[ A short editorial. Happening more and more, we all are seeing remarkable works of fiction these days but seldom stop to appreciate them. It’s good to be able to appreciate these works of fiction so you can avoid the companies that create them. ]
It is hard to beat the Russian absurdist author, Daniil Kharms, he spent a lot of energy creating anti-stories. Many are simply absurd but one in particular strikes me as particularly relevant these days, it is The Tale of the Red-Haired Man. It is an anti-story that resonates with some of the marketing coming out of some companies.
Some of the best works of absurdist fiction these days can be found in marketing literature. Recently, a well-known company advertised their prowess at replacing some unknown hardware, running an unknown application and running with unknown features. They did in a manner that an eight year old could understand. It was comic book marketing. It culminated at the end with some amazing number — their solution as claimed was thousands of times more performant than the decrepit, imaginary or real hardware they replaced. You know, the unknown hardware with the unknown configuration, running the unknown application by an unknown company needing unknown features.
Really, learn to appreciate these works so you can avoid these companies. If they can’t show off their product using a well-written white paper or a video that provides details of a use-case that includes hardware and software specifics as well as what was tested using a detailed configuration and information on the application and workloads.
Everywhere there is this need for speed. One flash array vendor thought that benchmarking a single VM to achieve a million IOPS was particularly useful or interesting. Marginally. However, I found that the real example of speed comes from Fusion IO and it has demonstrated it could deliver 9 million IOPS from a single 365 GB MLC Fusion ioDrive2 card. Watch the video the number is actually 9.6 million IOPS. Unbelievable.
And a quick brief on the use-case :
Here is a nice detailed presentation/talk from youtube on it :
And a presentation on it :
The key aspect beyond the sheer hardware effort is the work done in building programming interfaces via their SDK. By focusing not simply on sheer hardware but also on building useful programming interfaces for software developers, Fusion IO provides the tools to achieve very high IOPS. Many flash companies have focused on hardware – but here Fusion IO shows that a focus on hardware and software and file systems is at the heart of their tremendous performance.
If you couldn’t be there (like me), the second best thing are the videos of the keynote and sessions. Here you go :
In September of last year I made a small prediction that with a slew of new players and many more agile ones competing in the flash storage array area that they would pose a big problem for the leaders at the time. Specifically, I pointed to strong new storage competitors and storage/software features as one of the reasons why things would change. I said – Odds were that the next Gartner Report would look very different from the last one. And it does. You can find the original post at Sea Change : For a Gartner Report on Flash Storage : Last Year was, well, last year.
We have been in the midst of a ‘sea change’ in the area of flash storage and specifically flash storage arrays. Realistically, the 2012 report was highly unusual in that many of the big players had not yet entered into flash storage. It was also unusual because a number of smaller ones were just gaining traction (Kaminario, SolidFire, etc). Gartner has just released the latest flash storage report and in terms marketshare – IBM and Pure Storage have both taken the #1 and 2 spots. EMC and NetApp did reasonably well coming in at #4 and 5th. SolidFire which was not even on the map in 2012 and has done a good job at being close to Cisco and coming in ahead of HP.
Go to more posts on storage and flash storage blogs at http://digitalcld.com/cld/category/storage.
Mary Meeker, a partner at Kleiner Perkins Caufield Byers, and well known for her insights on technology trends delivered her annual information-heavy State of the Internet presentation at the recently concluded Code Conference. You can see the video of her talk and slides at the link:
Here are the slides :
Fusion-io, Dell, and Mellanox have built a very small footprint (16RU), extremely fast, and price-sensitive reference architecture for Oracle RAC 12c. It is very impressive on a number of counts. It further highlights the move to using local flash storage over remote flash storage arrays. This solution aims at reducing hardware sprawl and power consumption by achieving higher performance in a smaller footprint. From the description – “This reference architecture features four Fusion ION Accelerators and four Oracle RAC database nodes all connected through redundant Mellanox SX6036 switches. Each ION Accelerator in this reference architecture uses a Dell PowerEdge R720 with three 56 Gbps Mellanox ConnectX-3 InfiniBand cards and four industry-leading Fusion ioDrive2 2.4TB flash storage devices for a total of 9.6TB of all flash storage. Each of these ION Accelerator units fits in 2 rack units (2RU) and delivers well over 645,000 8K database IOPS and up to 12 GB/s sustained throughput. Data redundancy is maintained across pairs of ION Accelerators using synchronous writes, thus providing system and data high availability. The Oracle RAC nodes consist of Dell PowerEdge R620 servers. Each two-socket server consumes a mere 1U of rack space and yet is capable of pulling 1.4 million 8K IOPS from the ION Accelerator storage layer as measured by the Flexible IO Tester utility. The Oracle RAC nodes are connected to the ION Accelerators through redundant Mellanox switches. Each Oracle RAC node sees the ION Accelerator storage as simple multipath block storage. The multipath devices are aggregated by Oracle ASM to create a large and powerful diskgroup. Expanding the size and performance of the database is as easy as adding more ION Accelerator devices to the ASM disk group.” The links to the article and the Reference Architecture follow.
Increasingly, software vendors see the virtue of putting their flash storage locally on the server. For example, VMware engineers wrote recently that by replacing array shared storage with PCIe flash card storage on the servers they could substantially reduce power consumption and maintain high levels of performance.
