Scaling new HPC with Composable Architecture

[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

WekaIO controls their performance destiny

[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

The Network is Still the Computer

[Preamble: I have been invited by  GestaltIT as a delegate to their TechFieldDay from Oct 17-19, 2018 in the Silicon Valley USA. My expenses, travel and accommodation are 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]

Sun Microsystems coined the phrase “The Network is the Computer“. It became one of the most powerful ideologies in the computing world, but over the years, many technology companies have tried to emulate and practise the mantra, but fell short.

I have never heard of Drivescale. It wasn’t in my radar until the legendary NFS guru, Brian Pawlowski joined them in April this year. Beepy, as he is known, was CTO of NetApp and later at Pure Storage, and held many technology leadership roles, including leading the development of NFSv3 and v4.

Prior to Tech Field Day 17, I was given some “homework”. Stephen Foskett, Chief Cat Herder (as he is known) of Tech Field Days and Storage Field Days, highly recommended Drivescale and asked the delegates to pick up some notes on their technology. Going through a couple of the videos, Drivescale’s message and philosophy resonated well with me. Perhaps it was their Sun Microsystems DNA? Many of the Drivescale team members were from Sun, and I was previously from Sun as well. I was drinking Sun’s Kool Aid by the bucket loads even before I graduated in 1991, and so what Drivescale preached made a lot of sense to me.Drivescale is all about Scale-Out Architecture at the webscale level, to address the massive scale of data processing. To understand deeper, we must think about “Data Locality” and “Data Mobility“. I frequently use these 2 “points of discussion” in my consulting practice in architecting and designing data center infrastructure. The gist of data locality is simple – the closer the data is to the processing, the cheaper/lightweight/efficient it gets. Moving data – the data mobility part – is expensive.

Continue reading

The rise of RDMA

I have known of RDMA (Remote Direct Memory Access) for quite some time, but never in depth. But since my contract work ended last week, and I have some time off to do some personal development, I decided to look deeper into RDMA. Why RDMA?

In the past 1 year or so, RDMA has been appearing in my radar very frequently, and rightly so. The speedy development and adoption of NVMe (Non-Volatile Memory Express) have pushed All Flash Arrays into the next level. This pushes the I/O and the throughput performance bottlenecks away from the NVMe storage medium into the legacy world of SCSI.

Most network storage interfaces and protocols like SAS, SATA, iSCSI, Fibre Channel today still carry SCSI loads and would have to translate between NVMe and SCSI. NVMe-to-SCSI bridges have to be present to facilitate the translation.

In the slide below, shared at the Flash Memory Summit, there were numerous red boxes which laid out the SCSI connections and interfaces where SCSI-to-NVMe translation (and vice versa) would be required.

Continue reading

FlashForward to Beyond

The flash frenzy has reached its zenith in 2016. We now no longer are interested in listening to storage technology vendors touting the power of solid state storage (NAND Flash included) over spinning drives.

The capacity of 3D NAND Flash SSDs has reached a whopping 15.3TB (that is even bigger than the 12TB 7200RPM HDDs of today), and with deduplication and compression, the storage efficiency has reached a conservative 4:1 or 5:1. Effective capacity of most mid-end storage arrays can easily reach 1-2 Petabytes.

And flash and hybrid platforms have reached maturity in these few short years. So what is next?

The landscape has obviously changed. The performance landscape, the capacity landscape and all related to the storage data points have changed. And the speed of SSDs together with the up-and-coming NVMe and NVDIMM technology in new storage array controllers are also shifting the data bottlenecks to another part of the architecture. The development of I/O communications and interfaces has to change as well, to take advantage of the asynchronous I/Os in storage tiering and caching using NAND Flash.

With this mature and well understood landscape, it is time to take Flash to the next level. This next level comes in the form of an exciting end-user conference in Singapore on 25th April 2017. It is called FlashForward.

The 2016 FlashForward event in Europe has already garnered great support from the cream of the storage technologists around the world, and had fantastic feedbacks from the end-user attendees. That FlashForward event has also seen the birth of an international business and technology exchange in its inaugural introduction.  Yes, it is time to learn from the field experts, and it is time to build on the Flash Platform for new Data Services.

From the sponsorship package brochure I have received, it is definitely an event not to be missed.

