compute-edge_
▸ Status

All systems operational.

Last check 12 seconds ago · Refresh in 60s · 99.974% uptime over the last 90 days
Functions runtime Edge-deployed function execution across all PoPs
p50 latency8 ms
success rate (1h)99.998%
operational
KV Distributed key/value store
p50 read0.7 ms
replication lag340 ms
operational
Objects S3-compatible blob storage
p50 get11 ms
success rate (1h)100.000%
operational
Control plane Dashboard, CLI auth, deploy pipeline
api p5042 ms
success rate (1h)99.992%
operational
▸ PoP health · 90 days

14 PoPs · 6 regions

adl-01Adelaide, AU
uptime 99.99%p50 7 ms
syd-02Sydney, AU
uptime 100.00%p50 6 ms
per-01Perth, AU
uptime 99.94%p50 9 ms
mel-01Melbourne, AU
uptime 99.98%p50 7 ms
bne-01Brisbane, AU
uptime 100.00%p50 8 ms
akl-01Auckland, NZ
uptime 99.99%p50 8 ms
wlg-01Wellington, NZ
uptime 100.00%GA 2026-05-08
sin-01Singapore
uptime 99.97%p50 10 ms
nrt-02Tokyo, JP
uptime 100.00%p50 9 ms
hkg-01Hong Kong
uptime 99.92%p50 11 ms
fra-01Frankfurt, DE
uptime 99.96%p50 6 ms
ams-01Amsterdam, NL
uptime 100.00%p50 7 ms
tll-01Tallinn, EE
uptime 100.00%p50 4 ms
iad-01Ashburn, US
uptime 99.99%p50 9 ms
▸ Recent incidents

Last 90 days

Elevated p50 latency at fra-01 — brief BGP route flap
2026-04-22 · 14:32−14:51 UTC · 19 min
fra-01 · impact: Functions p50 up to 38 ms resolved

Frankfurt PoP saw a transient BGP route flap with our DE-CIX transit provider. Failed requests at <0.01%; p50 latency briefly elevated to ~38 ms before traffic was rebalanced through ams-01. Root cause was a misconfigured route reflector on the transit side, confirmed by DE-CIX.

Brief KV write rejection at per-01 after disk replacement
2026-03-08 · 02:14−02:28 UTC · 14 min
per-01 · impact: KV writes rejected (5xx) at per-01 only resolved

Hot-replaced an SSD in the Perth PoP. The replacement node took longer than expected to rejoin the KV write quorum (14 min vs the usual ~3). Reads were unaffected (served from other PoPs). KV writes returned 503 at Perth and were correctly retried by client SDKs.

Control plane — sign-in slow during dashboard deploy
2026-02-19 · 10:02−10:11 UTC · 9 min
control-plane · impact: dashboard sign-in p95 up to 4 s resolved

A dashboard deploy queued behind a long-running migration. Sign-in worked but was slow. Functions, KV, and Objects were unaffected throughout. Migration runtime is now bounded.

Get notified.

One email when an incident opens, one when it resolves. No marketing, ever.