A new storage benchmark – STAC-M3

9761778404_73283cbd17_nA week or so ago I was reading a DDN press release that said they had just published a STAC-M3 benchmark. I had never heard of STAC or their STAC-M3 so thought I would look them up.

STAC stands for Securities Technology Analyst Center and is an organization dedicated to testing system solutions for the financial services industries.

What does STAC-M3 do

It turns out that STAC-M3 simulates processing a time (ticker tape or tick) log of security transactions and identifyies the maximum and weighted bid along with various other statistics for a number (1%) of securities over various time periods (year, quarter, week, and day) in the dataset. They call it high-speed analytics on time-series data. This is a frequent use case for systems in the securities sector.

There are two versions of the STAC-M3 benchmark: Antuco and Kanaga. The Antuco version uses a statically sized dataset and the Kanaga uses more scaleable (varying number of client threads) queries over larger datasets. For example, the Antuco version uses 1 or 10 client threads for their test measurements whereas the Kanaga version scales client threads, in some cases, from 1 to 100 threads and uses more tick data in 3 different sized datasets.

Good, bad and ugly of STAC-M3

Access to STAC-M3 reports requires a login but it’s available for free. Some details are only available after you request them which can be combersome.

One nice thing about the STAC-M3 benchmark information is that it provides a decent summary of the amount of computational time involved in all the queries it performs. From a storage perspective, if one were to take this and just analyze the queries with minimal or light computation that come closer to a pure storage workload than computationally heavy queries.

Another nice thing about the STAC-M3 is that it in some cases it provides detailed statistical information about the distribution of metrics, including mean, median, min, max and standard deviation. Unfortunately, the current version of the STAC-M3 does not provide these statistics for the computational light measures that are of primary interest to me as a storage analyst. It would be very nice to see some of their statistical level reporting be adopted by SPCSPECsfs or Microsoft ESRP for their benchmark metrics.

STAC-M3 also provides a measure of storage efficiency, or how much storage it took to store the database. This is computed as the reference size of the dataset divided by the amount of storage it took to store the dataset. Although this could be interesting most of the benchmark reports I examined all had similar numbers for storage efficiency 171% or 172%.

The STAC-M3 benchmark is a full stack test. That is it measures the time from the point a query is issued to the point the query response is completed. Storage is just one part of this activity, computing the various statistics is another part and the database used to hold the stock tick data is another aspect of their test environment. But what is being measured is the query elapsed time. SPECsfs2014 has also recently changed over to be a full stack test, so it’s not that unusual anymore.

The other problem from a storage perspective (but not a STAC perspective) is that there is minimal write activity during any of the benchmark specific testing. There’s just one query that generates a lot of storage write activity all the rest are heavy read IO only.

Finally, there’s not a lot of description of the actual storage and server configuration available in the basic report. But this might be further detailed in the Configuration Disclosure report which you have to request permission to see.

STAC-M3 storage submissions

As it’s a stack benchmark we don’t find a lot of storage array submissions. Typical submissions include a database running on some servers with SSD-DAS or occasionally a backend storage array. In the case of DDN it was KX system’s kdb 3.2 database, with Intel Enterprise Edition servers for Lustre, with 8 Intel based DDN EXAscaler servers, talking to a DDN SFA12KX-40 storage array. In contrast, a previousr submission used an eXtremeDB Financial Edition 6.0 database running on Lucera Compute™ (16 Core SSD V2, Smart OS) nodes.

Looking back over the last couple of years of  submissions (STAC-M3 goes back to 2010), forstorage arrays, aside from the latest DDN SFA12KX-40, we find an IBM FlashSystem 840, NetApp EF550, IBM FlashSystem 810, a couple of other DDN SFA12K-40 storage solutions, and a Violin V3210 & V3220 submission.  Most of the storage array submissions were all-flash arrays, but the DDN SFA12KX-40 is a hybrid (flash-disk) appliance.

Some metrics from recent STAC-M3 storage array runs

STAC-M3-YRHIBID-MAXMBPS

In the above chart, we show the Maximum MBPS achieved in the year long high bid (YRHIBID) extraction testcase. DDN won this one handily with over 10GB/sec for its extraction result.