The FlashForward Conference in Singapore is exquisitely procured by Evito Ltd, under the stewardship of Mr. Paul Talbut. Paul is a very seasoned veteran in the global circuit as an SNIA director of several initiatives. He has been immensely involved in the development of several SNIA chapters around the world, including South Asia, Malaysia, India, China, and even Brazil. He also leads by example with the SNIA Global Steering Committee (GSC); he is the SNIA Global Education Director and at one time, SNIA DPCO (Data Protection & Capacity Optimization) global proctor.

I have had the honour working with Paul for almost 8 years now, and I am sure he will lead the FlashForward Conference with valuable insights and experiences.

This is probably the greatest period for the industry and end users to get involved in the FlashForward Conference. For one, it is endorsed by SNIA, the vendor-neutral association which has been the growth beacon of the storage networking industry.

Secondly, it is the perfect opportunity for technology vendors to build their mindshare with end users and customers. And with the endorsement of the independent field experts and technology practitioners, end users would have a field day garnering approvals for their decisions, as well as learning the best practices to build upon the Flash technology they have implemented in their data center space.

The sponsorship packages are listed below, and I do encourage technology vendors, especially the All-Flash vendors to use the FlashForward conference as a platform to build their mindshare, and most of all, their branding. Continue reading

Let’s smoke the storage peace pipe

NVMe (Non-Volatile Memory Express) is upon us. And in the next 2-3 years, we will see a slew of new storage solutions and technology based on NVMe.

Just a few days ago, The Register released an article “Seventeen hopefuls fight for the NVMe Fabric array crown“, and it was timely. I, for one, cannot be more excited about the development and advancement of NVMe and the upcoming NVMeF (NVMe over Fabrics).

This is it. This is the one that will end the wars of DAS, NAS and SAN and unite the warring factions between server-based SAN (the sexy name differentiating old DAS and new DAS) and the networked storage of SAN and NAS. There will be PEACE.

Remember this?

nutanix-nosan-buntingNutanix popularized the “No SAN” movement which later led to VMware VSAN and other server-based SAN solutions, hyperconverged techs such as PernixData (acquired by Nutanix), DataCore, EMC ScaleIO and also operated in hyperscalers – the likes of Facebook and Google. The hyperconverged solutions and the server-based SAN lines blurred of storage but still, they are not the usual networked storage architectures of SAN and NAS. I blogged about this, mentioning about how the pendulum has swung back to favour DAS, or to put it more appropriately, server-based SAN. There was always a “Great Divide” between the 2 modes of storage architectures. Continue reading

Really? Disk is Dead? From Violin?

A catchy email from one of the forums I subscribed to, caught my attention. It goes something like “…Grateful … Disk is Dead“. Here the blog from Kevin Doherty, a Senior Account Manager at Violin Memory.

Coming from Violin Memory, this is pretty obvious because they have an agenda against HDDs. They don’t use any disks at all …. in any form factor. They use VIMMs (Violin Inline Memory Modules), something no vendor in the industry use today.

violin-memory4

I recalled my blog in 2012, titled “Violin pulling the strings“. It came up here in South Asia with much fan fare, lots of razzmatazz and there was plenty of excitement. I was even invited to their product training at Ingram Micro in Singapore and met their early SE, Mike Thompson. Mike is still there I believe, but the EMC veteran in Singapore whom I mentioned in my previous blog, left almost a year later after joining. So was the ex-Sun, General Manager of Violin Memory in Singapore.

Continue reading

The reverse wars – DAS vs NAS vs SAN

It has been quite an interesting 2 decades.

In the beginning (starting in the early to mid-90s), SAN (Storage Area Network) was the dominant architecture. DAS (Direct Attached Storage) was on the wane as the channel-like throughput of Fibre Channel protocol coupled by the million-device addressing of FC obliterated parallel SCSI, which was only able to handle 16 devices and throughput up to 80 (later on 160 and 320) MB/sec.

NAS, defined by CIFS/SMB and NFS protocols – was happily chugging along the 100 Mbit/sec network, and occasionally getting sucked into the arguments about why SAN was better than NAS. I was already heavily dipped into NFS, because I was pretty much a SunOS/Solaris bigot back then.

When I joined NetApp in Malaysia in 2000, that NAS-SAN wars were going on, waiting for me. NetApp (or Network Appliance as it was known then) was trying to grow beyond its dot-com roots, into the enterprise space and guys like EMC and HDS were frequently trying to put NetApp down.

It’s a toy”  was the most common jibe I got in regular engagements until EMC suddenly decided to attack Network Appliance directly with their EMC CLARiiON IP4700. EMC guys would fondly remember this as the “NetApp killer“. Continue reading