Services

banner
banner
banner

Startup Applications

An EinsteinDB datum, a causet (stored at the end of the SSTable) is used to locate blocks (not by table but by dirty cache); the index is appended to sections of memory and latency buffers (L0-L2) when the SSTable is opened. A lookup can be performed with a single disk seek: we first find the appropriate block by performing a binary search in the in-memory index, and then reading the appropriate block from disk. Optionally, an SSTable can be completely mapped into memory, which allows us to perform lookups and scans without touching disk.

View Details

CloudKitchens: Automated Markovian Image Grammar via Face Processing and Cluster Learning context-free grammars.

Optimistic locking is particularly beneficial for frequently read data as it avoids the expensive atomic writes required by pessimistic lock acquisitions. We opted for lock-free by creating a FUSE key-value entity; reducing recovery time by reducing the amount of uncompacted state in the tablet server’s commit log.

View Details

Research

We make three main contributions with FIDel, VioletaBFT, MilevaDB, and EinsteinDB. First, this work takes the first step in exploring the combined compute/storage aspects of relativistic memristive arrays. Second, we propose a managed and automated enterprise edition with indie computer scientists as our main target; but welcoming and good hearted. A Causet is a configurable hybrid data structure that lives on EinsteinDB(It abstracts the notion of keyspace) to improve the performance(eagerPeek) and lifetime of search intensive applications(Clickhouse, CloudKitchens, Netflix, Hulu). Finally, we provide configurability by using Causets as both storage and logic and by using both conventional CMOS processors/cache hierarchies and memristive causet technologies.

View Details

Designers can choose to configure a causet array as CAM. We use 75% of the data set (i.e., three weeks) to train the models and then validate them using the remaining 25% data. We apply two stacked LSTM layers on the input, then connect them to a linear regression layer.

View Details

readers can safely access shared data concurrently with writers that are modifying it

allows both the writer and concurrent readers who access the same data to proceed and complete successfully

View Details
about

Beyond Lamport Clocks: Partitions, Transaction isolation levels, and serializability

To understand partitions, we need to know a little bit more about how EinsteinDB works. As with most ACID databases, EinsteinDB uses two-phase commit (2PC) and strict two-phase locking to ensure isolation and strong consistency. 2PC has been called the “anti-availability” protocol because all members must be up for it to work. Transactions in EinsteinDB will work as long as all of the touched groups have a quorum-elected leader and are on one side of the partition. This means that some transactions work perfectly and some will time out, but they are always consistent

Get Started
about
about