<div dir="ltr"><div dir="ltr"><div dir="ltr"><div dir="ltr"><div dir="ltr"><div dir="ltr"><div>Jonathan, I am going to stick my neck out here. I feel that HDFS was a 'thing of its time' - people are slavishly building clusters with local SATA drives to follow that recipe.</div><div>Current parallel filesystems have adapters which make them behave like HDFS</div><div><a href="http://docs.ceph.com/docs/master/cephfs/hadoop/">http://docs.ceph.com/docs/master/cephfs/hadoop/</a></div><div><a href="https://www.ibm.com/support/knowledgecenter/en/STXKQY_4.2.0/com.ibm.spectrum.scale.v4r2.adv.doc/bl1adv_hadoopconnector.htm">https://www.ibm.com/support/knowledgecenter/en/STXKQY_4.2.0/com.ibm.spectrum.scale.v4r2.adv.doc/bl1adv_hadoopconnector.htm</a></div><div><a href="http://wiki.lustre.org/index.php/Running_Hadoop_with_Lustre">http://wiki.lustre.org/index.php/Running_Hadoop_with_Lustre</a></div><div><br></div><div>Also you all know what is coming next. Julia. (Sorry all!)</div><div><a href="https://wilmott.com/big-time-series-analysis-with-juliadb/">https://wilmott.com/big-time-series-analysis-with-juliadb/</a> (I guess this is specific to finance)</div><div><a href="https://juliacomputing.github.io/JuliaDB.jl/latest/out_of_core/">https://juliacomputing.github.io/JuliaDB.jl/latest/out_of_core/</a><br></div><div><br></div></div></div></div></div></div></div><br><div class="gmail_quote"><div class="gmail_attr" dir="ltr">On Mon, 4 Mar 2019 at 11:16, Jonathan Aquilina <<a href="mailto:jaquilina@eagleeyet.net">jaquilina@eagleeyet.net</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;padding-left:1ex;border-left-color:rgb(204,204,204);border-left-width:1px;border-left-style:solid">I read though that postgres can handle time shift data no problem. I am just concerned if the clients would want to do complex big data analytics on the data. At this stage we are just prototyping but things are very up in the air at this point I am wondering though if sticking with HDFS and Hadoop is the best way to go for this in terms of performance and over all analytical capabilities.<br>
<br>
What I am trying to understand is how Hadoop being written in java is so performant.<br>
<br>
Regards,<br>
Jonathan<br>
<br>
On 04/03/2019, 12:11, "Beowulf on behalf of Fred Youhanaie" <<a href="mailto:beowulf-bounces@beowulf.org" target="_blank">beowulf-bounces@beowulf.org</a> on behalf of <a href="mailto:fly@anydata.co.uk" target="_blank">fly@anydata.co.uk</a>> wrote:<br>
<br>
Hi Jonathan<br>
<br>
I have used PostgreSQL for collecting data, but there's nothing there that would be of use to you!<br>
<br>
A few years ago I set up a similar system (in a hurry) in a small company. The bulk data was compressed and it was made available to the applications via NFS (IPoIB). The applications were responsible <br>
for decompressing and pre/post-processing the data. Later, one of the developers created a PostgreSQL based system to hold all the data, he used C++ for all the data handling. That system was never <br>
used, even though all the historical data was loaded into the database!<br>
<br>
Your choice of components is going to depend on how your analytics software are going to access the data. If the data are being read and processed once, then loading into a database, then querying it <br>
once may not pay off.<br>
<br>
Cheers,<br>
Fred<br>
<br>
On 04/03/2019 09:24, Jonathan Aquilina wrote:<br>
> Hi Fred,<br>
> <br>
> I and my colleague had done some research and found an extension for postgresql called timescaleDB, but then upon further research postgres on its own is good for such data as well. The thing is these are not going to be given to use as the data is coming in but in bulk at the end from the parent company.<br>
