High Performance Computing Archives - Page 4 of 8

Scaling new HPC with Composable Architecture

By cfheoh | May 10, 2019 - 4:50 pm |May 10, 2019 100Gigabit Ethernet, Analytics, API, Appliance, Artificial Intelligence, Big Data, Cloud, Clusters, Composable Infrastructure, Containers, Data Fabric, Data Management, Deep Learning, DellEMC, Drivescale, High Performance Computing, Hyperconvergence, Infiniband, Liqid, Machine Learning, nVidia, NVMe, PCIe, RDMA, Scale-out architecture, Software Defined Storage, Software-defined Datacenter, Tech Field Day, Unified Storage, Virtualization

2 Comments

[Disclosure: I was invited by Dell Technologies as a delegate to their Dell Technologies World 2019 Conference from Apr 29-May 1, 2019 in the Las Vegas USA. Tech Field Day Extra was an included activity as part of the Dell Technologies World. My expenses, travel, accommodation and conference fees were covered by Dell Technologies, the organizer and I was not obligated to blog or promote their technologies presented at this event. The content of this blog is of my own opinions and views]

Deep Learning, Neural Networks, Machine Learning and subsequently Artificial Intelligence (AI) are the new generation of applications and workloads to the commercial HPC systems. Different from the traditional, more scientific and engineering HPC workloads, I have written about the new dawn of supercomputing and the attractive posture of commercial HPC.

Don’t be idle

From the business perspective, the investment of HPC systems is high most of the time, and justifying it to the executives and the investors is not easy. Therefore, it is critical to keep feeding the HPC systems and significantly minimize the idle times for compute, GPUs, network and storage.

However, almost all HPC systems today are inflexible. Once assigned to a project, the resources pretty much stay with the project, even when the workload processing of the project is idle and waiting. Of course, we have to bear in mind that not all resources are fully abstracted, virtualized and software-defined whereby you can carve out pieces of the hardware and deliver a percentage of that resource. Case in point is the CPU, where you cannot assign certain clock cycles of CPU to one project and another half to the other. The technology isn’t there yet. Certain resources like GPU is going down the path of Virtual GPU, and into the realm of resource disaggregation. Eventually, all resources of the HPC systems – CPU, memory, FPGA, GPU, PCIe channels, NVMe paths, IOPS, bandwidth, burst buffers etc – should be disaggregated and pooled for disparate applications and workloads based on demands of usage, time and performance.

Hence we are beginning to see the disaggregated HPC systems resources composed and built up the meet the diverse mix and needs of HPC applications and workloads. This is even more acute when a AI project might grow cold, but the training of AL/ML/DL workloads continues to stay hot

Liqid the early leader in Composable Architecture

Continue reading →

Connecting ideas and people with Dell Influencers

By cfheoh | May 10, 2019 - 8:54 am |May 10, 2019 Analytics, Artificial Intelligence, Big Data, Big Switch Networks, Cloud, Composable Infrastructure, Data Management, Data Privacy, Data Protection, Data Security, Deep Learning, DellEMC, High Performance Computing, Hyperconvergence, Kemp Technologies, Liqid, Machine Learning, Microsoft, Software-defined Datacenter, Tech Field Day, VMware

AI Tweetup

In the razzmatazz, the most memorable moments were one of the Tweetups organized by Dr. Konstanze Alex (Konnie) and her team, and Tech Field Day Extra.

Tweetup was alien to me. I didn’t know how the concept work and I did google tweetup before that. There were a few tweetups on the topics of data protection and 5G, but the one that stood out for me was the AI tweetup.

Continue reading →

Dell go big with Cloud

By cfheoh | May 2, 2019 - 12:23 am |May 2, 2019 Acquisition, Amazon Web Services, API, Appliance, Artificial Intelligence, Backup, Cloud, Data Domain, Data Management, Data Protection, Data Security, Dell, DellEMC, Edge Computing, High Performance Computing, Hyperconvergence, Industry 4.0, Intel, IoT, Machine Learning, Software Defined Storage, Software-defined Datacenter, Tech Field Day, Virtualization, VMware

1 Comment

[Disclaimer: I have been invited by Dell Technologies as a delegate to their Dell Technologies World 2019 Conference from Apr 29-May 1, 2019 in the Las Vegas USA. My expenses, travel and accommodation are covered by Dell Technologies, the organizer and I am not obligated to blog or promote their technologies presented at this event. The content of this blog is of my own opinions and views]

Talk about big. Dell Technologies just went big with the Cloud.

The Microsoft Factor

Day 1 of Dell Technologies World 2019 (DTW19) started with a big surprise to many, including yours truly when Michael Dell, together with Pat Gelsinger invited Microsoft CEO, Satya Nadella on stage.

