Having a problem with HDFS NFS, addressed on another site where it is recommended to set hdfs-site.xml like...
<property>
<name>dfs.namenode.accesstime.precision</name>
<value>3600000</value>
<description>
The access time for HDFS file is precise upto this value. The default value is 1 hour. Setting a value of 0 disables access times for HDFS.
</description>
</property>
Am confused about what exactly "access times for HDFS" means / is. Looking at the hadoop docs, was still not able to determine. Could someone give better understanding as to what this is doing? Also, where is the nfs3 daemon log file?
Here is the answer that I was told from discussion on the apache hadoop mailing list:
I think access time refers to the POSIX atime attribute for files, the “time of last access” as described here for instance [1]. While HDFS keeps a correct modification time (mtime), which is important, easy and cheap, it only keeps a very low-resolution sense of last access time, which is less important, and expensive to monitor and record, as described here [2] and here [3]. It doesn’t even expose this low-rez atime value in the hadoop fs -stat command; you need to use Java if you want to read it from HDFS apis.
However, to have a conforming NFS api, you must present atime, and so the HDFS NFS implementation does. But first you have to configure it on. The documentation says that the default value is 3,600,000 milliseconds (1 hour), but many sites have been advised to turn it off entirely by setting it to zero, to improve HDFS overall performance. See for example here ( [4], section "Don’t let Reads become Writes”). So if your site has turned off atime in HDFS, you will need to turn it back on to fully enable NFS. Alternatively, you can maintain optimum efficiency by mounting NFS with the “noatime” option, as described in the document you reference.
I don’t know where the nfs3 daemon log file is, but it is almost certainly on the server node where you’ve configured the NFS service to be served from. Log into it and check under /var/log, eg with find /var/log -name ‘*nfs3*’ -print
[1] https://www.unixtutorial.org/atime-ctime-mtime-in-unix-filesystems
[2] https://issues.apache.org/jira/browse/HADOOP-1869
[3] https://superuser.com/questions/464290/why-is-cat-not-changing-the-access-time
[4] https://community.hortonworks.com/articles/43861/scaling-the-hdfs-namenode-part-4-avoiding-performa.html
Related
In Dask distributed documentation, they have the following information:
For example Dask developers use this ability to build in data locality
when we communicate to data-local storage systems like the Hadoop File
System. When users use high-level functions like
dask.dataframe.read_csv('hdfs:///path/to/files.*.csv') Dask talks to
the HDFS name node, finds the locations of all of the blocks of data,
and sends that information to the scheduler so that it can make
smarter decisions and improve load times for users.
However, it seems that the get_block_locations() was removed from the HDFS fs backend, so my question is: what is the current state of Dask regarding to HDFS ? Is it sending computation to nodes where data is local ? Is it optimizing the scheduler to take into account data locality on HDFS ?
Quite right, with the appearance of arrow's HDFS interface, which is now preferred over hdfs3, the consideration of block locations is no longer part of workloads accessing HDFS, since arrow's implementation doesn't include the get_block_locations() method.
However, we already wanted to remove the somewhat convoluted code which made this work, because we found that the inter-node bandwidth on test HDFS deployments was perfectly adequate that it made little practical difference in most workloads. The extra constrains on the size of the blocks versus the size of the partitions you would like in-memory created an additional layer of complexity.
By removing the specialised code, we could avoid the very special case that was being made for HDFS as opposed to external cloud storage (s3, gcs, azure) where it didn't matter which worker accessed which part of the data.
In short, yes the docs should be updated.
I am trying to obtain the size of directors in Google bucket but command is running a long time.
I have tried with 8TB data having 24k subdirectory and files, it is taking around 20~25 minutes, conversely, same data on HDFS is taking less than a minute to get the size.
commands that I use to get the size
hadoop fs -du gs://mybucket
gsutil du gs://mybucket
Please suggest how can I do it faster.
1 and 2 are nearly identical in that 1 uses GCS Connector.
GCS calculates usage by making list requests, which can take a long time if you have a large number of objects.
This article suggests setting up Access Logs as alternative to gsutil du:
https://cloud.google.com/storage/docs/working-with-big-data#data
However, you will likely still incur the same 20-25 minute cost if you intend to do any analytics on the data. From GCS Best Practices guide:
Forward slashes in objects have no special meaning to Cloud Storage,
as there is no native directory support. Because of this, deeply
nested directory- like structures using slash delimiters are possible,
but won't have the performance of a native filesystem listing deeply
nested sub-directories.
Assuming that you intend to analyze this data; you may want to consider benchmarking fetch performance of different file sizes and glob expressions with time hadoop distcp.
