NVMe Archives - Page 2 of 4

Storage Performance Considerations for AI Data Paths

By cfheoh | June 17, 2019 - 10:50 am |June 17, 2019 100Gigabit Ethernet, Algorithm, Analytics, API, Artificial Intelligence, Big Data, Cloud, Composable Infrastructure, Data, Data Fabric, Data Management, Data Privacy, Data Security, Digital Transformation, Drivescale, E8 Storage, Edge Computing, Elastifile, Excelero, Filesystems, High Performance Computing, Hyperconvergence, Industry 4.0, Infiniband, Intel, Liqid, Lustre, Machine Learning, Mellanox Technologies, NVMe, Object Storage, Performance Benchmark, Performance Caching, Quantum Corporation, RDMA, Software-defined Datacenter, Storage Optimization, Storage Tiering, ThinkParq, Vast Data, Virtualization, WekaIO

1 Comment

The hype of Deep Learning (DL), Machine Learning (ML) and Artificial Intelligence (AI) has reached an unprecedented frenzy. Every infrastructure vendor from servers, to networking, to storage has a word to say or play about DL/ML/AI. This prompted me to explore this hyped ecosystem from a storage perspective, notably from a storage performance requirement point-of-view.

One question on my mind

There are plenty of questions on my mind. One stood out and that is related to storage performance requirements.

Reading and learning from one storage technology vendor to another, the context of everyone’s play against their competitors seems to be “They are archaic, they are legacy. Our architecture is built from ground up, modern, NVMe-enabled“. And there are more juxtaposing, but you get the picture – “We are better, no doubt“.

Are the data patterns and behaviours of AI different? How do they affect the storage design as the data moves through the workflow, the data paths and the lifecycle of the AI ecosystem?

Continue reading →

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 →

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 →

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 →

Microsoft desires Mellanox

By cfheoh | December 20, 2018 - 11:02 am |December 20, 2018 100Gigabit Ethernet, Acquisition, Amazon, Artificial Intelligence, Cloud, Data Fabric, Data Management, Deep Learning, Edge Computing, High Performance Computing, Infiniband, Machine Learning, Mellanox Technologies, Microsoft, NVMe, Storage Field Day, Tech Field Day, Virtualization

The Return of SAN and NAS with AWS?

By cfheoh | December 3, 2018 - 10:31 am |December 3, 2018 Amazon, Appliance, Artificial Intelligence, Big Data, CIFS, Cloud, Data Availability, Data Management, Data Protection, Data Security, Deep Learning, Excelero, Fibre Channel, High Performance Computing, Hyperconvergence, iSCSI, Machine Learning, Mellanox, NAS, NetApp, NFS, NVMe, Object Storage, Openstack, Oracle, Reliability, Scale-out architecture, Server SAN, SMB, Snapshots, Software-defined Datacenter, Virtualization, VMware

1 Comment

AWS what?

Amazon Web Services announced Outposts at re:Invent last week. It was not much of a surprise for me because when AWS had their partnership with VMware in 2016, the undercurrents were there to have AWS services come right at the doorsteps of any datacenter. In my mind, AWS has built so far out in the cloud that eventually, the only way to grow is to come back to core of IT services – The Enterprise.

Their intentions were indeed stealthy, but I have been a believer of the IT pendulum. What has swung out to the left or right would eventually come back to the centre again. History has proven that, time and time again.

SAN and NAS coming back?

A friend of mine casually spoke about AWS Outposts announcements. “Does that mean SAN and NAS are coming back?” I couldn’t hide my excitement hearing the return but … be still, my beating heart!

I am a storage dinosaur now. My era started in the early 90s. SAN and NAS were a big part of my career, but cloud computing has changed and shaped the landscape of on-premises shared storage. SAN and NAS are probably closeted by the younger generation of storage engineers and storage architects, who are more adept to S3 APIs and Infrastructure-as-Code. The nuts and bolts of Fibre Channel, SMB (or CIFS if one still prefers it), and NFS are of lesser prominence, and concepts such as FLOGI, PLOGI, SMB mandatory locking, NFS advisory locking and even iSCSI IQN are probably alien to many of them.

What is Amazon Outposts?

In a nutshell, AWS will be selling servers and infrastructure gear. The AWS-branded hardware, starting from a single server to large racks, will be shipped to a customer’s datacenter or any hosting location, packaged with AWS popular computing and storage services, and optionally, with VMware technology for virtualized computing resources.

Taken from https://aws.amazon.com/outposts/

In a move ala-Azure Stack, Outposts completes the round trip of the IT Pendulum. It has swung to the left; it has swung to the right; it is now back at the centre. AWS is no longer public cloud computing company. They have just become a hybrid cloud computing company. Continue reading →

Is Pure Play Storage good?

By cfheoh | November 13, 2018 - 3:16 am |November 15, 2018 Acquisition, Analytics, Appliance, Artificial Intelligence, Cloud, Cloudian, Cohesity, Data Management, Data Protection, Data Security, Datera, Datrium, Deep Learning, Dell, DellEMC, Drivescale, E8 Storage, EMC, Excelero, Flash, Gartner, Hammerspace, HDS, Hedvig, Hitachi Vantara, Huawei, IBM, Kaminario, NetApp, Nimble Storage, Nutanix, NVMe, Panasas, Promise Technology, Pure Storage, Ryuusi, Scale-out architecture, Server SAN, Software Defined Storage, Software-defined Datacenter, Solid State Devices, Storage Field Day, Storage Market Share, Tech Field Day, Tegile, Tintri, Unified Storage, Violin Memory, WekaIO, XtremIO

1 Comment

I post storage and cloud related articles to my unofficial SNIA Malaysia Facebook community (you are welcomed to join) every day. It is a community I started over 9 years ago, and there are active live banters of the posts of the day. Casual, personal were the original reasons why I started the community on Facebook rather than on LinkedIn, and I have been curating it religiously for the longest time.

The Big 5 of Storage (it was Big 6 before this)

Looking back 8-9 years ago, the storage vendor landscape of today has not changed much. The Big 5 hegemony is still there, still dominating the Gartner Magic Quadrant for Enterprise and Mid-end Arrays, and is still there in the All-Flash quadrant as well, albeit the presence of Pure Storage in that market.

The Big 5 of today – Dell EMC, NetApp, HPE, IBM and Hitachi Vantara – were the Big 6 of 2009-2010, consisting of EMC, NetApp, Dell, HP, IBM and Hitachi Data Systems. The All-Flash, or Gartner calls it Solid State Arrays (SSA) market was still an afterthought, and Pure Storage was just founded. Pure Storage did not appear in my radar until 2 years later when I blogged about Pure Storage’s presence in the market.

Here’s a look at the Gartner Magic Quadrant for 2010:

We see Pure Play Storage vendors in the likes of EMC, NetApp, Hitachi Data Systems (before they adopted the UCP into their foray), 3PAR, Compellent, Pillar Data Systems, BlueArc, Xiotech, Nexsan, DDN and Infortrend. And when we compare that to the 2017 Magic Quadrant (I have not seen the 2018 one yet) below:

Continue reading →

Category Archives: NVMe