On Tue, Jun 2, 2009 at 10:53 PM, mibrahim <[email protected]> wrote: > > Hi, > > First thanks for the excellent contribution of hypertable. > > When a query is distributed on range servers, how does hypertable > guarantee that most of the data is on the same machine as the range > server, when the data is stored on a DFS like kfs ? > > It seems to me that running a query on local or almost local data and > moving the result is much faster than moving the data over the network > and running the query on it. However, the architectural overview and > this diagram ( http://www.hypertable.org/images/SystemOverview.jpg ) > implies that rangeservers are agnostic of the physical location of > their files and there is no communication between kfs and hypertable > in regards to which files are best represented by every range server.
AFAIK the locations are stored in the METADATA table. Currently the DfsBroker does not support using the location API. When speaking of that matter, I have a set of patches that enable location API in the DfsBroker. Shall I send them in ? > Is my understanding right - or is there another component that takes > care of this issue ? As mentioned above, the locations are stored in METADATA table. best, Mateusz --~--~---------~--~----~------------~-------~--~----~ You received this message because you are subscribed to the Google Groups "Hypertable Development" group. To post to this group, send email to [email protected] To unsubscribe from this group, send email to [email protected] For more options, visit this group at http://groups.google.com/group/hypertable-dev?hl=en -~----------~----~----~----~------~----~------~--~---
