data-konzept

'When we released Always On Availability Groups in SQL Server 2012 as a new and powerful way to achieve high availability, hardware environments included NUMA machines with low-end multi-core processors and SATA and SAN drives for storage (some SSDs). Performance issues surrounding Availability Groups typically were related to disk I/O or network speeds. As we moved towards SQL Server 2014, the pace of hardware accelerated. Our customers who deployed Availability Groups were now using servers for primary and secondary replicas with 12+ core sockets and flash storage SSD arrays providing microsecond to low millisecond latencies. While we were confident in the design of SQL Server 2012, several customers reported to us performance problems that did not appear to be with disk subsystems, CPU, or networks. The rapid acceleration in technology brought on a new discovery and paradigm. Now disk I/O and CPU capacity were no longer an issue. Our design needed to scale and be adaptable to the modern hardware on the market. We needed to start thinking about how fast can we replicate to a synchronous secondary replica in terms of % of the speed of a standalone workload. (one without a replica).'...

https://blogs.msdn.microsoft.com/sqlserverstorageengine/2016/09/26/sql-server-2016-it-just-runs-faster-always-on-availability-groups-turbocharged/