I intend to setup spark cluster on EC2. How much resources spark master instance actually needs? Since master is not involved in processing any of the tasks can it be the smallest EC2 instance?
This obviously depends on what kinds of jobs you're planning to run, how big is the cluster etc, so in that sense the advice to simply try different configurations is good. However, in my purely personal experience the driver instance should be at least at the level of the slave instances. This is mainly due to two reasons.
First of all, there are times when you need the result of the job in a single place. Maybe you just don't want to spend time combining files, maybe you need the results in some specific order which would be hard to achieve in a distributed way etc. but this means the driver should be able to hold all the data (as rdd.collect gathers the results to the driver instance).
Second of all, many of the shuffle-based operations seem to require a lot of memory from the driver. I'm not exactly sure about the details of why this happens (if anyone knows, please do share) but I can't count the number of times I've seen reduceyKey causing an out of memory error from the driver.
Edit: I have assumed you were using Spark's spark-ec2 script, which I believe does install the NameNode in the master instance. If the NameNode is not installed at the master intance, however, my answer has no validity as correctly pointed by #DemetriKots in the comments.
Although the master instance is not involved in data processing, it plays a major role during the management of the workload and resource allocation, e.g (all info is taken from the sources):
NameNode
The NameNode is the centerpiece of an HDFS file system. It keeps the directory tree of all files in the file system, and tracks where across the cluster the file data is kept. It does not store the data of these files itself.
Client applications talk to the NameNode whenever they wish to locate a file, or when they want to add/copy/move/delete a file. The NameNode responds the successful requests by returning a list of relevant DataNode servers where the data lives.
This (look for Hardware Recommendations for Hadoop on the left index) Hortonworks document specifies some recommendations for the master instance in a Hadoop cluster. While it might not be adequate for the slave instances (due to Spark's memory usage), I would say it can be useful in the case of the master instance in a Spark cluster.
Using HDFS for Nuodb as storage. Would this have a performance impact?
If I understand correctly, HDFS is better suited for batch mode or write once and read many times, types of application. Would it not increase the latency for record to be fetch in case it needs to read from storage?
On top of that HDFS block size concept, keep the file size small that would increase the network traffic while data is being fetch. Am I missing something here? Please point out the same.
How would Nuodb manage these kind of latency gotchas?
Good afternoon,
My name is Elisabete and I am the Technical Support Engineer over at NuoDB. I believe that I may have just answered this via your post on our own forum, but I'm responding here as well for anyone else who's curious.
First... a mini lesson on NuoDB architecture/layout:
The most basic NuoDB set-up includes:
Broker Agent
Transaction Engine (TE)
Storage Manager (SM) connected to an Archive Directory
Broker Agents keep track of all the moving parts in the domain (collection of machines hosting NuoDB processes) and provide client applications with connection information for the next available Transaction Engine.
Transaction Engines process incoming SQL requests and manage transactions.
Storage Managers read and write data to and from "disk" (Archive Directory)
All of these components can reside on a single machine, but an optimal set up would have them spread across multiple host machines (allowing each process to take full advantage of the host's available CPU/RAM). Also, while it's possible to run with just one of each component, this is a case where more is definitely more. Additional Brokers provide resiliency, additional TE's increase performance/speed and additional SM's ensure durability.
Ok, so now lets talk about Storage:
This is the "Archive Directory" that your storage manager is writing to. Currently, we support three modes of storage:
Local Files System
Amazon Web Services: Simple Storage volume (S3), Elastic Block Storage (EBS)
Hadoop Distributed Files System (HDFS)
So, to elaborate on how NuoDB works with HDFS... it doesn't know about the multiple machines that the HDFS layer is writing to. As far as the SM is concerned, it is reading and writing data atoms to a single directory. The HDFS layer decides how to then distribute and retrieve data to and from the cluster of machines it resides over.
And now to finally address the question of latency:
Here's the thing, whenever we introduce a remote storage device, we inevitably introduce some amount of additional latency because the SM now has further to go when reading/writing atoms to/from memory. HDFS likely adds a bit more, because now it needs to do it's magic divvying up, distributing, retrieving and reassembling data. Add to that discrepancy in network speed, etc.
I imagine that the gained disk space outweighs the cost in travel time, but this is something you'd have to decide on a case by case basis.
Now, all of that said... I haven't mentioned that TE and SM's both have the ability to cache data to local memory. The size of this cache is something you can set, when starting up each process. NuoDB uses a combination of Multi-Version Concurrency Control (MVCC) and a near constant stream of communication between all of the processes, to ensure that data held in cache is kept up to date with all of the changes happening within the system. Garbage Collection also kicks in and clears out atoms in a Least Recently Used order, when the cache grows close to hitting its limit.