Fusion IO has jumped on-board the Microsoft SQL Server 2014 in-memory features and has claimed up to 4x improvements in transaction per second and substantial reduction in data latencies. A nice little Fusion IO video that introduces SQL Server 2014:
Fusion ioMemory integrates into the SQL Server 2014 database engine buffer pool to improve IO throughput. The lower price points of the PCIe flash card products will no doubt put pressure on flash arrays.
Fusion IO has written a nice white paper detailing how their cards accelerate SQL Server 2014 by leveraging the new In-Memory features. Using their ioDrive2 Duo cards they substantially accelerated the performance, latency of transactions.
The performance brief shows an increase of 4.4 x more transaction with the ioDrive2 Duo 2.4TB versus an enterprise class disk array. It also shows that it delivers better latency – serving customers up to 73% faster and delivers 3.3x faster database startup times.
Here is a SQL Server 2014 In-Memory OLTP Overview :
The presentations from the O’Reilly Velocity 2013 Conference are available in video format. If you don’t what this conference is about :
- Three days of concentrated focus on key aspects of web performance, operations and mobile performance.
- Keynotes, tutorials and sessions
- Experts, visionaries and industry leaders converge along with hundreds of web developers, sys admins and other web professionals all under one roof.
The slides :
In addition – a recent post on immutable servers :
Fast performance is one aspect – but when you couple to a suite of data reduction technologies and storage features you get something much more useful and resilient. Some of the features in the latest arrays from Nimbus Data are well thought out and absolutely great from and enterprise and cloud perspective.
Nimbus Data has really arrived. Its new Gemini arrays challenges it’s competitors in a serious way. It has hopped over the leading flash array competitor by offering full non-disruptive upgrades coupled with full array redundancy, hot-swap-everything, in-line data reduction in the form of thin-provisioning, replication, deduplication and compression and NFS and CIFS. The amazing thing is that those are just the tip of the iceberg. A deep dive video really reveals an excellent design and some surprisingly great advancements to flash array technology in general :
It has also demonstrated something that many other leading flash vendors have not been able to do. It leverages eight 16 Gbs FC ports in its Nimbus Gemini arrays. It also offers two hot-swappable controllers. They have advanced the multi-protocol capability of the product by offering the ability to run 40 Gb ethernet and Infiniband at the the same time or alternatively ethernet and fiber channel at the same time. They have adapters that can run at 10 Gb ethernet. The controllers parallelize the IO across all 24 flash drives. The modules can be removed from the front – a great design for removing the flash modules (most excellent – no removing the array out of the rack, taking the top off and potentially having servicing dilemmas like some vendors).
In a new benchmark they demonstrated the strength of the new arrays at handling VDI. The benchmark was run with a Nimbus Gemini dual-controller 2U F400 all-flash array with 24 TB of raw capacity.
Data Point : The single array had 17.6 TB usable capacity for the test, and featured 24 one terabyte solid-state disks and a 4 TB cache with write-back caching. A single Nimbus Gemini F400 can support more than 4,000 simultaneous VDI users at less than $40 per desktop.
You can read the full report :
The focus on a unified array operating system (more on this in a future post) that offers a full range of storage features that I have written about in earlier posts is an important aspect of the new arrays.
Go to more posts on storage and flash storage at http://digitalcld.com/cld/category/storage.
If you look up ‘sea change’ you will find that it is a profound and notable transformation. We are in the midst of a sea change with regards to storage. There are two aspects to this change. One is simple – the move to flash storage from spinning disks and the second has to do with the players involved and the perpetual game of who is in first place.
If you haven’t noticed, PC vendors have been replacing spinning disks with SSDs. This has been happening for awhile and users for the most part really like it. The hint there, is that they like it because they like the performance. The only downside has been the capacity. Laptop vendors have been usually replacing the spinning disks with lower capacity SSDs, and this should be the second hint. SSDs have had higher costs and cost more per GB.
Let’s step over to what has been happening in enterprise storage. Last year – there was no real HDS, EMC, NetApp or Skyera all-flash array. So it was surprising to me that when a Gartner report came out that tagged EMC as #2 in the flash array market – it was to put it mildly, quite an accomplishment. EMC had only their XtremSW Cache product in 2012. Now, since March 5 of this year, EMC has executed a product revolution which has seen a whole family of new flash-based products that were announced. Hitachi has also joined in with a speedy all-flash array. NetApp also brought out an all-flash array in mid-February of this year. Skyera launched skyHawk this year and pre-announced what could be a game-changing array dubbed skyEagle. There are others that launched new all-flash storage systems – SolidFire delivering 3.4 PB SSD-based storage system aimed at the Cloud. Nimbus Data has recently delivered 48TB in 2U, it is a new and extremely well-engineered array that is fully redundant, has non-disruptive upgrades, has a full set of storage features such as de-duplication, compression, thin provisioning and replication. The list continues. In the process, whereas last year’s discussion was about IOPS and low latency characteristics, the arrival of many flash storage arrays that provide those benefits has moved the discussion to one of storage features and software-define storage. In any case, all the major storage vendors have bolted toward flash and a number of new flash storage array vendors have arrived. All of this describes the first sea change. Traditional spinning disk vendors moving toward flash and more generally storage itself moving toward flash. However, it also describes a second sea change – whoever was in the market last year faces a large armada of new all-flash competitors. Some of them are the giants – EMC, NetApp and Hitachi. Some of them are smaller but extremely agile and are producing complete flash products with storage features and compelling price-performance advantages.
Odds are the next Gartner Report will look very different from the last one.
Go to more posts on storage and flash storage blogs at http://digitalcld.com/cld/category/storage.