this skews the average, so no cause for alarm on that one.

Up next will be Day-2 Operations, Performance Monitoring with vROPS, I just have to write it first 🙂