presentation

Performance Tipping Points: Hitting Hardware Bottlenecks

PublishedJune 20, 2017
LanguageEnglish

Speaker: Akira Kurogane, Senior Technical Services Engineer, MongoDB

One week your active dataset consumes 90% of available RAM. The next week it's 110%. Is that a 10% or 99% performance degradation? Let's discover what it looks like when different hardware capacity limitations are hit. For example, memory vs. disk bottlenecks, the rare CPU bottleneck and network bottlenecks, seeing what happens when you drop a crucial index during peak load, or what happens when you run multiple WiredTiger nodes on the same server without limiting their cache size.

View Presentation

view presentation