On Fri, Oct 3, 2014 at 10:34 PM, Vladimir Rodionov <[email protected]>
wrote:

> I am thinking about the following:
>
> 1. Compaction On/Off per CF, Table, cluster. Both: minor and major
>
> Good during bulk load.
>
> - Disable compaction for table 'T'
> - Load 1B rows
> - Enable compaction for table 'T'
>
>
Sounds good. Nice if dynamic. Compactions have to ask master process if
they can run?


> 2. Local Compaction I/O throttle
>
> Set I/O limit per RS
>

How you thinking of doing this?  This to address heavy-compaction


>
> 3. Rack Compaction I/O throttle
>
> Set I/O limit per server rack. Good to control uplink bandwidth.
>
> 4. Cluster Compaction I/O throttle. Good to avoid compaction storms
>

Yeah, this has been proposed in the past.  Good idea.  Or, let master do a
rolling compaction over cluster or table.

St.Ack


>
> -Vladimir Rodionov
>

Reply via email to