Re: Performance Question

[Benjamin Kim]

Todd,

I upgraded, deleted the table and recreated it again because it was 
unaccessible, and re-introduced the downed tablet server after clearing out all 
kudu directories.

The Spark Streaming job is repopulating again.

Thanks,
Ben


> On Jul 18, 2016, at 10:32 AM, Todd Lipcon <t...@cloudera.com> wrote:
> 
> On Mon, Jul 18, 2016 at 10:31 AM, Benjamin Kim <bbuil...@gmail.com 
> <mailto:bbuil...@gmail.com>> wrote:
> Todd,
> 
> Thanks for the info. I was going to upgrade after the testing, but now, it 
> looks like I will have to do it earlier than expected.
> 
> I will do the upgrade, then resume.
> 
> OK, sounds good. The upgrade shouldn't invalidate any performance testing or 
> anything -- just fixes this important bug.
> 
> -Todd
> 
> 
>> On Jul 18, 2016, at 10:29 AM, Todd Lipcon <t...@cloudera.com 
>> <mailto:t...@cloudera.com>> wrote:
>> 
>> Hi Ben,
>> 
>> Any chance that you are running Kudu 0.9.0 instead of 0.9.1? There's a known 
>> serious bug in 0.9.0 which can cause this kind of corruption.
>> 
>> Assuming that you are running with replication count 3 this time, you should 
>> be able to move aside that tablet metadata file and start the server. It 
>> will recreate a new repaired replica automatically.
>> 
>> -Todd
>> 
>> On Mon, Jul 18, 2016 at 10:28 AM, Benjamin Kim <bbuil...@gmail.com 
>> <mailto:bbuil...@gmail.com>> wrote:
>> During my re-population of the Kudu table, I am getting this error trying to 
>> restart a tablet server after it went down. The job that populates this 
>> table has been running for over a week.
>> 
>> [libprotobuf ERROR google/protobuf/message_lite.cc:123] Can't parse message 
>> of type "kudu.tablet.TabletSuperBlockPB" because it is missing required 
>> fields: rowsets[2324].columns[15].block
>> F0718 17:01:26.783571   468 tablet_server_main.cc:55] Check failed: _s.ok() 
>> Bad status: IO error: Could not init Tablet Manager: Failed to open tablet 
>> metadata for tablet: 24637ee6f3e5440181ce3f20b1b298ba: Failed to load tablet 
>> metadata for tablet id 24637ee6f3e5440181ce3f20b1b298ba: Could not load 
>> tablet metadata from 
>> /mnt/data1/kudu/data/tablet-meta/24637ee6f3e5440181ce3f20b1b298ba: Unable to 
>> parse PB from path: 
>> /mnt/data1/kudu/data/tablet-meta/24637ee6f3e5440181ce3f20b1b298ba
>> *** Check failure stack trace: ***
>> @   0x7d794d  google::LogMessage::Fail()
>> @   0x7d984d  google::LogMessage::SendToLog()
>> @   0x7d7489  google::LogMessage::Flush()
>> @   0x7da2ef  google::LogMessageFatal::~LogMessageFatal()
>> @   0x78172b  (unknown)
>> @   0x344d41ed5d  (unknown)
>> @   0x7811d1  (unknown)
>> 
>> Does anyone know what this means?
>> 
>> Thanks,
>> Ben
>> 
>> 
>>> On Jul 11, 2016, at 10:47 AM, Todd Lipcon <t...@cloudera.com 
>>> <mailto:t...@cloudera.com>> wrote:
>>> 
>>> On Mon, Jul 11, 2016 at 10:40 AM, Benjamin Kim <bbuil...@gmail.com 
>>> <mailto:bbuil...@gmail.com>> wrote:
>>> Todd,
>>> 
>>> I had it at one replica. Do I have to recreate?
>>> 
>>> We don't currently have the ability to "accept data loss" on a tablet (or 
>>> set of tablets). If the machine is gone for good, then currently the only 
>>> easy way to recover is to recreate the table. If this sounds really 
>>> painful, though, maybe we can work up some kind of tool you could use to 
>>> just recreate the missing tablets (with those rows lost).
>>> 
>>> -Todd
>>> 
>>>> On Jul 11, 2016, at 10:37 AM, Todd Lipcon <t...@cloudera.com 
>>>> <mailto:t...@cloudera.com>> wrote:
>>>> 
>>>> Hey Ben,
>>>> 
>>>> Is the table that you're querying replicated? Or was it created with only 
>>>> one replica per tablet?
>>>> 
>>>> -Todd
>>>> 
>>>> On Mon, Jul 11, 2016 at 10:35 AM, Benjamin Kim <b...@amobee.com 
>>>> <mailto:b...@amobee.com>> wrote:
>>>> Over the weekend, a tablet server went down. It’s not coming back up. So, 
>>>> I decommissioned it and removed it from the cluster. Then, I restarted 
>>>> Kudu because I was getting a timeout  exception trying to do counts on the 
>>>> table. Now, when I try again. I get the same error.
>>>> 
>>>> 16/07/11 17:32:36 WARN scheduler.TaskSetManager: Lost task 46

Re: Performance Question

[Benjamin Kim]

Todd,

Thanks for the info. I was going to upgrade after the testing, but now, it 
looks like I will have to do it earlier than expected.

I will do the upgrade, then resume.

Cheers,
Ben


> On Jul 18, 2016, at 10:29 AM, Todd Lipcon <t...@cloudera.com> wrote:
> 
> Hi Ben,
> 
> Any chance that you are running Kudu 0.9.0 instead of 0.9.1? There's a known 
> serious bug in 0.9.0 which can cause this kind of corruption.
> 
> Assuming that you are running with replication count 3 this time, you should 
> be able to move aside that tablet metadata file and start the server. It will 
> recreate a new repaired replica automatically.
> 
> -Todd
> 
> On Mon, Jul 18, 2016 at 10:28 AM, Benjamin Kim <bbuil...@gmail.com 
> <mailto:bbuil...@gmail.com>> wrote:
> During my re-population of the Kudu table, I am getting this error trying to 
> restart a tablet server after it went down. The job that populates this table 
> has been running for over a week.
> 
> [libprotobuf ERROR google/protobuf/message_lite.cc:123] Can't parse message 
> of type "kudu.tablet.TabletSuperBlockPB" because it is missing required 
> fields: rowsets[2324].columns[15].block
> F0718 17:01:26.783571   468 tablet_server_main.cc:55] Check failed: _s.ok() 
> Bad status: IO error: Could not init Tablet Manager: Failed to open tablet 
> metadata for tablet: 24637ee6f3e5440181ce3f20b1b298ba: Failed to load tablet 
> metadata for tablet id 24637ee6f3e5440181ce3f20b1b298ba: Could not load 
> tablet metadata from 
> /mnt/data1/kudu/data/tablet-meta/24637ee6f3e5440181ce3f20b1b298ba: Unable to 
> parse PB from path: 
> /mnt/data1/kudu/data/tablet-meta/24637ee6f3e5440181ce3f20b1b298ba
> *** Check failure stack trace: ***
> @   0x7d794d  google::LogMessage::Fail()
> @   0x7d984d  google::LogMessage::SendToLog()
> @   0x7d7489  google::LogMessage::Flush()
> @   0x7da2ef  google::LogMessageFatal::~LogMessageFatal()
> @   0x78172b  (unknown)
> @   0x344d41ed5d  (unknown)
> @   0x7811d1  (unknown)
> 
> Does anyone know what this means?
> 
> Thanks,
> Ben
> 
> 
>> On Jul 11, 2016, at 10:47 AM, Todd Lipcon <t...@cloudera.com 
>> <mailto:t...@cloudera.com>> wrote:
>> 
>> On Mon, Jul 11, 2016 at 10:40 AM, Benjamin Kim <bbuil...@gmail.com 
>> <mailto:bbuil...@gmail.com>> wrote:
>> Todd,
>> 
>> I had it at one replica. Do I have to recreate?
>> 
>> We don't currently have the ability to "accept data loss" on a tablet (or 
>> set of tablets). If the machine is gone for good, then currently the only 
>> easy way to recover is to recreate the table. If this sounds really painful, 
>> though, maybe we can work up some kind of tool you could use to just 
>> recreate the missing tablets (with those rows lost).
>> 
>> -Todd
>> 
>>> On Jul 11, 2016, at 10:37 AM, Todd Lipcon <t...@cloudera.com 
>>> <mailto:t...@cloudera.com>> wrote:
>>> 
>>> Hey Ben,
>>> 
>>> Is the table that you're querying replicated? Or was it created with only 
>>> one replica per tablet?
>>> 
>>> -Todd
>>> 
>>> On Mon, Jul 11, 2016 at 10:35 AM, Benjamin Kim <b...@amobee.com 
>>> <mailto:b...@amobee.com>> wrote:
>>> Over the weekend, a tablet server went down. It’s not coming back up. So, I 
>>> decommissioned it and removed it from the cluster. Then, I restarted Kudu 
>>> because I was getting a timeout  exception trying to do counts on the 
>>> table. Now, when I try again. I get the same error.
>>> 
>>> 16/07/11 17:32:36 WARN scheduler.TaskSetManager: Lost task 468.3 in stage 
>>> 0.0 (TID 603, prod-dc1-datanode167.pdc1i.gradientx.com 
>>> <http://prod-dc1-datanode167.pdc1i.gradientx.com/>): 
>>> com.stumbleupon.async.TimeoutException: Timed out after 3ms when 
>>> joining Deferred@712342716(state=PAUSED, result=Deferred@1765902299, 
>>> callback=passthrough -> scanner opened -> wakeup thread Executor task 
>>> launch worker-2, errback=openScanner errback -> passthrough -> wakeup 
>>> thread Executor task launch worker-2)
>>> at com.stumbleupon.async.Deferred.doJoin(Deferred.java:1177)
>>> at com.stumbleupon.async.Deferred.join(Deferred.java:1045)
>>> at org.kududb.client.KuduScanner.nextRows(KuduScanner.java:57)
>>> at org.kududb.spark.kudu.RowResultIteratorScala.hasNext(KuduRDD.scala:99)
>>> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
>>> at 
>>> org.apache.spark.sql.execu

Re: Performance Question

[Benjamin Kim]

During my re-population of the Kudu table, I am getting this error trying to 
restart a tablet server after it went down. The job that populates this table 
has been running for over a week.

[libprotobuf ERROR google/protobuf/message_lite.cc:123] Can't parse message of 
type "kudu.tablet.TabletSuperBlockPB" because it is missing required fields: 
rowsets[2324].columns[15].block
F0718 17:01:26.783571   468 tablet_server_main.cc:55] Check failed: _s.ok() Bad 
status: IO error: Could not init Tablet Manager: Failed to open tablet metadata 
for tablet: 24637ee6f3e5440181ce3f20b1b298ba: Failed to load tablet metadata 
for tablet id 24637ee6f3e5440181ce3f20b1b298ba: Could not load tablet metadata 
from /mnt/data1/kudu/data/tablet-meta/24637ee6f3e5440181ce3f20b1b298ba: Unable 
to parse PB from path: 
/mnt/data1/kudu/data/tablet-meta/24637ee6f3e5440181ce3f20b1b298ba
*** Check failure stack trace: ***
@   0x7d794d  google::LogMessage::Fail()
@   0x7d984d  google::LogMessage::SendToLog()
@   0x7d7489  google::LogMessage::Flush()
@   0x7da2ef  google::LogMessageFatal::~LogMessageFatal()
@   0x78172b  (unknown)
@   0x344d41ed5d  (unknown)
@   0x7811d1  (unknown)

Does anyone know what this means?

Thanks,
Ben


> On Jul 11, 2016, at 10:47 AM, Todd Lipcon <t...@cloudera.com> wrote:
> 
> On Mon, Jul 11, 2016 at 10:40 AM, Benjamin Kim <bbuil...@gmail.com 
> <mailto:bbuil...@gmail.com>> wrote:
> Todd,
> 
> I had it at one replica. Do I have to recreate?
> 
> We don't currently have the ability to "accept data loss" on a tablet (or set 
> of tablets). If the machine is gone for good, then currently the only easy 
> way to recover is to recreate the table. If this sounds really painful, 
> though, maybe we can work up some kind of tool you could use to just recreate 
> the missing tablets (with those rows lost).
> 
> -Todd
> 
>> On Jul 11, 2016, at 10:37 AM, Todd Lipcon <t...@cloudera.com 
>> <mailto:t...@cloudera.com>> wrote:
>> 
>> Hey Ben,
>> 
>> Is the table that you're querying replicated? Or was it created with only 
>> one replica per tablet?
>> 
>> -Todd
>> 
>> On Mon, Jul 11, 2016 at 10:35 AM, Benjamin Kim <b...@amobee.com 
>> <mailto:b...@amobee.com>> wrote:
>> Over the weekend, a tablet server went down. It’s not coming back up. So, I 
>> decommissioned it and removed it from the cluster. Then, I restarted Kudu 
>> because I was getting a timeout  exception trying to do counts on the table. 
>> Now, when I try again. I get the same error.
>> 
>> 16/07/11 17:32:36 WARN scheduler.TaskSetManager: Lost task 468.3 in stage 
>> 0.0 (TID 603, prod-dc1-datanode167.pdc1i.gradientx.com 
>> <http://prod-dc1-datanode167.pdc1i.gradientx.com/>): 
>> com.stumbleupon.async.TimeoutException: Timed out after 3ms when joining 
>> Deferred@712342716(state=PAUSED, result=Deferred@1765902299, 
>> callback=passthrough -> scanner opened -> wakeup thread Executor task launch 
>> worker-2, errback=openScanner errback -> passthrough -> wakeup thread 
>> Executor task launch worker-2)
>> at com.stumbleupon.async.Deferred.doJoin(Deferred.java:1177)
>> at com.stumbleupon.async.Deferred.join(Deferred.java:1045)
>> at org.kududb.client.KuduScanner.nextRows(KuduScanner.java:57)
>> at org.kududb.spark.kudu.RowResultIteratorScala.hasNext(KuduRDD.scala:99)
>> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
>> at 
>> org.apache.spark.sql.execution.aggregate.TungstenAggregate$$anonfun$doExecute$1$$anonfun$2.apply(TungstenAggregate.scala:88)
>> at 
>> org.apache.spark.sql.execution.aggregate.TungstenAggregate$$anonfun$doExecute$1$$anonfun$2.apply(TungstenAggregate.scala:86)
>> at 
>> org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$20.apply(RDD.scala:710)
>> at 
>> org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$20.apply(RDD.scala:710)
>> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
>> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
>> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
>> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
>> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
>> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
>> at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
>> at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
>> at org.apache.spark.scheduler.Task.run(Task.scala:89)
>> at org.apache.spark.executor.Executor$TaskRunner.ru

Re: Performance Question

[Benjamin Kim]

Todd,

It’s no problem to start over again. But, a tool like that would be helpful. 
Gaps in data can be accommodated for by just back filling.

Thanks,
Ben

> On Jul 11, 2016, at 10:47 AM, Todd Lipcon <t...@cloudera.com> wrote:
> 
> On Mon, Jul 11, 2016 at 10:40 AM, Benjamin Kim <bbuil...@gmail.com 
> <mailto:bbuil...@gmail.com>> wrote:
> Todd,
> 
> I had it at one replica. Do I have to recreate?
> 
> We don't currently have the ability to "accept data loss" on a tablet (or set 
> of tablets). If the machine is gone for good, then currently the only easy 
> way to recover is to recreate the table. If this sounds really painful, 
> though, maybe we can work up some kind of tool you could use to just recreate 
> the missing tablets (with those rows lost).
> 
> -Todd
> 
>> On Jul 11, 2016, at 10:37 AM, Todd Lipcon <t...@cloudera.com 
>> <mailto:t...@cloudera.com>> wrote:
>> 
>> Hey Ben,
>> 
>> Is the table that you're querying replicated? Or was it created with only 
>> one replica per tablet?
>> 
>> -Todd
>> 
>> On Mon, Jul 11, 2016 at 10:35 AM, Benjamin Kim <b...@amobee.com 
>> <mailto:b...@amobee.com>> wrote:
>> Over the weekend, a tablet server went down. It’s not coming back up. So, I 
>> decommissioned it and removed it from the cluster. Then, I restarted Kudu 
>> because I was getting a timeout  exception trying to do counts on the table. 
>> Now, when I try again. I get the same error.
>> 
>> 16/07/11 17:32:36 WARN scheduler.TaskSetManager: Lost task 468.3 in stage 
>> 0.0 (TID 603, prod-dc1-datanode167.pdc1i.gradientx.com 
>> <http://prod-dc1-datanode167.pdc1i.gradientx.com/>): 
>> com.stumbleupon.async.TimeoutException: Timed out after 3ms when joining 
>> Deferred@712342716(state=PAUSED, result=Deferred@1765902299, 
>> callback=passthrough -> scanner opened -> wakeup thread Executor task launch 
>> worker-2, errback=openScanner errback -> passthrough -> wakeup thread 
>> Executor task launch worker-2)
>> at com.stumbleupon.async.Deferred.doJoin(Deferred.java:1177)
>> at com.stumbleupon.async.Deferred.join(Deferred.java:1045)
>> at org.kududb.client.KuduScanner.nextRows(KuduScanner.java:57)
>> at org.kududb.spark.kudu.RowResultIteratorScala.hasNext(KuduRDD.scala:99)
>> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
>> at 
>> org.apache.spark.sql.execution.aggregate.TungstenAggregate$$anonfun$doExecute$1$$anonfun$2.apply(TungstenAggregate.scala:88)
>> at 
>> org.apache.spark.sql.execution.aggregate.TungstenAggregate$$anonfun$doExecute$1$$anonfun$2.apply(TungstenAggregate.scala:86)
>> at 
>> org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$20.apply(RDD.scala:710)
>> at 
>> org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$20.apply(RDD.scala:710)
>> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
>> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
>> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
>> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
>> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
>> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
>> at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
>> at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
>> at org.apache.spark.scheduler.Task.run(Task.scala:89)
>> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
>> at 
>> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
>> at 
>> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
>> at java.lang.Thread.run(Thread.java:745)
>> 
>> Does anyone know how to recover from this?
>> 
>> Thanks,
>> Benjamin Kim
>> Data Solutions Architect
>> 
>> [a•mo•bee] (n.) the company defining digital marketing.
>> 
>> Mobile: +1 818 635 2900 <tel:%2B1%20818%20635%202900>
>> 3250 Ocean Park Blvd, Suite 200  |  Santa Monica, CA 90405  |  
>> www.amobee.com <http://www.amobee.com/>
>>> On Jul 6, 2016, at 9:46 AM, Dan Burkert <d...@cloudera.com 
>>> <mailto:d...@cloudera.com>> wrote:
>>> 
>>> 
>>> 
>>> On Wed, Jul 6, 2016 at 7:05 AM, Benjamin Kim <bbuil...@gmail.com 
>>> <mailto:bbuil...@gmail.com>> wrote:
>>> Over the weekend, the row count is up to <500M. I will give it another few 
>>> days to get to 1B rows. I sti

Re: Performance Question

[Benjamin Kim]

Todd,

I had it at one replica. Do I have to recreate?