All of this helps reduce latency, because the TE's can hold onto the data they reference most often and grab copies of data they don't have from sibling TE's. When they do resort to asking the SM's for data, there's a chance that the SM (or one of its sibling SM's) has a copy of the requested data in local cache, saving itself the trip out to the Archive Directory.
Whew.. that was a lot and I absolutely glossed over more than a few concepts. These topics are covered in greater depth via the new suite of white papers (and the new "green book") available on our main website. I'm currently also working on some visual guides, to help explain all of this.
If you'd like to know more about NuoDB or if I didn't quite answer your question.... please reach out to me directly via the NuoDB Community Forums (I respond to posts there, a bit faster).
Thank you,
Elisabete
Technical Support Engineer at NuoDB
From what I understood, Hadoop is a distributed storage system thingy. However what I don't really get is, can we replace normal RDBMS(MySQL, Postgresql, Oracle) with Hadoop? Or is Hadoop is just another type of filesystem and we CAN run RDBMS on it?
Also, can Django integrated with Hadoop? Usually, how web frameworks (ASP.NET, PHP, Java(JSP,JSF, etc) ) integrate themselves with Hadoop?
I am a bit confused with the Hadoop vs RDBMS and I would appreciate any explanation.
(Sorry, I read the documentation many times, but maybe due to my lack of knowledge in English, I find the documentation is a bit confusing most of the time)
What is Hadoop?
Imagine the following challange: you have a lot of data, and with a lot I mean at least Terabytes. You want to transform this data or extract some informations and process it into a format which is indexed, compressed or "digested" in a way so you can work with it.
Hadoop is able to parallelize such a processing job and, here comes the best part, takes care of things like redundant storage of the files, distribution of the task over different machines on the cluster etc (Yes, you need a cluster, otherwise Hadoop is not able to compensate the performance loss of the framework).
If you take a first look at the Hadoop ecosystem you will find 3 big terms: HDFS(Hadoop Filesystem), Hadoop itself(with MapReduce) and HBase(the "database" sometimes column store, which does not fits exactly)
HDFS is the Filesystem used by both Hadoop and HBase. It is a extra layer on top of the regular filesystem on your hosts. HDFS slices the uploaded Files in chunks (usually 64MB) and keeps them available in the cluster and takes care of their replication.
When Hadoop gets a task to execute, it gets the path of the input files on the HDFS, the desired output path, a Mapper and a Reducer Class. The Mapper and Reducer is usually a Java class passed in a JAR file.(But with Hadoop Streaming you can use any comandline tool you want). The mapper is called to process every entry (usually by line, e.g.: "return 1 if the line contains a bad F* word") of the input files, the output gets passed to the reducer, which merges the single outputs into a desired other format (e.g: addition of numbers). This is a easy way to get a "bad word" counter.
The cool thing: the computation of the mapping is done on the node: you process the chunks linearly and you move just the semi-digested (usually smaller) data over the network to the reducers.
And if one of the nodes dies: there is another one with the same data.
HBase takes advantage of the distributed storage of the files and stores its tables, splitted up in chunks on the cluster. HBase gives, contrary to Hadoop, random access to the data.
As you see HBase and Hadoop are quite different to RDMBS. Also HBase is lacking of a lot of concepts of RDBMS. Modeling data with triggers, preparedstatements, foreign keys etc. is not the thing HBase was thought to do (I'm not 100% sure about this, so correct me ;-) )
Can Django integrated with Hadoop?
For Java it's easy: Hadoop is written in Java and all the API's are there, ready to use.
For Python/Django I don't know (yet), but I'm sure you can do something with Hadoop streaming/Jython as a last resort.
I've found the following: Hadoopy and Python in Mappers and Reducers.
Hue, The Web UI for Hadoop is based on Django!
Django can connect with most RDMS, so you can use it with a Hadoop based solution.
Keep in mind, Hadoop is many things, so specifically, you want something with low latency such as HBase, don't try to use it with Hive or Impala.
Python has a thrift based binding, happybase, that let you query Hbase.
Basic (!) example of Django integration with Hadoop
[REMOVED LINK]
I use Oozie REST api for job execution, and 'hadoop cat' for grabbing job results (due to HDFS' distributed nature). The better appoach is to use something like Hoop for getting HDFS data. Anyway, this is not a simple solution.
P.S. I've refactored this code and placed it into https://github.com/Obie-Wan/django_hadoop.
Now it's a separate django app.