Analysis of implementations of and issues associated with the parallel programming framework MapReduce. Related subjects include:
I visited Cloudera Friday for, among other things, a chat about Impala with Marcel Kornacker and colleagues. Highlights included:
- Impala is meant to someday be a competitive MPP (Massively Parallel Processing) analytic RDBMS.
- At the moment, it is not one. For example, Impala lacks any meaningful form of workload management or query optimization.
- While Impala will run against any HDFS (Hadoop Distributed File System) file format, claims of strong performance assume that the data is in Parquet …
- … which is the replacement for the short-lived Trevni …
- … and which for most practical purposes is true columnar.
- Impala is also meant to be more than an RDBMS; Parquet and presumably in the future Impala can accommodate nested data structures.
- Just as Impala runs against most or all HDFS file formats, Parquet files can be used by most Hadoop execution engines, and of course by Pig and Hive.
- The Impala roadmap includes workload management, query optimization, data skipping, user-defined functions, hash distribution, two turtledoves, and a partridge in a pear tree.
Data gets into Parquet via batch jobs only — one reason it’s important that Impala run against multiple file formats — but background format conversion is another roadmap item. A single table can be split across multiple formats — e.g., the freshest data could be in HBase, with the rest is in Parquet.
A few days ago I posted Daniel Abadi’s thoughts in a discussion of Hadapt, Microsoft PDW (Parallel Data Warehouse)/PolyBase, Pivotal/Greenplum Hawq, and other SQL-Hadoop combinations. This is Dave DeWitt’s response. Emphasis mine.
|Categories: Benchmarks and POCs, Cloudera, Clustering, Data warehousing, Greenplum, Hadapt, Hadoop, MapReduce, Microsoft and SQL*Server, PostgreSQL, SQL/Hadoop integration||6 Comments|
The genesis of this post is:
- Dave DeWitt sent me a paper about Microsoft Polybase.
- I argued with Dave about the differences between Polybase and Hadapt.
- I asked Daniel Abadi for his opinion.
- Dan agreed with Dave, in a long email …
- … that he graciously permitted me to lightly-edit and post.
I love my life.
Per Daniel (emphasis mine): Read more
|Categories: Aster Data, Data warehousing, Greenplum, Hadapt, Hadoop, MapReduce, Microsoft and SQL*Server, SQL/Hadoop integration, Theory and architecture||10 Comments|
My client Syncsort:
- Is an ETL (Extract/Transform/Load) vendor, whose flagship product DMExpress was evidently renamed to DMX.
- Has a strong history in and fondness for sort.
- Has announced a new ETL product, DMX-h ETL Edition, which uses Hadoop MapReduce to parallelize DMX by controlling a copy of DMX that resides on every data node of the Hadoop cluster.*
- Has also announced the closely-related DMX-h Sort Edition, offering acceleration for the sorts inherent in Map and Reduce steps.
- Contributed a patch to Apache Hadoop to open up Hadoop MapReduce to make all this possible.
*Perhaps we should question Syncsort’s previous claims of having strong multi-node parallelism already.
The essence of the Syncsort DMX-h ETL Edition story is:
- DMX-h inherits the various ETL-suite trappings of DMX.
- Syncsort claims DMX-h has major performance advantages vs., for example, Hive- or Pig-based alternatives.
- With a copy of DMX on every node, DMX-h can do parallel load/export.
Hadoop 2.0/YARN is the first big step in evolving Hadoop beyond a strict Map/Reduce paradigm, in that it at least allows for the possibility of non- or beyond-MapReduce processing engines. While YARN didn’t meet its target of general availability around year-end 2012, Arun Murthy of Hortonworks told me recently that:
- Yahoo is a big YARN user.
- There are other — paying — YARN users.
- YARN general availability is now targeted for well before the end of 2013.
