Edge Compute Infrastructure for Experience Business

on YouTube ↗39m

" summary

Adobe builds a geo-distributed compute edge using Kafka for streaming, Aerospike as the edge data store, and XDR plus custom replication to sync a central unified profile hub to many edges. The system handles ~10 PB of 60–90 day lookback data, distills it to ~20 TB of edge signals, sustains 4–5M hits/sec with a 4:1 read:read-modify-write pattern, targets 2 ms 95th‑percentile reads, accepts ~5s loose‑consistency sync, and supports mixed tenancy and reactive/proactive replication.

AI-written summary · about

" chapters (9)

1. 0:00AEROSPIKE USER SUMMIT 2018
2. 5:51Computation for an Enterprise Experience Business
3. 6:51Adobe Edge Continuum
4. 12:40Adobe Cloud Platform: Unified Profile
5. 15:50Adobe Edge Components
6. 19:46Adobe Edge Store: Features
7. 21:39Adobe: Edge System Scale
8. 25:21Adobe Edge Store: Horizontal Scaling
9. 27:54Adobe Edge Store: Synchronization

" related talks

• 32mDistributed Personalization in Edge Computing EnvironmentSandeep Nawathe · Aerospike Virtual Summit ’20
• 33mUsing Aerospike as a Real-time System-of-Record for Adobe Experience Cloud Services on AzureRichard Li, Aravind Sriram · Aerospike Digital Summit 2021
• 23mAdobe + Aerospike: Real-time Streaming SegmentationSandeep Nawathe · Aerospike Summit 2023
• 36maccelerating the digital agendaDr. Sudhir Kumar Mittal · Aerospike Summit 2022: Mission Now
• 40mMastering small chunks of data in high frequency ad-tech systemsThomas Peruzzi · Aerospike Virtual Summit ’20
• 48mThe real-time database to build your AI futureAmit Shah, Lenley Hensarling, Shai Peretz, Ujjwal Wadhawan · AWS re:Invent 2023
• 40mDeveloping highly scalable applications with AerospikeVenkat Thamminana · Aerospike Virtual Summit ’20
• 32mBuilding a Real-time Ingestion Platform using Kafka and AerospikeMatteo Pelati · Aerospike Virtual Summit ’20