Thanks,
Ben


> On Jul 11, 2016, at 10:37 AM, Todd Lipcon <t...@cloudera.com> wrote:
> 
> Hey Ben,
> 
> Is the table that you're querying replicated? Or was it created with only one 
> replica per tablet?
> 
> -Todd
> 
> On Mon, Jul 11, 2016 at 10:35 AM, Benjamin Kim <b...@amobee.com 
> <mailto:b...@amobee.com>> wrote:
> Over the weekend, a tablet server went down. It’s not coming back up. So, I 
> decommissioned it and removed it from the cluster. Then, I restarted Kudu 
> because I was getting a timeout  exception trying to do counts on the table. 
> Now, when I try again. I get the same error.
> 
> 16/07/11 17:32:36 WARN scheduler.TaskSetManager: Lost task 468.3 in stage 0.0 
> (TID 603, prod-dc1-datanode167.pdc1i.gradientx.com 
> <http://prod-dc1-datanode167.pdc1i.gradientx.com/>): 
> com.stumbleupon.async.TimeoutException: Timed out after 3ms when joining 
> Deferred@712342716(state=PAUSED, result=Deferred@1765902299, 
> callback=passthrough -> scanner opened -> wakeup thread Executor task launch 
> worker-2, errback=openScanner errback -> passthrough -> wakeup thread 
> Executor task launch worker-2)
> at com.stumbleupon.async.Deferred.doJoin(Deferred.java:1177)
> at com.stumbleupon.async.Deferred.join(Deferred.java:1045)
> at org.kududb.client.KuduScanner.nextRows(KuduScanner.java:57)
> at org.kududb.spark.kudu.RowResultIteratorScala.hasNext(KuduRDD.scala:99)
> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
> at 
> org.apache.spark.sql.execution.aggregate.TungstenAggregate$$anonfun$doExecute$1$$anonfun$2.apply(TungstenAggregate.scala:88)
> at 
> org.apache.spark.sql.execution.aggregate.TungstenAggregate$$anonfun$doExecute$1$$anonfun$2.apply(TungstenAggregate.scala:86)
> at 
> org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$20.apply(RDD.scala:710)
> at 
> org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$20.apply(RDD.scala:710)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
> at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
> at org.apache.spark.scheduler.Task.run(Task.scala:89)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
> at 
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
> at 
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
> at java.lang.Thread.run(Thread.java:745)
> 
> Does anyone know how to recover from this?
> 
> Thanks,
> Benjamin Kim
> Data Solutions Architect
> 
> [a•mo•bee] (n.) the company defining digital marketing.
> 
> Mobile: +1 818 635 2900 <tel:%2B1%20818%20635%202900>
> 3250 Ocean Park Blvd, Suite 200  |  Santa Monica, CA 90405  |  www.amobee.com 
> <http://www.amobee.com/>
>> On Jul 6, 2016, at 9:46 AM, Dan Burkert <d...@cloudera.com 
>> <mailto:d...@cloudera.com>> wrote:
>> 
>> 
>> 
>> On Wed, Jul 6, 2016 at 7:05 AM, Benjamin Kim <bbuil...@gmail.com 
>> <mailto:bbuil...@gmail.com>> wrote:
>> Over the weekend, the row count is up to <500M. I will give it another few 
>> days to get to 1B rows. I still get consistent times ~15s for doing row 
>> counts despite the amount of data growing.
>> 
>> On another note, I got a solicitation email from SnappyData to evaluate 
>> their product. They claim to be the “Spark Data Store” with tight 
>> integration with Spark executors. It claims to be an OLTP and OLAP system 
>> with being an in-memory data store first then to disk. After going to 
>> several Spark events, it would seem that this is the new “hot” area for 
>> vendors. They all (MemSQL, Redis, Aerospike, Datastax, etc.) claim to be the 
>> best "Spark Data Store”. I’m wondering if Kudu will become this too? With 
>> the performance I’ve seen so far, it would seem that it can be a contender. 
>> All that is needed is a hardened Spark connector package, I would think. The 
>> next evaluation I will be conducting is to see if SnappyData’s claims are 
>> valid by doing my own tests.
>> 
>> It's hard to compare Kudu against any other data store without a lot of 
>> analysis and thorough benchmarking, 

Re: Performance Question

[Benjamin Kim]

Dan,

This is good to hear as we are heavily invested in Spark as are many of our 
competitors in the AdTech/Telecom world. It would be nice to have Kudu be on 
par with the other data store technologies in terms of Spark usability, so as 
to not choose one based on “who provides it now in production”, as management 
tends to say.

Cheers,
Ben

> On Jul 6, 2016, at 9:46 AM, Dan Burkert <d...@cloudera.com> wrote:
> 
> 
> 
> On Wed, Jul 6, 2016 at 7:05 AM, Benjamin Kim <bbuil...@gmail.com 
> <mailto:bbuil...@gmail.com>> wrote:
> Over the weekend, the row count is up to <500M. I will give it another few 
> days to get to 1B rows. I still get consistent times ~15s for doing row 
> counts despite the amount of data growing.
> 
> On another note, I got a solicitation email from SnappyData to evaluate their 
> product. They claim to be the “Spark Data Store” with tight integration with 
> Spark executors. It claims to be an OLTP and OLAP system with being an 
> in-memory data store first then to disk. After going to several Spark events, 
> it would seem that this is the new “hot” area for vendors. They all (MemSQL, 
> Redis, Aerospike, Datastax, etc.) claim to be the best "Spark Data Store”. 
> I’m wondering if Kudu will become this too? With the performance I’ve seen so 
> far, it would seem that it can be a contender. All that is needed is a 
> hardened Spark connector package, I would think. The next evaluation I will 
> be conducting is to see if SnappyData’s claims are valid by doing my own 
> tests.
> 
> It's hard to compare Kudu against any other data store without a lot of 
> analysis and thorough benchmarking, but it is certainly a goal of Kudu to be 
> a great platform for ingesting and analyzing data through Spark.  Up till 
> this point most of the Spark work has been community driven, but more 
> thorough integration testing of the Spark connector is going to be a focus 
> going forward.
> 
> - Dan
> 
>  
> Cheers,
> Ben
> 
> 
> 
>> On Jun 15, 2016, at 12:47 AM, Todd Lipcon <t...@cloudera.com 
>> <mailto:t...@cloudera.com>> wrote:
>> 
>> Hi Benjamin,
>> 
>> What workload are you using for benchmarks? Using spark or something more 
>> custom? rdd or data frame or SQL, etc? Maybe you can share the schema and 
>> some queries
>> 
>> Todd
>> 
>> Todd
>> 
>> On Jun 15, 2016 8:10 AM, "Benjamin Kim" <bbuil...@gmail.com 
>> <mailto:bbuil...@gmail.com>> wrote:
>> Hi Todd,
>> 
>> Now that Kudu 0.9.0 is out. I have done some tests. Already, I am impressed. 
>> Compared to HBase, read and write performance are better. Write performance 
>> has the greatest improvement (> 4x), while read is > 1.5x. Albeit, these are 
>> only preliminary tests. Do you know of a way to really do some conclusive 
>> tests? I want to see if I can match your results on my 50 node cluster.
>> 
>> Thanks,
>> Ben
>> 
>>> On May 30, 2016, at 10:33 AM, Todd Lipcon <t...@cloudera.com 
>>> <mailto:t...@cloudera.com>> wrote:
>>> 
>>> On Sat, May 28, 2016 at 7:12 AM, Benjamin Kim <bbuil...@gmail.com 
>>> <mailto:bbuil...@gmail.com>> wrote:
>>> Todd,
>>> 
>>> It sounds like Kudu can possibly top or match those numbers put out by 
>>> Aerospike. Do you have any performance statistics published or any 
>>> instructions as to measure them myself as good way to test? In addition, 
>>> this will be a test using Spark, so should I wait for Kudu version 0.9.0 
>>> where support will be built in?
>>> 
>>> We don't have a lot of benchmarks published yet, especially on the write 
>>> side. I've found that thorough cross-system benchmarks are very difficult 
>>> to do fairly and accurately, and often times users end up misguided if they 
>>> pay too much attention to them :) So, given a finite number of developers 
>>> working on Kudu, I think we've tended to spend more time on the project 
>>> itself and less time focusing on "competition". I'm sure there are use 
>>> cases where Kudu will beat out Aerospike, and probably use cases where 
>>> Aerospike will beat Kudu as well.
>>> 
>>> From my perspective, it would be great if you can share some details of 
>>> your workload, especially if there are some areas you're finding Kudu 
>>> lacking. Maybe we can spot some easy code changes we could make to improve 
>>> performance, or suggest a tuning variable you could change.
>>> 
>>> -Todd
>>> 
>>> 
>>>> On May 27

Re: Performance Question

[Benjamin Kim]

Over the weekend, the row count is up to <500M. I will give it another few days 
to get to 1B rows. I still get consistent times ~15s for doing row counts 
despite the amount of data growing.

On another note, I got a solicitation email from SnappyData to evaluate their 
product. They claim to be the “Spark Data Store” with tight integration with 
Spark executors. It claims to be an OLTP and OLAP system with being an 
in-memory data store first then to disk. After going to several Spark events, 
it would seem that this is the new “hot” area for vendors. They all (MemSQL, 
Redis, Aerospike, Datastax, etc.) claim to be the best "Spark Data Store”. I’m 
wondering if Kudu will become this too? With the performance I’ve seen so far, 
it would seem that it can be a contender. All that is needed is a hardened 
Spark connector package, I would think. The next evaluation I will be 
conducting is to see if SnappyData’s claims are valid by doing my own tests.

Cheers,
Ben


> On Jun 15, 2016, at 12:47 AM, Todd Lipcon <t...@cloudera.com> wrote:
> 
> Hi Benjamin,
> 
> What workload are you using for benchmarks? Using spark or something more 
> custom? rdd or data frame or SQL, etc? Maybe you can share the schema and 
> some queries
> 
> Todd
> 
> Todd
> 
> On Jun 15, 2016 8:10 AM, "Benjamin Kim" <bbuil...@gmail.com 
> <mailto:bbuil...@gmail.com>> wrote:
> Hi Todd,
> 
> Now that Kudu 0.9.0 is out. I have done some tests. Already, I am impressed. 
> Compared to HBase, read and write performance are better. Write performance 
> has the greatest improvement (> 4x), while read is > 1.5x. Albeit, these are 
> only preliminary tests. Do you know of a way to really do some conclusive 
> tests? I want to see if I can match your results on my 50 node cluster.
> 
> Thanks,
> Ben
> 
>> On May 30, 2016, at 10:33 AM, Todd Lipcon <t...@cloudera.com 
>> <mailto:t...@cloudera.com>> wrote:
>> 
>> On Sat, May 28, 2016 at 7:12 AM, Benjamin Kim <bbuil...@gmail.com 
>> <mailto:bbuil...@gmail.com>> wrote:
>> Todd,
>> 
>> It sounds like Kudu can possibly top or match those numbers put out by 
>> Aerospike. Do you have any performance statistics published or any 
>> instructions as to measure them myself as good way to test? In addition, 
>> this will be a test using Spark, so should I wait for Kudu version 0.9.0 
>> where support will be built in?
>> 
>> We don't have a lot of benchmarks published yet, especially on the write 
>> side. I've found that thorough cross-system benchmarks are very difficult to 
>> do fairly and accurately, and often times users end up misguided if they pay 
>> too much attention to them :) So, given a finite number of developers 
>> working on Kudu, I think we've tended to spend more time on the project 
>> itself and less time focusing on "competition". I'm sure there are use cases 
>> where Kudu will beat out Aerospike, and probably use cases where Aerospike 
>> will beat Kudu as well.
>> 
>> From my perspective, it would be great if you can share some details of your 
>> workload, especially if there are some areas you're finding Kudu lacking. 
>> Maybe we can spot some easy code changes we could make to improve 
>> performance, or suggest a tuning variable you could change.
>> 
>> -Todd
>> 
>> 
>>> On May 27, 2016, at 9:19 PM, Todd Lipcon <t...@cloudera.com 
>>> <mailto:t...@cloudera.com>> wrote:
>>> 
>>> On Fri, May 27, 2016 at 8:20 PM, Benjamin Kim <bbuil...@gmail.com 
>>> <mailto:bbuil...@gmail.com>> wrote:
>>> Hi Mike,
>>> 
>>> First of all, thanks for the link. It looks like an interesting read. I 
>>> checked that Aerospike is currently at version 3.8.2.3, and in the article, 
>>> they are evaluating version 3.5.4. The main thing that impressed me was 
>>> their claim that they can beat Cassandra and HBase by 8x for writing and 
>>> 25x for reading. Their big claim to fame is that Aerospike can write 1M 
>>> records per second with only 50 nodes. I wanted to see if this is real.
>>> 
>>> 1M records per second on 50 nodes is pretty doable by Kudu as well, 
>>> depending on the size of your records and the insertion order. I've been 
>>> playing with a ~70 node cluster recently and seen 1M+ writes/second 
>>> sustained, and bursting above 4M. These are 1KB rows with 11 columns, and 
>>> with pretty old HDD-only nodes. I think newer flash-based nodes could do 
>>> better.
>>>  
>>> 
>>> To answer your questions, we have a DMP with user profiles with many

Re: Performance Question

[Benjamin Kim]

Hi Todd,

I changed the key to be what you suggested, and I can’t tell the difference 
since it was already fast. But, I did get more numbers.

> 104M rows in Kudu table
- read: 8s
- count: 16s
- aggregate: 9s

The time to read took much longer from 0.2s to 8s, counts were the same 16s, 
and aggregate queries look longer from 6s to 9s.

I’m still impressed.