Arun further told me about Tez, the next-generation Hadoop processing engine he’s working on, which he also discussed in a recent blog post:
With the emergence of Apache Hadoop YARN as the basis of next generation data-processing architectures, there is a strong need for an application which can execute a complex DAG [Directed Acyclic Graph] of tasks which can then be shared by Apache Pig, Apache Hive, Cascading and others. The constrained DAG expressible in MapReduce (one set of maps followed by one set of reduces) often results in multiple MapReduce jobs which harm latency for short queries (overhead of launching multiple jobs) and throughput for large-scale queries (too much overhead for materializing intermediate job outputs to the filesystem). With Tez, we introduce a more expressive DAG of tasks, within a single application or job, that is better aligned with the required processing task – thus, for e.g., any given SQL query can be expressed as a single job using Tez.
This is similar to the approach of BDAS Spark:
Rather than being restricted to Maps and Reduces, Spark has more numerous primitive operations, including map, reduce, sample, join, and group-by. You can do these more or less in any order.
although Tez won’t match Spark’s richer list of primitive operations.
More specifically, there will be six primitive Tez operations:
- HDFS (Hadoop Distributed File System) input and output.
- Sorting on input and output (I’m not sure why that’s two operations rather than one).
- Shuffling of input and output (ditto).
A Map step would compound HDFS input, output sorting, and output shuffling; a Reduce step compounds — you guessed it! — input sorting, input shuffling, and HDFS output.
I can’t think of much in the way of algorithms that would be logically impossible in MapReduce yet possible in Tez. Rather, the main point of Tez seems to be performance, performance consistency, response-time consistency, and all that good stuff. Specific advantages that Arun and I talked about included:
- The requirement for materializing (onto disk) intermediate results that you don’t want to is gone. (Yay!)
- Hadoop jobs will step on each other’s toes less. Instead of Maps and Reduces from unrelated jobs getting interleaved, all the operations from a single job will by default be executed in one chunk. (Even so, I see no reason to expect early releases of Tez to do a great job on highly concurrent mixed workload management.)
- Added granularity brings opportunities for additional performance enhancements, for example in the area of sorting. (Arun loves sorts.)
|Categories: Databricks, Spark and BDAS, Hadoop, Hortonworks, MapReduce, Workload management, Yahoo||14 Comments|
Spark and Shark are interesting alternatives to MapReduce and Hive. At a high level:
- Rather than persisting data to disk after every step, as MapReduce does, Spark instead writes to something called RDDs (Resilient Distributed Datasets), which can live in memory.
- Rather than being restricted to maps and reduces, Spark has more numerous primitive operations, including map, reduce, sample, join, and group-by. You can do these more or less in any order. All the primitives are parallel with respect to the RDDs.
- Shark is a lot like Hive, only rewritten (in significant parts) and running over Spark.
- There’s an approach to launching tasks quickly — ~5 milliseconds or so — that I unfortunately didn’t grasp.
The key concept here seems to be the RDD. Any one RDD:
- Is a collection of Java objects, which should have the same or similar structure.
- Can be partitioned/distributed and shuffled/redistributed across the cluster.
- Doesn’t have to be entirely in memory at once.
Otherwise, there’s a lot of flexibility; an RDD can be a set of tuples, a collection of XML documents, or whatever other reasonable kind of dataset you want. And I gather that:
- At the moment, RDDs expire at the end of a job.
- This restriction will be lifted in a future release.
|Categories: Data models and architecture, Databricks, Spark and BDAS, Hadoop, MapReduce, Memory-centric data management, Open source, Parallelization, SQL/Hadoop integration||10 Comments|
UC Berkeley’s AMPLab is working on a software stack that:
- Is meant (among other goals) to improve upon Hadoop …
- … but also to interoperate with it, and which in fact …
- … uses significant parts of Hadoop.
- Seems to have the overall name BDAS (Berkeley Data Analytics System).
The whole thing has $30 million in projected funding (half government, half industry) and a 6-year plan (which they’re 2 years into).