STAC-M3-YRHIBID-MEANRTHowever in the next chart, we show the Mean Response (query elapsed) Time (in msec.) for the query that extracts the Year long High Bid data extraction test (YRHIBID). In this case the IBM FlashSystem 810 did much better than the DDN or even the more recent IBM FlashSystem 840.

Unexpectedly, the top MBPS storage didn’t achieve the best mean response time for the YRHIBID query. I would have thought the mean response time and the maximum MBPS would show the same rankings. Not clear to me why this is, it’s the mean response time not minimum or maximum. Although the maximum response time would show the same rankings. An issue with the YRHIBID is that it doesn’t report standard deviation, median or minimum response time results. Having these other metrics might have shed some more light on this anomaly but for now this is all we have.

If anyone knows of other storage (or stack) level benchmarks for other verticals please let me know and I would be glad to dig into them to see if they provide some interesting viwes on storage performance.

Comments?

 Photo Credit(s): Stock market quotes in newspaper by Andreas Poike

Max MBPS and Mean RT Charts (c) 2015 Silverton Consulting, Inc., All Rights Reserved

DDN unchains Wolfcreek, unleashes IME and updates WOS

16371098088_3b264f5844_zIt’s not every day that we get a vendor claiming 2.5X the top SPC-1 IOPS (currently held by Hitachi G1000 VSP all flash array at ~2M IOPS) as DataDirect Networks (DDN) has claimed for an all-flash version of their new Wolfcreek hyper converged appliance. DDN says their new 4U appliance is capable of 60GB/sec of throughput and over 5M IOPS. (See their press release for more information.) Unclear if these are SPC-1 IOPS or not, but I haven’t seen any SPC-1 report on it yet.

In addition to the new Wolfcreek appliance, DDN announced their new Infinite Memory Engine™ (IME) flash caching software and WOS® 360 V2.0, an enhanced version of their object storage.

DDN if you haven’t heard of them has done well in the Web 2.0 environments and is a leading supplier to high performance computing (HPC) sites. They have object storage system (WOS), all flash block storage (SFA12KXi), hybrid (disk-SSD) block storage (SFA7700X™ & SFA12KX™), Lustre file appliance (EXAScaler), IBM GPFS™ NAS appliance (GRIDScaler), media server appliance (MEDIAScaler™) and  software defined storage (Storage Fusion Accelerator [SFX™] flash caching software).

Wolfcreek hyper converged appliance

The converged solution comes in a 4U appliance using dual Haswell Intel microprocessors (with up to 18 cores each), includes a PCIe fabric which supports 48-NVMe flash cards or 72-SFF SSDs. With the NVMe or SSDs, Wolfcreek will be using their new IME software to accelerate IO activity.

Wolfcreek IME software supports either burst mode IO caching cluster or a storage cluster of nodes. I assume burst mode is a storage caching layer for backend file system stoorage. As a storage cluster I assume this would include some of their scale-out file system software on the nodes. Wolfcreek cluster interconnect is 40Gb Infiniband or 10/40Gb Ethernet and also will support Intel’s Omni-Path. The Wolfcreek appliance is compatible with HPC Lustre and IBM GPFS scale out file systems.

Wolfcreek appliance can be a great platform for OpenStack and Hadoop environments. But it also supports virtual machine hypervisors from VMware, Citrix and Microsoft. DDN says that the Wolfcreek appliance can scale up to support 100K VMs. I’ve been told that IME will not be targeted to work with Hypervisors in the first release.

Recall that with a hyper converged appliance, some portion of the system resources (memory and CPU cores) must be devoted to server and VM application activities and the remainder to storage activity. How this is divided up and whether this split is dynamic (changes over time) or static (fixed over time) in the Wolfcreek appliance is not indicated.

The hyper converged field is getting crowded of late what with VMware EVO:RAIL, Nutanix, ScaleComputing, Simplivity and others coming out with solutions. But there aren’t many that support all-flash storage and it seems unusual that hyper converged customers would have need for that much IO performance. But I could be wrong, especially for HPC customers.

