article thumbnail

Migrating Netflix to GraphQL Safely

The Netflix TechBlog

Before GraphQL: Monolithic Falcor API implemented and maintained by the API Team Before moving to GraphQL, our API layer consisted of a monolithic server built with Falcor. A single API team maintained both the Java implementation of the Falcor framework and the API Server. To launch Phase 1 safely, we used AB Testing.

Traffic 353
article thumbnail

USENIX LISA2021 Computing Performance: On the Horizon

Brendan Gregg

I summarized these topics and more as a plenary conference talk, including my own predictions (as a senior performance engineer) for the future of computing performance, with a focus on back-end servers. on Upcoming Sapphire Rapids CPUs,” [link] Oct 2020 - [Liu 20] Linda Liu, “Samsung QVO vs EVO vs PRO: What’s the Difference?

Insiders

Sign Up for our Newsletter

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

Trending Sources

article thumbnail

USENIX SREcon APAC 2022: Computing Performance: What's on the Horizon

Brendan Gregg

My personal opinion is that I don't see a widespread need for more capacity given horizontal scaling and servers that can already exceed 1 Tbyte of DRAM; bandwidth is also helpful, but I'd be concerned about the increased latency for adding a hop to more memory. Clone Disk],” - [link] 2020 - [Moore 20] Samuel K. Ford, et al., “TCP

article thumbnail

Cloud infrastructure monitoring in action: Dynatrace on Dynatrace

Dynatrace

As of September 2020, we run 51 clusters on 1100 EC2 instances distributed across six AWS Regions ensuring that all our users can leverage the Dynatrace Software Intelligence Platform to monitor their hybrid-multi cloud environments. Sydney, we have a disk write latency problem! Dynatrace news.

article thumbnail

Dynatrace Managed turnkey Premium High Availability for globally distributed data centers (Early Adopter)

Dynatrace

The network latency between cluster nodes should be around 10 ms or less. For Premium HA, this has been extended from 10 ms latency (in the same network region) to around 100 ms network latency due to asynchronous data replication between regions. In the image below, three downed nodes make an entire cluster unavailable.

article thumbnail

KeyCDN Launches New POP in Mexico

KeyCDN

The POP is strategially located within the country and lowers latency overall. KeyCDN is always on the lookout for ways to minimize latency and accelerate asset delivery worldwide. For more POPs planned, check our current network for a list of both active and planned edge server locations. Hola Mexico!

Latency 111
article thumbnail

USENIX SREcon APAC 2022: Computing Performance: What's on the Horizon

Brendan Gregg

My personal opinion is that I don't see a widespread need for more capacity given horizontal scaling and servers that can already exceed 1 Tbyte of DRAM; bandwidth is also helpful, but I'd be concerned about the increased latency for adding a hop to more memory. Clone Disk],” [link] , 2020 [Moore 20] Samuel K.