incubator-cassandra-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Paul Prescod <>
Subject Re: Worst case #iops to read a row
Date Tue, 13 Apr 2010 18:55:09 GMT
On Tue, Apr 13, 2010 at 11:31 AM, Benjamin Black <> wrote:
> ...
> How frequently do you want to write SSTables?  How much memory do you
> want Memtables to consume?  How long do you want to wait between
> Memtable flushes?  There is an entire wiki page on  Memtable tuning:
> .  There is a
> thorough discussion on the various tuning parameters around buffering
> and writing here:
> .

I'm confused about the relevance of these numbers to read iops. About
the only place I can find a description of "compactions" is here:

"To bound the number of SSTable files that must be consulted on reads,
and to reclaim space taken by unused data, Cassandra performs
compactions: merging multiple old SSTable files into a single new one.
Compactations are triggered when at least 4 SStables has been flushed
to disk. "

> Do you understand you are assuming there have been no compactions,
> which would be extremely bad practice given this number of SSTables?

What do you mean by "bad practice"? The document above implies that it
is nearly impossible. It implies that you will have between 1 and 4
SSTables. Does the administrator have a choice in this matter?

I am probably being totally naive, but is the answer to the question
"worst iops on read" just:

 3 reads per SSTable * 4 SStables * ReplicationFactor ?

= 3 * 4 * 3 = 36?

 Paul Prescod

View raw message