Tag: EMLC

Posted on

Part II: EMC announces XtremIO General Availability, speeds and feeds

Storage I/O trends

XtremIO flash SSD more than storage I/O speed

Following up part I of this two-part series, here are more more details, insights and perspectives about EMC XtremIO and it’s generally availability that were announced today.

XtremIO the basics

  • All flash Solid State Device (SSD) based solution
  • Cluster of up to four X-Brick nodes today
  • X-Bricks available in 10TB increments today, 20TB in January 2014
  • 25 eMLC SSD drives per X-Brick with redundant dual processor controllers
  • Provides server-side iSCSI and Fibre Channel block attachment
  • Integrated data footprint reduction (DFR) including global dedupe and thin provisioning
  • Designed for extending duty cycle, minimizing wear of SSD
  • Removes need for dedicated hot spare drives
  • Capable of sustained performance and availability with multiple drive failure
  • Only unique data blocks are saved, others tracked via in-memory meta data pointers
  • Reduces overhead of data protection vs. traditional small RAID 5 or RAID 6 configurations
  • Eliminates overhead of back-end functions performance impact on applications
  • Deterministic  storage I/O performance (IOPs, latency, bandwidth) over life of system

When would you use XtremIO vs. another storage system?

If you need all enterprise like data services including thin provisioning, dedupe, resiliency with deterministic performance on an all-flash system with raw capacity from 10-40TB (today) then XtremIO could be a good fit. On the other hand, if you need a mix of SSD based storage I/O performance (IOPS, latency or bandwidth) along with some HDD based space capacity, then a hybrid or traditional storage system could be the solution. Then there are hybrid scenarios where a hybrid storage system, array or appliance (mix of SSD and HDD) are used for most of the applications and data, with an XtremIO handling more tasks that are demanding.

How does XtremIO compare to others?

EMC with XtremIO is taking a different approach than some of their competitors whose model is to compare their faster flash-based solutions vs. traditional mid-market and enterprise arrays, appliances or storage systems on a storage I/O IOP performance basis. With XtremIO there is improved performance measured in IOPs or database transactions among other metrics that matter. However there is also an emphasis on consistent, predictable, quality of service (QoS) or what is known as deterministic storage I/O performance basis. This means both higher IOPs with lower latency while doing normal workload along with background data services (snapshots, data footprint reduction, etc).

Some of the competitors focus on how many IOPs or work they can do, however without context or showing impact to applications when back-ground tasks or other data services are in use. Other differences include how cluster nodes are interconnected (for scale out solutions) such as use of Ethernet and IP-based networks vs dedicated InfiniBand or PCIe fabrics. Host server attachment will also differ as some are only iSCSI or Fibre Channel block, or NAS file, or give a mix of different protocols and interfaces.

An industry trend however is to expand beyond the flash SSD need for speed focus by adding context along with QoS, deterministic behavior and addition of data services including snapshots, local and remote replication, multi-tenancy, metering and metrics, security among other items.

Storage I/O trends

Who or what are XtremIO competition?

To some degree vendors who only have PCIe flash SSD cards might place themselves as the alternative to all SSD or hybrid mixed SSD and HDD based solutions. FusionIO used to take that approach until they acquired NexGen (a storage system) and now have taken a broader more solution balanced approach of use the applicable tool for the task or application at hand.

Other competitors include the all SSD based storage arrays, systems or appliance vendors which includes legacy existing as well as startups vendors that include among others IBM who bought TMS (flashsystems), NetApp (EF540), Solidfire, Pure, Violin (who did a recent IPO) and Whiptail (bought by Cisco).  Then there are the hybrid which is a long list including Cloudbyte (software), Dell, EMCs other products, HDS, HP, IBM, NetApp, Nexenta (Software), Nimble, Nutanix, Oracle, Simplivity and Tintri among others.

What’s new with this XtremIO announcement

10TB X-Bricks enable 10 to 40TB (physical space capacity) per cluster (available on 11/19/13). 20TB X-Bricks (larger capacity drives) will double the space capacity in January 2014. If you are doing the math, that means either a single brick (dual controller) system, or up to four bricks (nodes, each with dual controllers) configurations. Common across all system configurations are data features such as thin provisioning, inline data footprint reduction (e.g. dedupe) and XtremIO Data Protection (XDP).

What does XtremIO look like?

XtremIO consists of up to four nodes (today) based on what EMC calls X-Bricks.
EMC XtremIO X-Brick
25 SSD drive X-Brick

Each 4U X-Brick has 25 eMLC SSD drives in a standard EMC 2U DAE (disk enclosure) like those used with the VNX and VMAX for SSD and Hard Disk Drives (HDD). In addition to the 2U drive shelve, there are a pair of 1U storage processors (e.g. controllers) that give redundancy and shared access to the storage shelve.

XtremIO Architecture
XtremIO X-Brick block diagram

XtremIO storage processors (controllers) and drive shelve block diagram. Each X-Brick and their storage processors or controllers communicate with each other and other X-Bricks via a dedicated InfiniBand using Remote Direct Memory Access (RDMA) fabric for memory to memory data transfers. The controllers or storage processors (two per X-Brick) each have dual processors with eight cores for compute, along with 256GB of DRAM memory. Part of each controllers DRAM memory is set aside as a mirror its partner or peer and vise versa with access being over the InfiniBand fabric.

XtremIO fabric
XtremIO X-Brick four node fabric cluster or instance

How XtremIO works

Servers access XtremIO X-Bricks using iSCSI and Fibre Channel for block access. A responding X-Brick node handles the storage I/O request and in the case of a write updates other nodes. In the case of a write, the handling node or controller (aka storage processor) checks its meta data map in memory to see if the data is new and unique. If so, the data gets saved to SSD along with meta data information updated across all nodes. Note that data gets ingested and chunked or sharded into 4KB blocks. So for example if a 32KB storage I/O request from the server arrives, that is broken (e.g. chunk or shard) into 8 4KB pieces each with a mathematical unique fingerprint created. This fingerprint is compared to what is known in the in memory meta data tables (this is a hexadecimal number compare so a quick operation). Based on the comparisons if unique the data is saved and pointers created, if already exists, then pointers are updated.

In addition to determining if unique data, the fingerprint is also used for generate a balanced data dispersal plan across the nodes and SSD devices. Thus there is the benefit of reducing duplicate data during ingestion, while also reducing back-end IOs within the XtremIO storage system. Another byproduct is the reduction in time spent on garbage collection or other background tasks commonly associated with SSD and other storage systems.

Meta data is kept in memory with a persistent copied written to reserved area on the flash SSD drives (think of as a vault area) to support and keep system state and consistency. In between data consistency points the meta data is kept in a log journal like how a database handles log writes. What’s different from a typical database is that XtremIO XIOS platform software does these consistency point writes for persistence on a granularity of seconds vs. hours or minutes.

Storage I/O trends

What about rumor that XtremIO can only do 4KB IOPs?

Does this mean that the smallest storage I/O or IOP that XtremIO can do is 4GB?

That is a rumor or some fud I have heard floated by a competitor (or two or three) that assumes if only 4KB internal chunk or shard being used for processing, that must mean no IOPs smaller than 4KB from a server.

XtremIO can do storage I/O IOP sizes of 512 bytes (e.g. the standard block size) as do other systems. Note that the standard server storage I/O block or IO size is 512 bytes or multiples of that unless the new 4KB advanced format (AF) block size being used which based on my conversations with EMC, AF is not supported, yet. (Updated 11/15/13 EMC has indicated that host (front-end) 4K AF support, along with 512 byte emulation modes are available now with XIOS). Also keep in mind that since XtremIO XIOS internally is working with 4KB chunks or shards, that is a stepping stone for being able to eventually leverage back-end AF drive support in the future should EMC decide to do so (Updated 11/15/13 Waiting for confirmation from EMC about if back-end AF support is now enabled or not, will give more clarity as it is recieved).

