Storage is down; Server clusters and Servers and services are degraded.
30-day uptime
99.815%
Services answering
31 / 32
1 down
Open incidents
0
none posted
Last check
17:24 UTC
4 s ago
Past 30 days
5
incidents resolved
Services
Each check runs every 60 s · touch, hover or use the arrow keys on a bar to read a day
Neura Name
Operational
99.99% over 30 days
100% uptime
100% uptime
100% uptime
99.95% uptime
100% uptime
100% uptime
100% uptime
100% uptime
100% uptime
Payments
Operational
100% over 30 days
100% uptime
100% uptime
100% uptime
Neura Build
Operational
100% over 30 days
100% uptime
100% uptime
100% uptime
100% uptime
Neura Zone
Operational
99.72% over 30 days
99.50% uptime
99.90% uptime
100% uptime
Neura Space
Outage
99.05% over 30 days
98.86% uptime
99.21% uptime
97.35% uptime
99.84% uptime
100% uptime
GitLab
Operational
99.93% over 30 days
99.93% uptime
Platform
Degraded
99.81% over 30 days
99.59% uptime
99.72% uptime
99.81% uptime
100% uptime
100% uptime
Neva
Operational
100% over 30 days
100% uptime
100% uptime
30 days ago
Operational
Degraded
Outage
No data
Today
Past incidents
Some Neura Spaces offline again for up to 13 minutes
ResolvedNeura Space
Started
Oct 18, 12:53 UTC
Last update
Oct 18, 20:29 UTC
Status
Resolved
Duration
17 min
Updates
ResolvedOct 18, 20:29 UTC
Between 12:53 and 13:10 UTC about 40 Neura Spaces were offline again, each for 8 to 13 minutes, for the same reason as the outage at 03:13 UTC: the services that store Space data ran out of memory. No data was lost. Adding storage capacity and changing how storage copies are rebuilt fixed it, and Spaces have run normally since 13:10 UTC. (Recorded after the fact.)
Some Neura Spaces offline for up to 13 minutes
ResolvedNeura Space
Started
Oct 18, 03:13 UTC
Last update
Oct 18, 20:29 UTC
Status
Resolved
Duration
13 min
Updates
ResolvedOct 18, 20:29 UTC
Between 03:13 and 03:26 UTC about 40 Neura Spaces were offline, each for 8 to 13 minutes. The services that store Space data ran out of memory and restarted, and the Spaces on them stopped until they came back. No data was lost. We added storage capacity; the same failure returned at 12:53 UTC (see the entry above). (Recorded after the fact.)
Brief errors on the Neura Space test Space during an update
ResolvedNeura Space
Started
Oct 17, 15:05 UTC
Last update
Oct 17, 18:46 UTC
Status
Resolved
Duration
5 min
Updates
ResolvedOct 17, 18:46 UTC
Between 15:05 and 15:10 UTC, while we updated our test Space (the Space that gets every update first), its sign-in and Neva answered with errors. People's own Spaces were not part of this update and were not affected. The test Space has answered normally since 15:10 UTC. (Recorded after the fact.)
Reduced storage redundancy in Neura Space
ResolvedNeura Space
Started
Oct 17, 11:38 UTC
Last update
Oct 17, 18:46 UTC
Status
Resolved
Duration
6 h 47 min
Updates
ResolvedOct 17, 18:46 UTC
Between 11:38 and 18:25 UTC, short stalls on the servers under Neura Space storage made some Space disks lose one of their three copies for a while. Spaces kept working on the other copies and no data was lost. Every copy was rebuilt automatically, the last at 18:25 UTC. We have stopped placing new copies on the server that stalled most often and are looking into the cause. (Recorded after the fact.)
Sign-in unavailable for 8 minutes
ResolvedNeura Name
Started
Oct 16, 13:35 UTC
Last update
Oct 17, 18:46 UTC
Status
Resolved
Duration
8 min
Updates
ResolvedOct 17, 18:46 UTC
Between 13:35 and 13:43 UTC nobody could sign in to Neura: neura.name, and through it Neura Build, Neura Zone and Neura Space. An update to our sign-in service went out with a wrong database setting. We corrected the setting and sign-in has worked since 13:43 UTC. We now check that setting after every update to the sign-in service. (Recorded after the fact.)
