Dumps/Snapshot hosts

Snapshot (XML dumps generation) cluster information

These hosts generate the XML dumps. For information about the hosts that serve them, see Dumps/Dump servers.

We have one mini snapshot cluster. Eventually another will be set up in codfw.

In D.C.:

snapshot1001: primary, PowerEdge R815, Ubuntu 12.04.2, 64GB RAM, 4 8-core Opterons, 2 80GB HDs
snapshot1002: primary, PowerEdge R410, Ubuntu 12.04.2, 12GB RAM, 2 6-core Xeons, 500GB HD
snapshot1003: primary, PowerEdge R410, Ubuntu 12.04.2, 12GB RAM, 2 6-core Xeons, 500GB HD
snapshot1004: primary, PowerEdge R410, Ubuntu 12.04.2, 12GB RAM, 2 6-core Xeons, 500GB HD

The beefier server (with 4 8-core cpus) is a dedicated machine for the en wikipedia dumps.

The dumps monitor which cleans up stale locks and generates the index.html file, can run on either snapshot1002 or snapshot1004.

Worker nodes:

En wikipedia dumps run on snapshot1001 via the dump scheduler.

All other dumps run on snapshot1002 and snapshot1004 via the dump scheduler.

For info on running the dumps, see Dumps#Starting_dump_runs.

All dump-related cron jobs run on snapshot 1003. From here central auth dumps are run, wikidata json dumps are generated, and so on.