What else is EMC doing with XtremIO?

  • VCE Vblock XtremIO systems for SAP HANA (and other databases) in memory databases along with VDI optimized solutions.
  • VPLEX and XtremIO for extended distance local, metro and wide area HA, BC and DR.
  • EMC PowerPath XtremIO storage I/O path optimization and resiliency.
  • Secure Remote Support (aka phone home) and auto support integration.

Boosting your available software license minutes (ASLM) with SSD

Another use of SSD has been in the past the opportunity to make better use of servers stretching their usefulness or delaying purchase of new ones by improving their effective use to do more work. In the past this technique of using SSDs to delay a server or CPU upgrade was used when systems when hardware was more expensive, or during the dot com bubble to fill surge demand gaps.  This has the added benefit of stretching database and other expensive software licenses to go further or do more work. The less time servers spend waiting for IOP’s means more time for doing useful work and bringing value of the software license. Otoh, the more time spent waiting is lot available software minutes which is cost overhead.

Think of available software licence minutes (ASLM) in terms of available software license minutes where if doing useful work your software is providing value. On the other hand if those minutes are not used for useful work (e.g. spent waiting or lost due to CPU or server or IO wait, then they are lost). This is like airlines and available seat miles (ASM) metric where if left empty it’s a lost opportunity, however if used, then value, not to mention if yield management applied to price that seat differently. To make up for that loss many organizations have to add extra servers and thus more software licensing costs.

Storage I/O trends

Can we get a side of context with them metrics?

EMC along with some other vendors are starting to give more context with their storage I/O performance metrics that matter than simple IOP’s or Hero Marketing Metrics. However context extends beyond performance to also availability and space capacity which means data protection overhead. As an example, EMC claims 25% for RAID 5 and 20% for RAID 6 or 30% for RAID 5/RAID 6 combo where a 25 drive (SSD) XDP has a 8% overhead. However this assumes a 4+1 (5 drive) RAID , not apples to apples comparison on a space overhead basis. For example a 25 drive RAID 5 (24+1) would have around an 4% parity protection space overhead or a RAID 6 (23+2) about 8%.

Granted while the space protection overhead might be more apples to apples with the earlier examples to XDP, there are other differences. For example solutions such as XDP can be more tolerant to multiple drive failures with faster rebuilds than some of the standard or basic RAID implementations. Thus more context and clarity would be helpful.

StorageIO would like see vendors including EMC along with startups who give data protection space overhead comparisons without context to do so (and applaud those who provide context). This means providing the context for data protection space overhead comparisons similar to performance metrics that matter. For example simply state with an asterisk or footnote comparing a 4+1 RAID 5 vs. a 25 drive erasure or forward error correction or dispersal or XDP or wide stripe RAID for that matter (e.g. can we get a side of context). Note this is in no way unique to EMC and in fact quite common with many of the smaller startups as well as established vendors.

General comments

My laundry list of items which for now would be nice to have’s, however for you might be need to have would include native replication (today leverages Recover Point), Advanced Format (4KB) support for servers (Updated 11/15/13 Per above, EMC has confirmed that host/server-side (front-end) AF along with 512 byte emulation modes exist today), as well as SSD based drives, DIF (Data Integrity Feature), and Microsoft ODX among others. While 12Gb SAS server to X-Brick attachment for small in the cabinet connectivity might be nice for some, more practical on a go forward basis would be 40GbE support.

Now let us see what EMC does with XtremIO and how it competes in the market. One indicator to watch in the industry and market of the impact or presence of EMC XtremIO is the amount of fud and mud that will be tossed around. Perhaps time to make a big bowl of popcorn, sit back and enjoy the show…

Ok, nuff said (for now).

Cheers
Gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved

Posted on

EMC announces XtremIO General Availability (Part I)

Storage I/O trends

EMC announces XtremIO flash SSD General Availability

EMC announced today the general availability (GA) if the all flash Solid State Device (SSD) XtremIO that they acquired a little over a year ago. Earlier this year EMC announced directed availability (DA) of the EMC version of XtremIO as part of other SSD hardware and software updates (here and here). The XtremIO GA announcement also follows that of the VNX2 or MCx released in September of this year that also has flash SSD enhancements along with doing more with available resources.

EMC XtremIO flash SSD boosting storage I/O performance

As an industry trend, the question is not if SSD is in your future, rather where, when, how much, what to use along with coexistence to complement Hard Disk Drive (HDD) based solutions in some environments. This also means that SSD is like real estate where location matters, not to mention having different types of technologies, packaging, solutions to meet various needs (and price points). This all ties back to the best server and storage I/O or IOP is the one that you do know have to do, the second best is the one with the least impact and best application benefit.

From industry adoption to customer deployment

EMC has evolved the XtremIO platform from a pre-acquisition solution to an first EMC version that was offered to an early set of customers e.g. DA.

I suspect that the DA was as much a focus on getting early customer feedback, addressing immediate needs or opportunities as wells as getting the EMC sales and marketing teams messaging, marching orders aligned and deployed. The latter would be rather important to decrease or avoid the temptation to cannibalize existing product sales with the shiny new technology (SNT). Likewise, it would be important for EMC to not create isolated pockets or fenced off products as some other vendors often do.

EMC XtremIO X-Brick
25 SSD drive X-Brick

What is being announced?

  • General availability vs. directed or limited availability
  • Version 2.2 of the XIOS platform software
  • Integrating with EMC support and service tools

Let us get back go this announcement and XtremIO of which EMC has indicated that they have several customers who have now done either $1M or $5M USD deals. EMC has claimed over 1.5 PBytes have been booked and deployed, or with data footprint reduction (DFR) including dedupe over 10PB effective capacity. Note that for those who are focused on dedupe or DFR reduction ratios 10:1.5 may not be as impressive as seen with some backup solutions, however keep in mind that this is for primary high performance storage vs. secondary or tertiary storage devices.

As part of this announcement, EMC has also release V2.2 of the XtremIO platform software (XIOS). Hence a normal new product should start with a version 1.0 at launch, however as explained this is both a new version of the technology as well as the initial GA by EMC.

Also as part of this announcement, EMC is making available XtremIO 10TB X-Bricks with 25 eMLC SSD drives each, along with dual controllers (storage processors). EMC has indicated that it will make available a 20TB X-Brick using larger capacity SSD drives in January 2014. Note that the same type of SSD drives must be used in the systems. Currently there can be up to four X-Bricks per XtremIO cluster or instance that are interconnected using a dedicated InfiniBand Fabric. Application servers access the XtremIO X-Bricks using standard Fibre Channel or Ethernet and IP based iSCSI. In addition to the hardware platform items, the XtremIO platform software (XIOS) includes built-in on the fly data footprint reduction (DFR) using global dedupe during data ingestion and placement. Other features include thin provisioning, VMware VAII, data protection and self-balancing data placement.

Storage I/O trends

Who or what applications are XtremIO being positioned for?

Some of XtremIO industry sectors include:

  • Financial and insurance services
  • Medical, healthcare and life sciences
  • Manufacturing, retail and warehouse management
  • Government and defense
  • Media and entertainment

Application and workload focus:

  • VDI including replacing linked clones with ability to do full clone without overhead
  • Server virtualization where aggregation causes aggravation with many mixed IOPs
  • Database for reducing latency, boosting IOPs as well as improving software license costs.

Databases such as IBM DB2, Oracle RAC, Microsoft SQLserver and MySQL among others have traditionally for decades been a prime opportunity for SSD (DRAM and flash). This also includes newer NoSQL or key value stores and meta data repositories for object such as Mongo, Hbase, Cassandra, Riak among others. Typical focus includes placing entire instances, or specific files and objects such as indices, journals and redo logs, import/export temp or scratch space, message queries and high activity tables among others.

What about overlap with other EMC products?

