Dear Wiki user, You have subscribed to a wiki page or wiki category on "Hadoop Wiki" for change notification.
The following page has been changed by stack: http://wiki.apache.org/hadoop/Hbase/NewFileFormat ------------------------------------------------------------------------------ * Optimal random-access * Iterate over keys only, rather than mapfiles currenty key+values always. This'd be useful when trying to find closest. TFile and SequenceFile can do this (Its not exposed in !MapFile). * Smart getClosest and getClosestAtOrBefore [https://issues.apache.org/jira/browse/HBASE-792 hbase-792] + * Get vs. Scan accesses. Latter has state. + * Sharing blocks and indices: Can have multiple Readers on a single file (e.g. many concurrent Scanners). If so, rather than read in index for each instance, share indices if one already in-memory. Same for file blocks. Only make trip to datanode if not already instance of the (read-only) block in mem. === Index === TODO, but the TFile block-based rather than !MapFile interval-based would seem better for us; indices then are of predicatable size; a seek to the index position will load at an amenable spot when blocks are compressed.