There’s much more to hyper convergence than just having storage and compute in the same node. The software that links it all together, manages, monitors and deploys these combined hypervisor, storage and server systems is almost as important as any of the  hardware. There wasn’t much talk about the software that DDN is putting together for Wolfcreek but it’s still early yet. With their roots in HPC, it’s likely that any DDN hyper converged solution will target this market first and broaden out from there.

Infinite Memory Engine (IME)

IME is an outgrowth of DDN’s SFX software and seem to act as a caching layer for parallel file system IO. It makes use of NVMe or SSDs for its IO caching. And according to DDN can offer up to 1000X IO acceleration to storage or 100X file system acceleration.

It does this primarily by providing an application aware IO caching layer and supplying more effective IO to the file system layer using PCIe NVMe or SSD flash storage for hardware IO acceleration. According to the information provided by DDN, IME can provide 50 GB/sec bandwidth to a host compute cluster while only doing 4GB/sec of throughput to a backend file system, presumably by better caching of file IO.

WOS 360 V2.0

The new WOS 360 V2.0 object storage system features include

  • Higher density storage package with 98-8TB SATA drives or 768TB raw capacity in 4U) supporting 8B objects each and over 100B objects in a cluster.
  • Native SWIFT API support for OpenStack environments  which includes gateway or embedded deployments, up to 5000 concurrent users and 5B objects/namespace.
  • Global ObjectAssure data encoding with lower storage overhead (1.5x or a 20% reduction from their previous encoding option) for highly durable and available object storage usiing a two level hierarchical erasure code for object storage.
  • Enhanced network security with SSL  which provides end-to-end SSL network data transport between clients and WOS and betweenWOS storage nodes.
  • Simplified cluster installation, deployment and maintenance with can now deploy a WOS cluster in minutes, with a simple point and click GUI for installation and cluster deployment with automated non-disruptive software upgrade.
  • Performance improvements for better video streaming, content distribution and large file transfers with improved QoS for latency sensitive applications.

~~~~

Probably more going on with DDN than covered here but this hits the highlights. I wish there was more on their Wolfcreek appliance and its various configurations and performance benchmarks but there’s not.

Comments?

 Photo Credits: wolf-63503+1920 by _Liquid

 

Object Storage Summit wrap up

Attended ExecEvent’s first Next-Gen Object Storage Summit in Miami this past week.  Learned a lot there and met a lot of the players and movers in this space.  Here is a summary of what happened during the summit.

Janae starting a debate on Object Storage
Janae starting a debate on Object Storage

Spent most of the morning of the first day discussing some parameters of  object storage in general. Janae got up and talked about 4 major adopters for object storage:

  1. Rapid Responders – these customer have data in long term storage and it  just keeps building and needs to be stored in scaleable storage. They believe someday they  will need access to it and have no idea when. But when they want it, they want it fast. Rapid responder adoption  is based on the unpredictability of access. As such, having the data on scaleable disk object storage makes sense.  Some examples include black operations sites with massive surveillance feeds which maybe needed fast sometime after initial analysis and medical archives.
  2. Distributed (content) Enterprises – geographically distributed enterprises with users around the globe that need shared access to data.  Distributed enterprises often have 100 or so users sharing data access dispersed around the globe and want shared access to data.   Object storage can dispurse the data to provide local caching across the world for better data and meta-data latency.  Media and Entertainment are key customers in this space but design shops that follow the sun also have the problem.
  3. Private Cloud(y) – data centers adopt the cloud for a number of reasons but sometimes it’s just mandated.  In these cases, direct control over cloud storage with the economics of major web service providers can be an alluring proposition.  Some object storage solutions roll in with cloud like economics and on premises solutions and responsiveness, the best of all worlds.  Enterprise IT forced to move to the cloud are in this category.
  4. Big Hadoop(ers) – lots of data to analyze but with no understanding of when it will be analyzed.  Some Hadoopers can schedule analytics but most don’t know what they will want until they finish with the last analysis. In these cases, having direct access to all the data on an object store can cut setup time considerably.

There were other aspects of Janae’s session but these seemed of most interest. We spent the debating aspects of object storage rest of the morning getting an overview on Scality customers. At the end of the morning we debating aspects of object storage.  I thought Jean-Luc from Data Direct Networks had the best view of this when he said object storage is at it’s core, data storage that has scalability, resilience, performance and distribution.

