A start of the journal against cold disk will have significant IO latency when compared to hot performance. A solution for this is a warm up procedure.
Workaround: on startup use the DumpJournal utility (which is also accessible from the REST API) to force a full scan of all index pages: See http://wiki.bigdata.com/wiki/index.php/IOOptimization#Branching_Factors
Proposed solution: Use a modified version of the logic in DumpJournal to scan only the non-leaf nodes of the committed versions of the indices. This will force them into both the file system and Java heaps.
Note: the warmup procedure is integrated into web.xml. It can be enabled using the warmupTimeout context-param in web.xml.