You are viewing a plain text version of this content. The canonical link for it is here.
Posted to user@cassandra.apache.org by "sj.climber" <sj...@gmail.com> on 2012/04/15 19:32:54 UTC
Long start-up times
Hi,
I have 2 column families with approx 50 GB of compressed data (~150GB
uncompressed). The data resides in a keyspace replicated 2-way, hosted by a
2-node Cassandra cluster (v1.0.8), both with 74GB RAM and 16 cores. Key
caches are set to 1.0.
I'm noticing that it can take upwards of 15+ minutes for the node to start
up (i.e. before it becomes responsive to thrift clients). During this time,
the logs suggest the system is blocked opening the data files.
Is this expected behaviour? Are there any best practices for reducing node
startup time?
Thanks in advance!
--
View this message in context: http://cassandra-user-incubator-apache-org.3065146.n2.nabble.com/Long-start-up-times-tp7468307p7468307.html
Sent from the cassandra-user@incubator.apache.org mailing list archive at Nabble.com.
Re: Long start-up times
Posted by Jonathan Ellis <jb...@gmail.com>.
On Sun, Apr 15, 2012 at 2:47 PM, sj.climber <sj...@gmail.com> wrote:
> Also, I see in 1.0.9 there's a fix for a potentially related issue (see
> https://issues.apache.org/jira/browse/CASSANDRA-4023). Any thoughts on
> this?
My thought is, upgrading is a no-brainer if that's a pain point for you. :)
--
Jonathan Ellis
Project Chair, Apache Cassandra
co-founder of DataStax, the source for professional Cassandra support
http://www.datastax.com
Re: Long start-up times
Posted by "sj.climber" <sj...@gmail.com>.
Thanks, Edward.
What do you suppose a reasonable value for index_interval might be? If I'm
anyways setting keys_cached to 1.0, what would the implications be of
setting index_interval very high (perhaps 1000, 10000 or even higher--my
data set involves a large number of smallish rows)? I imagine the first
read for a given key would have higher latency, but subsequent reads would
be unaffected (since they would use the key cache), no?
Also, I see in 1.0.9 there's a fix for a potentially related issue (see
https://issues.apache.org/jira/browse/CASSANDRA-4023). Any thoughts on
this?
Thanks again!
--
View this message in context: http://cassandra-user-incubator-apache-org.3065146.n2.nabble.com/Long-start-up-times-tp7468307p7468581.html
Sent from the cassandra-user@incubator.apache.org mailing list archive at Nabble.com.
Re: Long start-up times
Posted by Edward Capriolo <ed...@gmail.com>.
This is normal although time seems on the higher side. Adjusting the
IndexInterval should effect the sampling time.
On Sun, Apr 15, 2012 at 1:32 PM, sj.climber <sj...@gmail.com> wrote:
> Hi,
>
> I have 2 column families with approx 50 GB of compressed data (~150GB
> uncompressed). The data resides in a keyspace replicated 2-way, hosted by a
> 2-node Cassandra cluster (v1.0.8), both with 74GB RAM and 16 cores. Key
> caches are set to 1.0.
>
> I'm noticing that it can take upwards of 15+ minutes for the node to start
> up (i.e. before it becomes responsive to thrift clients). During this time,
> the logs suggest the system is blocked opening the data files.
>
> Is this expected behaviour? Are there any best practices for reducing node
> startup time?
>
> Thanks in advance!
>
> --
> View this message in context: http://cassandra-user-incubator-apache-org.3065146.n2.nabble.com/Long-start-up-times-tp7468307p7468307.html
> Sent from the cassandra-user@incubator.apache.org mailing list archive at Nabble.com.