The afternoon sessions were deep dives with the sponsors of the Object Summit.

  • Nexsan talked about there Assureon product line (EverTrust acquisition).  SHA1 and MD5 hashes are made of every object then as objects are replicated to other sites, the hashes are both checked to insure the data hasn’t been corrupted and the are  periodically checked (every 90 days) to see if the data is still correct. If it’s corrupted,  other replica’s obtained and re-instated.  In addition, Assureon has some unique immutable access logs that provide an almost “chain of custody” for objects in the system.  Finally, Assureon uses a Microsoft Windows Agent that is Windows Certified and installs without disruption to allow any user (or administrator) to identify files, directories, or file systems to be migrated to the object store.
  • Cleversafe was up next and talked about their market success with their distributed dsNet® object store and provided some proof points. [Full disclosure: I have recently been under contract with Cleversafe]. For instance, today they have under management over 15 billion objects and deployments with over 70PBs in production They have shipped over 170PB of dsNet storage to customers around the world. Cleversafe has many patents covering their information dispersal algorithms and performance optimization.  Some of their sites are in the Federal government installations with a few web intensive clients as well, the most notable being Shutterfly, photo sharing site.  Although dsNet is inherently geographical distributed  all these “sites” could easily be configured over 1 to 3 locations or more for simpler DR-like support.
  • Quantum talked about their Lattus product  built ontop of Amplidata’s technology. Lattus uses 36TB storage nodes, controller nodes to provide erasure coding for geographical data integrity and NAS gateway nodes.  The NAS gateway provides CIFS and NFS to objects. The Latus-C deployment is a forever disk archive for cloud like deployments. This system provides erasure coding for objects in the system which are then dispersed across up to 3 sites (today, with 4 site dispersal under test).  Their roadmap Lattus-M is going to be a managed file system offering that operates in conjunction with their StorNext product with ILMlike policy management. Farther out, on the roadmap is a Lattus-H which offers object repository for Hadoop clusters that can gain rapid access to data for analysis.
  • Scality talked about their success in major multi-tennant environments that need rock-solid reliability and great performance. Their big customers are major web providers that supply email services. Scality is a software product that builds a ring of object storage nodes that supplies the backend storage where the email data is held.  Scality is priced on a per end-user capacity stored. Today the product supports RestFul interfaces, CDMI (think email storage interface), Scality File System (based on FUSE, a POSIX compliant Linux file system). NFS interface is coming early next year.  With the Scality Ring, nodes can go down but the data is still available with rapid response time.  Nodes can be replicated or spread across multiple locations
  • Data Direct Networks (DDN) is coming at the problem from the High Performance Computing market and have an very interesting scaleable solution with extreme performance. DDN products are featured in many academic labs and large web 2.0 environments.  The WOS object storage supports just about any interface you want Java, PHP, Python, RestFULL, NFS/CIFS, S3 and others. They claim very high performance something on the order of 350MB/sec read and 250MB/sec write (I think per node) of object data transfers.  Nodes come in 240TB units and one can have up to 256 nodes in a WOS system.   One customer uses a WOS node to land local sensor streams then ships it to other locations for analysis.
View from the Summit balcony, 2nd day
View from the Summit balcony, 2nd day

The next day was spent with Nexsan and DDN talking about their customer base and some of their success stories. We spent the remainder of the morning talking about the startup world which surrounds some object storage technology and the inhibiters to broader adoption of the technology.

In the end there’s a lot of education needed to jump start this market place. Education about both the customer problems that can be solved with object stores and the product differences that are out there today.  I argued (forcefully) that what’s needed to accelerate adoption was some standard interface protocol that all object storage systems could utilize. Such a standard protocol would enable a more rapid ecosystem build out and ultimately more enterprise adoption.

One key surprise to me was that the problems their customers are seeing is something all IT customers will have some day. Jean-Luc called it the democratization of the HPC problems. Big Data is driving object storage requirements into the enterprise in a big way…

Comments?