If you simply looked at the above list of sectors (among others) or applications, you could easily come to a conclusion that there is or would be overlap. Granted in some environments there will be which means XtremIO (or other vendors solutions) may be the primary storage solution. On the other hand since everything is not the same in most data centers or information factories, there will be a mix of storage systems handling various tasks. This is where EMC will need to be careful learning what they did during DA on where to place XtremIO and how to positing to complement when and where needed other solutions, or as applicable being a replacement.

XtremIO Announcement Summary

  • All flash SSD storage solution with iSCSI and Fibre Channel server attachment
  • Scale out and scale up performance while keeping latency low and deterministic
  • Enhanced flash duty cycle (wear leveling) to increase program / erase (P/E) cycles durability
  • Can complement other storage systems, arrays or appliances or function as a standalone
  • Coexists and complements host side caching hardware and software
  • Inline always on data footprint reduction (DFR) including dedupe (global dedupe without performance compromise), space saving snapshots and copies along with thin provisioning

Storage I/O trends

Some General Comment and Perspectives

Overall, XtremIO gives EMC and their customers, partners and prospects a new technology to use and add to their toolbox for addressing various challenges. SSD is in your future, when, where, with what and how are questions not to mention how much. After all, a bit of flash SSD in the right location used effectively can have a large impact. On the other hand, a lot of flash SSD in the wrong place or not used effectively will cost you lots of cash. Key for EMC and their partners will be to articulate clearly, where XtremIO fits vs. other solutions without adding complexity.

Checkout part II of this series to learn more about XtremIO including what it is, how it works, competition and added perspectives.

Ok, nuff said (for now).

Cheers
Gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved

Posted on

Can RAID extend the life of nand flash SSD?

Storage I/O trends

Can RAID extend nand flash SSD life?

Imho, the short answer is YES, under some circumstances.

There is a myth and some FUD that RAID (Redundant Array of Independent Disks) can shorten the life durability of nand flash SSD (Solid State Device) vs. HDD (Hard Disk Drives) due to extra IOP’s. The reality is that depending on how configured, RAID level, implementation and other factors, nand flash SSD can be extended as I discuss in this here video.

Video

Nand flash SSD cells and wear

First, there is a myth that nand flash SSD does not have moving parts like hard disk drives (HDD’s) thus do not wear out or break. That is just a myth in that nand flash by its nature wears out with write usage. This is due to how they store data in cells that have a rated number of program erase (P/E) cycles that vary by type of medium. For example, Single Level Cell (SLC) has a longer P/E life duration vs. Multi-Level Cells (MLC) and eMLC that stack multiple cells together.

There are a number of factors that contribute to nand flash wear, also known as duty cycle or durability tied to P/E. For example, some storage systems or controllers do a better job both at the lower level flash translation layer (FTL) in addition to controllers, firmware, caching using DRAM and IO optimization such as write ordering or grouping.

Now what about this RAID and SSD thing?

Ok first as a recap keep in mind that there are many RAID levels along with variations, enhancements and where, or how implemented ranging from software to hardware, adapters to controllers to storage systems.

In the case of RAID 1 or mirroring, just like replication or other one to one or one too many copy operation a write to one device is echoed to another. In the case of RAID 5, data is spread across drives and parity; however, the parity is rotated across all drives in an equal manner.

Some FUD or myths or misunderstandings come into play is that not all RAID 5 implementations as an example are not the same. Some do a better job of buffering or caching data in battery protected mirrored DRAM memory until a full stripe write can occur, or if needed, a partial write.

Another attribute is the chunk or shard size (how much data is sent to each drive member) along with the stripe width (how many drives). Some systems have narrow stripes of say 3+1 or 4+1 or 5+1 while others can be 14+1 or 15+1 or wider. Thus, data can be written across a wider number of drives reducing the P/E consumption or use of a single drive depending on implementation.

How about RAID 6 (dual parity)?

Same thing, it is a matter of how well the implementation is, how the write gathering is done and so forth.

What about RAID wearing out nand flash SSD?

While it is possible that it has or can occur depending on type of RAID implementation, lack of caching or optimization, configuration, type of SSD, RAID level and other things, in general I will say myth busted.

Want some proof?

I could go through a long technical proof point and citing lots of facts, figures, experts and so forth leaving you all silenced and dazed similar to the students listening to Ben Stein in Ferris Buelers day off (Click here to see what I mean) asking “anybody anybody Buleler?

Ben Stein via https://nostagjicmoviesandthings.blogspot.com
Image via nostagjicmoviesandthings.blogspot.com

How about some simple SSD and storage math?

On a very conservative basis, my estimate is that around 250PB of nand flash SSD drives are shipped and installed on a revenue basis attached to or in storage systems and appliances. Combine what Dell + DotHill + EMC + Fujitsu + HDS + HP + IBM (including TMS) + NEC + NetApp + NEC + Oracle among other legacy along with new all flash as well as hybrid vendors (e.g. Cloudbyte, FusionIO (Via their Nexgen acquisition), Kaminario, Greenbytes, Nutanix or Nimble, Purestorage, Starboard or Solidfire, Tegile or Tintri, Violin or Whiptail among others).

It is also a safe assumption based on how customers configure and use those and other storage systems is with some form of RAID. Thus if things were as bad as some researchers were, vendors and their pundits have made them out to be, wouldn’t’t we be hearing of those issues?

Is it just a RAID 5 problem and that RAID 6 magically corrects the problem?

Well, that depends on apples to apples vs. apples to oranges comparisons.

For example if you are using a 14+2 (16 drive) RAID 6 to compare to say a 3+1 (4 drive) RAID 5 that is not a fair comparison. Granted, it is a handy one if you are a vendor that supports wider RAID groups, stripes and ranks vs. those who do not. However also keep in mind that some legacy vendors actually also support wide stripes and RAID groups.

So in some cases the magic is not in the RAID level, rather the implementation or how configured or lack thereof.

Video

Watch this TechTarget produced video recorded live while I was at EMCworld 2013 to learn more.

Otherwise, ok, nuff said (for now).

Cheers
Gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved

Posted on

Part II: XtremIO, XtremSW and XtremSF EMC flash ssd portfolio redefined

Part one of this two-part post provided a summary of today’s EMC (@EMCflash) announcement around XtremIO and renaming VFCache to XtremSF and associated software as XtremSW.

Storage I/O industry trends and perspectives

Synopsis of announcement

  • Product rollout and selective availability of the new all flash SSD array XtremIO
  • Rename server-side PCIe ssd flash cards from VFCache to XtremSF
  • New XtremSF models including enhanced multi-level cell (eMLC) with larger capacities
  • Rename VFCache caching software to XtremSW (enables cache mode vs. target mode)

Now lets take a closer look at what was announced along with what it means in terms of Industry Trends and Perspectives.

XtremIO  has been in customer beta for some time and now those along with some other early customers are able to acquire the product. In addition, EMC is opening up XtremIO to more prospective customers (Directed Availability) who have requirements or needs that line up with the products target market capabilities.

Storage I/O industry trends and perspectives

What this means is that XtremIO is not being simply put out into the general product population for broad distribution. Instead, it is being put into a controlled release (Directed Availability) to help customers, partners and EMC sales decide where best to use it and thus risk revenue prevention in other areas. The criteria or target opportunity (at least initially) are little-data applications including OLTP, server virtualization (where aggregation can cause aggravation) along with virtual desktop or VDI. In other words, many of the traditional or legacy IOP focused SSD opportunities.

In addition to XtremIO EMC has renamed their VFCache PCIe flash SSD cards (Launched February 2012) to XtremSF along with new models with both SLC and MLC nand flash. Also as part of today’s announcement EMC is renaming the cache software for XtremSF (e.g. VFCache) to be known as XtremSW. Now if that did not prompt the question of if you can now buy XtremSF as a target mode only card without the cache software the answer is yes.

What is XtremIO?

