Home/ Questions/Q 7697281
In Process

The Archive Base Latest Questions

Editorial Team
  • 0
Asked: 2026-05-31T21:58:31+00:00

My use case expects heavy read load – there are two possible model design

  • 0

My use case expects heavy read load – there are two possible model design strategies:

  1. Tiny rows with row cache: In this case row is small enough to fit into RAM and all columns are being cached. Read access should be fast.

  2. Wide rows with key cache. Wide rows with large columns amount are to big for row cache. Access to column subset requires HDD seek.

As I understand using wide rows is a good design pattern. But we would need to disable row cache – so …. what is the benefit of such wide row (at least for read access)?

Which approach is better 1 or 2?

Share

Leave an answer

You must login to add an answer.

Need An Account,

1 Answer

  1. Editorial Team

    Row cache does not necessary increase read performance.

    When row cache is disabled and with enabled key cache Cassandra will read data directly from HDD jumping directly to right offset (based on key cache). In this case operating system will cache HDD access.

    Cassandra opens file as virtual file – in this case file is handled as “read from memory” in reality first read goes to HDD and second read is being served from RAM. Only already accessed file parts are loaded into RAM (plus read ahead 128kb)

    My load tests (3 Servers with 8 Core xenon, 24GB RAM, 60GB data in Cassandra) has showed, that row cache and file system cache have similar performance – OS cache causes lower CPU load

    • 0