There was nothing new about Microsoft working with Dell Technologies. Both have been great partners since the PC days, but when they announced Azure VMware Solutions to the 15,000+ attendees of the conference, there was a second of disbelief, followed by an ovation of euphoria.

VMware solutions will run native on Microsoft Azure Cloud. The spread of vSphere, VSAN, vCenter, NSX-T and VMware tools and environment will run on Azure Bare Metal Infrastructure at multiple Azure locations. How big is that. Continue reading →

Lift and Shift Begone!

By cfheoh | April 25, 2019 - 5:30 pm |April 25, 2019 Amazon, Amazon Web Services, Cloud, Composable Infrastructure, Data Availability, Data Fabric, Data Management, High Performance Computing, Hyperconvergence, Mellanox Technologies, NetApp, NVMe, Server SAN, Software Defined Storage

1 Comment

I am excited. New technologies are bringing the data (and storage) closer to processing and compute than ever before. I believe the “Lift and Shift” way would be a thing of the past … soon.

Data is heavy

Moving data across the network is painful. Moving data across distributed networks is even more painful. To compile the recent first image of a black hole, an amount of 5PB or more had to shipped for central processing. If this was moved over a 10 Gigabit network, it would have taken weeks.

Furthermore, data has dependencies. Snapshots, clones, and other data relationships with applications and processes render data inert, weighing it down like an anchor of a ship.

When I first started in the industry more than 25 years ago, Direct Attached Storage (DAS) was the dominating storage platform. I had a bulky Sun MultiDisk Pack connected via Fast SCSI to my SPARCstation 2 (diagram below):

Then I was assigned as the implementation engineer for Hock Hua Bank (now defunct) retail banking project in their Sibu HQ in East Malaysia. It was the first Sun SPARCstorage 1000 (photo below), running a direct attached Fibre Channel 0.25 Gbps FCAL (Fibre Channel Arbitrated Loop). It was the cusp of the birth of SAN (Storage Area Network).

Photo from https://www.cca.org/dave/tech/sys5/

The proliferation of SAN over the next 2 decades pushed DAS into obscurity, until SAS (Serial Attached SCSI) came about. Added to the mix was the prominence of Cloud Storage. But on-premises storage and Cloud Storage didn’t always come together. There was always a valley between the 2, until the public clouds gained a stronger foothold in the minds of IT and businesses. Today, both on-premises storage and cloud storage are slowly cosying as one Data Singularity, thanks to vision and conceptualization of data fabrics. NetApp was an early proponent of the Data Fabric concept 4 years ago. Continue reading →

WekaIO controls their performance destiny

By cfheoh | March 17, 2019 - 5:33 pm |March 17, 2019 Amazon Web Services, Analytics, Appliance, Big Data, CIFS, Cloud, Deep Learning, Filesystems, Flash, High Performance Computing, Infiniband, Linux, Lustre, Machine Learning, Mellanox Technologies, NAS, NetApp, NFS, NVMe, Object Storage, PCIe, Performance Benchmark, Performance Caching, RDMA, Scale-out architecture, SMB, Software Defined Storage, Storage Field Day, Storage Optimization, Storage Tiering, Tech Field Day, Virtualization, WekaIO, Western Digital

3 Comments

[Preamble: I have been invited by GestaltIT as a delegate to their Tech Field Day for Storage Field Day 18 from Feb 27-Mar 1, 2019 in the Silicon Valley USA. My expenses, travel and accommodation were covered by GestaltIT, the organizer and I was not obligated to blog or promote their technologies presented at this event. The content of this blog is of my own opinions and views]

I was first introduced to WekaIO back in Storage Field Day 15. I did not blog about them back then, but I have followed their progress quite attentively throughout 2018. 2 Storage Field Days and a year later, they were back for Storage Field Day 18 with a new CTO, Andy Watson, and several performance benchmark records.

Blowout year

2018 was a blowout year for WekaIO. They have experienced over 400% growth, placed #1 in the Virtual Institute IO-500 10-node performance challenge, and also became #1 in the SPEC SFS 2014 performance and latency benchmark. (Note: This record was broken by NetApp a few days later but at a higher cost per client)

The Virtual Institute for I/O IO-500 10-node performance challenge was particularly interesting, because it pitted WekaIO against Oak Ridge National Lab (ORNL) Summit supercomputer, and WekaIO won. Details of the challenge were listed in Blocks and Files and WekaIO Matrix Filesystem became the fastest parallel file system in the world to date.