Specific projects of note in all that include:
- Mesos, a cluster manager. I don’t know much about Mesos, but it seems to be in production use, most notably at Twitter supporting Storm.
- Spark, a replacement for MapReduce and the associated execution stack.
- Shark, a replacement for Hive.
|Categories: ClearStory Data, Databricks, Spark and BDAS, Hadoop, MapReduce, Parallelization, Specific users, SQL/Hadoop integration||10 Comments|
I’ve been known to gripe that covering big companies such as Microsoft is hard. Still, Doug Leland of Microsoft’s SQL Server team checked in for phone calls in August and again today, and I think I got enough to be worth writing about, albeit at a survey level only,
Subjects I’ll mention include:
- Parallel Data Warehouse
- Columnar data management
- In-memory data management (Hekaton)
One topic I can’t yet comment about is MOLAP/ROLAP, which is a pity; if anybody can refute my claim that ROLAP trumps MOLAP, it’s either Microsoft or Oracle.
Microsoft’s slides mentioned Yahoo refining a 6 petabyte Hadoop cluster into a 24 terabyte SQL Server “cube”, which was surprising in light of Yahoo’s history as an Oracle reference.
|Categories: Columnar database management, Data warehouse appliances, Data warehousing, Database compression, Hadoop, Hortonworks, In-memory DBMS, MapReduce, Market share and customer counts, Microsoft and SQL*Server, Oracle, Yahoo||10 Comments|
My clients at Couchbase checked in.
- After multiple delays, Couchbase 2.0 is well into beta, with general availability being delayed by the holiday season as much as anything else.
- Couchbase (the company) now has >350 subscription customers, almost all for Couchbase (the product) — which is to say for what was known as Membase, which is basically a persistent version of Memcached.
- There also are many users of open source Couchbase, most famously LinkedIn.
- Orbitz is a much-mentioned flagship paying Couchbase customer.
- Couchbase customers mainly seem to be replacing a caching layer, Memcached or otherwise.
- Couchbase headcount is just under 100.
The big changes in Couchbase 2.0 versus the previous (1.8.x) version are:
- JSON storage, including secondary indexes.
- Multi-data-center replication.
- A back-end change from SQLite to a heavily forked version of CouchDB, called Couchstore.
Couchbase 2.0 is upwards-compatible with prior versions of Couchbase (and hence with Memcached), but not with CouchDB.
Technology notes on Couchbase 2.0 include: Read more
|Categories: Basho and Riak, Cache, Cassandra, Clustering, Couchbase, MapReduce, Market share and customer counts, MongoDB and 10gen, NoSQL, Open source, Structured documents||4 Comments|
My clients at Cloudant, Couchbase, and 10gen/MongoDB (Edit: See Alex Popescu’s comment below) all boast the feature incremental MapReduce. (And they’re not the only ones.) So I feel like making a quick post about it. For starters, I’ll quote myself about Cloudant:
The essence of Cloudant’s incremental MapReduce seems to be that data is selected only if it’s been updated since the last run. Obviously, this only works for MapReduce algorithms whose eventual output can be run on different subsets of the target data set, then aggregated in a simple way.
These implementations of incremental MapReduce are hacked together by teams vastly smaller than those working on Hadoop, and surely fall short of Hadoop in many areas such as performance, fault-tolerance, and language support. That’s a given. Still, if the jobs are short and simple, those deficiencies may be tolerable.
A StackOverflow thread about MongoDB’s version of incremental MapReduce highlights some of the implementation challenges.
But all practicality aside, let’s return to the point that incremental MapReduce only works for some kinds of MapReduce-based algorithms, and consider how much of a limitation that really is. Looking at the Map steps sheds a little light: Read more
|Categories: Cloudant, Couchbase, EAI, EII, ETL, ELT, ETLT, Hadoop, MapReduce, MongoDB and 10gen, RDF and graphs||1 Comment|