Cheers,
Ben 

> On Jun 15, 2016, at 12:47 AM, Todd Lipcon <t...@cloudera.com> wrote:
> 
> Hi Benjamin,
> 
> What workload are you using for benchmarks? Using spark or something more 
> custom? rdd or data frame or SQL, etc? Maybe you can share the schema and 
> some queries
> 
> Todd
> 
> Todd
> 
> On Jun 15, 2016 8:10 AM, "Benjamin Kim" <bbuil...@gmail.com 
> <mailto:bbuil...@gmail.com>> wrote:
> Hi Todd,
> 
> Now that Kudu 0.9.0 is out. I have done some tests. Already, I am impressed. 
> Compared to HBase, read and write performance are better. Write performance 
> has the greatest improvement (> 4x), while read is > 1.5x. Albeit, these are 
> only preliminary tests. Do you know of a way to really do some conclusive 
> tests? I want to see if I can match your results on my 50 node cluster.
> 
> Thanks,
> Ben
> 
>> On May 30, 2016, at 10:33 AM, Todd Lipcon <t...@cloudera.com 
>> <mailto:t...@cloudera.com>> wrote:
>> 
>> On Sat, May 28, 2016 at 7:12 AM, Benjamin Kim <bbuil...@gmail.com 
>> <mailto:bbuil...@gmail.com>> wrote:
>> Todd,
>> 
>> It sounds like Kudu can possibly top or match those numbers put out by 
>> Aerospike. Do you have any performance statistics published or any 
>> instructions as to measure them myself as good way to test? In addition, 
>> this will be a test using Spark, so should I wait for Kudu version 0.9.0 
>> where support will be built in?
>> 
>> We don't have a lot of benchmarks published yet, especially on the write 
>> side. I've found that thorough cross-system benchmarks are very difficult to 
>> do fairly and accurately, and often times users end up misguided if they pay 
>> too much attention to them :) So, given a finite number of developers 
>> working on Kudu, I think we've tended to spend more time on the project 
>> itself and less time focusing on "competition". I'm sure there are use cases 
>> where Kudu will beat out Aerospike, and probably use cases where Aerospike 
>> will beat Kudu as well.
>> 
>> From my perspective, it would be great if you can share some details of your 
>> workload, especially if there are some areas you're finding Kudu lacking. 
>> Maybe we can spot some easy code changes we could make to improve 
>> performance, or suggest a tuning variable you could change.
>> 
>> -Todd
>> 
>> 
>>> On May 27, 2016, at 9:19 PM, Todd Lipcon <t...@cloudera.com 
>>> <mailto:t...@cloudera.com>> wrote:
>>> 
>>> On Fri, May 27, 2016 at 8:20 PM, Benjamin Kim <bbuil...@gmail.com 
>>> <mailto:bbuil...@gmail.com>> wrote:
>>> Hi Mike,
>>> 
>>> First of all, thanks for the link. It looks like an interesting read. I 
>>> checked that Aerospike is currently at version 3.8.2.3, and in the article, 
>>> they are evaluating version 3.5.4. The main thing that impressed me was 
>>> their claim that they can beat Cassandra and HBase by 8x for writing and 
>>> 25x for reading. Their big claim to fame is that Aerospike can write 1M 
>>> records per second with only 50 nodes. I wanted to see if this is real.
>>> 
>>> 1M records per second on 50 nodes is pretty doable by Kudu as well, 
>>> depending on the size of your records and the insertion order. I've been 
>>> playing with a ~70 node cluster recently and seen 1M+ writes/second 
>>> sustained, and bursting above 4M. These are 1KB rows with 11 columns, and 
>>> with pretty old HDD-only nodes. I think newer flash-based nodes could do 
>>> better.
>>>  
>>> 
>>> To answer your questions, we have a DMP with user profiles with many 
>>> attributes. We create segmentation information off of these attributes to 
>>> classify them. Then, we can target advertising appropriately for our sales 
>>> department. Much of the data processing is for applying models on all or if 
>>> not most of every profile’s attributes to find similarities (nearest 
>>> neighbor/clustering) over a large number of rows when batch processing or a 
>>> small subset of rows for quick online scoring. So, our use case is a 
>>> typical advanced analytics scenario. We have tried HBase, but it 

Re: Performance Question

[Benjamin Kim]

Todd,

FYI. The key  is unique for every row so rows are not going to already exist. 
Basically, everything is an INSERT.

val generateUUID = udf(() => UUID.randomUUID().toString)

As you can see, we are using UUID java library to create the key.

Cheers,
Ben

> On Jun 29, 2016, at 1:32 PM, Todd Lipcon <t...@cloudera.com> wrote:
> 
> On Wed, Jun 29, 2016 at 11:32 AM, Benjamin Kim <bbuil...@gmail.com 
> <mailto:bbuil...@gmail.com>> wrote:
> Todd,
> 
> I started Spark streaming more events into Kudu. Performance is great there 
> too! With HBase, it’s fast too, but I noticed that it pauses here and there, 
> making it take seconds for > 40k rows at a time, while Kudu doesn’t. The 
> progress bar just blinks by. I will keep this running until it hits 1B rows 
> and rerun my performance tests. This, hopefully, will give better numbers.
> 
> Cool! We have invested a lot of work in making Kudu have consistent 
> performance, like you mentioned. It's generally been my experience that most 
> mature ops people would prefer a system which consistently performs well 
> rather than one which has higher peak performance but occasionally stalls.
> 
> BTW, what is your row key design? One exception to the above is that, if 
> you're doing random inserts, you may see performance "fall off a cliff" once 
> the size of your key columns becomes larger than the aggregate memory size of 
> your cluster, if you're running on hard disks. Our inserts require checks for 
> duplicate keys, and that can cause random disk IOs if your keys don't fit 
> comfortably in cache. This is one area that HBase is fundamentally going to 
> be faster based on its design.
> 
> -Todd
> 
> 
>> On Jun 28, 2016, at 4:26 PM, Todd Lipcon <t...@cloudera.com 
>> <mailto:t...@cloudera.com>> wrote:
>> 
>> Cool, thanks for the report, Ben. For what it's worth, I think there's still 
>> some low hanging fruit in the Spark connector for Kudu (for example, I 
>> believe locality on reads is currently broken). So, you can expect 
>> performance to continue to improve in future versions. I'd also be 
>> interested to see results on Kudu for a much larger dataset - my guess is a 
>> lot of the 6 seconds you're seeing is constant overhead from Spark job 
>> setup, etc, given that the performance doesn't seem to get slower as you 
>> went from 700K rows to 13M rows.
>> 
>> -Todd
>> 
>> On Tue, Jun 28, 2016 at 3:03 PM, Benjamin Kim <bbuil...@gmail.com 
>> <mailto:bbuil...@gmail.com>> wrote:
>> FYI.
>> 
>> I did a quick-n-dirty performance test.
>> 
>> First, the setup:
>> QA cluster:
>> 15 data nodes
>> 64GB memory each
>> HBase is using 4GB of memory
>> Kudu is using 1GB of memory
>> 1 HBase/Kudu master node
>> 64GB memory
>> HBase/Kudu master is using 1GB of memory each
>> 10Gb Ethernet
>> 
>> Using Spark on both to load/read events data (84 columns per row), I was 
>> able to record performance for each. On the HBase side, I used the Phoenix 
>> 4.7 Spark plugin where DataFrames can be used directly. On the Kudu side, I 
>> used the Spark connector. I created an events table in Phoenix using the 
>> CREATE TABLE statement and created the equivalent in Kudu using the Spark 
>> method based off of a DataFrame schema.
>> 
>> Here are the numbers for Phoenix/HBase.
>> 1st run:
>> > 715k rows
>> - write: 2.7m
>> 
>> > 715k rows in HBase table
>> - read: 0.1s
>> - count: 3.8s
>> - aggregate: 61s
>> 
>> 2nd run:
>> > 5.2M rows
>> - write: 11m
>> * had 4 region servers go down, had to retry the 5.2M row write
>> 
>> > 5.9M rows in HBase table
>> - read: 8s
>> - count: 3m
>> - aggregate: 46s
>> 
>> 3rd run:
>> > 6.8M rows
>> - write: 9.6m
>> 
>> > 12.7M rows
>> - read: 10s
>> - count: 3m
>> - aggregate: 44s
>> 
>> 
>> Here are the numbers for Kudu.
>> 1st run:
>> > 715k rows
>> - write: 18s
>> 
>> > 715k rows in Kudu table
>> - read: 0.2s
>> - count: 18s
>> - aggregate: 5s
>> 
>> 2nd run:
>> > 5.2M rows
>> - write: 33s
>> 
>> > 5.9M rows in Kudu table
>> - read: 0.2s
>> - count: 16s
>> - aggregate: 6s
>> 
>> 3rd run:
>> > 6.8M rows
>> - write: 27s
>> 
>> > 12.7M rows in Kudu table
>> - read: 0.2s
>> - count: 16s
>> - aggregate: 6s
>> 
>> The Kudu results are impressive if you take these number as-is. Kudu is 
>> clo

Re: Performance Question

[Benjamin Kim]

Todd,

I started Spark streaming more events into Kudu. Performance is great there 
too! With HBase, it’s fast too, but I noticed that it pauses here and there, 
making it take seconds for > 40k rows at a time, while Kudu doesn’t. The 
progress bar just blinks by. I will keep this running until it hits 1B rows and 
rerun my performance tests. This, hopefully, will give better numbers.

Thanks,
Ben


> On Jun 28, 2016, at 4:26 PM, Todd Lipcon <t...@cloudera.com> wrote:
> 
> Cool, thanks for the report, Ben. For what it's worth, I think there's still 
> some low hanging fruit in the Spark connector for Kudu (for example, I 
> believe locality on reads is currently broken). So, you can expect 
> performance to continue to improve in future versions. I'd also be interested 
> to see results on Kudu for a much larger dataset - my guess is a lot of the 6 
> seconds you're seeing is constant overhead from Spark job setup, etc, given 
> that the performance doesn't seem to get slower as you went from 700K rows to 
> 13M rows.
> 
> -Todd
> 
> On Tue, Jun 28, 2016 at 3:03 PM, Benjamin Kim <bbuil...@gmail.com 
> <mailto:bbuil...@gmail.com>> wrote:
> FYI.
> 
> I did a quick-n-dirty performance test.
> 
> First, the setup:
> QA cluster:
> 15 data nodes
> 64GB memory each
> HBase is using 4GB of memory
> Kudu is using 1GB of memory
> 1 HBase/Kudu master node
> 64GB memory
> HBase/Kudu master is using 1GB of memory each
> 10Gb Ethernet
> 
> Using Spark on both to load/read events data (84 columns per row), I was able 
> to record performance for each. On the HBase side, I used the Phoenix 4.7 
> Spark plugin where DataFrames can be used directly. On the Kudu side, I used 
> the Spark connector. I created an events table in Phoenix using the CREATE 
> TABLE statement and created the equivalent in Kudu using the Spark method 
> based off of a DataFrame schema.
> 
> Here are the numbers for Phoenix/HBase.
> 1st run:
> > 715k rows
> - write: 2.7m
> 
> > 715k rows in HBase table
> - read: 0.1s
> - count: 3.8s
> - aggregate: 61s
> 
> 2nd run:
> > 5.2M rows
> - write: 11m
> * had 4 region servers go down, had to retry the 5.2M row write
> 
> > 5.9M rows in HBase table
> - read: 8s
> - count: 3m
> - aggregate: 46s
> 
> 3rd run:
> > 6.8M rows
> - write: 9.6m
> 
> > 12.7M rows
> - read: 10s
> - count: 3m
> - aggregate: 44s
> 
> 
> Here are the numbers for Kudu.
> 1st run:
> > 715k rows
> - write: 18s
> 
> > 715k rows in Kudu table
> - read: 0.2s
> - count: 18s
> - aggregate: 5s
> 
> 2nd run:
> > 5.2M rows
> - write: 33s
> 
> > 5.9M rows in Kudu table
> - read: 0.2s
> - count: 16s
> - aggregate: 6s
> 
> 3rd run:
> > 6.8M rows
> - write: 27s
> 
> > 12.7M rows in Kudu table
> - read: 0.2s
> - count: 16s
> - aggregate: 6s
> 
> The Kudu results are impressive if you take these number as-is. Kudu is close 
> to 18x faster at writing (UPSERT). Kudu is 30x faster at reading (HBase times 
> increase as data size grows).  Kudu is 7x faster at full row counts. Lastly, 
> Kudu is 3x faster doing an aggregate query (count distinct event_id’s per 
> user_id). *Remember that this is small cluster, times are still respectable 
> for both systems, HBase could have been configured better, and the HBase 
> table could have been better tuned.
> 
> Cheers,
> Ben
> 
> 
>> On Jun 15, 2016, at 10:13 AM, Dan Burkert <d...@cloudera.com 
>> <mailto:d...@cloudera.com>> wrote:
>> 
>> Adding partition splits when range partitioning is done via the 
>> CreateTableOptions.addSplitRow 
>> <http://getkudu.io/apidocs/org/kududb/client/CreateTableOptions.html#addSplitRow-org.kududb.client.PartialRow->
>>  method.  You can find more about the different partitioning options in the 
>> schema design guide 
>> <http://getkudu.io/docs/schema_design.html#data-distribution>.  We generally 
>> recommend sticking to hash partitioning if possible, since you don't have to 
>> determine your own split rows.
>> 
>> - Dan
>> 
>> On Wed, Jun 15, 2016 at 9:17 AM, Benjamin Kim <bbuil...@gmail.com 
>> <mailto:bbuil...@gmail.com>> wrote:
>> Todd,
>> 
>> I think the locality is not within our setup. We have the compute cluster 
>> with Spark, YARN, etc. on its own, and we have the storage cluster with 
>> HBase, Kudu, etc. on another. We beefed up the hardware specs on the compute 
>> cluster and beefed up storage capacity on the storage cluster. We got this 
>> setup idea from the Databricks folks. I do have a question. I created the 
>

Re: Performance Question

[Benjamin Kim]

FYI.

I did a quick-n-dirty performance test.

First, the setup:
QA cluster:
15 data nodes
64GB memory each
HBase is using 4GB of memory
Kudu is using 1GB of memory
1 HBase/Kudu master node
64GB memory
HBase/Kudu master is using 1GB of memory each
10Gb Ethernet

Using Spark on both to load/read events data (84 columns per row), I was able 
to record performance for each. On the HBase side, I used the Phoenix 4.7 Spark 
plugin where DataFrames can be used directly. On the Kudu side, I used the 
Spark connector. I created an events table in Phoenix using the CREATE TABLE 
statement and created the equivalent in Kudu using the Spark method based off 
of a DataFrame schema.

Here are the numbers for Phoenix/HBase.
1st run:
> 715k rows
- write: 2.7m

> 715k rows in HBase table
- read: 0.1s
- count: 3.8s
- aggregate: 61s

2nd run:
> 5.2M rows
- write: 11m
* had 4 region servers go down, had to retry the 5.2M row write

> 5.9M rows in HBase table
- read: 8s
- count: 3m
- aggregate: 46s

3rd run:
> 6.8M rows
- write: 9.6m

> 12.7M rows
- read: 10s
- count: 3m
- aggregate: 44s


Here are the numbers for Kudu.
1st run:
> 715k rows
- write: 18s

> 715k rows in Kudu table
- read: 0.2s
- count: 18s
- aggregate: 5s

2nd run:
> 5.2M rows
- write: 33s

> 5.9M rows in Kudu table
- read: 0.2s
- count: 16s
- aggregate: 6s

3rd run:
> 6.8M rows
- write: 27s

> 12.7M rows in Kudu table
- read: 0.2s
- count: 16s
- aggregate: 6s

The Kudu results are impressive if you take these number as-is. Kudu is close 
to 18x faster at writing (UPSERT). Kudu is 30x faster at reading (HBase times 
increase as data size grows).  Kudu is 7x faster at full row counts. Lastly, 
Kudu is 3x faster doing an aggregate query (count distinct event_id’s per 
user_id). *Remember that this is small cluster, times are still respectable for 
both systems, HBase could have been configured better, and the HBase table 
could have been better tuned.

Cheers,
Ben


> On Jun 15, 2016, at 10:13 AM, Dan Burkert <d...@cloudera.com> wrote:
> 
> Adding partition splits when range partitioning is done via the 
> CreateTableOptions.addSplitRow 
> <http://getkudu.io/apidocs/org/kududb/client/CreateTableOptions.html#addSplitRow-org.kududb.client.PartialRow->
>  method.  You can find more about the different partitioning options in the 
> schema design guide 
> <http://getkudu.io/docs/schema_design.html#data-distribution>.  We generally 
> recommend sticking to hash partitioning if possible, since you don't have to 
> determine your own split rows.
> 
> - Dan
> 
> On Wed, Jun 15, 2016 at 9:17 AM, Benjamin Kim <bbuil...@gmail.com 
> <mailto:bbuil...@gmail.com>> wrote:
> Todd,
> 
> I think the locality is not within our setup. We have the compute cluster 
> with Spark, YARN, etc. on its own, and we have the storage cluster with 
> HBase, Kudu, etc. on another. We beefed up the hardware specs on the compute 
> cluster and beefed up storage capacity on the storage cluster. We got this 
> setup idea from the Databricks folks. I do have a question. I created the 
> table to use range partition on columns. I see that if I use hash partition I 
> can set the number of splits, but how do I do that using range (50 nodes * 10 
> = 500 splits)?
> 
> Thanks,
> Ben
> 
> 
>> On Jun 15, 2016, at 9:11 AM, Todd Lipcon <t...@cloudera.com 
>> <mailto:t...@cloudera.com>> wrote:
>> 
>> Awesome use case. One thing to keep in mind is that spark parallelism will 
>> be limited by the number of tablets. So, you might want to split into 10 or 
>> so buckets per node to get the best query throughput.
>> 
>> Usually if you run top on some machines while running the query you can see 
>> if it is fully utilizing the cores.
>> 
>> Another known issue right now is that spark locality isn't working properly 
>> on replicated tables so you will use a lot of network traffic. For a perf 
>> test you might want to try a table with replication count 1
>> 
>> On Jun 15, 2016 5:26 PM, "Benjamin Kim" <bbuil...@gmail.com 
>> <mailto:bbuil...@gmail.com>> wrote:
>> Hi Todd,
>> 
>> I did a simple test of our ad events. We stream using Spark Streaming 
>> directly into HBase, and the Data Analysts/Scientists do some 
>> insight/discovery work plus some reports generation. For the reports, we use 
>> SQL, and the more deeper stuff, we use Spark. In Spark, our main data 
>> currency store of choice is DataFrames.
>> 
>> The schema is around 83 columns wide where most are of the string data type.
>> 
>> "event_type", "timestamp", "event_valid", "event_subtype", "user_ip", 
>> "user_id", "mappable_id&q

Re: Spark on Kudu

[Benjamin Kim]

Dan,

Out of curiosity, I was looking through the spark-csv code in Github and tried 
to see what makes it work for the “CREATE TABLE” statement, while it doesn’t 
for spark-kudu. There are differences in the way both are done, CsvRelation vs. 
KuduRelation. I’m still learning how this works though and what implications 
these differences are. In your opinion, is this the right place to start?