It is a new all flash SSD storage array. XtremIO is a Cluster, grid or collection of nodes called bricks with linear performance scaling providing block based all flash SSD storage. Data services consists of data footprint reduction (DFR) including inline global (across all nodes or bricks) dedupe on 4Kbyte chunks along with thin provisioning. Global dedupe is done on ingest using a combination of flash buffered meta-data (tables, index or dictionary) of what has been seen before along with multi-threaded software to leverage multi-core processors. Using the global dedupe at ingest; only new unique data is saved based on 4 Kbyte chunks.

Performance per EMC scales from one single node to more second node or a fourth node. Note: architecturally more nodes can be added with EMC indicating added models will be available in the future.

In addition to DFR, other data services including writable snapshots, and auto-load balancing when new bricks are added. Note that in a normal running XtremIO, data is automatically spread across the nodes for both performance and resiliency. Data only needs to be moved or load-balanced in the background when new bricks are added. Instant copy snapshots are supported along with writable snapshots. Currently replication is done via external EMC products such as VPLEX or RecoverPoint with statement of directions (SOD) for future enhancements.

Additional attributes of XtremIO include:

  • Each node or brick (X-Brick) has up to 16 (16 was Gen 1 hardware platform, it is now 25 SSD drives)
  • All bricks are involved in IO and storage processing
  • Positioned by EMC as Software Defined (no proprietary hardware)
  • Four x 8Gb Fibre Channel (8GFC) and four x 10Gb Ethernet (iSCSI) per brick
  • Bricks communicate with each other via a separate interconnect network or fabric
  • Bricks have redundant processors (think of as controllers) with multiple sockets and cores
  • 4KB random read IOP’s scale from 250K (one brick), 500K (two bricks) and 1 Million (four bricks). For 4K random write IOPS, the numbers are 100K, 200K and 400K across one, two and four brick configurations with low latency and all data services running (EMC supplied numbers)

In addition to 4K being a commonly used or referred to IO size, it is also the same size as the new industry standard Advanced Format (AF). Today the standard storage block, page or sector size is 512 bytes however AF moves that to a larger 4,096 bytes (e.g. 4KB) to closer align with larger IO sizes. Note that many HDD’s and some SSD’s today support AF and provide 512 byte emulation modes for compatibility.

What is XtremSF?

VFCache is renamed XtremSF with new models using eMLC as companion to existing SLC PCIe  cards and blade server mezzanine cards. EMC is emphasizing performance metrics that matter including IOPs that are relative to customer workloads such as 4K, 8K or larger with mix of reads and writes with low latency. In addition to IOPs with latency, size along with reads or writes for little data, EMC is also showing bandwidth or throughput numbers for big-data and big-bandwidth.

Model
Capacity
Read Transfer GB/sec
Write Transfer GB/sec
Random 4K Read (IOPS)
Random 4K Write (IOPS)

Random 4K Mixed ( IOPS)

Read latency (usec)
Write latency (usec)
2200 (eMLC)
2.2 TB
2.47
1.1
343K
105K
206K
87us
30us
700 (SLC)
700 GB
2.9
1.8
712K
197K
411K
50us
13us
550 (eMLC)
550 GB
1.36
512 MB/s
174K
49K
96K
87us
37us
350 (SLC)
350 GB
2.9
756 MB/s
715K
95K
267K
50us
13us

Sampling of SLC and eMLC XtremSF PCIe SSD cards performance characteristics (via EMC) including latency measured in microseconds). Note performance differences due to some cards being based on SLC and others on eMLC.

Additional attributes, some new and some previously announced include:

  • 8X  PCIe bandwidth lanes for performance
  • No IO impact to applications during garbage collection
  • Supports multi-core processor workloads with parallel design
  • Low CPU overhead by off-loading functions to PCIe card
  • Half-height, half-length PCIe form factor
  • Wear-leveling for nand flash program/erase (P/E) cycle duration
Other storage, server and systems vendors including Cisco, Dell, HP, IBM, NetApp and Oracle offer various PCIe nand flash SSD cards either as target, cache or mixed modes. Manufactures or suppliers of PCIe nand flash SSD cache and target cards include among others FusionIO, Intel, LSI, Micron , OCZ and Virident (who is partnered with Seagate).

What is XtremSW?

Server side flash software (not to be confused with FAST) for using XtremSF as a tier 0 (server-side) ssd cache or target. In target mode the XtremSF functions as a high performance persistent local dedicated direct attached storage (DAS) device. Cache mode enables frequently accessed data to be kept close to the applications off-loading underlying storage systems to be more effectively used. The XtremSW complements back-end storage systems for data protection and persistence along with investment protection of those assets.

Storage I/O industry trends and perspectives

What this all means

SSD is in your future, question is where, when and with what.

Why not just use SSD (DRAM and or nand flash) everywhere?

Keep in mind that in the data center (traditional, virtual or cloud) everything is not the same. Thus the simple answer is that there is not enough of it available at a low enough price point (think closer to Hard Disk Drives (HDD) costs) to fit into customers budget. Sure SSDs provide better performance and productivity benefits, however while there is no such thing as a data or information recession, there are budget constraints.

Another reason why SSD cant simply be used everywhere are physical (and logical) constraints such as amount of memory a server can directly access, or current DDR3 DIMMs (this could change with DDR4 according to Micron) can only address and work with DRAM, PCIe bus physical slot space, operating and hypervisor addressing limits among others.

If SSD (DRAM and or nand flash) were priced were priced low enough (e.g. much closer to HDDs) and available SSD including both DRAM and nand flash (SLC, MLC, eMLC, TLC, etc) along with emerging Phase Change Memory (PCM) are at the convergence of traditional memory and data storage. While some storage (or server) professionals may not agree, storage is an extension of memory and thus part of the traditional server and storage memory hierarchy shown below.

Storage I/O and cache locality of reference

This brings up the locality of reference topic also shown in the following figure where the best IO is the one that does not have to be done. The second best is the one that can be done closest to application to a given level of service. Locality of reference which is important for servers and storage systems including caching refers to how close frequently accessed data is to where it is needed. For some applications this means as much DRAM main memory in a server as possible either clustered, with battery backup or other data persistency protection including onboard HDD or SSD (e.g. towards the top of the hierarchy).

nand flash SSD and storage I/O location options

There are other applications where localized SSD (DRAM or nand flash) are a benefit to compliment main memory or as a persistent cache and target such as PCIe cards or SAS and SATA drives. Further down the stack and for housing larger amounts of storage with performance (reads or writes, random or sequential) along with data services is where all SSD and hybrid (mix of SSD and HDD) fit. Even further down the stack and for a broader segment is where cloud storage services based on SSD such as those from Rackspace (Cloud Block Storage with SSD) and Amazon (provisioned IOPS for EBS) have a play. Lets not forget about SSD in laptop, tablets and workstations, for example I have a Samsung model 830 in my Lenvo X1.

Storage I/O industry trends and perspectives

Some general industry trends include:

  • SSD is like real estate, location can matter, a little can go a long way
  • SSD media options include DRAM and nand flash (SLC, MLC, eMLC, TLC)
  • Portfolios broadening with different products for various needs
  • SSD functionality in servers, appliances, storage systems and cloud services
  • All flash SSD arrays have not killed off all traditional or hybrid storage arrays
  • Focus expanding from Just a Bunch Of SSD (JBOS) to enterprise like functionality
  • Software needs hardware, hardware needs software, the two work better together
  • Comparing meaningful metrics that matter vs. industry marketing metrics

Related items about nand flash, SSD and metrics related themes:

Storage I/O industry trends and perspectives

Some additional thoughts and perspectives

Does this mean traditional storage arrays are now dead?

IMHO, no, there will be some cannibalization of existing storage systems by XtremIO within EMC customers or prospects if not managed, as well as via those from others. Keep in mind that recently EMC announced enhancements to their VMAX including entry-level options for service providers. Some new opportunities opened up will be where traditional all SSD (flash or dram) systems have historically had success.

