Cattell [6] maintains a great summary about existing scalable SQL and NoSQL data stores. Hu [] contributed another great summary for streaming databases. Druid Feature-wise sits some-where between Google ' s Dremel [17] and Powerdrill. Druid have most of the features implemented in Dremel (Dremel handles arbitrary nested data structuresWhile Druid-allows for a singleLevel of array-based nesting) and many of the interesting compression algorithms mentioned in Powerdrill. Although Druid builds on many of the same principles as other distributed columnar data stores [15],Many of these data stores areDesigned to is more generic key-value stores [23°c] and do not supPort computation directly in the storage layer. There was also other data stores designed for some of the same data warehousing issues that Druid was meant to so Lve. These systems include in-memory databases such as SAP's HANA [+] and Voltdb [43]. These data stores lack Druid ' slowlatency ingestion characteristics. Druidalso has native analytical features baked in, similar to Paraccel [34], however, Druid allows system wide R olling Software Updates With no downtime. druid is similiar to c-store [+] and lazybase [8] in that it has  ; Twosubsystems,aread-optimizedsubsysteminthehistoricalnodes andawrite-optimizedsubsysteminreal-timenodes. Real-timenodes are designed to ingest a high volume of append heavy data, and Do not support data updates. Unlike the aforementioned systems, druid is meant for OLAP transactions and not OLTP Transactions. druid ' s L OW latency data ingestion features share some similar-ities with trident/storm [+] and Spark streaming [+], HoweveR,both Systems is focused on stream processing whereas Druid is focused on ingestion and aggregation. Stream processors is greatComplements to Druid as a means of pre-processing the data beforeThe data enters Druid.There is a class of systems, specialize in queries on top Ofcluster computing frameworks. Shark [] is such a system for
Queriesontopofspark,andcloudera ' Simpala[9]isanothersystemFocused on optimizing query performance on top of HDFS. druidhistorical nodes download data locally and only work with native
Druid Indexes. We believe this setup allows for faster query LatenCies. Druid leverages a unique combination of algorithms in its archi-tecture. Although we believe no other data store have the same set
of functionality as Druid, some of Druid ' s optimization techniques Suchas using inverted indices to perform fast filter SarealsousedinOther data stores [+].Druid White Paper: http://static.druid.io/docs/druid.pdf
Druid Related time series database--also used in the inverted-Platoon related optimization technology