Thanks,
Ben


> On Jun 17, 2016, at 11:08 AM, Dan Burkert <d...@cloudera.com> wrote:
> 
> Hi Ben,
> 
> To your first question about `CREATE TABLE` syntax with Kudu/Spark SQL, I do 
> not think we support that at this point.  I haven't looked deeply into it, 
> but we may hit issues specifying Kudu-specific options (partitioning, column 
> encoding, etc.).  Probably issues that can be worked through eventually, 
> though.  If you are interested in contributing to Kudu, this is an area that 
> could obviously use improvement!  Most or all of our Spark features have been 
> completely community driven to date.
>  
> I am assuming that more Spark support along with semantic changes below will 
> be incorporated into Kudu 0.9.1.
> 
> As a rule we do not release new features in patch releases, but the good news 
> is that we are releasing regularly, and our next scheduled release is for the 
> August timeframe (see JD's roadmap 
> <https://lists.apache.org/thread.html/1a3b949e715a74d7f26bd9c102247441a06d16d077324ba39a662e2a@1455234076@%3Cdev.kudu.apache.org%3E>
>  email about what we are aiming to include).  Also, Cloudera does publish 
> snapshot versions of the Spark connector here 
> <https://repository.cloudera.com/cloudera/cloudera-repos/org/kududb/>, so the 
> jars are available if you don't mind using snapshots.
>  
> Anyone know of a better way to make unique primary keys other than using UUID 
> to make every row unique if there is no unique column (or combination 
> thereof) to use.
> 
> Not that I know of.  In general it's pretty rare to have a dataset without a 
> natural primary key (even if it's just all of the columns), but in those 
> cases UUID is a good solution.
>  
> This is what I am using. I know auto incrementing is coming down the line 
> (don’t know when), but is there a way to simulate this in Kudu using Spark 
> out of curiosity?
> 
> To my knowledge there is no plan to have auto increment in Kudu.  
> Distributed, consistent, auto incrementing counters is a difficult problem, 
> and I don't think there are any known solutions that would be fast enough for 
> Kudu (happy to be proven wrong, though!).
> 
> - Dan
>  
> 
> Thanks,
> Ben
> 
>> On Jun 14, 2016, at 6:08 PM, Dan Burkert <d...@cloudera.com 
>> <mailto:d...@cloudera.com>> wrote:
>> 
>> I'm not sure exactly what the semantics will be, but at least one of them 
>> will be upsert.  These modes come from spark, and they were really designed 
>> for file-backed storage and not table storage.  We may want to do append = 
>> upsert, and overwrite = truncate + insert.  I think that may match the 
>> normal spark semantics more closely.
>> 
>> - Dan
>> 
>> On Tue, Jun 14, 2016 at 6:00 PM, Benjamin Kim <bbuil...@gmail.com 
>> <mailto:bbuil...@gmail.com>> wrote:
>> Dan,
>> 
>> Thanks for the information. That would mean both “append” and “overwrite” 
>> modes would be combined or not needed in the future.
>> 
>> Cheers,
>> Ben
>> 
>>> On Jun 14, 2016, at 5:57 PM, Dan Burkert <d...@cloudera.com 
>>> <mailto:d...@cloudera.com>> wrote:
>>> 
>>> Right now append uses an update Kudu operation, which requires the row 
>>> already be present in the table. Overwrite maps to insert.  Kudu very 
>>> recently got upsert support baked in, but it hasn't yet been integrated 
>>> into the Spark connector.  So pretty soon these sharp edges will get a lot 
>>> better, since upsert is the way to go for most spark workloads.
>>> 
>>> - Dan
>>> 
>>> On Tue, Jun 14, 2016 at 5:41 PM, Benjamin Kim <bbuil...@gmail.com 
>>> <mailto:bbuil...@gmail.com>> wrote:
>>> I tried to use the “append” mode, and it worked. Over 3.8 million rows in 
>>> 64s. I would assume that now I can use the “overwrite” mode on existing 
>>> data. Now, I have to find answers to these questions. What would happen if 
>>> I “append” to the data in the Kudu table if the data already exists? What 
>>> would happen if I “overwrite” existing data when the DataFrame has data in 
>>> it that does not exist in the Kudu table? I need to evaluate the best way 
>>> to simulate the UPSERT behavior in HBase 

Re: Spark on Kudu

[Benjamin Kim]

Dan,

The roadmap is very informative. I am looking forward to the official 1.0 
release! It would be so much easier for us to use in every aspect compared to 
HBase.

Cheers,
Ben


> On Jun 17, 2016, at 11:08 AM, Dan Burkert <d...@cloudera.com> wrote:
> 
> Hi Ben,
> 
> To your first question about `CREATE TABLE` syntax with Kudu/Spark SQL, I do 
> not think we support that at this point.  I haven't looked deeply into it, 
> but we may hit issues specifying Kudu-specific options (partitioning, column 
> encoding, etc.).  Probably issues that can be worked through eventually, 
> though.  If you are interested in contributing to Kudu, this is an area that 
> could obviously use improvement!  Most or all of our Spark features have been 
> completely community driven to date.
>  
> I am assuming that more Spark support along with semantic changes below will 
> be incorporated into Kudu 0.9.1.
> 
> As a rule we do not release new features in patch releases, but the good news 
> is that we are releasing regularly, and our next scheduled release is for the 
> August timeframe (see JD's roadmap 
> <https://lists.apache.org/thread.html/1a3b949e715a74d7f26bd9c102247441a06d16d077324ba39a662e2a@1455234076@%3Cdev.kudu.apache.org%3E>
>  email about what we are aiming to include).  Also, Cloudera does publish 
> snapshot versions of the Spark connector here 
> <https://repository.cloudera.com/cloudera/cloudera-repos/org/kududb/>, so the 
> jars are available if you don't mind using snapshots.
>  
> Anyone know of a better way to make unique primary keys other than using UUID 
> to make every row unique if there is no unique column (or combination 
> thereof) to use.
> 
> Not that I know of.  In general it's pretty rare to have a dataset without a 
> natural primary key (even if it's just all of the columns), but in those 
> cases UUID is a good solution.
>  
> This is what I am using. I know auto incrementing is coming down the line 
> (don’t know when), but is there a way to simulate this in Kudu using Spark 
> out of curiosity?
> 
> To my knowledge there is no plan to have auto increment in Kudu.  
> Distributed, consistent, auto incrementing counters is a difficult problem, 
> and I don't think there are any known solutions that would be fast enough for 
> Kudu (happy to be proven wrong, though!).
> 
> - Dan
>  
> 
> Thanks,
> Ben
> 
>> On Jun 14, 2016, at 6:08 PM, Dan Burkert <d...@cloudera.com 
>> <mailto:d...@cloudera.com>> wrote:
>> 
>> I'm not sure exactly what the semantics will be, but at least one of them 
>> will be upsert.  These modes come from spark, and they were really designed 
>> for file-backed storage and not table storage.  We may want to do append = 
>> upsert, and overwrite = truncate + insert.  I think that may match the 
>> normal spark semantics more closely.
>> 
>> - Dan
>> 
>> On Tue, Jun 14, 2016 at 6:00 PM, Benjamin Kim <bbuil...@gmail.com 
>> <mailto:bbuil...@gmail.com>> wrote:
>> Dan,
>> 
>> Thanks for the information. That would mean both “append” and “overwrite” 
>> modes would be combined or not needed in the future.
>> 
>> Cheers,
>> Ben
>> 
>>> On Jun 14, 2016, at 5:57 PM, Dan Burkert <d...@cloudera.com 
>>> <mailto:d...@cloudera.com>> wrote:
>>> 
>>> Right now append uses an update Kudu operation, which requires the row 
>>> already be present in the table. Overwrite maps to insert.  Kudu very 
>>> recently got upsert support baked in, but it hasn't yet been integrated 
>>> into the Spark connector.  So pretty soon these sharp edges will get a lot 
>>> better, since upsert is the way to go for most spark workloads.
>>> 
>>> - Dan
>>> 
>>> On Tue, Jun 14, 2016 at 5:41 PM, Benjamin Kim <bbuil...@gmail.com 
>>> <mailto:bbuil...@gmail.com>> wrote:
>>> I tried to use the “append” mode, and it worked. Over 3.8 million rows in 
>>> 64s. I would assume that now I can use the “overwrite” mode on existing 
>>> data. Now, I have to find answers to these questions. What would happen if 
>>> I “append” to the data in the Kudu table if the data already exists? What 
>>> would happen if I “overwrite” existing data when the DataFrame has data in 
>>> it that does not exist in the Kudu table? I need to evaluate the best way 
>>> to simulate the UPSERT behavior in HBase because this is what our use case 
>>> is.
>>> 
>>> Thanks,
>>> Ben
>>> 
>>> 
>>> 
>>>> On Jun 14, 2016, at 5:05 PM, Benjamin Kim <bbuil...@gmai

Re: Spark on Kudu

[Benjamin Kim]

I am assuming that more Spark support along with semantic changes below will be 
incorporated into Kudu 0.9.1.

Anyone know of a better way to make unique primary keys other than using UUID 
to make every row unique if there is no unique column (or combination thereof) 
to use.

import java.util.UUID
val generateUUID = udf(() => UUID.randomUUID().toString)

This is what I am using. I know auto incrementing is coming down the line 
(don’t know when), but is there a way to simulate this in Kudu using Spark out 
of curiosity?

Thanks,
Ben

> On Jun 14, 2016, at 6:08 PM, Dan Burkert <d...@cloudera.com> wrote:
> 
> I'm not sure exactly what the semantics will be, but at least one of them 
> will be upsert.  These modes come from spark, and they were really designed 
> for file-backed storage and not table storage.  We may want to do append = 
> upsert, and overwrite = truncate + insert.  I think that may match the normal 
> spark semantics more closely.
> 
> - Dan
> 
> On Tue, Jun 14, 2016 at 6:00 PM, Benjamin Kim <bbuil...@gmail.com 
> <mailto:bbuil...@gmail.com>> wrote:
> Dan,
> 
> Thanks for the information. That would mean both “append” and “overwrite” 
> modes would be combined or not needed in the future.
> 
> Cheers,
> Ben
> 
>> On Jun 14, 2016, at 5:57 PM, Dan Burkert <d...@cloudera.com 
>> <mailto:d...@cloudera.com>> wrote:
>> 
>> Right now append uses an update Kudu operation, which requires the row 
>> already be present in the table. Overwrite maps to insert.  Kudu very 
>> recently got upsert support baked in, but it hasn't yet been integrated into 
>> the Spark connector.  So pretty soon these sharp edges will get a lot 
>> better, since upsert is the way to go for most spark workloads.
>> 
>> - Dan
>> 
>> On Tue, Jun 14, 2016 at 5:41 PM, Benjamin Kim <bbuil...@gmail.com 
>> <mailto:bbuil...@gmail.com>> wrote:
>> I tried to use the “append” mode, and it worked. Over 3.8 million rows in 
>> 64s. I would assume that now I can use the “overwrite” mode on existing 
>> data. Now, I have to find answers to these questions. What would happen if I 
>> “append” to the data in the Kudu table if the data already exists? What 
>> would happen if I “overwrite” existing data when the DataFrame has data in 
>> it that does not exist in the Kudu table? I need to evaluate the best way to 
>> simulate the UPSERT behavior in HBase because this is what our use case is.
>> 
>> Thanks,
>> Ben
>> 
>> 
>> 
>>> On Jun 14, 2016, at 5:05 PM, Benjamin Kim <bbuil...@gmail.com 
>>> <mailto:bbuil...@gmail.com>> wrote:
>>> 
>>> Hi,
>>> 
>>> Now, I’m getting this error when trying to write to the table.
>>> 
>>> import scala.collection.JavaConverters._
>>> val key_seq = Seq(“my_id")
>>> val key_list = List(“my_id”).asJava
>>> kuduContext.createTable(tableName, df.schema, key_seq, new 
>>> CreateTableOptions().setNumReplicas(1).addHashPartitions(key_list, 100))
>>> 
>>> df.write
>>> .options(Map("kudu.master" -> kuduMaster,"kudu.table" -> tableName))
>>> .mode("overwrite")
>>> .kudu
>>> 
>>> java.lang.RuntimeException: failed to write 1000 rows from DataFrame to 
>>> Kudu; sample errors: Not found: key not found (error 0)Not found: key not 
>>> found (error 0)Not found: key not found (error 0)Not found: key not found 
>>> (error 0)Not found: key not found (error 0)
>>> 
>>> Does the key field need to be first in the DataFrame?
>>> 
>>> Thanks,
>>> Ben
>>> 
>>>> On Jun 14, 2016, at 4:28 PM, Dan Burkert <d...@cloudera.com 
>>>> <mailto:d...@cloudera.com>> wrote:
>>>> 
>>>> 
>>>> 
>>>> On Tue, Jun 14, 2016 at 4:20 PM, Benjamin Kim <bbuil...@gmail.com 
>>>> <mailto:bbuil...@gmail.com>> wrote:
>>>> Dan,
>>>> 
>>>> Thanks! It got further. Now, how do I set the Primary Key to be a 
>>>> column(s) in the DataFrame and set the partitioning? Is it like this?
>>>> 
>>>> kuduContext.createTable(tableName, df.schema, Seq(“my_id"), new 
>>>> CreateTableOptions().setNumReplicas(1).addHashPartitions(“my_id"))
>>>> 
>>>> java.lang.IllegalArgumentException: Table partitioning must be specified 
>>>> using setRangePartitionColumns or addHashPartitions
>>>> 
>>>> Yep.  The `Seq("my_id")` part of that call is sp

Re: Spark on Kudu

[Benjamin Kim]

Since I have created permanent tables using org.apache.spark.sql.jdbc and 
com.databricks.spark.csv with sqlContext, I was wondering if I can do the same 
with Kudu tables?

CREATE TABLE 
USING org.kududb.spark.kudu
OPTIONS ("kudu.master” "kudu_master","kudu.table” "kudu_tablename”)

Is this possible? By the way, the above didn’t work for me.

Thanks,
Ben

> On Jun 14, 2016, at 6:08 PM, Dan Burkert <d...@cloudera.com> wrote:
> 
> I'm not sure exactly what the semantics will be, but at least one of them 
> will be upsert.  These modes come from spark, and they were really designed 
> for file-backed storage and not table storage.  We may want to do append = 
> upsert, and overwrite = truncate + insert.  I think that may match the normal 
> spark semantics more closely.
> 
> - Dan
> 
> On Tue, Jun 14, 2016 at 6:00 PM, Benjamin Kim <bbuil...@gmail.com 
> <mailto:bbuil...@gmail.com>> wrote:
> Dan,
> 
> Thanks for the information. That would mean both “append” and “overwrite” 
> modes would be combined or not needed in the future.
> 
> Cheers,
> Ben
> 
>> On Jun 14, 2016, at 5:57 PM, Dan Burkert <d...@cloudera.com 
>> <mailto:d...@cloudera.com>> wrote:
>> 
>> Right now append uses an update Kudu operation, which requires the row 
>> already be present in the table. Overwrite maps to insert.  Kudu very 
>> recently got upsert support baked in, but it hasn't yet been integrated into 
>> the Spark connector.  So pretty soon these sharp edges will get a lot 
>> better, since upsert is the way to go for most spark workloads.
>> 
>> - Dan
>> 
>> On Tue, Jun 14, 2016 at 5:41 PM, Benjamin Kim <bbuil...@gmail.com 
>> <mailto:bbuil...@gmail.com>> wrote:
>> I tried to use the “append” mode, and it worked. Over 3.8 million rows in 
>> 64s. I would assume that now I can use the “overwrite” mode on existing 
>> data. Now, I have to find answers to these questions. What would happen if I 
>> “append” to the data in the Kudu table if the data already exists? What 
>> would happen if I “overwrite” existing data when the DataFrame has data in 
>> it that does not exist in the Kudu table? I need to evaluate the best way to 
>> simulate the UPSERT behavior in HBase because this is what our use case is.
>> 
>> Thanks,
>> Ben
>> 
>> 
>> 
>>> On Jun 14, 2016, at 5:05 PM, Benjamin Kim <bbuil...@gmail.com 
>>> <mailto:bbuil...@gmail.com>> wrote:
>>> 
>>> Hi,
>>> 
>>> Now, I’m getting this error when trying to write to the table.
>>> 
>>> import scala.collection.JavaConverters._
>>> val key_seq = Seq(“my_id")
>>> val key_list = List(“my_id”).asJava
>>> kuduContext.createTable(tableName, df.schema, key_seq, new 
>>> CreateTableOptions().setNumReplicas(1).addHashPartitions(key_list, 100))
>>> 
>>> df.write
>>> .options(Map("kudu.master" -> kuduMaster,"kudu.table" -> tableName))
>>> .mode("overwrite")
>>> .kudu
>>> 
>>> java.lang.RuntimeException: failed to write 1000 rows from DataFrame to 
>>> Kudu; sample errors: Not found: key not found (error 0)Not found: key not 
>>> found (error 0)Not found: key not found (error 0)Not found: key not found 
>>> (error 0)Not found: key not found (error 0)
>>> 
>>> Does the key field need to be first in the DataFrame?
>>> 
>>> Thanks,
>>> Ben
>>> 
>>>> On Jun 14, 2016, at 4:28 PM, Dan Burkert <d...@cloudera.com 
>>>> <mailto:d...@cloudera.com>> wrote:
>>>> 
>>>> 
>>>> 
>>>> On Tue, Jun 14, 2016 at 4:20 PM, Benjamin Kim <bbuil...@gmail.com 
>>>> <mailto:bbuil...@gmail.com>> wrote:
>>>> Dan,
>>>> 
>>>> Thanks! It got further. Now, how do I set the Primary Key to be a 
>>>> column(s) in the DataFrame and set the partitioning? Is it like this?
>>>> 
>>>> kuduContext.createTable(tableName, df.schema, Seq(“my_id"), new 
>>>> CreateTableOptions().setNumReplicas(1).addHashPartitions(“my_id"))
>>>> 
>>>> java.lang.IllegalArgumentException: Table partitioning must be specified 
>>>> using setRangePartitionColumns or addHashPartitions
>>>> 
>>>> Yep.  The `Seq("my_id")` part of that call is specifying the set of 
>>>> primary key columns, so in this case you have specified the single PK 
>>>> column "my_id".  The `addHas

Re: Performance Question

[Benjamin Kim]

Todd,

I think the locality is not within our setup. We have the compute cluster with 
Spark, YARN, etc. on its own, and we have the storage cluster with HBase, Kudu, 
etc. on another. We beefed up the hardware specs on the compute cluster and 
beefed up storage capacity on the storage cluster. We got this setup idea from 
the Databricks folks. I do have a question. I created the table to use range 
partition on columns. I see that if I use hash partition I can set the number 
of splits, but how do I do that using range (50 nodes * 10 = 500 splits)?

