Skip to content

Topic

Connectivity Capacity Planning

Designing applications, uploads, and site connectivity around a 100/20 floor with 20Mbps upstream.

Current stories

buildOne report1 publisher

Meta's WhatsApp passed 30 million messages a second at the World Cup final

Meta's engineers say WhatsApp carried more than 30 million messages per second at the July 19 World Cup final, 1.23x its New Year's Eve peak. Meta says the capacity buffers it pre-provisioned were its most effective lever.

Reality

Evidence48
Adoption
Not scored
Hype gap+15
Incentives60
Confidence55
leadershipOne report1 publisher

Infrastructure leaders say AI demand has erased cheap CPU spot capacity

CTOs told Gergely Orosz that CPU spot pricing, once up to 90% below list, has nearly vanished as AI workloads absorb spare cloud capacity. Teams whose compute budgets assumed spot rates now have to plan for getting capacity at all, on top of paying more for it.

Reality

Evidence35
Adoption35
Hype gap+25
Incentives30
Confidence40
buildOne report1 publisher

CTOs say AI demand is wiping out cloud CPU spot discounts of up to 90%

CTOs and infrastructure heads told the Pragmatic Engineer that cloud CPU spot capacity, once up to 90% off, is nearly impossible to get as AI absorbs supply. At standard prices, work budgeted at the deepest spot rate costs ten times as much.

Reality

Evidence35
Adoption40
Hype gap+25
Incentives30
Confidence40
leadershipOne report1 publisher

Aerospike's CTO would judge a database at 3x load with a node down and two years of data growth

Srini Srinivasan argues that evaluations run at comfortable utilization only measure the flat part of the queueing curve. His alternative asks for p99.9 under conditions a two-week bake-off has to manufacture.

Publishers:forbes.com

Reality

Evidence42
Adoption
Not scored
Hype gap+20
Incentives85
Confidence60
buildOne report1 publisher

Every project in a Foundry account draws IPs from the same delegated subnet

In a bring-your-own-VNet Foundry Agent Service deployment, hosted agent sessions and data proxy instances take addresses from one delegated subnet. When it fills, session creation answers HTTP 429 subnet_exhausted.

Publishers:dev.to

Reality

Evidence28
Adoption
Not scored
Hype gap+35
Incentives30
Confidence42
buildOne report1 publisher

One shared hosting login puts ten client sites in a single failure domain

A hosting guide from EniyiSunucum sets one account per client as the minimum boundary for an agency portfolio. The part of it worth keeping is the queueing account of why a neighbour's traffic spike hurts.

Publishers:dev.to

Reality

Evidence30
Adoption
Not scored
Hype gap+8
Incentives60
Confidence55
buildOne report1 publisher

Polling 100,000 clients at 1 Hz spends 819 Mbps on request headers before any payload

A dev.to post works the header-overhead sum for short polling and lands on 102.4 MB/s of pure framing metadata. The same sum separates polling from a held-open connection, and the three protocols in its title all sit on the same side of it.

Publishers:dev.to

Reality

Evidence45
Adoption
Not scored
Hype gap+30
Incentives20
Confidence50
buildOne report1 publisher

Kafka share groups swap partition ownership for a 2,000-record lock budget

KIP-932 lets a group run more consumers than a topic has partitions by locking each record for 30 seconds and counting its deliveries. The idempotence, the retries and the lock sizing become the application's job.

Publishers:dev.to

Reality

Evidence62
Adoption30
Hype gap0
Incentives25
Confidence55
leadershipOne report1 publisher

A Meta infrastructure lead argues that who degrades first belongs in writing before the outage

Manas Chaudhari, tech lead for WhatsApp's messaging infrastructure at Meta, says forecasting capacity is the easy half, and the hard half is agreeing in advance which customers and features get dropped first.

Publishers:forbes.com

Reality

Evidence38
Adoption15
Hype gap+18
Incentives55
Confidence55
buildOne report1 publisher

Red Hat's two-node OpenShift edge clusters leave one survivor carrying the whole workload

TNA keeps a third etcd vote in a lightweight arbiter; TNF fences the dead node over its BMC. Both keep an edge cluster running on two servers, and both leave one survivor to run everything the site was running.

Publishers:dev.to

Reality

Evidence48
Adoption25
Hype gap+10
Incentives55
Confidence50
buildOne report1 publisher

One arithmetic line turns last year's peak hour into a baseline -- then headroom sets this year's Black Friday concurrency target

A twelve-week countdown for Black Friday 2026 sizes the load target from sessions per hour and average session length, then pushes a journey-level test past that target until the response-time tail bends.

Publishers:dev.to

Reality

Evidence50
Adoption
Not scored
Hype gap+10
Incentives30
Confidence55
buildOne report1 publisher

GitHub bought three months of Actions headroom by rerouting a third of its jobs

GitHub's August availability report reads as a capacity argument rather than a bug report, with the Actions fix described as containment and the harder database failovers still ahead of it.

Publishers:github.blog

Reality

Evidence60
Adoption72
Hype gap+5
Incentives78
Confidence58
buildOne report1 publisher

Two vCPUs rendered 5,000 separately editable sites at 150 requests a second

Kooboo shipped the request-level CSVs and the provisioning script behind a ten-minute run that averaged 45.6% CPU, so the interesting question is no longer the headline but which of its conditions your own tenants share.

Publishers:dev.to

Reality

Evidence55
Adoption
Not scored
Hype gap+10
Incentives80
Confidence58
buildOne report1 publisher

Sizing a session broker in open sessions lands a 200-person org on a 512 MB VM

A proxied session costs about 320 KB of buffers and goroutine stacks, so peak load for a mid-size engineering organisation is tens of megabytes, and the constraint that actually bites is the controller's network interface.

Publishers:dev.to

Reality

Evidence46
Adoption
Not scored
Hype gap−12
Incentives66
Confidence54
buildOne report1 publisher

A 100-worker PHP-FPM pool tops out at 500 req/sec on a 200ms endpoint

Worker occupancy is arrival rate times service time, which is why an in-controller Redis hit only moves the ceiling and an edge proxy is the only layer that stops a request before a worker is allocated.

Publishers:dev.to

Reality

Evidence28
Adoption
Not scored
Hype gap+55
Incentives85
Confidence55
buildOne report1 publisher

Video bytes decide whether Immich needs 1.35x or 1.6x your library

A sizing guide for a 20,000 item Immich import puts the floor at four cores and 6 GB of RAM, but the disk figure moves with how much unplayable video you own, and three first-hour settings decide whether you pay for the processing twice.

Publishers:dev.to

Reality

Evidence30
Adoption
Not scored
Hype gap+15
Incentives30
Confidence38
buildOne report1 publisher

Docker Swarm blocks a new task over memory the running container never touches

Two declared reservations totalling 110% of node memory left a task pending in a single-node lab while both containers idled at 480 KiB. Cutting one reservation to 20% released it with nothing else changed.

Publishers:dev.to

Reality

Evidence72
Adoption
Not scored
Hype gap−5
Incentives22
Confidence63