> <br>
> Have you used postgresql for such type's of data and how has it performed?<br>
> <br>
> Regards,<br>
> Jonathan<br>
> <br>
> On 04/03/2019, 10:19, "Beowulf on behalf of Fred Youhanaie" <<a href="mailto:beowulf-bounces@beowulf.org" target="_blank">beowulf-bounces@beowulf.org</a> on behalf of <a href="mailto:fly@anydata.co.uk" target="_blank">fly@anydata.co.uk</a>> wrote:<br>
> <br>
> Hi Jonathan,<br>
> <br>
> It seems you're collecting metrics and time series data. Perhaps a time series database (TSDB) is an option for you. There are a few of these out there, but I don't have any personal recommendation.<br>
> <br>
> Cheers,<br>
> Fred<br>
> <br>
> On 04/03/2019 07:04, Jonathan Aquilina wrote:<br>
> > These would be numerical data such as integers or floating point numbers.<br>
> ><br>
> > -----Original Message-----<br>
> > From: Tony Brian Albers <<a href="mailto:tba@kb.dk" target="_blank">tba@kb.dk</a>><br>
> > Sent: 04 March 2019 08:04<br>
> > To: <a href="mailto:beowulf@beowulf.org" target="_blank">beowulf@beowulf.org</a>; Jonathan Aquilina <<a href="mailto:jaquilina@eagleeyet.net" target="_blank">jaquilina@eagleeyet.net</a>><br>
> > Subject: Re: [Beowulf] Large amounts of data to store and process<br>
> ><br>
> > Hi Jonathan,<br>
> ><br>
> > From my limited knowledge of the technologies, I would say that HBase with file pointers to the files placed on HDFS would suit you well.<br>
> ><br>
> > But if the files are log files, consider some tools that are suited for analyzing those like Kibana.<br>
> ><br>
> > /tony<br>
> ><br>
> ><br>
> > On Mon, 2019-03-04 at 06:55 +0000, Jonathan Aquilina wrote:<br>
> >> Hi Tony,<br>
> >><br>
> >> Sadly I cant go into much detail due to me being under an NDA. At this<br>
> >> point with the prototype we have around 250gb of sample data but again<br>
> >> this data is dependent on the type of air craft. Larger aircraft and<br>
> >> longer flights will generate a lot more data as they have more<br>
> >> sensors and will log more data than the sample data that I have. The<br>
> >> sample data is 250gb for 35 aircraft of the same type.<br>
> >><br>
> >> Regards,<br>
> >> Jonathan<br>
> >><br>
> >> -----Original Message-----<br>
> >> From: Tony Brian Albers <<a href="mailto:tba@kb.dk" target="_blank">tba@kb.dk</a>><br>
> >> Sent: 04 March 2019 07:48<br>
> >> To: <a href="mailto:beowulf@beowulf.org" target="_blank">beowulf@beowulf.org</a>; Jonathan Aquilina <<a href="mailto:jaquilina@eagleeyet.net" target="_blank">jaquilina@eagleeyet.net</a>><br>
> >> Subject: Re: [Beowulf] Large amounts of data to store and process<br>
> >><br>
> >> On Mon, 2019-03-04 at 06:38 +0000, Jonathan Aquilina wrote:<br>
> >>> Good Morning all,<br>
> >>><br>
> >>> I am working on a project that I sadly cant go into much detail but<br>
> >>> there will be quite large amounts of data that will be ingested by<br>
> >>> this system and would need to be efficiently returned as output to<br>
> >>> the end user in around 10 min or so. I am in discussions with<br>
> >>> another partner involved in this project about the best way forward<br>
> >>> on this.<br>
> >>><br>
> >>> For me given the amount of data (and it is a huge amount of data)<br>
> >>> that an RDBMS such as postgresql would be a major bottle neck.<br>
> >>> Another thing that was considered flat files, and I think the best<br>
> >>> for that would be a Hadoop cluster with HDFS. But in the case of HPC<br>
> >>> how can such an environment help in terms of ingesting and analytics<br>
> >>> of large amounts of data? Would said flat files of data be put on a<br>
> >>> SAN/NAS or something and through an NFS share accessed that way for<br>