Thanks,
Ben

> On Jun 15, 2016, at 9:11 AM, Todd Lipcon <t...@cloudera.com> wrote:
> 
> Awesome use case. One thing to keep in mind is that spark parallelism will be 
> limited by the number of tablets. So, you might want to split into 10 or so 
> buckets per node to get the best query throughput.
> 
> Usually if you run top on some machines while running the query you can see 
> if it is fully utilizing the cores.
> 
> Another known issue right now is that spark locality isn't working properly 
> on replicated tables so you will use a lot of network traffic. For a perf 
> test you might want to try a table with replication count 1
> 
> On Jun 15, 2016 5:26 PM, "Benjamin Kim" <bbuil...@gmail.com 
> <mailto:bbuil...@gmail.com>> wrote:
> Hi Todd,
> 
> I did a simple test of our ad events. We stream using Spark Streaming 
> directly into HBase, and the Data Analysts/Scientists do some 
> insight/discovery work plus some reports generation. For the reports, we use 
> SQL, and the more deeper stuff, we use Spark. In Spark, our main data 
> currency store of choice is DataFrames.
> 
> The schema is around 83 columns wide where most are of the string data type.
> 
> "event_type", "timestamp", "event_valid", "event_subtype", "user_ip", 
> "user_id", "mappable_id",
> "cookie_status", "profile_status", "user_status", "previous_timestamp", 
> "user_agent", "referer",
> "host_domain", "uri", "request_elapsed", "browser_languages", "acamp_id", 
> "creative_id",
> "location_id", “pcamp_id",
> "pdomain_id", "continent_code", "country", "region", "dma", "city", "zip", 
> "isp", "line_speed",
> "gender", "year_of_birth", "behaviors_read", "behaviors_written", 
> "key_value_pairs", "acamp_candidates",
> "tag_format", "optimizer_name", "optimizer_version", "optimizer_ip", 
> "pixel_id", “video_id",
> "video_network_id", "video_time_watched", "video_percentage_watched", 
> "video_media_type",
> "video_player_iframed", "video_player_in_view", "video_player_width", 
> "video_player_height",
> "conversion_valid_sale", "conversion_sale_amount", 
> "conversion_commission_amount", "conversion_step",
> "conversion_currency", "conversion_attribution", "conversion_offer_id", 
> "custom_info", "frequency",
> "recency_seconds", "cost", "revenue", “optimizer_acamp_id",
> "optimizer_creative_id", "optimizer_ecpm", "impression_id", "diagnostic_data",
> "user_profile_mapping_source", "latitude", "longitude", "area_code", 
> "gmt_offset", "in_dst",
> "proxy_type", "mobile_carrier", "pop", "hostname", "profile_expires", 
> "timestamp_iso", "reference_id",
> "identity_organization", "identity_method"
> 
> Most queries are like counts of how many users use what browser, how many are 
> unique users, etc. The part that scares most users is when it comes to 
> joining this data with other dimension/3rd party events tables because of 
> shear size of it.
> 
> We do what most companies do, similar to what I saw in earlier presentations 
> of Kudu. We dump data out of HBase into partitioned Parquet tables to make 
> query performance manageable.
> 
> I will coordinate with a data scientist today to do some tests. He is working 
> on identity matching/record linking of users from 2 domains: US and 
> Singapore, using probabilistic deduping algorithms. I will load the data from 
> ad events from both countries, and let him run his process against this data 
> in Kudu. I hope this will “w

Re: Performance Question

[Benjamin Kim]

Hi Todd,

I did a simple test of our ad events. We stream using Spark Streaming directly 
into HBase, and the Data Analysts/Scientists do some insight/discovery work 
plus some reports generation. For the reports, we use SQL, and the more deeper 
stuff, we use Spark. In Spark, our main data currency store of choice is 
DataFrames.

The schema is around 83 columns wide where most are of the string data type.

"event_type", "timestamp", "event_valid", "event_subtype", "user_ip", 
"user_id", "mappable_id",
"cookie_status", "profile_status", "user_status", "previous_timestamp", 
"user_agent", "referer",
"host_domain", "uri", "request_elapsed", "browser_languages", "acamp_id", 
"creative_id",
"location_id", “pcamp_id",
"pdomain_id", "continent_code", "country", "region", "dma", "city", "zip", 
"isp", "line_speed",
"gender", "year_of_birth", "behaviors_read", "behaviors_written", 
"key_value_pairs", "acamp_candidates",
"tag_format", "optimizer_name", "optimizer_version", "optimizer_ip", 
"pixel_id", “video_id",
"video_network_id", "video_time_watched", "video_percentage_watched", 
"video_media_type",
"video_player_iframed", "video_player_in_view", "video_player_width", 
"video_player_height",
"conversion_valid_sale", "conversion_sale_amount", 
"conversion_commission_amount", "conversion_step",
"conversion_currency", "conversion_attribution", "conversion_offer_id", 
"custom_info", "frequency",
"recency_seconds", "cost", "revenue", “optimizer_acamp_id",
"optimizer_creative_id", "optimizer_ecpm", "impression_id", "diagnostic_data",
"user_profile_mapping_source", "latitude", "longitude", "area_code", 
"gmt_offset", "in_dst",
"proxy_type", "mobile_carrier", "pop", "hostname", "profile_expires", 
"timestamp_iso", "reference_id",
"identity_organization", "identity_method"

Most queries are like counts of how many users use what browser, how many are 
unique users, etc. The part that scares most users is when it comes to joining 
this data with other dimension/3rd party events tables because of shear size of 
it.

We do what most companies do, similar to what I saw in earlier presentations of 
Kudu. We dump data out of HBase into partitioned Parquet tables to make query 
performance manageable.

I will coordinate with a data scientist today to do some tests. He is working 
on identity matching/record linking of users from 2 domains: US and Singapore, 
using probabilistic deduping algorithms. I will load the data from ad events 
from both countries, and let him run his process against this data in Kudu. I 
hope this will “wow” the team.

Thanks,
Ben

> On Jun 15, 2016, at 12:47 AM, Todd Lipcon <t...@cloudera.com> wrote:
> 
> Hi Benjamin,
> 
> What workload are you using for benchmarks? Using spark or something more 
> custom? rdd or data frame or SQL, etc? Maybe you can share the schema and 
> some queries
> 
> Todd
> 
> Todd
> 
> On Jun 15, 2016 8:10 AM, "Benjamin Kim" <bbuil...@gmail.com 
> <mailto:bbuil...@gmail.com>> wrote:
> Hi Todd,
> 
> Now that Kudu 0.9.0 is out. I have done some tests. Already, I am impressed. 
> Compared to HBase, read and write performance are better. Write performance 
> has the greatest improvement (> 4x), while read is > 1.5x. Albeit, these are 
> only preliminary tests. Do you know of a way to really do some conclusive 
> tests? I want to see if I can match your results on my 50 node cluster.
> 
> Thanks,
> Ben
> 
>> On May 30, 2016, at 10:33 AM, Todd Lipcon <t...@cloudera.com 
>> <mailto:t...@cloudera.com>> wrote:
>> 
>> On Sat, May 28, 2016 at 7:12 AM, Benjamin Kim <bbuil...@gmail.com 
>> <mailto:bbuil...@gmail.com>> wrote:
>> Todd,
>> 
>> It sounds like Kudu can possibly top or match those numbers put out by 
>> Aerospike. Do you have any performance statistics published or any 
>> instructions as to measure them myself as good way to test? In addition, 
>> this will be a test using Spark, so should I wait for Kudu version 0.9.0 
>> where support will be built in?
>> 
>> We don't hav

Re: Performance Question

[Benjamin Kim]

Hi Todd,

Now that Kudu 0.9.0 is out. I have done some tests. Already, I am impressed. 
Compared to HBase, read and write performance are better. Write performance has 
the greatest improvement (> 4x), while read is > 1.5x. Albeit, these are only 
preliminary tests. Do you know of a way to really do some conclusive tests? I 
want to see if I can match your results on my 50 node cluster.

Thanks,
Ben

> On May 30, 2016, at 10:33 AM, Todd Lipcon <t...@cloudera.com> wrote:
> 
> On Sat, May 28, 2016 at 7:12 AM, Benjamin Kim <bbuil...@gmail.com 
> <mailto:bbuil...@gmail.com>> wrote:
> Todd,
> 
> It sounds like Kudu can possibly top or match those numbers put out by 
> Aerospike. Do you have any performance statistics published or any 
> instructions as to measure them myself as good way to test? In addition, this 
> will be a test using Spark, so should I wait for Kudu version 0.9.0 where 
> support will be built in?
> 
> We don't have a lot of benchmarks published yet, especially on the write 
> side. I've found that thorough cross-system benchmarks are very difficult to 
> do fairly and accurately, and often times users end up misguided if they pay 
> too much attention to them :) So, given a finite number of developers working 
> on Kudu, I think we've tended to spend more time on the project itself and 
> less time focusing on "competition". I'm sure there are use cases where Kudu 
> will beat out Aerospike, and probably use cases where Aerospike will beat 
> Kudu as well.
> 
> From my perspective, it would be great if you can share some details of your 
> workload, especially if there are some areas you're finding Kudu lacking. 
> Maybe we can spot some easy code changes we could make to improve 
> performance, or suggest a tuning variable you could change.
> 
> -Todd
> 
> 
>> On May 27, 2016, at 9:19 PM, Todd Lipcon <t...@cloudera.com 
>> <mailto:t...@cloudera.com>> wrote:
>> 
>> On Fri, May 27, 2016 at 8:20 PM, Benjamin Kim <bbuil...@gmail.com 
>> <mailto:bbuil...@gmail.com>> wrote:
>> Hi Mike,
>> 
>> First of all, thanks for the link. It looks like an interesting read. I 
>> checked that Aerospike is currently at version 3.8.2.3, and in the article, 
>> they are evaluating version 3.5.4. The main thing that impressed me was 
>> their claim that they can beat Cassandra and HBase by 8x for writing and 25x 
>> for reading. Their big claim to fame is that Aerospike can write 1M records 
>> per second with only 50 nodes. I wanted to see if this is real.
>> 
>> 1M records per second on 50 nodes is pretty doable by Kudu as well, 
>> depending on the size of your records and the insertion order. I've been 
>> playing with a ~70 node cluster recently and seen 1M+ writes/second 
>> sustained, and bursting above 4M. These are 1KB rows with 11 columns, and 
>> with pretty old HDD-only nodes. I think newer flash-based nodes could do 
>> better.
>>  
>> 
>> To answer your questions, we have a DMP with user profiles with many 
>> attributes. We create segmentation information off of these attributes to 
>> classify them. Then, we can target advertising appropriately for our sales 
>> department. Much of the data processing is for applying models on all or if 
>> not most of every profile’s attributes to find similarities (nearest 
>> neighbor/clustering) over a large number of rows when batch processing or a 
>> small subset of rows for quick online scoring. So, our use case is a typical 
>> advanced analytics scenario. We have tried HBase, but it doesn’t work well 
>> for these types of analytics.
>> 
>> I read, that Aerospike in the release notes, they did do many improvements 
>> for batch and scan operations.
>> 
>> I wonder what your thoughts are for using Kudu for this.
>> 
>> Sounds like a good Kudu use case to me. I've heard great things about 
>> Aerospike for the low latency random access portion, but I've also heard 
>> that it's _very_ expensive, and not particularly suited to the columnar scan 
>> workload. Lastly, I think the Apache license of Kudu is much more appealing 
>> than the AGPL3 used by Aerospike. But, that's not really a direct answer to 
>> the performance question :)
>>  
>> 
>> Thanks,
>> Ben
>> 
>> 
>>> On May 27, 2016, at 6:21 PM, Mike Percy <mpe...@cloudera.com 
>>> <mailto:mpe...@cloudera.com>> wrote:
>>> 
>>> Have you considered whether you have a scan heavy or a random access heavy 
>>> workload? Have you considered whether you always access / update a whole 
>>> row vs only a partial r

Re: Spark on Kudu

[Benjamin Kim]

I tried to use the “append” mode, and it worked. Over 3.8 million rows in 64s. 
I would assume that now I can use the “overwrite” mode on existing data. Now, I 
have to find answers to these questions. What would happen if I “append” to the 
data in the Kudu table if the data already exists? What would happen if I 
“overwrite” existing data when the DataFrame has data in it that does not exist 
in the Kudu table? I need to evaluate the best way to simulate the UPSERT 
behavior in HBase because this is what our use case is.

Thanks,
Ben


> On Jun 14, 2016, at 5:05 PM, Benjamin Kim <bbuil...@gmail.com> wrote:
> 
> Hi,
> 
> Now, I’m getting this error when trying to write to the table.
> 
> import scala.collection.JavaConverters._
> val key_seq = Seq(“my_id")
> val key_list = List(“my_id”).asJava
> kuduContext.createTable(tableName, df.schema, key_seq, new 
> CreateTableOptions().setNumReplicas(1).addHashPartitions(key_list, 100))
> 
> df.write
> .options(Map("kudu.master" -> kuduMaster,"kudu.table" -> tableName))
> .mode("overwrite")
> .kudu
> 
> java.lang.RuntimeException: failed to write 1000 rows from DataFrame to Kudu; 
> sample errors: Not found: key not found (error 0)Not found: key not found 
> (error 0)Not found: key not found (error 0)Not found: key not found (error 
> 0)Not found: key not found (error 0)
> 
> Does the key field need to be first in the DataFrame?
> 
> Thanks,
> Ben
> 
>> On Jun 14, 2016, at 4:28 PM, Dan Burkert <d...@cloudera.com 
>> <mailto:d...@cloudera.com>> wrote:
>> 
>> 
>> 
>> On Tue, Jun 14, 2016 at 4:20 PM, Benjamin Kim <bbuil...@gmail.com 
>> <mailto:bbuil...@gmail.com>> wrote:
>> Dan,
>> 
>> Thanks! It got further. Now, how do I set the Primary Key to be a column(s) 
>> in the DataFrame and set the partitioning? Is it like this?
>> 
>> kuduContext.createTable(tableName, df.schema, Seq(“my_id"), new 
>> CreateTableOptions().setNumReplicas(1).addHashPartitions(“my_id"))
>> 
>> java.lang.IllegalArgumentException: Table partitioning must be specified 
>> using setRangePartitionColumns or addHashPartitions
>> 
>> Yep.  The `Seq("my_id")` part of that call is specifying the set of primary 
>> key columns, so in this case you have specified the single PK column 
>> "my_id".  The `addHashPartitions` call adds hash partitioning to the table, 
>> in this case over the column "my_id" (which is good, it must be over one or 
>> more PK columns, so in this case "my_id" is the one and only valid 
>> combination).  However, the call to `addHashPartition` also takes the number 
>> of buckets as the second param.  You shouldn't get the 
>> IllegalArgumentException as long as you are specifying either 
>> `addHashPartitions` or `setRangePartitionColumns`.
>> 
>> - Dan
>>  
>> 
>> Thanks,
>> Ben
>> 
>> 
>>> On Jun 14, 2016, at 4:07 PM, Dan Burkert <d...@cloudera.com 
>>> <mailto:d...@cloudera.com>> wrote:
>>> 
>>> Looks like we're missing an import statement in that example.  Could you 
>>> try:
>>> 
>>> import org.kududb.client._
>>> and try again?
>>> 
>>> - Dan
>>> 
>>> On Tue, Jun 14, 2016 at 4:01 PM, Benjamin Kim <bbuil...@gmail.com 
>>> <mailto:bbuil...@gmail.com>> wrote:
>>> I encountered an error trying to create a table based on the documentation 
>>> from a DataFrame.
>>> 
>>> :49: error: not found: type CreateTableOptions
>>>   kuduContext.createTable(tableName, df.schema, Seq("key"), new 
>>> CreateTableOptions().setNumReplicas(1))
>>> 
>>> Is there something I’m missing?
>>> 
>>> Thanks,
>>> Ben
>>> 
>>>> On Jun 14, 2016, at 3:00 PM, Jean-Daniel Cryans <jdcry...@apache.org 
>>>> <mailto:jdcry...@apache.org>> wrote:
>>>> 
>>>> It's only in Cloudera's maven repo: 
>>>> https://repository.cloudera.com/cloudera/cloudera-repos/org/kududb/kudu-spark_2.10/0.9.0/
>>>>  
>>>> <https://repository.cloudera.com/cloudera/cloudera-repos/org/kududb/kudu-spark_2.10/0.9.0/>
>>>> 
>>>> J-D
>>>> 
>>>> On Tue, Jun 14, 2016 at 2:59 PM, Benjamin Kim <bbuil...@gmail.com 
>>>> <mailto:bbuil...@gmail.com>> wrote:
>>>> Hi J-D,
>>>> 
>>>> I installed Kudu 0.9.0 using CM, but I can’t find t

Re: Spark on Kudu

[Benjamin Kim]

Hi,

Now, I’m getting this error when trying to write to the table.

import scala.collection.JavaConverters._
val key_seq = Seq(“my_id")
val key_list = List(“my_id”).asJava
kuduContext.createTable(tableName, df.schema, key_seq, new 
CreateTableOptions().setNumReplicas(1).addHashPartitions(key_list, 100))

df.write
.options(Map("kudu.master" -> kuduMaster,"kudu.table" -> tableName))
.mode("overwrite")
.kudu

java.lang.RuntimeException: failed to write 1000 rows from DataFrame to Kudu; 
sample errors: Not found: key not found (error 0)Not found: key not found 
(error 0)Not found: key not found (error 0)Not found: key not found (error 
0)Not found: key not found (error 0)

Does the key field need to be first in the DataFrame?

