Catalogue

Cards
165
Records
486
Workloads
19
Corpus version
74847648e25a
Workload
Kind
Setup

92 of 486 records match; the first 20 are shown.

KindRecordOrganisationYearSetup
Decision

Measure Above-the-Fold completion, paginate with a server-side cache, and render HTML templates concurrently

uber-2026-eats-search-pipeline#d1

Uber2026Sharded
Decision

Drop low-yield lexical retrieval arms, deduplicate chains earlier, and group features by product embeddings

uber-2026-eats-search-pipeline#d2

Uber2026Sharded
Decision

Split monolithic hydration into parallel ranking and presentation phases and remove false DAG dependencies

uber-2026-eats-search-pipeline#d3

Uber2026Sharded
Decision

Hedge slow requests across four presentation hydration dependency layers to reduce tail latency

uber-2026-eats-search-pipeline#d4

Uber2026Sharded
Decision

Move ads bid scoring to a columnar layout with in-memory ad data and drop redundant serialization

uber-2026-eats-search-pipeline#d5

Uber2026Sharded
Decision

Fix encoding, embedding size, service-mesh connection caps, and Go GC overhead found via profiling

uber-2026-eats-search-pipeline#d6

Uber2026Sharded
Decision

Replace managed object storage with Versity S3 Gateway on one server, backed up by rsync, to stop provider slowdowns

healthchecks-2026-object-storage#d1peak under 1,000 requests/s

Healthchecks.io2026One server
Failure

Users who follow hundreds of thousands of accounts made hot shards that slowed the timelines sharing them

bluesky-2025-lossy-timelines#f1peak of 100,000 requests/s or more

Bluesky2025Sharded
Decision

Drop timeline writes with a probability set by how many accounts a user follows, accepting imperfect timelines

bluesky-2025-lossy-timelines#d1peak of 100,000 requests/s or more

Bluesky2025Sharded
Decision

Cache high-follow accounts in a Redis sorted set loaded into memory every 30 seconds instead of reading follow counts per write

bluesky-2025-lossy-timelines#d2peak of 100,000 requests/s or more

Bluesky2025Sharded
Decision

Move the public sites from bare-metal data centers to Kubernetes in one GCP region, using Windows Kubernetes for legacy .NET apps

stackoverflow-2025-cloud-migration#d1

Stack Overflow2025One site
Decision

Run SQL Server on dedicated high-memory GCP VMs with half the CPU cores disabled instead of managed cloud SQL

stackoverflow-2025-cloud-migration#d2

Stack Overflow2025One site
Decision

Use GCP MemoryStore for Redis with key prefixes instead of self-hosting Redis on Kubernetes

stackoverflow-2025-cloud-migration#d3

Stack Overflow2025One site
Decision

Self-host Elasticsearch on Kubernetes with the ECK operator instead of using Elastic Cloud

stackoverflow-2025-cloud-migration#d4

Stack Overflow2025One site
Decision

Load-test the cloud stack in isolated Terraform-built environments matching production before migrating

stackoverflow-2025-cloud-migration#d5

Stack Overflow2025One site
Decision

Plan to put public assets behind Cloudflare CDN and process its logs in Snowflake, retiring HAProxy logs and TPS

stackoverflow-2025-cloud-migration#d6

Stack Overflow2025One site
Decision

Package cross-cloud deployments in CNAB containers deployed via Octopus Deploy and GitHub Actions

stackoverflow-2025-cloud-migration#d7

Stack Overflow2025One site
Decision

Build DocDB as a self-managed sharded DBaaS in Go over MongoDB Community with a minimal query API

stripe-2024-docdb#d1peak of 100,000 requests/s or more

Stripe2024Sharded
Decision

Sort bulk-imported chunk data by common index attributes before inserting into B-tree storage

stripe-2024-docdb#d2peak of 100,000 requests/s or more

Stripe2024Sharded
Decision

Replicate migration writes bidirectionally from Kafka and S3 CDC oplogs and verify with snapshots

stripe-2024-docdb#d3peak of 100,000 requests/s or more

Stripe2024Sharded

72 more records. Sign in to see all 92.