Traditional SSD and new dedicated SSD systems include Texas Memory Systems (TMS) bought by IBM in 2012, and the recently announced NetApp EF540 (and future FlashRay) along with startups Solidfire, Violin, Whiptail among others. There will be environments where XtremIO may take care of all storage needs for a customer or specific application or piece of it. Then there will be other situations where XtremIO will go-exist with EMC or other vendor’s storage solutions as part of a data infrastructure.

Storage I/O industry trends and perspectives

Who will EMC be competing against with XtremIO?

Certainly the startups or smaller players such as Violin, Whiptail, Purestorage, Solidfire along with IBM/TMS and NetApp EF540 (eventually FlashRay as well) among others.

There will also be some competition with other hybrid storage array vendors that have a mix of HDD and SSD. XtremIO will also compete in some situations on its own vs. other PCIe flash target and cache cards such as FusionIO, however for the most part those will up against XtremSF and XtremSW.

Why the slow or “Directed Availability” rollout?

Why not? By taking a controlled rollout selecting and qualifying customers for XtremIO, EMC gets to manage how the product goes out into production and control how it is used to increase chances of success. Unlike a startup that would be forced to try to put their new technology anywhere, EMC has the luxury of selecting where it goes, not to mention needing to avoid introducing a revenue prevention play for its other products.

Overall, I give an Atta boy and Atta girl to the EMC crew for a Product Defined Announcement (PDA) extending their flash portfolio to complement their different customers and prospects various environment needs. Now watch EMC, NetApp and others step up their flash dance moves to see who will out flash the others in the eXtreme flash games, not to mention emerging software defined marketing moves (SDMM) ;) .

Ok, nuff said.

Cheers Gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved

Posted on

EMC VMAX 10K, looks like high-end storage systems are still alive (part II)

StorageIO industry trends cloud, virtualization and big data

This is the second in a multi-part series of posts (read first post here) looking at if large enterprise and legacy storage systems are dead, along with what todays EMC VMAX 10K updates mean.

Thus on January 14 2013 it is time for a new EMC Virtual Matrix (VMAX) model 10,000 (10K) storage system. EMC has been promoting their January 14 live virtual event for a while now. January significance is that is when (along with May or June) is when many new systems, solutions or upgrades are made on a staggered basis.

Historically speaking, January and February, along with May and June is when you have seen many of the larger announcements from EMC being made. Case in point, back in February of 2012 VFCache was released, then May (2012) in Las Vegas at EMCworld there were 42 announcements made and others later in the year.

Click here to see images of the car stuffing or click here to watch a video.

Let’s not forget back in February of 2012 VFCache was released, and go back to January 2011 there was the record-setting event in New York City complete with 26 people being compressed, deduped, singled instanced, optimized, stacked and tiered into a mini cooper (Coop) automobile (read and view more here).

Now back to the VMAX 10K enhancements

As an example of a company, product family and specific storage system model, still being alive is the VMAX 10K. Although this announcement by EMC is VMAX 10K centric, there is also a new version of the Enginuity software (firmware, storage operating system, valueware) that runs across all VMAX based systems including VMAX 20K and VMAX 40K. Read here, here and here and here to learn more about VMAX and Enginuity systems in general.

Some main themes of this announcement include Tier 1 reliability, availability and serviceability (RAS) storage systems functionality at tier 2 pricing for traditional, virtual and cloud data centers.

Some other themes of this announcement by EMC:

  • Flexible, scalable and resilient with performance to meet dynamic needs
  • Support private, public and hybrid cloud along with federated storage models
  • Simplified decision-making, acquisition, installation and ongoing management
  • Enable traditional, virtual and cloud workloads
  • Complement its siblings VMAX 40K, 20K and SP (Service Provider) models

Note that the VMAX SP is a model configured and optimized for easy self-service and private cloud, storage as a service (SaaS), IT as a Service (ITaaS) and public cloud service providers needing multi-tenant capabilities with service catalogs and associated tools.

So what is new with the VMAX 10K?

It is twice as fast (per EMC performance results) as earlier VMAX 10K by leveraging faster 2.8GHz Intel westmere vs. earlier 2.5GHz westmere processors. In addition to faster cores, there are more, from 4 to 6 on directors, from 8 to 12 on VMAX 10K engines. The PCIe (Gen 2) IO busses remain unchanged as does the RapidIO interconnect.  RapidIO  used for connecting nodes and engines,  while PCIe is used for adapter and device connectivity. Memory stays the same at up to 128GB of global DRAM cache, along with dual virtual matrix interfaces (how the nodes are connected). Note that there is no increase in the amount of DRAM based cache memory in this new VMAX 10K model.

This should prompt the question of for traditional cache centric or dependent for performance storage systems such as VMAX, how much are they now CPU and their associated L1 / L2 cache dependent or effective? Also how much has the Enginuity code under the covers been enhanced to leverage the multiple cores and threads thus shifting from being cache memory dependent processor hungry.

Also new with the updated VMAX 10K include:

  • Support for dense 2.5 inch drives, along with mixed 2.5 inch and 3.5 inch form factor devices with a maximum of 1,560 HDDs. This means support for 2.5 inch 1TB 7,200 RPM SAS HDDs, along with fast SAS HDDs, SLC/MLC and eMLC solid state devices (SSD) also known as electronic flash devices (EFD). Note that with higher density storage configurations, good disk enclosures become more important to counter or prevent the effects of drive vibration, something that leading vendors are paying attention to and so should customers.
  • EMC is also with the VMAX 10K adding support for certain 3rd party racks or cabinets to be used for mounting the product. This means being able to mount the VMAX main system and DAE components into selected cabinets or racks to meet specific customer, colo or other environment needs for increased flexibility.
  • For security, VMAX 10K also supports Data at Rest Encryption or (D@RE) which is implemented within the VMAX platform. All data encrypted on every drive, every drive type (drive independent) within the VMAX platform to avoid performance impacts. AES 256 fixed block encryption with FIPS 140-2 validation (#1610) using embedded or external key management including RSA Key Manager. Note that since the storage system based encryption is done within the VMAX platform or controller, not only is the encrypt / decrypt off-loaded from servers, it also means that any device from SSD to HDD to third-party storage arrays can be encrypted. This is in contrast to drive based approaches such as self encrypting devices (SED) or other full drive encryption approaches. With embedded key management, encryption keys kept and managed within the VMAX system while external mode leverages RSA key management as part of a broader security solution approach.
  • In terms of addressing ease of decision-making and acquisition, EMC has bundled core Enginuity software suite (virtual provisioning, FTS and FLM, DCP (dynamic cache partitioning), host I/O limits, Optimizer/virtual LUN and integrated RecoverPoint splitter). In addition are bundles for optimization (FAST VP, EMC Unisphere for VMAX with heat map and dashboards), availability (TimeFinder for VMAX 10K) and migration (Symmetrix migration suite, Open Replicator, Open Migrator, SRDF/DM, Federated Live Migration). Additional optional software include RecoverPoint CDP, CRR and CLR, Replication Manager, PowerPath, SRDF/S, SRDF/A and SRDF/DM, Storage Configuration Advisor, Open Replicator with Dynamic Mobility and ControlCenter/ProSphere package.

Who needs a VMAX 10K or where can it be used?

As the entry-level model of the VMAX family, certain organizations who are growing and looking for an alternative to traditional mid-range storage systems should be a primary opportunity. Assuming the VMAX 10K can sell at tier-2 prices with a focus of tier-1 reliability, feature functionality, and simplification while allowing their channel partners to make some money, then EMC can have success with this product. The challenge however will be helping their direct and channel partner sales organizations to avoid competing with their own products (e.g. high-end VNX) vs. those of others.