Thanks,
Ben

> On Jun 14, 2016, at 4:28 PM, Dan Burkert <d...@cloudera.com> wrote:
> 
> 
> 
> On Tue, Jun 14, 2016 at 4:20 PM, Benjamin Kim <bbuil...@gmail.com 
> <mailto:bbuil...@gmail.com>> wrote:
> Dan,
> 
> Thanks! It got further. Now, how do I set the Primary Key to be a column(s) 
> in the DataFrame and set the partitioning? Is it like this?
> 
> kuduContext.createTable(tableName, df.schema, Seq(“my_id"), new 
> CreateTableOptions().setNumReplicas(1).addHashPartitions(“my_id"))
> 
> java.lang.IllegalArgumentException: Table partitioning must be specified 
> using setRangePartitionColumns or addHashPartitions
> 
> Yep.  The `Seq("my_id")` part of that call is specifying the set of primary 
> key columns, so in this case you have specified the single PK column "my_id". 
>  The `addHashPartitions` call adds hash partitioning to the table, in this 
> case over the column "my_id" (which is good, it must be over one or more PK 
> columns, so in this case "my_id" is the one and only valid combination).  
> However, the call to `addHashPartition` also takes the number of buckets as 
> the second param.  You shouldn't get the IllegalArgumentException as long as 
> you are specifying either `addHashPartitions` or `setRangePartitionColumns`.
> 
> - Dan
>  
> 
> Thanks,
> Ben
> 
> 
>> On Jun 14, 2016, at 4:07 PM, Dan Burkert <d...@cloudera.com 
>> <mailto:d...@cloudera.com>> wrote:
>> 
>> Looks like we're missing an import statement in that example.  Could you try:
>> 
>> import org.kududb.client._
>> and try again?
>> 
>> - Dan
>> 
>> On Tue, Jun 14, 2016 at 4:01 PM, Benjamin Kim <bbuil...@gmail.com 
>> <mailto:bbuil...@gmail.com>> wrote:
>> I encountered an error trying to create a table based on the documentation 
>> from a DataFrame.
>> 
>> :49: error: not found: type CreateTableOptions
>>   kuduContext.createTable(tableName, df.schema, Seq("key"), new 
>> CreateTableOptions().setNumReplicas(1))
>> 
>> Is there something I’m missing?
>> 
>> Thanks,
>> Ben
>> 
>>> On Jun 14, 2016, at 3:00 PM, Jean-Daniel Cryans <jdcry...@apache.org 
>>> <mailto:jdcry...@apache.org>> wrote:
>>> 
>>> It's only in Cloudera's maven repo: 
>>> https://repository.cloudera.com/cloudera/cloudera-repos/org/kududb/kudu-spark_2.10/0.9.0/
>>>  
>>> <https://repository.cloudera.com/cloudera/cloudera-repos/org/kududb/kudu-spark_2.10/0.9.0/>
>>> 
>>> J-D
>>> 
>>> On Tue, Jun 14, 2016 at 2:59 PM, Benjamin Kim <bbuil...@gmail.com 
>>> <mailto:bbuil...@gmail.com>> wrote:
>>> Hi J-D,
>>> 
>>> I installed Kudu 0.9.0 using CM, but I can’t find the kudu-spark jar for 
>>> spark-shell to use. Can you show me where to find it?
>>> 
>>> Thanks,
>>> Ben
>>> 
>>> 
>>>> On Jun 8, 2016, at 1:19 PM, Jean-Daniel Cryans <jdcry...@apache.org 
>>>> <mailto:jdcry...@apache.org>> wrote:
>>>> 
>>>> What's in this doc is what's gonna get released: 
>>>> https://github.com/cloudera/kudu/blob/master/docs/developing.adoc#kudu-integration-with-spark
>>>>  
>>>> <https://github.com/cloudera/kudu/blob/master/docs/developing.adoc#kudu-integration-with-spark>
>>>> 
>>>> J-D
>>>> 
>>>> On Tue, Jun 7, 2016 at 8:52 PM, Benjamin Kim <bbuil...@gmail.com 
>>>> <mailto:bbuil...@gmail.com>> wrote:
>>>> Will this be documented with examples once 0.9.0 comes out?
>>>> 
>>>> Thanks,
>>>> Ben
>>>> 
>>>> 
>>>>> On May 28, 2016, at 3:22 PM, Jean-Daniel Cryans <jdcry...@apache.org 
>

Re: Spark on Kudu

[Benjamin Kim]

Dan,

Thanks! It got further. Now, how do I set the Primary Key to be a column(s) in 
the DataFrame and set the partitioning? Is it like this?

kuduContext.createTable(tableName, df.schema, Seq(“my_id"), new 
CreateTableOptions().setNumReplicas(1).addHashPartitions(“my_id"))

java.lang.IllegalArgumentException: Table partitioning must be specified using 
setRangePartitionColumns or addHashPartitions

Thanks,
Ben


> On Jun 14, 2016, at 4:07 PM, Dan Burkert <d...@cloudera.com> wrote:
> 
> Looks like we're missing an import statement in that example.  Could you try:
> 
> import org.kududb.client._
> and try again?
> 
> - Dan
> 
> On Tue, Jun 14, 2016 at 4:01 PM, Benjamin Kim <bbuil...@gmail.com 
> <mailto:bbuil...@gmail.com>> wrote:
> I encountered an error trying to create a table based on the documentation 
> from a DataFrame.
> 
> :49: error: not found: type CreateTableOptions
>   kuduContext.createTable(tableName, df.schema, Seq("key"), new 
> CreateTableOptions().setNumReplicas(1))
> 
> Is there something I’m missing?
> 
> Thanks,
> Ben
> 
>> On Jun 14, 2016, at 3:00 PM, Jean-Daniel Cryans <jdcry...@apache.org 
>> <mailto:jdcry...@apache.org>> wrote:
>> 
>> It's only in Cloudera's maven repo: 
>> https://repository.cloudera.com/cloudera/cloudera-repos/org/kududb/kudu-spark_2.10/0.9.0/
>>  
>> <https://repository.cloudera.com/cloudera/cloudera-repos/org/kududb/kudu-spark_2.10/0.9.0/>
>> 
>> J-D
>> 
>> On Tue, Jun 14, 2016 at 2:59 PM, Benjamin Kim <bbuil...@gmail.com 
>> <mailto:bbuil...@gmail.com>> wrote:
>> Hi J-D,
>> 
>> I installed Kudu 0.9.0 using CM, but I can’t find the kudu-spark jar for 
>> spark-shell to use. Can you show me where to find it?
>> 
>> Thanks,
>> Ben
>> 
>> 
>>> On Jun 8, 2016, at 1:19 PM, Jean-Daniel Cryans <jdcry...@apache.org 
>>> <mailto:jdcry...@apache.org>> wrote:
>>> 
>>> What's in this doc is what's gonna get released: 
>>> https://github.com/cloudera/kudu/blob/master/docs/developing.adoc#kudu-integration-with-spark
>>>  
>>> <https://github.com/cloudera/kudu/blob/master/docs/developing.adoc#kudu-integration-with-spark>
>>> 
>>> J-D
>>> 
>>> On Tue, Jun 7, 2016 at 8:52 PM, Benjamin Kim <bbuil...@gmail.com 
>>> <mailto:bbuil...@gmail.com>> wrote:
>>> Will this be documented with examples once 0.9.0 comes out?
>>> 
>>> Thanks,
>>> Ben
>>> 
>>> 
>>>> On May 28, 2016, at 3:22 PM, Jean-Daniel Cryans <jdcry...@apache.org 
>>>> <mailto:jdcry...@apache.org>> wrote:
>>>> 
>>>> It will be in 0.9.0.
>>>> 
>>>> J-D
>>>> 
>>>> On Sat, May 28, 2016 at 8:31 AM, Benjamin Kim <bbuil...@gmail.com 
>>>> <mailto:bbuil...@gmail.com>> wrote:
>>>> Hi Chris,
>>>> 
>>>> Will all this effort be rolled into 0.9.0 and be ready for use?
>>>> 
>>>> Thanks,
>>>> Ben
>>>> 
>>>> 
>>>>> On May 18, 2016, at 9:01 AM, Chris George <christopher.geo...@rms.com 
>>>>> <mailto:christopher.geo...@rms.com>> wrote:
>>>>> 
>>>>> There is some code in review that needs some more refinement.
>>>>> It will allow upsert/insert from a dataframe using the datasource api. It 
>>>>> will also allow the creation and deletion of tables from a dataframe
>>>>> http://gerrit.cloudera.org:8080/#/c/2992/ 
>>>>> <http://gerrit.cloudera.org:8080/#/c/2992/>
>>>>> 
>>>>> Example usages will look something like:
>>>>> http://gerrit.cloudera.org:8080/#/c/2992/5/docs/developing.adoc 
>>>>> <http://gerrit.cloudera.org:8080/#/c/2992/5/docs/developing.adoc>
>>>>> 
>>>>> -Chris George
>>>>> 
>>>>> 
>>>>> On 5/18/16, 9:45 AM, "Benjamin Kim" <bbuil...@gmail.com 
>>>>> <mailto:bbuil...@gmail.com>> wrote:
>>>>> 
>>>>> Can someone tell me what the state is of this Spark work?
>>>>> 
>>>>> Also, does anyone have any sample code on how to update/insert data in 
>>>>> Kudu using DataFrames?
>>>>> 
>>>>> Thanks,
>>>>> Ben
>>>>> 
>>>>> 
>>>>>> On Apr 13, 2016, at 8:22 AM, Chris George <chris

Re: [ANNOUNCE] Apache Kudu (incubating) 0.9.0 released

[Benjamin Kim]

Hi J-D,

I would like to get this started especially now that UPSERT and Spark SQL 
DataFrames support. But, how do I use Cloudera Manager to deploy it? Is there a 
parcel available yet? Is there a new CSD file to be downloaded? I currently 
have CM 5.7.0 installed.

Thanks,
Ben



> On Jun 10, 2016, at 7:39 AM, Jean-Daniel Cryans  wrote:
> 
> The Apache Kudu (incubating) team is happy to announce the release of Kudu 
> 0.9.0!
> 
> Kudu is an open source storage engine for structured data which supports 
> low-latency random access together with efficient analytical access patterns. 
> It is designed within the context of the Apache Hadoop ecosystem and supports 
> many integrations with other data analytics projects both inside and outside 
> of the Apache Software Foundation.
> 
> This latest version adds basic UPSERT functionality and an improved Apache 
> Spark Data Source that doesn’t rely on the MapReduce I/O formats. It also 
> improves Tablet Server restart time as well as write performance under high 
> load. Finally, Kudu now enforces the specification of a partitioning scheme 
> for new tables.
> 
> Download it here: http://getkudu.io/releases/0.9.0/ 
> 
> 
> Regards,
> 
> The Apache Kudu (incubating) team
> 
> ===
> 
> Apache Kudu (incubating) is an effort undergoing incubation at The Apache 
> Software
> Foundation (ASF), sponsored by the Apache Incubator PMC. Incubation is
> required of all newly accepted projects until a further review
> indicates that the infrastructure, communications, and decision making
> process have stabilized in a manner consistent with other successful
> ASF projects. While incubation status is not necessarily a reflection
> of the completeness or stability of the code, it does indicate that
> the project has yet to be fully endorsed by the ASF.

Re: Spark on Kudu

[Benjamin Kim]

Hi Chris,

Will all this effort be rolled into 0.9.0 and be ready for use?

Thanks,
Ben

> On May 18, 2016, at 9:01 AM, Chris George <christopher.geo...@rms.com> wrote:
> 
> There is some code in review that needs some more refinement.
> It will allow upsert/insert from a dataframe using the datasource api. It 
> will also allow the creation and deletion of tables from a dataframe
> http://gerrit.cloudera.org:8080/#/c/2992/ 
> <http://gerrit.cloudera.org:8080/#/c/2992/>
> 
> Example usages will look something like:
> http://gerrit.cloudera.org:8080/#/c/2992/5/docs/developing.adoc 
> <http://gerrit.cloudera.org:8080/#/c/2992/5/docs/developing.adoc>
> 
> -Chris George
> 
> 
> On 5/18/16, 9:45 AM, "Benjamin Kim" <bbuil...@gmail.com 
> <mailto:bbuil...@gmail.com>> wrote:
> 
> Can someone tell me what the state is of this Spark work?
> 
> Also, does anyone have any sample code on how to update/insert data in Kudu 
> using DataFrames?
> 
> Thanks,
> Ben
> 
> 
>> On Apr 13, 2016, at 8:22 AM, Chris George <christopher.geo...@rms.com 
>> <mailto:christopher.geo...@rms.com>> wrote:
>> 
>> SparkSQL cannot support these type of statements but we may be able to 
>> implement similar functionality through the api.
>> -Chris
>> 
>> On 4/12/16, 5:19 PM, "Benjamin Kim" <bbuil...@gmail.com 
>> <mailto:bbuil...@gmail.com>> wrote:
>> 
>> It would be nice to adhere to the SQL:2003 standard for an “upsert” if it 
>> were to be implemented.
>> 
>> MERGE INTO table_name USING table_reference ON (condition)
>>  WHEN MATCHED THEN
>>  UPDATE SET column1 = value1 [, column2 = value2 ...]
>>  WHEN NOT MATCHED THEN
>>  INSERT (column1 [, column2 ...]) VALUES (value1 [, value2 …])
>> 
>> Cheers,
>> Ben
>> 
>>> On Apr 11, 2016, at 12:21 PM, Chris George <christopher.geo...@rms.com 
>>> <mailto:christopher.geo...@rms.com>> wrote:
>>> 
>>> I have a wip kuduRDD that I made a few months ago. I pushed it into gerrit 
>>> if you want to take a look. http://gerrit.cloudera.org:8080/#/c/2754/ 
>>> <http://gerrit.cloudera.org:8080/#/c/2754/>
>>> It does pushdown predicates which the existing input formatter based rdd 
>>> does not.
>>> 
>>> Within the next two weeks I’m planning to implement a datasource for spark 
>>> that will have pushdown predicates and insertion/update functionality (need 
>>> to look more at cassandra and the hbase datasource for best way to do this) 
>>> I agree that server side upsert would be helpful.
>>> Having a datasource would give us useful data frames and also make spark 
>>> sql usable for kudu.
>>> 
>>> My reasoning for having a spark datasource and not using Impala is: 1. We 
>>> have had trouble getting impala to run fast with high concurrency when 
>>> compared to spark 2. We interact with datasources which do not integrate 
>>> with impala. 3. We have custom sql query planners for extended sql 
>>> functionality.
>>> 
>>> -Chris George
>>> 
>>> 
>>> On 4/11/16, 12:22 PM, "Jean-Daniel Cryans" <jdcry...@apache.org 
>>> <mailto:jdcry...@apache.org>> wrote:
>>> 
>>> You guys make a convincing point, although on the upsert side we'll need 
>>> more support from the servers. Right now all you can do is an INSERT then, 
>>> if you get a dup key, do an UPDATE. I guess we could at least add an API on 
>>> the client side that would manage it, but it wouldn't be atomic.
>>> 
>>> J-D
>>> 
>>> On Mon, Apr 11, 2016 at 9:34 AM, Mark Hamstra <m...@clearstorydata.com 
>>> <mailto:m...@clearstorydata.com>> wrote:
>>> It's pretty simple, actually.  I need to support versioned datasets in a 
>>> Spark SQL environment.  Instead of a hack on top of a Parquet data store, 
>>> I'm hoping (among other reasons) to be able to use Kudu's write and 
>>> timestamp-based read operations to support not only appending data, but 
>>> also updating existing data, and even some schema migration.  The most 
>>> typical use case is a dataset that is updated periodically (e.g., weekly or 
>>> monthly) in which the the preliminary data in the previous window (week or 
>>> month) is updated with values that are expected to remain unchanged from 
>>> then on, and a new set of preliminary values for the current window need to 
>>> be added/appended.
>>> 
>>> Using Kudu's Java API an

Re: Performance Question

[Benjamin Kim]

Todd,

It sounds like Kudu can possibly top or match those numbers put out by 
Aerospike. Do you have any performance statistics published or any instructions 
as to measure them myself as good way to test? In addition, this will be a test 
using Spark, so should I wait for Kudu version 0.9.0 where support will be 
built in?