Control, control and control

I studied WekaIO’s architecture prior to this Field Day. And I spent quite a bit of time digesting and understanding their data paths, I/O paths and control paths, in particular, the diagram below:

Starting from the top right corner of the diagram, applications on the Linux client (running Weka Client software) and it presents to the Linux client as a POSIX-compliant file system. Through the network, the Linux client interacts with the WekaIO kernel-based VFS (virtual file system) driver which coordinates the Front End (grey box in upper right corner) to the Linux client. Other client-based protocols such as NFS, SMB, S3 and HDFS are also supported. The Front End then interacts with the NIC (which can be 10/100G Ethernet, Infiniband, and NVMeoF) through SR-IOV (single root IO virtualization), bypassing the Linux kernel for maximum throughput. This is with WekaIO’s own networking stack in user space. Continue reading →

StorPool – Block storage managed well

By cfheoh | March 13, 2019 - 8:34 am |March 13, 2019 100Gigabit Ethernet, API, Cloud, Clusters, Data Availability, Data Management, Disks, Filesystems, High Performance Computing, iSCSI, Linux, Lustre, Nexenta, NVMe, Openstack, Performance Benchmark, Performance Caching, Scale-out architecture, Server SAN, Software Defined Storage, Storage Field Day, Storage Optimization, Storpool, Tech Field Day, Virtualization, VMware

2 Comments

Storage technology is complex. Storage infrastructure and data management operations are not trivial, despite what the hyperscalers like Amazon Web Services and Microsoft Azure would like you to think. As the adoption of cloud infrastructure services grow, the small and medium businesses/enterprises (SMB/SME) are usually left to their own devices to manage the virtual storage infrastructure. Cloud Service Providers (CSPs) addressing the SMB/SME market are looking for easier, worry-free, software-defined storage to elevate their value to their customers.

Managed high performance block storage

Enter StorPool.

StorPool is a scale-out block storage technology, capable of delivering 1 million+ IOPS with sub-milliseconds response times. As described by fellow delegate, Ray Lucchesi in his recent blog, they were able to achieve these impressive performance numbers in their demo, without the high throughput RDMA network or the storage class memory of Intel Optane. Continue reading →

VAST Data must be something special

By cfheoh | February 28, 2019 - 9:59 pm |March 1, 2019 Analytics, Artificial Intelligence, Big Data, CIFS, Cloud, Clusters, Composable Infrastructure, Data, Data Fabric, Data Management, Data Protection, Deduplication, Edge Computing, Filesystems, High Performance Computing, Infiniband, Machine Learning, NAS, NFS, NVMe, Object Storage, Scale-out architecture, Software Defined Storage, Tech Field Day, Vast Data, XtremIO

3 Comments

Vast Data coming out bash!

The delegates of Storage Field Days were always the lucky bunch. We have witnessed several storage technology companies coming out of stealth at these Tech Field Days. The recent ones in memory for me were Excelero and Hammerspace. But to have one where the venerable storage doyen, Mr. Howard Marks, Vast Data new tech evangelist, to introduce the deep dive of Vast Data technology was something special.

For those who knew Howard, he is fiercely independent, very storage technology smart, opinionated and not easily impressed. As a storage technology connoisseur myself, I believe Howard must have seen something special in Vast Data. They must be doing something extremely unique and impressive that someone like Howard could not resist, and made him jump to the vendor side. This sets the tone of my blog.

Continue reading →

Minio – the minimalist object storage technology

By cfheoh | February 7, 2019 - 10:57 am |February 7, 2019 Amazon Web Services, Analytics, API, Appliance, Big Data, Cloud, Data, Data Archiving, Data Fabric, Data Management, Data Protection, Data Security, Deep Learning, Disaster Recovery, Edge Computing, Filesystems, Flash, FreeNAS, HDS, High Performance Computing, Hitachi Vantara, Industry 4.0, Katana Logic, Linux, Machine Learning, Minio, NAS, NetApp, NFS, Object Storage, Openstack, Redhat, Scale-out architecture, Tech Field Day

4 Comments

The Marie Kondo Konmari fever is sweeping the world. Her decluttering and organizing the home methods are leading to a new way of life – Minimalism.

Complicated Storage Experience

Storage technology and its architecture are complex. We layer upon layer of abstraction and virtualization into storage design until at some stage, choke points lead to performance degradation, and management becomes difficult.

I recalled a particular training I attended back in 2006. I just joined Hitachi Data Systems for the Shell GUSto project. I was in Baltimore for the Hitachi NAS course. This was not their HNAS (their BlueArc acquisition) but their home grown NAS based on Linux. In the training, we were setting up NFS service. There were 36 steps required to setup and provision NFS and if there was a misstep, you start from the first command again. Coming from NetApp at the time, it was horrendous. NetApp ONTAP NFS setup and provisioning probably took 3 commands, and this Hitachi NAS setup and configuration was so much more complex. In the end, the experience was just unworldly for me.

