On July 11, 2008 starting at 10pm we will have a brief network outage to restructure our routing tables. We are planning two hours to deal with any quirks that may come up, however our Cisco network engineer estimates the total downtime to be under 30 minutes.
During this downtime DreamHost will be completely inaccessible, however [...]
The puncher file server for users on the postal cluster required a quick reboot this evening. The cause of this reboot was battery issues and caused services across several servers to become unresponsive for a short amount of time. Services are being restarted now tho and should be back up momentarily.
Please note that there will [...]
For security reasons, we’ll be upgrading kernels on some of our servers today, requiring a quick reboot. It’s only about 15% of the servers, so most of you won’t notice any impact. We’ll also be putting some measures in place to prevent unnecessarily long downtimes so total downtime should be in the range [...]
We are experiencing some file server issues with the “janky” cluster which are causing some higher loads and email slowness. Our network file server admins are investigating the cause to get this fixed as soon as possible. Our apologies for the inconvenience. When we have further information we will update this post.
– Update –
At [...]
We are currently experiencing an outage in the spunky cluster. This is affecting your ability to connect to the incoming / outgoing mailserver. Our Admins are currently working to resolve the issue. There aren’t any further details at this time. Again, we sincerely apologize for any inconvenience this may have caused. Please check back here [...]
We are upgrading the file server gloat to the next update release of Solaris. This should resolve the crashing issues we have been experiencing over the past week or two. We have tested this upgrade on multiple other machines and it has cleared up the SATA driver bug with which the servers seem to ship.
This [...]
One of the file servers is having issues serving NFS requests to servers in the Janky cluster. This could potentially impact users on the following clusters:
adonis agamemnon ajax aphrodite apollo aries atlas baachus barefoottours calypso charon charybdis chronos coolblue daedalus dione dionysus electra erebus erida eros ganesha gorgon hades hecate hector helios hephaestus hera heracles [...]
Folks on blingy might be experiencing some issues with their sites coming up right now. The main network file server on the cluster was in need of a reboot and was causing some problems for customers. Once the issue is resolved we will update this entry with as much information as we possibly can.
Update: A [...]
Two of the file servers serving the janky cluster have rebooted themselves due to a hung process working on the filesystem. They are both back up and serving files again, and we are working on cleaning things up. We will post an update when we feel everything is back to normal.
Update: one of [...]
The “trailer” filer is currently down and we’re attempting to bring it back up! We will update everyone as soon as we’ve brought it back to life! If you are on any of the following servers, you will be affected by this:
afree annie apu arnie bart bigredgiant bitters brandine busycards carl cheeky cletus dansweb dawber [...]
Comments: