1 / 11

OLTP is Totally Different by Michael Stonebraker

OLTP is Totally Different by Michael Stonebraker. Products. Old Way Oracle, DB2, SQLServer, Postgres, MySQL … New Way Hekaton, Hana, MemSQL, VoltDB, SQLFire,…. Main Memory Storage. 1 Tbyte costs (maybe) $25K and declining rapidly If your data doesn’t fit then wait a couple of years

uttara
Download Presentation

OLTP is Totally Different by Michael Stonebraker

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. OLTP is Totally DifferentbyMichael Stonebraker

  2. Products • Old Way • Oracle, DB2, SQLServer, Postgres, MySQL … • New Way • Hekaton, Hana, MemSQL, VoltDB, SQLFire,…

  3. Main Memory Storage • 1 Tbyte costs (maybe) $25K and declining rapidly • If your data doesn’t fit then wait a couple of years • NVRAM will push this way out later this decade

  4. Anti-Caching (VLDB ‘14) • Main memory format for data • When memory fills, gather cold tuples and write to an archive (in main memory format) • When a transaction has a “miss”, abort it but continue with “fake processing” to find all the absent data • Get and “pin” the needed data • Reschedule transaction when all needed data in main memory • Numbers from H-Store implementation

  5. Some Data From Nirmesh Malvaiya • Implemented Aries in VoltDB • Compared against the VoltDB scheme • Asynchronous checkpoints • Command logging

  6. Some Data From Nirmesh Malvaiya • 1.5 X run-time performance gain • 1.5 X penalty at recovery time • Almost all OLTP applications demand HA • Only run recovery for cluster-wide failures • E.g. power outage

  7. Concurrency Control • MVCC popular (Hana, Hekaton) • Time stamp order popular (H-Store/VoltDB) • Lightweight combinations of time stamp order and dynamic locking (Calvin, Dora) • I don’t know anybody who is doing normal dynamic locking • It’s too slow!!!!

  8. How to Implement HA • Active-Passive • As in the traditional wisdom • Active-Active • Send update transactions to all copies • Each executes transaction logic • Requires deterministic scheduling!!!

  9. Net-Net on OLTP • Main memory DBMS • With anti-caching • And command logging • Deterministic concurrency control • HA via active-active • Has nothing to do with the traditional wisdom!!!

More Related