i hava 10 topology in my cluster.when i submit some topology later,the
worker across the cluster in machine changed not smooth.there is
printscreen in the accessory.
i want some suggestion or train of thinking
thanks a lot
-
Hi guys,
We are using Riak as a State to write and read data from different riak
buckets. (We are using this code
https://github.com/hackreduce/storm-hackathon/blob/master/src/main/java/org/hackreduce/storm/example/riak/RiakBackingMap.java
)
We first write to a bucket with partitionPersist,
thanks
:timed-out means that the worker did not heartbeat to the supervisor in time.
(This happens on local disk.)
Check that your workers have enough jvm heap space. If not, garbage collection
for the JVM will cause progressively slower heartbeats until the supervisor
thinks they are dead and
I have not seen this before, if you could file a JIRA on this that would be
great.
- Bobby
From: Danijel Schiavuzzi dani...@schiavuzzi.commailto:dani...@schiavuzzi.com
Reply-To:
user@storm.incubator.apache.orgmailto:user@storm.incubator.apache.org
Yes it will run in the same thread as the task.
On 6/3/14, 10:14 PM, Xueming Li james.xueming...@gmail.com wrote:
Sorry, changed the title to make it more accurate.
On Tue, Jun 3, 2014 at 11:12 PM, Xueming Li james.xueming...@gmail.com
wrote:
Or do I need to worry about synchronization
IMetric and the metrics parts in storm are built on top of storm itself. If
you need something that sends out metrics more regularly then Imetric does,
just send them as regular tuples to a bolt you setup to collect them.
- Bobby
From: Xueming Li
I haven't used it yet, but a lot of people get pointed to metrics_storm:
https://github.com/ooyala/metrics_storm
With this blog post that discusses it:
http://engineering.ooyala.com/blog/open-sourcing-metrics-storm
Michael Noll also has a nice blog post about streaming Storm 0.9 metrics to
Be careful when using Coda Hale's Metrics package when measuring latency.
Consider using Gil Tene'sHigh Dynamic Range Histogram instead:
http://hdrhistogram.github.io/HdrHistogram/
-Dan
From: and...@parsely.com
Date: Mon, 16 Jun 2014 18:20:11 -0400
Subject: Re: Extracting Performance Metrics
To:
What kind of issues does Metrics have that leads you to recommend
HdrHistogram?
On Jun 16, 2014 6:57 PM, Dan dcies...@hotmail.com wrote:
Be careful when using Coda Hale's Metrics package when measuring latency.
Consider using Gil Tene's
High Dynamic Range Histogram instead:
If you can afford a bit more time for insertion, consider also t-digest.
Differences relative to the high dynamic range histogram system include:
- HDR histograms assume an exponential distribution. t-digest handles
arbitrary distributions
- t-digest is much more accurate near extreme values.
CodeHale doesn't handle extreme skew on measurements well last time I
looked. For throughput, averages are great. For latency, you need very
high percentiles to understand what is happening.
On Mon, Jun 16, 2014 at 6:00 PM, Michael Rose mich...@fullcontact.com
wrote:
What kind of issues does
Hi, all
I’ve been struggling to import the maven project: storm-starter into eclipse on
mac. I installed a storm cluster on a remote ubuntu server, and I git cloned
the storm starter into the ubuntu server already. I run the sample topologies
locally on ubuntu server successfully.
Now I want
13 matches
Mail list logo