Consolidation of servers with virtualization, along with storage system consolidation to remove complexity in management and costs should be another opportunity with the ability to virtualize third-party storage. I would expect EMC and their channel partners to place the VMAX 10K with its storage virtualization of third-party storage as an alternative to HDS VSP (aka USP/USPV) and the HP XP P9000 (Hitachi based) products, or for block storage needs the NetApp V-Series among others. There could be some scenarios where the VMAX 10K could be positioned as an alternative to the IBM V7000 (SVC based) for virtualizing third-party storage, or for larger environments, some of the software based appliances where there is a scaling with stability (performance, availability, capacity, ease of management, feature functionality) concerns.

Another area where the VMAX 10K could see action which will fly in the face of some industry thinking is for deployment in new and growing managed service providers (MSP), public cloud, and community clouds (private consortiums) looking for an alternative to open source based, or traditional mid-range solutions. Otoh, I cant wait to hear somebody think outside of both the old and new boxes about how a VMAX 10K could be used beyond traditional applications or functionality. For example filling it up with a few SSDs, and then balance with 1TB 2.5 inch SAS HDD and 3.5 inch 3TB (or larger when available) HDDs as an active archive target leveraging the built-in data compression.

How about if EMC were to support cloud optimized HDDs such as the Seagate Constellation Cloud Storage (CS) HDDs that were announced late in 2012 as well as the newer enterprise class HDDs for opening up new markets? Also keep in mind that some of the new 2.5 inch SAS 10,000 (10K) HDDs have the same performance capabilities as traditional 3.5 inch 15,000 (15K) RPM drives in a smaller footprint to help drive and support increased density of performance and capacity with improved energy effectiveness.

How about attaching a VMAX 10K with the right type of cost-effective (aligned to a given scenario) SSD or HDDs or third-party storage to a cluster or grid of servers that are running OpenStack including Swift, CloudStack, Basho Riak CS, Celversafe, Scality, Caringo, Ceph or even EMCs own ATMOS (that supports external storage) for cloud storage or object based storage solutions? Granted that would be thinking outside of the current or new box thinking to move away from RAID based systems in favor or low-cost JBOD storage in servers, however what the heck, let’s think in pragmatic ways.

Will EMC be able to open new markets and opportunities by making the VMAX and its Enginuity software platform and functionality more accessible and affordable leveraging the VMAX 10K as well as the VMAX SP? Time will tell, after all, I recall back in the mid to late 90s, and then again several times during the 2000s similar questions or conversations not to mention the demise of the large traditional storage systems.

Continue reading about what else EMC announced on January 14 2013 in addition to VMAX 10K updates here in the next post in this series. Also check out Chucks EMC blog to see what he has to say.

Ok, nuff said (for now).

Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press, 2011), The Green and Virtual Data Center (CRC Press, 2009), and Resilient Storage Networks (Elsevier, 2004)

twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved

Posted on

SSD past, present and future with Jim Handy

Now also available via

This is a new episode in the continuing StorageIO industry trends and perspectives pod cast series (you can view more episodes or shows along with other audio and video content here) as well as listening via iTunes or via your preferred means using this RSS feed (https://storageio.com/StorageIO_Podcast.xml)

StorageIO industry trends cloud, virtualization and big data

In this episode, I talk with SSD nand flash and DRAM chip analyst Jim Handy of Objective Analysis at the LSI AIS (Accelerating Innovation Summit) 2012 in San Jose. Our conversation includes SSD past, present and future, market and industry trends, who are doing what and things to keep an eye and ear, open for along with server, storage and memory convergence.

Click here (right-click to download MP3 file) or on the microphone image to listen to the conversation with Jim and myself.

StorageIO podcast

Also available via

Watch (and listen) for more StorageIO industry trends and perspectives audio blog posts pod casts and other upcoming events. Also be sure to heck out other related pod casts, videos, posts, tips and industry commentary at StorageIO.com and StorageIOblog.com.

Enjoy this episode SSD Past, Present and Future with Jim Handy.

Ok, nuff said.

Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press, 2011), The Green and Virtual Data Center (CRC Press, 2009), and Resilient Storage Networks (Elsevier, 2004)

twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2012 StorageIO and UnlimitedIO All Rights Reserved

Posted on

How much SSD do you need vs. want?

Storage I/O Industry Trends and Perspectives

I have been getting asked by IT customers, VAR’s and even vendors how much solid state device (SSD) storage is needed or should be installed to address IO performance needs to which my standard answer is it depends.

I also am also being asked if there is rule of thumb (RUT) of how much SSD you should have either in terms of the number of devices or a percentage; IMHO, the answer is it depends. Sure, there are different RUTs floating around based on different environments, applications, workloads however are they applicable to your needs.

What I would recommend is instead of focusing on percentages, RUTs, or other SWAG estimate’s or PIROMA calculations, look at your current environment and decide where the activity or issues are. If you know how many fast hard disk drives (HDD) are needed to get to a certain performance level and amount of used capacity that is a good starting point.

If you do not have that information, use tools from your server, storage or third-party provider to gain insight into your activity to help size SSD. Also if you have a database environment and are not familiar with the tools, talk with your DBA’s to have them run some reports that show performance information the two of you can discuss to zero in hot spots or opportunity for SSD.

Keep in mind when looking at SSD what is that you are trying to address by installing SSD. For example, is there a specific or known performance bottleneck resulting in poor response time or latency or is there a general problem or perceived opportunity?

Storage I/O Industry Trends and Perspectives

Is there a lack of bandwidth for large data transfers or is there a constraint on how many IO operations per second (e.g. IOPS) or transaction or activity that can be done in a given amount of time. In other words the more you know where or what the bottleneck is including if you can trace it back to a single file, object, database, database table or other item the closer you are to answering how much SSD you will need.

As an example if using third-party tools or those provided by SSD vendors or via other sources you decide that your IO bottleneck are database transaction logs and system paging files, then having enough SSD space capacity to fit those in part of the solution. However, what happens when you remove the first set of bottlenecks, what new ones will appear and will you have enough space capacity on your SSD to accommodate the next in line hot spot?

Keep in mind that you may want more SSD however what can you get budget approval to buy now without having more proof and a business case. Get some extra SSD space capacity to use for what you are confident can address other bottlenecks, or, enable new capabilities.

On other hand if you can only afford enough SSD to get started, make sure you also protect it. If you decide that two SSD devices (PCIe cache or target cards, drives or appliances) will take care of your performance and capacity needs, make sure to keep availability in mind. This means having extra SSD devices for RAID 1 mirroring, replication or other form of data protection and availability. Keep in mind that while traditional hard disk drive (HDD) storage is often gauged on cost per capacity, or dollar per GByte or dollar per TByte, with SSD measure its value on cost to performance. For example, how many IOPS, or response time improvement or bandwidth are obtained to meet your specific needs per dollar spent.

Related links
What is the best kind of IO? The one you do not have to do
Is SSD dead? No, however some vendors might be
Speaking of speeding up business with SSD storage
Has SSD put Hard Disk Drives (HDD’s) On Endangered Species List?
Why SSD based arrays and storage appliances can be a good idea (Part I)
EMC VFCache respinning SSD and intelligent caching (Part I)
SSD options for Virtual (and Physical) Environments Part I: Spinning up to speed on SSD

Ok, nuff said for now

Cheers Gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press, 2011), The Green and Virtual Data Center (CRC Press, 2009), and Resilient Storage Networks (Elsevier, 2004)

twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2012 StorageIO and UnlimitedIO All Rights Reserved

Posted on

Are large storage arrays dead at the hands of SSD?

Storage I/O trends

An industry trends and perspective.

.

Are large storage arrays dead at the hands of SSD? Short answer NO not yet.
There is still a place for traditional storage arrays or appliances particular those with extensive features, functionality and reliability availability serviceability (RAS). In other words, there is still a place for large (and small) storage arrays or appliances including those with SSDs.

