Thank you Rob, that's all really useful information. As our production
cluster is going to grow over time it looks like we may need to stick with
vnodes (but maybe not 256) and as you say hope the work to improve their
inefficiencies progresses quite quickly.
In real reality, vnodes were almost
Hi all,
I've noticed increased latency on our tomcat REST-service (average 30ms,
max 2sec). We are using Cassandra 1.2.16 with official DataStax Java
driver v1.0.3.
Our setup:
* 2 DCs
* each DC: 7 nodes
* RF=5
* Leveled compaction
After cassandra restart on all nodes, the latencies are
Hi all,
I've noticed increased latency on our tomcat REST-service (average 30ms,
max 2sec). We are using Cassandra 1.2.16 with official DataStax Java
driver v1.0.3.
Our setup:
* 2 DCs
* each DC: 7 nodes
* RF=5
* Leveled compaction
After cassandra restart on all nodes, the latencies are
Hi all,
I've noticed increased latency on our tomcat REST-service (average 30ms,
max 2sec). We are using Cassandra 1.2.16 with official DataStax Java
driver v1.0.3.
Our setup:
* 2 DCs
* each DC: 7 nodes
* RF=5
* Leveled compaction
After cassandra restart on all nodes, the latencies are
Is compaction keeping up? Those replication settings are high - for every
write, 10 nodes are doing something).
What other monitoring stats do you have - what is IO, CPU and network
traffic like? Is the JVM GC activity growing?
Anything else stick out like growing number of network connections
On Wed, May 21, 2014 at 12:59 AM, opensaf dev opensaf...@gmail.com wrote:
When I run as user cassandra, it starts and runs fine.
Why do you want to run Cassandra as a different user?
--
Patricia Gorla
@patriciagorla
Consultant
Apache Cassandra Consulting
http://www.thelastpickle.com
I took a look at the Ohloh stats here:
https://www.ohloh.net/p/cassandra/contributors/summary
Note that committers are not the same as contributors. Dozens of people
contribute patches that are committed to the codebase without being
committers.
Over the last year, the top four contributors
I agree we the community should be careful about drawing conclusions.
For the long term health and vitality of Cassandra, I feel more
contributors should be invited to become committers.
On Fri, May 23, 2014 at 12:17 PM, Jim Ancona j...@anconafamily.com wrote:
I took a look at the Ohloh stats
On Fri, May 16, 2014 at 10:56 AM, Kevin Burton bur...@spinn3r.com wrote:
Perhaps because the developers are working on DSE :-P
FWIW, and I am not necessarily known for being the biggest defender of
Datastax and the relationship of their commercial interests to the
architectural direction of
Datastax have also gone far out of their way to support companies using
Cassandra regardless of if it happens to be the DSE or not. We are not part
of any paid agreement with the company and I had a Datastax employee
sending me texts late on a weekend to help me through an issue I was having
with
Another thing to keep in mind--even core pieces like the Linux kernel are
dominated by corporations. Less than 20% of contributions last year were
made by non-corporate sponsored contributors. Obviously, this is a bit
different, but many parts of the open source world depend on upstream
I think we can all agree that DataStax has been a positive for Cassandra.
There's no point arguing that in my mind.
A separate but important consideration is long term health of a project.
Many apache projects face this issue. When a project doesn't continually
grow the contributors and
I have a different service which controls the cassandra service for high
availability.
Thanks
Dev
On Fri, May 23, 2014 at 7:35 AM, Patricia Gorla
patri...@thelastpickle.comwrote:
On Wed, May 21, 2014 at 12:59 AM, opensaf dev opensaf...@gmail.comwrote:
When I run as user cassandra, it
On Fri, May 23, 2014 at 2:08 PM, opensaf dev opensaf...@gmail.com wrote:
I have a different service which controls the cassandra service for high
availability.
IMO, starting or stopping a Cassandra node should never be a side effect of
another system's properties. YMMV.
On Tue, May 20, 2014 at 10:07 AM, Kevin Burton bur...@spinn3r.com wrote:
This has not been my experience… In my benchmarks over the years noatime
has mattered.
Have you compared to the atime case or the relatime case? The point of the
FAQ link posted is that the default behavior in XFS when
15 matches
Mail list logo