Thanks,
Ben


> On May 27, 2016, at 9:19 PM, Todd Lipcon <t...@cloudera.com> wrote:
> 
> On Fri, May 27, 2016 at 8:20 PM, Benjamin Kim <bbuil...@gmail.com 
> <mailto:bbuil...@gmail.com>> wrote:
> Hi Mike,
> 
> First of all, thanks for the link. It looks like an interesting read. I 
> checked that Aerospike is currently at version 3.8.2.3, and in the article, 
> they are evaluating version 3.5.4. The main thing that impressed me was their 
> claim that they can beat Cassandra and HBase by 8x for writing and 25x for 
> reading. Their big claim to fame is that Aerospike can write 1M records per 
> second with only 50 nodes. I wanted to see if this is real.
> 
> 1M records per second on 50 nodes is pretty doable by Kudu as well, depending 
> on the size of your records and the insertion order. I've been playing with a 
> ~70 node cluster recently and seen 1M+ writes/second sustained, and bursting 
> above 4M. These are 1KB rows with 11 columns, and with pretty old HDD-only 
> nodes. I think newer flash-based nodes could do better.
>  
> 
> To answer your questions, we have a DMP with user profiles with many 
> attributes. We create segmentation information off of these attributes to 
> classify them. Then, we can target advertising appropriately for our sales 
> department. Much of the data processing is for applying models on all or if 
> not most of every profile’s attributes to find similarities (nearest 
> neighbor/clustering) over a large number of rows when batch processing or a 
> small subset of rows for quick online scoring. So, our use case is a typical 
> advanced analytics scenario. We have tried HBase, but it doesn’t work well 
> for these types of analytics.
> 
> I read, that Aerospike in the release notes, they did do many improvements 
> for batch and scan operations.
> 
> I wonder what your thoughts are for using Kudu for this.
> 
> Sounds like a good Kudu use case to me. I've heard great things about 
> Aerospike for the low latency random access portion, but I've also heard that 
> it's _very_ expensive, and not particularly suited to the columnar scan 
> workload. Lastly, I think the Apache license of Kudu is much more appealing 
> than the AGPL3 used by Aerospike. But, that's not really a direct answer to 
> the performance question :)
>  
> 
> Thanks,
> Ben
> 
> 
>> On May 27, 2016, at 6:21 PM, Mike Percy <mpe...@cloudera.com 
>> <mailto:mpe...@cloudera.com>> wrote:
>> 
>> Have you considered whether you have a scan heavy or a random access heavy 
>> workload? Have you considered whether you always access / update a whole row 
>> vs only a partial row? Kudu is a column store so has some awesome 
>> performance characteristics when you are doing a lot of scanning of just a 
>> couple of columns.
>> 
>> I don't know the answer to your question but if your concern is performance 
>> then I would be interested in seeing comparisons from a perf perspective on 
>> certain workloads.
>> 
>> Finally, a year ago Aerospike did quite poorly in a Jepsen test: 
>> https://aphyr.com/posts/324-jepsen-aerospike 
>> <https://aphyr.com/posts/324-jepsen-aerospike>
>> 
>> I wonder if they have addressed any of those issues.
>> 
>> Mike
>> 
>> On Friday, May 27, 2016, Benjamin Kim <bbuil...@gmail.com 
>> <mailto:bbuil...@gmail.com>> wrote:
>> I am just curious. How will Kudu compare with Aerospike 
>> (http://www.aerospike.com <http://www.aerospike.com/>)? I went to a Spark 
>> Roadshow and found out about this piece of software. It appears to fit our 
>> use case perfectly since we are an ad-tech company trying to leverage our 
>> user profiles data. Plus, it already has a Spark connector and has a 
>> SQL-like client. The tables can be accessed using Spark SQL DataFrames and, 
>> also, made into SQL tables for direct use with Spark SQL ODBC/JDBC 
>> Thriftserver. I see from the work done here 
>> http://gerrit.cloudera.org:8080/#/c/2992/ 
>> <http://gerrit.cloudera.org:8080/#/c/2992/> that the Spark integration is 
>> well underway and, from the looks of it lately, almost complete. I would 
>> prefer to use Kudu since we are already a Cloudera shop, and Kudu is easy to 
>> deploy and configure using Cloudera Manager. I also hope that some of 
>> Aerospike’s speed optimization techniques can make it into Kudu in the 
>> future, if they have not been already thought of or included.
>> 
>> Just some thoughts…
>> 
>> Cheers,
>> Ben
>> 
>> 
>> -- 
>> --
>> Mike Percy
>> Software Engineer, Cloudera
>> 
>> 
> 
> 
> 
> 
> -- 
> Todd Lipcon
> Software Engineer, Cloudera

Re: Performance Question

[Benjamin Kim]

Hi Mike,

First of all, thanks for the link. It looks like an interesting read. I checked 
that Aerospike is currently at version 3.8.2.3, and in the article, they are 
evaluating version 3.5.4. The main thing that impressed me was their claim that 
they can beat Cassandra and HBase by 8x for writing and 25x for reading. Their 
big claim to fame is that Aerospike can write 1M records per second with only 
50 nodes. I wanted to see if this is real.

To answer your questions, we have a DMP with user profiles with many 
attributes. We create segmentation information off of these attributes to 
classify them. Then, we can target advertising appropriately for our sales 
department. Much of the data processing is for applying models on all or if not 
most of every profile’s attributes to find similarities (nearest 
neighbor/clustering) over a large number of rows when batch processing or a 
small subset of rows for quick online scoring. So, our use case is a typical 
advanced analytics scenario. We have tried HBase, but it doesn’t work well for 
these types of analytics.

I read, that Aerospike in the release notes, they did do many improvements for 
batch and scan operations.

I wonder what your thoughts are for using Kudu for this.

Thanks,
Ben


> On May 27, 2016, at 6:21 PM, Mike Percy <mpe...@cloudera.com> wrote:
> 
> Have you considered whether you have a scan heavy or a random access heavy 
> workload? Have you considered whether you always access / update a whole row 
> vs only a partial row? Kudu is a column store so has some awesome performance 
> characteristics when you are doing a lot of scanning of just a couple of 
> columns.
> 
> I don't know the answer to your question but if your concern is performance 
> then I would be interested in seeing comparisons from a perf perspective on 
> certain workloads.
> 
> Finally, a year ago Aerospike did quite poorly in a Jepsen test: 
> https://aphyr.com/posts/324-jepsen-aerospike 
> <https://aphyr.com/posts/324-jepsen-aerospike>
> 
> I wonder if they have addressed any of those issues.
> 
> Mike
> 
> On Friday, May 27, 2016, Benjamin Kim <bbuil...@gmail.com 
> <mailto:bbuil...@gmail.com>> wrote:
> I am just curious. How will Kudu compare with Aerospike 
> (http://www.aerospike.com <http://www.aerospike.com/>)? I went to a Spark 
> Roadshow and found out about this piece of software. It appears to fit our 
> use case perfectly since we are an ad-tech company trying to leverage our 
> user profiles data. Plus, it already has a Spark connector and has a SQL-like 
> client. The tables can be accessed using Spark SQL DataFrames and, also, made 
> into SQL tables for direct use with Spark SQL ODBC/JDBC Thriftserver. I see 
> from the work done here http://gerrit.cloudera.org:8080/#/c/2992/ 
> <http://gerrit.cloudera.org:8080/#/c/2992/> that the Spark integration is 
> well underway and, from the looks of it lately, almost complete. I would 
> prefer to use Kudu since we are already a Cloudera shop, and Kudu is easy to 
> deploy and configure using Cloudera Manager. I also hope that some of 
> Aerospike’s speed optimization techniques can make it into Kudu in the 
> future, if they have not been already thought of or included.
> 
> Just some thoughts…
> 
> Cheers,
> Ben
> 
> 
> -- 
> --
> Mike Percy
> Software Engineer, Cloudera
> 
> 

Performance Question

[Benjamin Kim]

I am just curious. How will Kudu compare with Aerospike 
(http://www.aerospike.com)? I went to a Spark Roadshow and found out about this 
piece of software. It appears to fit our use case perfectly since we are an 
ad-tech company trying to leverage our user profiles data. Plus, it already has 
a Spark connector and has a SQL-like client. The tables can be accessed using 
Spark SQL DataFrames and, also, made into SQL tables for direct use with Spark 
SQL ODBC/JDBC Thriftserver. I see from the work done here 
http://gerrit.cloudera.org:8080/#/c/2992/ that the Spark integration is well 
underway and, from the looks of it lately, almost complete. I would prefer to 
use Kudu since we are already a Cloudera shop, and Kudu is easy to deploy and 
configure using Cloudera Manager. I also hope that some of Aerospike’s speed 
optimization techniques can make it into Kudu in the future, if they have not 
been already thought of or included.

Just some thoughts…

Cheers,
Ben

Re: Spark on Kudu

[Benjamin Kim]

Can someone tell me what the state is of this Spark work?

Also, does anyone have any sample code on how to update/insert data in Kudu 
using DataFrames?

Thanks,
Ben


> On Apr 13, 2016, at 8:22 AM, Chris George <christopher.geo...@rms.com> wrote:
> 
> SparkSQL cannot support these type of statements but we may be able to 
> implement similar functionality through the api.
> -Chris
> 
> On 4/12/16, 5:19 PM, "Benjamin Kim" <bbuil...@gmail.com 
> <mailto:bbuil...@gmail.com>> wrote:
> 
> It would be nice to adhere to the SQL:2003 standard for an “upsert” if it 
> were to be implemented.
> 
> MERGE INTO table_name USING table_reference ON (condition)
>  WHEN MATCHED THEN
>  UPDATE SET column1 = value1 [, column2 = value2 ...]
>  WHEN NOT MATCHED THEN
>  INSERT (column1 [, column2 ...]) VALUES (value1 [, value2 …])
> 
> Cheers,
> Ben
> 
>> On Apr 11, 2016, at 12:21 PM, Chris George <christopher.geo...@rms.com 
>> <mailto:christopher.geo...@rms.com>> wrote:
>> 
>> I have a wip kuduRDD that I made a few months ago. I pushed it into gerrit 
>> if you want to take a look. http://gerrit.cloudera.org:8080/#/c/2754/ 
>> <http://gerrit.cloudera.org:8080/#/c/2754/>
>> It does pushdown predicates which the existing input formatter based rdd 
>> does not.
>> 
>> Within the next two weeks I’m planning to implement a datasource for spark 
>> that will have pushdown predicates and insertion/update functionality (need 
>> to look more at cassandra and the hbase datasource for best way to do this) 
>> I agree that server side upsert would be helpful.
>> Having a datasource would give us useful data frames and also make spark sql 
>> usable for kudu.
>> 
>> My reasoning for having a spark datasource and not using Impala is: 1. We 
>> have had trouble getting impala to run fast with high concurrency when 
>> compared to spark 2. We interact with datasources which do not integrate 
>> with impala. 3. We have custom sql query planners for extended sql 
>> functionality.
>> 
>> -Chris George
>> 
>> 
>> On 4/11/16, 12:22 PM, "Jean-Daniel Cryans" <jdcry...@apache.org 
>> <mailto:jdcry...@apache.org>> wrote:
>> 
>> You guys make a convincing point, although on the upsert side we'll need 
>> more support from the servers. Right now all you can do is an INSERT then, 
>> if you get a dup key, do an UPDATE. I guess we could at least add an API on 
>> the client side that would manage it, but it wouldn't be atomic.
>> 
>> J-D
>> 
>> On Mon, Apr 11, 2016 at 9:34 AM, Mark Hamstra <m...@clearstorydata.com 
>> <mailto:m...@clearstorydata.com>> wrote:
>> It's pretty simple, actually.  I need to support versioned datasets in a 
>> Spark SQL environment.  Instead of a hack on top of a Parquet data store, 
>> I'm hoping (among other reasons) to be able to use Kudu's write and 
>> timestamp-based read operations to support not only appending data, but also 
>> updating existing data, and even some schema migration.  The most typical 
>> use case is a dataset that is updated periodically (e.g., weekly or monthly) 
>> in which the the preliminary data in the previous window (week or month) is 
>> updated with values that are expected to remain unchanged from then on, and 
>> a new set of preliminary values for the current window need to be 
>> added/appended.
>> 
>> Using Kudu's Java API and developing additional functionality on top of what 
>> Kudu has to offer isn't too much to ask, but the ease of integration with 
>> Spark SQL will gate how quickly we would move to using Kudu and how 
>> seriously we'd look at alternatives before making that decision. 
>> 
>> On Mon, Apr 11, 2016 at 8:14 AM, Jean-Daniel Cryans <jdcry...@apache.org 
>> <mailto:jdcry...@apache.org>> wrote:
>> Mark,
>> 
>> Thanks for taking some time to reply in this thread, glad it caught the 
>> attention of other folks!
>> 
>> On Sun, Apr 10, 2016 at 12:33 PM, Mark Hamstra <m...@clearstorydata.com 
>> <mailto:m...@clearstorydata.com>> wrote:
>> Do they care being able to insert into Kudu with SparkSQL
>> 
>> I care about insert into Kudu with Spark SQL.  I'm currently delaying a 
>> refactoring of some Spark SQL-oriented insert functionality while trying to 
>> evaluate what to expect from Kudu.  Whether Kudu does a good job supporting 
>> inserts with Spark SQL will be a key consideration as to whether we adopt 
>> Kudu.
>> 
>> I'd like to know more about why SparkSQL inserts in necessa

Sparse Data

[Benjamin Kim]

Can Kudu handle the use case where sparse data is involved? In many of our 
processes, we deal with data that can have any number of columns and many 
previously unknown column names depending on what attributes are brought in at 
the time. Currently, we use HBase to handle this. Since Kudu is based on HBase, 
can it do the same? Or, do we have to use a map data type column for this?

Thanks,
Ben

Re: Spark on Kudu

[Benjamin Kim]

Chris,

That would be great! And a first! I think everyone would take notice if KImpala 
had this.