Is there a place for newer flash SSD storage systems, appliances and architectures? Yes
Similar to how there is a place for traditional midrange storage arrays or appliances have found their roles vs. traditional higher end so-called enterprise arrays. Think as an example  EMC CLARiiON/VNX or HP EVA/P6000 or HDS AMS/HUS or NetApp FAS or IBM DS5000 or IBM V7000 among others vs. EMC Symmetrix/DMX/VMAX or HP P10000/3Par or HDS VSP/USP or IBM DS8000. In addition to traditional enterprise or high-end storage systems and midrange also known as modular, there are also specialized appliances or targets such as for backup/restore and archiving. Also do not forget the IO performance SSD appliances like those from TMS among others that have been around for a while.

Is the role of large storage systems changing or evolving? Yes
Given their scale and ability to do large amounts of work in a dense footprint, for some the role of these systems is still mission critical tier 1 application and data support. For other environments, their role continues to evolve being used for high-density tier 2 bulk or even near-line storage for on-line access at scale.

Storage I/O trends

Does this mean there is completion between the old and new systems? Yes
In some circumstances as we have seen already with SSD solutions. Some will place as competing or replacements while others as complementing. For example in the PCIe flash SSD card segment EMC VFCache is positioned is complementing Dell, EMC, HDS, HP, IBM, NetApp, Oracle or others storage vs. FusionIO who positions as a replacement for the above and others. Another scenario is how some SSD vendors have and continue to position their all-flash SSD arrays using either drives or PCIe cards to complement and coexist with other storage systems in an environment (e.g. data center level tiering) vs. as a replacement. Also keep in mind SSD solutions that also support a mix of flash devices and traditional HDDs for capacity and cost savings or cloud access in the same solution.

Does this mean that the industry has adopted all SSD appliances as the state of art?
Avoid confusing industry adoption or talk with industry and customer deployment. They are similar, however one is focused on what the industry talks about or discusses as state of art or the future while the other is what customers are doing. Certainly some of the new flash SSD appliance and storage startups such as Solidfire, Nexgen, Violin, Whiptail or veteran TMS among others have promising futures, some of which may actually be in play with the current SSD market shakeout and consolidation.

Does that mean everybody is going SSD?
SSD customer adoption and deployment continues to grow, however so too does the deployment of high-capacity HDDs.

Storage I/O trends

Do SSDs need HDDs, do HDDs need SSDs? Yes
Granted there are environments where needs can be addressed by all of one or the other. However at least near term, there is a very strong market for tiering and mix of SSD, some fast HDDs and lots of high-capacity HDDs to meet various needs including performance, availability, capacity, energy and economics. After all, there is no such thing, as a data or information recession yet budgets are tight or being reduced. Likewise, people and data are living longer.

What does this mean?
If there, were no such thing as a data recession and budgets a non-issue, perhaps everything could move to all flash SSD storage systems. However, we also know that people and data are living longer along with changing data life-cycle patterns. There is also the need for performance to close the traditional data center IO performance to space capacity gap and bottlenecks as well as store and keep data longer.

There will continue to be a need for a mix of high-capacity and high performance. More IO will continue to gravitate towards the IO appliances, however more data will settle in for longer-term retention and continued access as data life-cycle continue to evolve. Watch for more SSD and cache in the large systems, along with higher density SAS-NL (SAS Near Line e.g. high capacity) type drives appearing in those systems.

If you like new shiny new toys or technology (SNTs) to buy, sell or talk about, there will be plenty of those to continue industry adoption while for those who are focused on industry deployment, there will be a mix of new, and continued evolution for implementation.

Related links
Industry adoption vs. industry deployment, is there a difference?

Industry trend: People plus data are aging and living longer

No Such Thing as an Information Recession

Changing Lifecycles & Data Footprint Reduction
What is the best kind of IO? The one you do not have to do
Is SSD dead? No, however some vendors might be
Speaking of speeding up business with SSD storage
Are Hard Disk Drives (HDD’s) getting too big?
IT and storage economics 101, supply and demand
Has SSD put Hard Disk Drives (HDD’s) On Endangered Species List?
Why SSD based arrays and storage appliances can be a good idea (Part I)
Researchers and marketers don’t agree on future of nand flash SSD
EMC VFCache respinning SSD and intelligent caching (Part I)
SSD options for Virtual (and Physical) Environments Part I: Spinning up to speed on SSD

Ok, nuff said for now

Cheers Gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press, 2011), The Green and Virtual Data Center (CRC Press, 2009), and Resilient Storage Networks (Elsevier, 2004)

twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2012 StorageIO and UnlimitedIO All Rights Reserved

Posted on

More Storage IO momentus HHDD and SSD moments part II

This follows the first of a two-part series on my latest experiences with Hybrid Hard Disk Drives (HHDD’s) and Solid State Devices (SSD’s). In my ongoing last momentus moment post I discussed what I have done with HHDD’s and setting the stage for expanded SSD use. I have the newer HHDD’s, e.g. Seagate Momentus XT II 750GB (8GB SLC nand flash) installed and have since bought another from Amazon as well as having some of the older 500GB (4GB SLC nand flash) in various systems. Those are all functioning great, however still waiting and looking forward to the rumored firmware enhancements to boost write capabilities.

This brings me up to the latest momentus moment which now includes SSD’s.

Well its two years later and I now have a 256GB (usable capacity is lower) Samsung SSD that I bought from Amazon.com and installed in one of my laptops and just as when I made the first switch to HHDD’s, I also have a backup copy/clone to fall back to in case of emergency.

Was it worth the wait? Yes, particularly using the HHDD’s to bridge the gap and enable some productivity gain which more than paid for them based on some different projects. I’m already seeing productivity improvements that will make future upgrades more easy to justify (to myself).

I deviated from my strategy a bit and installed the SSD about six months earlier than I was planning to do so because of a physical barrier. That physical barrier was my new traveling laptop only accepts 7mm height 2.5 inch small form factor devices and the 750GB HHDD that I had planned on installing was 2.5mm to thick which pushed up the SSD installation.

What will become of the 750GB HHDD? Its being redeployed to help speed up file serving, backups and other functions.

Will I replace the HHDD’s in my other workstations and laptops now with SSD’s? Across the board no, not yet, however there is one other system that is a prime candidate to maybe upgrade in a month or two (maybe less).

Will I stick with the Samsung SSD’s or look at other options? I’m keeping my options open and using this as a gauge to test and compare other options in a real world working environment as opposed to a lab bench test simulation. In other words, taking the next step past the lab test and product reviews, gaining comfort and confidence and then trying out with real use activity.

What will happen in the future as I install more SSD’s and have surplus HHDD’s? Redeployed them of course into file or NAS servers, backup targets that in turn will replace HDD’s that will either get retired, or redeployed to replace older, smaller capacity, higher cost to handle HDD’s used for offsite protection.

I tried using the software that came with the SSD to do the cloning and should have known better, however wanted to see what the latest version of ghost was like (it was a waste of time to be polite). Instead I used Seagate Discwizard (aka Acronis) which requires at least one Seagate product (source or target) for cloning.

Cloning from the Seagate HHDD that have been previously cloned from the Hitachi HDD that came with the laptop, was a none issue. However, I wanted to see what would happen if I attached the Samsung SSD to the Seagate Goflex cable and clone directly from the Hitachi HDD, it worked. Hence another reason to have some of the Seagate Goflex cables (USB and eSATA) like the ones I bought at Amazon.com around in your toolbox.

While I do not have concrete empirical numbers to share, cloning from a HDD to a SSD is shall we say fast, however, what’s really fun to watch is cloning from a HHDD to a SSD using an eSata (GoFlex) connector adapter. The reason I say that it is fun is that you don’t have to sit and wait for hours, it’s not minutes to move 100s of GBs, however you can very much see the progress bar move at a good pace.

Also, I put the HHDD on an eSata port and try that out as a backup or data dump target if you have the need for speed, capacity and cost effectiveness, yes its fast, has lots of capacity and so forth. Now if Seagate and Synology or EMC Iomega would get their acts together and add support for the HHDD’s in those different unified SMB and SOHO NAS solutions, that would be way cool.

