hi,
I have found that ignite-spark-1.7.0 doesn't support spark 2.0.x. Does
it support spark 1.6.x?
--
View this message in context:
http://apache-ignite-users.70518.x6.nabble.com/Can-ignite-spark-support-spark-1-6-x-tp9358.html
Sent from the Apache Ignite Users mailing list archive at
If IGFS can't hold more input data, will it flush data to HDFS? How IGFS
flush data to HDFS? Async or sync?
If it a async mode, when IGFS can't hold more data, it will using cache
expire policy. And if the data which is expired is not persisted to HDFS
timely, the data will be lost. Is is
I am using ignite hadoop accelerate to improve my map-reduce job. I am always
encountered "java heap size" problem, though I have offer more than 80GB to
ignite. The map-reduce job will write more than 150GB data to IGFS. When
IGFS will sync data to HDFS? When processing a map-reduce job, do I
I can find the WARN in logs. The stuck should be caused by a long running
cache operations. How to locate what cause the long running cache
operations. My map-reduce job can run successfully without ignite hadoop
accelerator.
[GridCachePartitionExchangeManager] Found long running cache
I use the following configuration to avoid this problem. However, I after
doing this, I encounter an another problem which makes my job stuck. The
issue is described in another message:
MapReduce Job stuck when using ignite hadoop accelerator
Hi,
Recently, I did some experiments to test the map-reduce job's
performance with ignite hadoop accelerator. It really make sense to
accelerate a map-reduce job. In my previous experiment, I store a 10GB file
into IGFS. I design a I/O intensive job whose duty is only to read the 10GB
file.
I use the following configuration to avoid this problem.
--
View this message in context:
http://apache-ignite-users.70518.x6.nabble.com/How-to-config-timeout-configuration-tp9206p9215.html
Sent from the Apache
Maybe it is caused by the configuration. And the first load is always slow. I
tuned the configuration and the job goes well on my cluster.
--
View this message in context:
I solved the problem by myself.
Is it ignite's bug? Though I have set the following variable in .bashrc,
ignite still can't get the related hadoop jar.
*export IGNITE_LIBS=$IGNITE_LIBS:"$IGNITE_HOME/libs/*":$HADOOP_CLASSPATH*
Now I have solved this problem by copying related hadoop jars
hi,
I am new to ignite. I downloaded "apache-ignite-hadoop-1.7.0-bin.zip". I
unzip it and configured it as the doc
"https://apacheignite-fs.readme.io/docs/installing-on-apache-hadoop; says.
When I try to run the script "ignite.sh", it gave out the exception:
class
I will try it. Thanks.
--
View this message in context:
http://apache-ignite-users.70518.x6.nabble.com/Can-ignite-accelerate-a-single-spark-job-by-using-IGFS-tp9167p9170.html
Sent from the Apache Ignite Users mailing list archive at Nabble.com.
Hi,
I know igniteRDD can be used to improve spark jobs by sharing the RDD
among spark jobs. However, in our situation, all the spark jobs are
independent and they don't need to share others' RDDs.
Can I put all my data in IGFS to improve a single spark job's
performance?
--
View this
Hi Franke,
Let me clarify our situation more detailed. We want to store all our
data in memory and all the job will never access the backend data. However,
we still need backend storage such as HDFS to persist in memory data
asynchronously in case of data lose which is caused by node failure.
hi vincent,
I've got the idea that load backend data in the cache will effect the
performance. However, in our situation, we will store all the data in
memory. For example, assume that we have a 10GB file all in memory. All the
data is pinned in memory(Does ignite support pinning date in
Hi,
Recently, I have used alluxio for about two month. However, it does't
satisfy our requirement. We want to use alluxio as a memory cache layer
which can easily interagte with Hadoop or Spark to accelerate our spark or
map-reduce job. Unfortunately, it doesn't work. I have done many tests
15 matches
Mail list logo