We will be performing major network upgrades to our backbone network in Paris during the night of 23-24 March 2013.
The purpose of this work is to replace our current (aging) backbone network routers with newer generation equipment allowing for increased capacity, performance and resilience. During this time, all Gandi services in Paris will experience brief periods of network unavailability and/or instability as the migration proceeds.
This activity will not impact the individual Gandi services themselves, but rather only the network connectivity between the internet and those services. As a result, there will be no need for hosting customers to restart their IaaS or PaaS servers/instances. Services in our Baltimore datacentre will not be directly affected by this maintenance, but some periods of routing instability and reconvergence may be experienced, though these will be far less prevalent than for the Paris services.
This migration will commence at 01:30 CET (00:30 GMT) on Sunday 24 March 2013, and we estimate between 10 and 15 minutes of major network outage during the initial migration, followed by a number of brief periods of network instability during the remainder of the migration. The entire migration activity should last approximately 90 minutes, but no more than two hours.
Operations will be ended at 05:00 AM CET (04:00 AM GMT).
We apologise in advance for any inconvenience this may cause.
Due to a fibre cut between Telehouse2 and Equinix in Paris, some Gandi services are disrupted. We are attempting to mitigate as much as possible, but some services are dependent on this inter-site connectivity. Our fibre suppliers are working to resolve the issue as soon as possible.
14:00 CET (13:00 GMT): Connectivity has been restored.
We have experienced a partial power failure at Equinix PA2 at 10:07 CEST this morning. The power failure lasted a few seconds, but had a knock-on effect on some equipment, notably some older generation equipment with single power supply causing them to reboot, and lose network connectivity with some backend services.
Our teams are working to restore all affected services.
Due to a fiber cut in Paris, some domain registration activities may be unavailable or unresponsive as the registries concerned are not accessible via the internet or peering points. Connections via the PANAP and SFINX peering exchanges are especially affected. We are monitoring the situation and will update when we have more information. (Note that this fiber cut has an impact on many providers, and not only Gandi.)
Update: 10:10 CET: Connectivity restored for most peers at SFINX. Panap still has several peers down. Connectivity to registries should be operational now.
Some customers may have experienced some degradation or a brief outage of the Gandi Mail service for mailboxes located on the affected switch module. The Gandi Website may also have experienced slower performance.
The affected card was replaced and all services are now fully operational as of 19:54 CET.
We apologise for any inconvenience this may have caused, and we are investigating with our supplier as to the cause of the hardware fault.