Cheers,
Ben


> On Apr 13, 2016, at 8:22 AM, Chris George <christopher.geo...@rms.com> wrote:
> 
> SparkSQL cannot support these type of statements but we may be able to 
> implement similar functionality through the api.
> -Chris
> 
> On 4/12/16, 5:19 PM, "Benjamin Kim" <bbuil...@gmail.com 
> <mailto:bbuil...@gmail.com>> wrote:
> 
> It would be nice to adhere to the SQL:2003 standard for an “upsert” if it 
> were to be implemented.
> 
> MERGE INTO table_name USING table_reference ON (condition)
>  WHEN MATCHED THEN
>  UPDATE SET column1 = value1 [, column2 = value2 ...]
>  WHEN NOT MATCHED THEN
>  INSERT (column1 [, column2 ...]) VALUES (value1 [, value2 …])
> 
> Cheers,
> Ben
> 
>> On Apr 11, 2016, at 12:21 PM, Chris George <christopher.geo...@rms.com 
>> <mailto:christopher.geo...@rms.com>> wrote:
>> 
>> I have a wip kuduRDD that I made a few months ago. I pushed it into gerrit 
>> if you want to take a look. http://gerrit.cloudera.org:8080/#/c/2754/ 
>> <http://gerrit.cloudera.org:8080/#/c/2754/>
>> It does pushdown predicates which the existing input formatter based rdd 
>> does not.
>> 
>> Within the next two weeks I’m planning to implement a datasource for spark 
>> that will have pushdown predicates and insertion/update functionality (need 
>> to look more at cassandra and the hbase datasource for best way to do this) 
>> I agree that server side upsert would be helpful.
>> Having a datasource would give us useful data frames and also make spark sql 
>> usable for kudu.
>> 
>> My reasoning for having a spark datasource and not using Impala is: 1. We 
>> have had trouble getting impala to run fast with high concurrency when 
>> compared to spark 2. We interact with datasources which do not integrate 
>> with impala. 3. We have custom sql query planners for extended sql 
>> functionality.
>> 
>> -Chris George
>> 
>> 
>> On 4/11/16, 12:22 PM, "Jean-Daniel Cryans" <jdcry...@apache.org 
>> <mailto:jdcry...@apache.org>> wrote:
>> 
>> You guys make a convincing point, although on the upsert side we'll need 
>> more support from the servers. Right now all you can do is an INSERT then, 
>> if you get a dup key, do an UPDATE. I guess we could at least add an API on 
>> the client side that would manage it, but it wouldn't be atomic.
>> 
>> J-D
>> 
>> On Mon, Apr 11, 2016 at 9:34 AM, Mark Hamstra <m...@clearstorydata.com 
>> <mailto:m...@clearstorydata.com>> wrote:
>> It's pretty simple, actually.  I need to support versioned datasets in a 
>> Spark SQL environment.  Instead of a hack on top of a Parquet data store, 
>> I'm hoping (among other reasons) to be able to use Kudu's write and 
>> timestamp-based read operations to support not only appending data, but also 
>> updating existing data, and even some schema migration.  The most typical 
>> use case is a dataset that is updated periodically (e.g., weekly or monthly) 
>> in which the the preliminary data in the previous window (week or month) is 
>> updated with values that are expected to remain unchanged from then on, and 
>> a new set of preliminary values for the current window need to be 
>> added/appended.
>> 
>> Using Kudu's Java API and developing additional functionality on top of what 
>> Kudu has to offer isn't too much to ask, but the ease of integration with 
>> Spark SQL will gate how quickly we would move to using Kudu and how 
>> seriously we'd look at alternatives before making that decision. 
>> 
>> On Mon, Apr 11, 2016 at 8:14 AM, Jean-Daniel Cryans <jdcry...@apache.org 
>> <mailto:jdcry...@apache.org>> wrote:
>> Mark,
>> 
>> Thanks for taking some time to reply in this thread, glad it caught the 
>> attention of other folks!
>> 
>> On Sun, Apr 10, 2016 at 12:33 PM, Mark Hamstra <m...@clearstorydata.com 
>> <mailto:m...@clearstorydata.com>> wrote:
>> Do they care being able to insert into Kudu with SparkSQL
>> 
>> I care about insert into Kudu with Spark SQL.  I'm currently delaying a 
>> refactoring of some Spark SQL-oriented insert functionality while trying to 
>> evaluate what to expect from Kudu.  Whether Kudu does a good job supporting 
>> inserts with Spark SQL will be a key consideration as to whether we adopt 
>> Kudu.
>> 
>> I'd like to know more about why SparkSQL inserts in necessary for you. Is it 
>> just that you currently 

Re: Spark on Kudu

[Benjamin Kim]

gt; 
> FWIW the plan is to get to 1.0 in late Summer/early Fall. At Cloudera all our 
> resources are committed to making things happen in time, and a more fully 
> featured Spark integration isn't in our plans during that period. I'm really 
> hoping someone in the community will help with Spark, the same way we got a 
> big contribution for the Flume sink. 
> 
> J-D
> 
> On Sun, Apr 10, 2016 at 11:29 AM, Benjamin Kim <bbuil...@gmail.com 
> <mailto:bbuil...@gmail.com>> wrote:
> Yes, we took Kudu for a test run using 0.6 and 0.7 versions. But, since it’s 
> not “production-ready”, upper management doesn’t want to fully deploy it yet. 
> They just want to keep an eye on it though. Kudu was so much simpler and 
> easier to use in every aspect compared to HBase. Impala was great for the 
> report writers and analysts to experiment with for the short time it was up. 
> But, once again, the only blocker was the lack of Spark support for our Data 
> Developers/Scientists. So, production-level data population won’t happen 
> until then.
> 
> I hope this helps you get an idea where I am coming from…
> 
> Cheers,
> Ben
> 
> 
>> On Apr 10, 2016, at 11:08 AM, Jean-Daniel Cryans <jdcry...@apache.org 
>> <mailto:jdcry...@apache.org>> wrote:
>> 
>> On Sun, Apr 10, 2016 at 12:30 AM, Benjamin Kim <bbuil...@gmail.com 
>> <mailto:bbuil...@gmail.com>> wrote:
>> J-D,
>> 
>> The main thing I hear that Cassandra is being used as an updatable hot data 
>> store to ensure that duplicates are taken care of and idempotency is 
>> maintained. Whether data was directly retrieved from Cassandra for 
>> analytics, reports, or searches, it was not clear as to what was its main 
>> use. Some also just used it for a staging area to populate downstream tables 
>> in parquet format. The last thing I heard was that CQL was terrible, so that 
>> rules out much use of direct queries against it.
>> 
>> I'm no C* expert, but I don't think CQL is meant for real analytics, just 
>> ease of use instead of plainly using the APIs. Even then, Kudu should beat 
>> it easily on big scans. Same for HBase. We've done benchmarks against the 
>> latter, not the former.
>>  
>> 
>> As for our company, we have been looking for an updatable data store for a 
>> long time that can be quickly queried directly either using Spark SQL or 
>> Impala or some other SQL engine and still handle TB or PB of data without 
>> performance degradation and many configuration headaches. For now, we are 
>> using HBase to take on this role with Phoenix as a fast way to directly 
>> query the data. I can see Kudu as the best way to fill this gap easily, 
>> especially being the closest thing to other relational databases out there 
>> in familiarity for the many SQL analytics people in our company. The other 
>> alternative would be to go with AWS Redshift for the same reasons, but it 
>> would come at a cost, of course. If we went with either solutions, Kudu or 
>> Redshift, it would get rid of the need to extract from HBase to parquet 
>> tables or export to PostgreSQL to support more of the SQL language using by 
>> analysts or the reporting software we use..
>> 
>> Ok, the usual then *smile*. Looks like we're not too far off with Kudu. Have 
>> you folks tried Kudu with Impala yet with those use cases?
>>  
>> 
>> I hope this helps.
>> 
>> It does, thanks for nice reply.
>>  
>> 
>> Cheers,
>> Ben 
>> 
>>> On Apr 9, 2016, at 2:00 PM, Jean-Daniel Cryans <jdcry...@apache.org 
>>> <mailto:jdcry...@apache.org>> wrote:
>>> 
>>> Ha first time I'm hearing about SMACK. Inside Cloudera we like to refer to 
>>> "Impala + Kudu" as Kimpala, but yeah it's not as sexy. My colleagues who 
>>> were also there did say that the hype around Spark isn't dying down.
>>> 
>>> There's definitely an overlap in the use cases that Cassandra, HBase, and 
>>> Kudu cater to. I wouldn't go as far as saying that C* is just an interim 
>>> solution for the use case you describe.
>>> 
>>> Nothing significant happened in Kudu over the past month, it's a storage 
>>> engine so things move slowly *smile*. I'd love to see more contributions on 
>>> the Spark front. I know there's code out there that could be integrated in 
>>> kudu-spark, it just needs to land in gerrit. I'm sure folks will happily 
>>> review it.
>>> 
>>> Do you have relevant experiences you can share? I'd love to learn more 
>>> about the use cases for which you envision using Kud

Re: Spark on Kudu

[Benjamin Kim]

Yes, we took Kudu for a test run using 0.6 and 0.7 versions. But, since it’s 
not “production-ready”, upper management doesn’t want to fully deploy it yet. 
They just want to keep an eye on it though. Kudu was so much simpler and easier 
to use in every aspect compared to HBase. Impala was great for the report 
writers and analysts to experiment with for the short time it was up. But, once 
again, the only blocker was the lack of Spark support for our Data 
Developers/Scientists. So, production-level data population won’t happen until 
then.

I hope this helps you get an idea where I am coming from…

Cheers,
Ben

> On Apr 10, 2016, at 11:08 AM, Jean-Daniel Cryans <jdcry...@apache.org> wrote:
> 
> On Sun, Apr 10, 2016 at 12:30 AM, Benjamin Kim <bbuil...@gmail.com 
> <mailto:bbuil...@gmail.com>> wrote:
> J-D,
> 
> The main thing I hear that Cassandra is being used as an updatable hot data 
> store to ensure that duplicates are taken care of and idempotency is 
> maintained. Whether data was directly retrieved from Cassandra for analytics, 
> reports, or searches, it was not clear as to what was its main use. Some also 
> just used it for a staging area to populate downstream tables in parquet 
> format. The last thing I heard was that CQL was terrible, so that rules out 
> much use of direct queries against it.
> 
> I'm no C* expert, but I don't think CQL is meant for real analytics, just 
> ease of use instead of plainly using the APIs. Even then, Kudu should beat it 
> easily on big scans. Same for HBase. We've done benchmarks against the 
> latter, not the former.
>  
> 
> As for our company, we have been looking for an updatable data store for a 
> long time that can be quickly queried directly either using Spark SQL or 
> Impala or some other SQL engine and still handle TB or PB of data without 
> performance degradation and many configuration headaches. For now, we are 
> using HBase to take on this role with Phoenix as a fast way to directly query 
> the data. I can see Kudu as the best way to fill this gap easily, especially 
> being the closest thing to other relational databases out there in 
> familiarity for the many SQL analytics people in our company. The other 
> alternative would be to go with AWS Redshift for the same reasons, but it 
> would come at a cost, of course. If we went with either solutions, Kudu or 
> Redshift, it would get rid of the need to extract from HBase to parquet 
> tables or export to PostgreSQL to support more of the SQL language using by 
> analysts or the reporting software we use..
> 
> Ok, the usual then *smile*. Looks like we're not too far off with Kudu. Have 
> you folks tried Kudu with Impala yet with those use cases?
>  
> 
> I hope this helps.
> 
> It does, thanks for nice reply.
>  
> 
> Cheers,
> Ben 
> 
>> On Apr 9, 2016, at 2:00 PM, Jean-Daniel Cryans <jdcry...@apache.org 
>> <mailto:jdcry...@apache.org>> wrote:
>> 
>> Ha first time I'm hearing about SMACK. Inside Cloudera we like to refer to 
>> "Impala + Kudu" as Kimpala, but yeah it's not as sexy. My colleagues who 
>> were also there did say that the hype around Spark isn't dying down.
>> 
>> There's definitely an overlap in the use cases that Cassandra, HBase, and 
>> Kudu cater to. I wouldn't go as far as saying that C* is just an interim 
>> solution for the use case you describe.
>> 
>> Nothing significant happened in Kudu over the past month, it's a storage 
>> engine so things move slowly *smile*. I'd love to see more contributions on 
>> the Spark front. I know there's code out there that could be integrated in 
>> kudu-spark, it just needs to land in gerrit. I'm sure folks will happily 
>> review it.
>> 
>> Do you have relevant experiences you can share? I'd love to learn more about 
>> the use cases for which you envision using Kudu as a C* replacement.
>> 
>> Thanks,
>> 
>> J-D
>> 
>> On Fri, Apr 8, 2016 at 12:45 PM, Benjamin Kim <bbuil...@gmail.com 
>> <mailto:bbuil...@gmail.com>> wrote:
>> Hi J-D,
>> 
>> My colleagues recently came back from Strata in San Jose. They told me that 
>> everything was about Spark and there is a big buzz about the SMACK stack 
>> (Spark, Mesos, Akka, Cassandra, Kafka). I still think that Cassandra is just 
>> an interim solution as a low-latency, easily queried data store. I was 
>> wondering if anything significant happened in regards to Kudu, especially on 
>> the Spark front. Plus, can you come up with your own proposed stack acronym 
>> to promote?
>> 
>> Cheers,
>> Ben
>> 
>> 
>>> On Mar 1, 2016, at 12:20 PM, Je

Re: Spark on Kudu

[Benjamin Kim]

Hi J-D,

Quick question… Is there an ETA for KUDU-1214? I want to target a version of 
Kudu to begin real testing of Spark against it for our devs. At least, I can 
tell them what timeframe to anticipate.

Just curious,
Benjamin Kim
Data Solutions Architect

[a•mo•bee] (n.) the company defining digital marketing.

Mobile: +1 818 635 2900
3250 Ocean Park Blvd, Suite 200  |  Santa Monica, CA 90405  |  
www.amobee.com<http://www.amobee.com/>

On Feb 24, 2016, at 3:51 PM, Jean-Daniel Cryans 
<jdcry...@apache.org<mailto:jdcry...@apache.org>> wrote:

The DStream stuff isn't there at all. I'm not sure if it's needed either.

The kuduRDD is just leveraging the MR input format, ideally we'd use scans 
directly.

The SparkSQL stuff is there but it doesn't do any sort of pushdown. It's really 
basic.

The goal was to provide something for others to contribute to. We have some 
basic unit tests that others can easily extend. None of us on the team are 
Spark experts, but we'd be really happy to assist one improve the kudu-spark 
code.

J-D

On Wed, Feb 24, 2016 at 3:41 PM, Benjamin Kim 
<bbuil...@gmail.com<mailto:bbuil...@gmail.com>> wrote:
J-D,

It looks like it fulfills most of the basic requirements (kudu RDD, kudu 
DStream) in KUDU-1214. Am I right? Besides shoring up more Spark SQL 
functionality (Dataframes) and doing the documentation, what more needs to be 
done? Optimizations?

I believe that it’s a good place to start using Spark with Kudu and compare it 
to HBase with Spark (not clean).

Thanks,
Ben


On Feb 24, 2016, at 3:10 PM, Jean-Daniel Cryans 
<jdcry...@apache.org<mailto:jdcry...@apache.org>> wrote:

AFAIK no one is working on it, but we did manage to get this in for 0.7.0: 
https://issues.cloudera.org/browse/KUDU-1321

It's a really simple wrapper, and yes you can use SparkSQL on Kudu, but it will 
require a lot more work to make it fast/useful.

Hope this helps,

J-D

On Wed, Feb 24, 2016 at 3:08 PM, Benjamin Kim 
<bbuil...@gmail.com<mailto:bbuil...@gmail.com>> wrote:
I see this KUDU-1214<https://issues.cloudera.org/browse/KUDU-1214> targeted for 
0.8.0, but I see no progress on it. When this is complete, will this mean that 
Spark will be able to work with Kudu both programmatically and as a client via 
Spark SQL? Or is there more work that needs to be done on the Spark side for it 
to work?

Just curious.

Cheers,
Ben

Re: Spark on Kudu

[Benjamin Kim]

J-D,

It looks like it fulfills most of the basic requirements (kudu RDD, kudu 
DStream) in KUDU-1214. Am I right? Besides shoring up more Spark SQL 
functionality (Dataframes) and doing the documentation, what more needs to be 
done? Optimizations?

I believe that it’s a good place to start using Spark with Kudu and compare it 
to HBase with Spark (not clean).

Thanks,
Ben


> On Feb 24, 2016, at 3:10 PM, Jean-Daniel Cryans <jdcry...@apache.org> wrote:
> 
> AFAIK no one is working on it, but we did manage to get this in for 0.7.0: 
> https://issues.cloudera.org/browse/KUDU-1321 
> <https://issues.cloudera.org/browse/KUDU-1321>
> 
> It's a really simple wrapper, and yes you can use SparkSQL on Kudu, but it 
> will require a lot more work to make it fast/useful.
> 
> Hope this helps,
> 
> J-D
> 
> On Wed, Feb 24, 2016 at 3:08 PM, Benjamin Kim <bbuil...@gmail.com 
> <mailto:bbuil...@gmail.com>> wrote:
> I see this KUDU-1214 <https://issues.cloudera.org/browse/KUDU-1214> targeted 
> for 0.8.0, but I see no progress on it. When this is complete, will this mean 
> that Spark will be able to work with Kudu both programmatically and as a 
> client via Spark SQL? Or is there more work that needs to be done on the 
> Spark side for it to work?
> 
> Just curious.
> 
> Cheers,
> Ben
> 
> 

Spark on Kudu

[Benjamin Kim]

I see this KUDU-1214  targeted 
for 0.8.0, but I see no progress on it. When this is complete, will this mean 
that Spark will be able to work with Kudu both programmatically and as a client 
via Spark SQL? Or is there more work that needs to be done on the Spark side 
for it to work?

Just curious.

Cheers,
Ben

Re: Kudu Release

[Benjamin Kim]

Jean,

Very organized outline. Looking forward to the 0.7 release. I am hoping that 
most of your points are addressed and completed by 1.0 release this fall.

Thanks,
Ben


> On Feb 23, 2016, at 8:31 AM, Jean-Daniel Cryans <jdcry...@apache.org> wrote:
> 
> Hi Ben,
> 
> Please see this thread on the dev list: 
> http://mail-archives.apache.org/mod_mbox/incubator-kudu-dev/201602.mbox/%3CCAGpTDNcMBWwX8p%2ByGKzHfL2xcmKTScU-rhLcQFSns1UVSbrXhw%40mail.gmail.com%3E
>  
> <http://mail-archives.apache.org/mod_mbox/incubator-kudu-dev/201602.mbox/%3CCAGpTDNcMBWwX8p%2ByGKzHfL2xcmKTScU-rhLcQFSns1UVSbrXhw%40mail.gmail.com%3E>
> 
> Thanks,
> 
> J-D
> 
> On Tue, Feb 23, 2016 at 8:23 AM, Benjamin Kim <bbuil...@gmail.com 
> <mailto:bbuil...@gmail.com>> wrote:
> Any word as to the release roadmap?
> 
> Thanks,
> Ben
>