In a recent experiment using Amazon RDS instance and a VM running in an on-prem Nutanix cluster, both using Skylake class processors with similar clock speeds and vCPU count. The SQLServer database on Nutanix delivered almost 2X the transaction rate as the same workload running on Amazon RDS.
It turns out that migrating an existing SQLServer VM to RDS using the same vCPU count as on-prem may yield only half the expected performance for CPU heavy database workloads. The root cause is how Amazon thinks about vCPU compared to on-prem.
A Nutanix cluster can persist a replicated write across two nodes in around 250 uSec which is critical for single-threaded DB write workloads. The performance compares very well with hosted cloud database instances using the same class of processor (db.r5.4xlarge in the figure below). The metrics below are for SQL insert transactions not the underlying IO.
Single threaded commit heavy insert rates. Latency as seen from SQL insert statement.
AOS 6.1 greatly improved database performance on Nutanix especially when the guest VM uses just a single disk for all the database files. The underlying change is known as vdisk sharding. Basically it allows the Nutanix CVM to scale up the number of threads used to service a single virtual disk under heavy load.
From the SQL Window of SQL*Server. Issue these commands to drop the tables and procedures created by HammerDB. This will allow you (for instance) to re-create the database, or create a new database with more warehouses (larger size) while retaining the same name/DB layout.
Some versions of HammerDB (e.g. 3.2) may induce imbalanced NUMA utilization with SQL Server.
This can easily be observed with Resource monitor. When NUMA imbalance occurs one of the NUMA nodes will show much larger utilization than the other. E.g.
Imbalanced NUMA usage by SQL Server.
The cause and fix is well documented on this blog. In short HammerDB issues a short lived connection, for every persistent connection. This causes the SQL Server Round-robin allocation to send all the persistent worker threads to a single NUMA Node! To resolve this issue, simply comment out line #212 in the driver script.
Comment out this line to work-around the HammerDB NUMA imbalance problem.
If successful you will immediately see that the NUMA nodes are more balanced. Whether this results in more/better performance will depend on exactly where the bottleneck is.
TL;DR It’s pretty easy to get 1M SQL TPM running a TPC-C like workload on a single Nutanix node. Use 1 vDisk for Log files, and 6 vDisks for data files. SQL Server needs enough CPU and RAM to drive it. I used 16 vCPU’s and 64G of RAM.
Running database servers on Nutanix is an increasing trend and DBA’s are naturally skeptical about moving their DB’s to new platforms. I recently had the chance to run some DB benchmarks on a couple of nodes in our lab. My goal was to achieve 1M SQL transactions per node, and have that be linearly scalable across multiple nodes.
It turned out to be ridiculously easy to generate decent numbers using SQL Server. As a Unix and Oracle old-timer it was a shock to me, just how simple it is to throw up a SQL server instance. In this experiment, I am using Windows Server 2012 and SQL-Server 2012.
For the test DB I provision 1 Disk for the SQL log files, and 6 disks for the data files. Temp and the other system DB files are left unchanged. Nothing is tuned or tweaked on the Nutanix side, everything is setup as per standard best practices – no “benchmark specials”.
Load is being generated by HammerDB configured to run the OLTP database workload. I get a little over 1Million SQL transactions per minute (TPM) on a single Nutanix node. The scaling is more-or-less linear, yielding 4.2 Million TPM with 4 Nutanix nodes, which fit in a single 2U chassis . Each node is running both the DB itself, and the shared storage using NDFS. I stopped at 6 nodes, because that’s all I had access to at the time.
The thing that blew me away in this was just how simple it had been. Prior to using SQL server, I had been trying to set up Oracle to do the same workload. It was a huge effort that took me back to the 1990’s, configuring kernel parameters by hand – just to stand up the DB. I’ll come back to Oracle at a later date.
My SQL Server is configured with 16 vCPU’s and 64GB of RAM, so that the SQL server VM itself has as many resources as possible, so as not to be the bottleneck.
I use the following flags on SQL server. In SQL terminology these are known as traceflags which are set in the SQL console (I used “DBCC trace status” to display the following. These are fairly standard and are mentioned in our best practice guide.
One thing I did change from the norm was to set the target recovery time to 240 seconds, rather than let SQL server determine the recovery time dynamically. I found that in the benchmarking scenario, SQL server would not do any background flushing at all, and then suddenly would checkpoint a huge amount of data which caused the TPM to fluctuate wildly. With the recovery time hard coded to 240 seconds, the background page flusher keeps up with the incoming workload, and does not need to issue huge checkpoints. My guess is that in real (non benchmark conditions) SQL server waits for the incoming work to drop-off and issues the checkpoint at that time. Since my benchmark never backs off, SQL server eventually has to issue the checkpoint.