> >>> computational purposes?<br>
> >>><br>
> >>> Regards,<br>
> >>> Jonathan<br>
> >>> _______________________________________________<br>
> >>> Beowulf mailing list, <a href="mailto:Beowulf@beowulf.org" target="_blank">Beowulf@beowulf.org</a> sponsored by Penguin<br>
> >>> Computing To change your subscription (digest mode or unsubscribe)<br>
> >>> visit http:/ /<a href="http://www.beowulf.org/mailman/listinfo/beowulf" target="_blank" rel="noreferrer">www.beowulf.org/mailman/listinfo/beowulf</a><br>
> >><br>
> >> Good morning,<br>
> >><br>
> >> Around here, we're using HBase for similar purposes. We have a bunch<br>
> >> of smaller nodes storing the data and all the management nodes(ambari,<br>
> >> HDFS namenodes etc.) are vm's.<br>
> >><br>
> >> Our nodes are configured so that we have a maximum of 2 cores per disk<br>
> >> spindle and 4G of memory for each core. This seems to do the trick and<br>
> >> is pretty responsive.<br>
> >><br>
> >> But to be able to provide better advice, you will probably need to go<br>
> >> into a bit more detail about what types of data you will be storing<br>
> >> and which kind of calculations you want to perform.<br>
> >><br>
> >> /tony<br>
> >><br>
> >><br>
> >> --<br>
> >> Tony Albers - Systems Architect - IT Development Royal Danish Library,<br>
> >> Victor Albecks Vej 1, 8000 Aarhus C, Denmark<br>
> >> Tel: +45 2566 2383 - CVR/SE: 2898 8842 - EAN: 5798000792142<br>
> ><br>
> > --<br>
> > Tony Albers - Systems Architect - IT Development Royal Danish Library, Victor Albecks Vej 1, 8000 Aarhus C, Denmark<br>
> > Tel: +45 2566 2383 - CVR/SE: 2898 8842 - EAN: 5798000792142<br>
> > _______________________________________________<br>
> > Beowulf mailing list, <a href="mailto:Beowulf@beowulf.org" target="_blank">Beowulf@beowulf.org</a> sponsored by Penguin Computing<br>
> > To change your subscription (digest mode or unsubscribe) visit <a href="http://www.beowulf.org/mailman/listinfo/beowulf" target="_blank" rel="noreferrer">http://www.beowulf.org/mailman/listinfo/beowulf</a><br>
> ><br>
> _______________________________________________<br>
> Beowulf mailing list, <a href="mailto:Beowulf@beowulf.org" target="_blank">Beowulf@beowulf.org</a> sponsored by Penguin Computing<br>
> To change your subscription (digest mode or unsubscribe) visit <a href="http://www.beowulf.org/mailman/listinfo/beowulf" target="_blank" rel="noreferrer">http://www.beowulf.org/mailman/listinfo/beowulf</a><br>
> <br>
> <br>
> _______________________________________________<br>
> Beowulf mailing list, <a href="mailto:Beowulf@beowulf.org" target="_blank">Beowulf@beowulf.org</a> sponsored by Penguin Computing<br>
> To change your subscription (digest mode or unsubscribe) visit <a href="http://www.beowulf.org/mailman/listinfo/beowulf" target="_blank" rel="noreferrer">http://www.beowulf.org/mailman/listinfo/beowulf</a><br>
> <br>
_______________________________________________<br>
Beowulf mailing list, <a href="mailto:Beowulf@beowulf.org" target="_blank">Beowulf@beowulf.org</a> sponsored by Penguin Computing<br>
To change your subscription (digest mode or unsubscribe) visit <a href="http://www.beowulf.org/mailman/listinfo/beowulf" target="_blank" rel="noreferrer">http://www.beowulf.org/mailman/listinfo/beowulf</a><br>
<br>
<br>
_______________________________________________<br>
Beowulf mailing list, <a href="mailto:Beowulf@beowulf.org" target="_blank">Beowulf@beowulf.org</a> sponsored by Penguin Computing<br>
To change your subscription (digest mode or unsubscribe) visit <a href="http://www.beowulf.org/mailman/listinfo/beowulf" target="_blank" rel="noreferrer">http://www.beowulf.org/mailman/listinfo/beowulf</a><br>
</blockquote></div>