Introducing Minio to my world, to Malaysia

Continue reading →

Quantum Corp should spin off Stornext

By cfheoh | January 7, 2019 - 8:27 am |January 7, 2019 Acquisition, Analytics, API, Appliance, Artificial Intelligence, Backup, Big Data, Cloud, Commvault, Data, Data Archiving, Data Availability, Data Corruption, Data Domain, Data Fabric, Data Management, Data Protection, Data Security, Deduplication, Dell, DellEMC, Disaster Recovery, eDiscovery, Filesystems, High Performance Computing, Hyperconvergence, NetApp, Object Storage, Panasas, Pure Storage, Quantum Corporation, Scale-out architecture, Software Defined Storage, Stornext, Tape, Tapes

1 Comment

What’s happening at Quantum Corporation?

I picked up the latest development news about Quantum Corporation. Last month, in December 2018, they secured a USD210 million financial lifeline to support their deflating business and their debts. And if you follow their development, they are with their 3rd CEO in the past 12 months, which is quite extraordinary. What is happening at Quantum Corp?

Quantum Logo (PRNewsFoto/Quantum Corp.)

Stornext – The Swiss Army knife of Data Management

I have known Quantum since 2000, very focused on the DLT tape library business. At that time, prior to the coming of LTO, DLT and its successor, SuperDLT dominated the tape market together with IBM. In 2006, they acquired ADIC, another tape vendor and became one of the largest tape library vendors in the world. From the ADIC acquisition, Quantum also got their rights on Stornext, a high performance scale out file system. I was deeply impressed with Stornext, and I once called it the Swiss Army knife of Data Management. The versatility of Stornext addressed many of the required functions within the data management lifecycle and workflows, and thus it has made its name in the Media and Entertainment space.

Jack of all trades, master of none

However, Quantum has never reached great heights in my opinion. They are everything to everybody, like a Jack of all trades, master of none. They are backup with their tape libraries and DXi series, archive and tiering with the Lattus, hybrid storage with QXS, and file system and scale-out with Stornext. If they have good business run rates and a healthy pipeline, having a broad product line is fine and dandy. But Quantum has been having CEO changes like turning a turnstile, and amid “a few” accounting missteps and a 2018 CEO who only lasted 5 months, they better steady their rocking boat quickly. Continue reading →

Storage and Data Management Planning crucial for Malaysian SMBs

By cfheoh | January 2, 2019 - 8:30 am |January 2, 2019 Backup, Big Data, Business Continuity, Cloud, Data, Data Availability, Data Management, Data Protection, Data Security, Disaster Recovery, High Performance Computing, Hyperconvergence, Machine Learning, NVMe, Performance Caching, Reliability, Scale-out architecture, Server SAN, Software Defined Storage, Software-defined Datacenter

Hybrid IT for 2019 and beyond

2019 is here.

I am especially buoyed by the strong network storage industry footing in 2018, reported by The Register last week. 2018 was certainly a blowout year for storage infrastructure and storage software, both for on-premises and the cloud computing platforms. The AWS Outposts announcement over a month ago also just affirmed that the new world is Hybrid IT. And there is plenty to look forward to in 2019.

Malaysian Economic Doldrums

Things are not as rosy for the Malaysia economy in 2019. It will be a challenging 2019 as reported by the Edge, a local business publication. The GDP (gross domestic product) of the first half of 2018 shrunk, from 5.9% in 2017, to 4.65%, and it is estimated to be 4.9% in 2019. With an inexperienced new government, a weak currency, and more competitive economies emerging in ASEAN, Malaysia small and medium businesses (SMBs) could be challenged.

The knee jerk reaction would be to cut the IT spending and revert to buying on price. This has happened too often, because there are always other operating costs that may be more pressing. Furthermore, many of the SMBs are still aimless when it comes to transforming their businesses into the digital data era, groping in the dark and sputtering to get its worth with their IT investments. Often, many are misinformed and stumbled, resulting in much higher wastage and costs.

There is a local saying here:

“Good thing No Cheap; Cheap thing No Good“

And the saying is very apt to describe that there is value in investing well, and the price factor should not always be the main determinant criteria of buying IT infrastructure, software and services.

Many of these SMBs also lack experienced IT staff to manage their IT environment. There is also a hurried urgency to modernize IT, because a well-planned and executed IT strategy and operations would definitely increase their Competitive Advantage. Continue reading →

Category Archives: High Performance Computing