Live data from Hacker News

Bluesky April 2026 Outage Post-Mortem

pckt.blog

1–10 of 85 posts

Re: Bluesky April 2026 Outage Post-Mortem

#2
> What I had missed is that we deployed a new internal service last week that sent less than three GetPostRecord requests per second, but it did sometimes send batches of 15-20 thousand URIs at a time. Typically, we'd probably be doing between 1-50 post lookups per request.

That’ll do it.

Re: Bluesky April 2026 Outage Post-Mortem

#3

> What I had missed is that we deployed a new internal service last week that sent less than three GetPostRecord requests per second, but it did sometimes send batches of 15-20 thousand URIs at a time. Typically, we'd probably be doing between 1-50 post lookups per request. That’ll do it.

Zero, one, many, many thousands.

Re: Bluesky April 2026 Outage Post-Mortem

#4

> What I had missed is that we deployed a new internal service last week that sent less than three GetPostRecord requests per second, but it did sometimes send batches of 15-20 thousand URIs at a time. Typically, we'd probably be doing between 1-50 post lookups per request. That’ll do it.

Ahh, the three relevant numbers in development: 0, 1, and infinity.

Re: Bluesky April 2026 Outage Post-Mortem

#7
> The timing of these log spikes lined up with drops in user-facing traffic, which makes sense. Our data plane heavily uses memcached to keep load off our main Scylla database, and if we're exhausting ports, that's a huge problem.

I expect this is common.

Post reply on HN