Will I be racing to put SSD’s in my other laptops or workstations soon? Probably not as there are things in the works and working their way into and through the market place that I wanted to wait for, and thus will wait for now, that is unless a more interesting opportunity pops up.

Related links on SDD, HHDD and HDD
More Storage IO momentus HHDD and SSD moments part I
More Storage IO momentus HHDD and SSD moments part II
IO IO it is off to Storage and IO metrics we go
New Seagate Momentus XT Hybrid drive (SSD and HDD)
Other Momentus moments posts here here, here, here and here
SSD and Storage System Performance
Speaking of speeding up business with SSD storage
Are Hard Disk Drives (HDD’s) getting too big?
Has SSD put Hard Disk Drives (HDD’s) On Endangered Species List?
Why SSD based arrays and storage appliances can be a good idea (Part I)
Why SSD based arrays and storage appliances can be a good idea (Part II)
IT and storage economics 101, supply and demand
Researchers and marketers dont agree on future of nand flash SSD
EMC VFCache respinning SSD and intelligent caching (Part I)
EMC VFCache respinning SSD and intelligent caching (Part II)
SSD options for Virtual (and Physical) Environments Part I: Spinning up to speed on SSD
SSD options for Virtual (and Physical) Environments Part II: The call to duty, SSD endurance
SSD options for Virtual (and Physical) Environments Part III: What type of SSD is best for you?
SSD options for Virtual (and Physical) Environments Part IV: What type of SSD is best for your needs

Ok, nuff said for now.

Cheers Gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press, 2011), The Green and Virtual Data Center (CRC Press, 2009), and Resilient Storage Networks (Elsevier, 2004)

twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2012 StorageIO and UnlimitedIO All Rights Reserved

Posted on

More Storage IO momentus HHDD and SSD moments part I

This is the first of a two part series on my latest experiences with HHDD and SSD’s

About two years ago I wanted to start installing solid state devices (SSD’s) into my workstations and laptops. Like many others, I found the expensive price for the limited capacity gains of the then generation SSD’s did not make for a good business decision based on my needs. Don’t get me wrong, I have been a huge fan of SSD for decades as an IT user, vendor, analysts, consultant and consumer and still am. In fact I have some SSD’s used for different purposes as well as many Hard Disk Drives (HDD) and Hybrid Hard Disk Drives (HHDD’s). Almost two years ago when I first tested the HHDD’s, I did an first post in this ongoing series and this two-part post is part of that string of experiences observed evolving from HDD’s to HHDD’s to SSD’s


Image courtesy of Seagate.com

As a refresher, HHDD’s like the Seagate Momentus XT combine a traditional 7,200 RPM 2.5 inch 500GB or 750GB HDD with an integrated single level cell (SLC) nand flash SSD within the actual device. The SSD in the HHDD’s is part of the HDD’s controller complementing the existing DRAM buffer by adding 4GB (500GB models) or 8GB (750GB models) of fast nand flash SSD cache. This means that no external special controller, adapter, data movement or migration software are required to get the performance boost over a traditional HDD and the capacity above a SSD at an affordable cost. In other words, the HHDD’s bridge the gap between those who need large capacity and some performance increases, without having to spend a lot on a lower capacity SSD.

However based on my needs or business requirements two years ago I found the justification to get all the extra performance of  SSD not quite there when. Back two years ago my thinking was that it would be about two maybe three years before the right point for a mix of performance, availability (or reliability e.g. duty cycles), capacity and economics aligned.

Note that this was based on my specific needs and requirements as opposed to my wants or wishes (I wanted SSD back then, however my budget needed to go elsewhere). My requirements and performance needs are probably not the same as yours or others might be. I also wanted to see the incremental technology, product and integration improvements ranging from duty cycle or program/erase cycles (P/E) with newer firmware and flash translation layers (FTLs) among other things. Particularly with multilevel cell (MLC) or enhanced multilevel cell (eMLC) which helps bring the cost down while boosting the capacity, I’m seeing enough to have more confidence in those devices. Note that for the past couple of years I have used single level cell (SLC) nand flash SSD technology in my HHDD’s, the same SSD flash technology that has been found in enterprise class storage.

While I wanted SSD’s two years ago in my laptops and workstations to improve productivity which involves a lot of content creation in addition to consumption, however as mentioned above, there were barriers. So instead of sitting on the sidelines, waiting for SSD’s to either become lower cost, or more capacity for a given cost, or wishing somebody would send me some free stuff (that may or may not have worked), I took a different route. That route was to try the HHDD’s such as Seagate Momentus XT.

Disclosure: Seagate sent me my first HHDD for first testing and verifications before buying several more from Amazon.com and installing them in all laptops, workstations and a server (not all servers have the HHDD’s, or at least yet).

The main reason I went with the HHDD’s two years ago and continue to use them today is to bridge the gap and gain some benefit vs. waiting and wishing and talking about what SSD’s would enable me to do in the future while missing out on productivity enhancements.

The HHDD’s also appealed to me in that my laptops are space constrained for putting two drives and playing the hybrid configuration game of installing both a small SSD and HDD and migrating data back and forth. Sure I could do that for in the office or carry an extra external device around however been there, done that in the past and want to move away from those types of models where possible.

Related links on SDD, HHDD and HDD
More Storage IO momentus HHDD and SSD moments part I
More Storage IO momentus HHDD and SSD moments part II
IO IO it is off to Storage and IO metrics we go
New Seagate Momentus XT Hybrid drive (SSD and HDD)
Other Momentus moments posts here here, here, here and here
SSD and Storage System Performance
Speaking of speeding up business with SSD storage
Are Hard Disk Drives (HDD’s) getting too big?
Has SSD put Hard Disk Drives (HDD’s) On Endangered Species List?
Why SSD based arrays and storage appliances can be a good idea (Part I)
Why SSD based arrays and storage appliances can be a good idea (Part II)
IT and storage economics 101, supply and demand
Researchers and marketers dont agree on future of nand flash SSD
EMC VFCache respinning SSD and intelligent caching (Part I)
EMC VFCache respinning SSD and intelligent caching (Part II)
SSD options for Virtual (and Physical) Environments Part I: Spinning up to speed on SSD
SSD options for Virtual (and Physical) Environments Part II: The call to duty, SSD endurance
SSD options for Virtual (and Physical) Environments Part III: What type of SSD is best for you?
SSD options for Virtual (and Physical) Environments Part IV: What type of SSD is best for your needs

Ok, nuff said for now, lets resume this discussion in part II.

Cheers Gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press, 2011), The Green and Virtual Data Center (CRC Press, 2009), and Resilient Storage Networks (Elsevier, 2004)

twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2012 StorageIO and UnlimitedIO All Rights Reserved

Posted on

Why SSD based arrays and storage appliances can be a good idea (Part II)

This is the second of a two-part post about why storage arrays and appliances with SSD drives can be a good idea, here is link to the first post.

So again, why would putting drive form factors SSDs be a bad idea for existing storage systems, arrays and appliances?

Benefits of SSD drive in storage systems, arrays and appliances:

  • Familiarity with customers who buy and use these devices
  • Reduces time to market enabling customers to innovate via deployment
  • Establish comfort and confidence with SSD technology for customers
  • Investment protection of currently installed technology (hardware and software)
  • Interoperability with existing interfaces, infrastructure, tools and policies
  • Reliability, availability and serviceability (RAS) depending on vendor implementation
  • Features and functionality (replicate, snapshot, policy, tiering, application integration)
  • Known entity in terms of hardware, software, firmware and microcode (good or bad)
  • Share SSD technology across more servers or accessing applications
  • Good performance assuming no controller, hardware or software bottlenecks
  • Wear leveling and other SSD flash management if implemented
  • Can end performance bottlenecks if backend (drives) are a problem
  • Coexist or complemented with server-based SSD caching

Note, the mere presence of SSD drives in a storage system, array or appliance will not guarantee or enable the above items to be enabled, nor to their full potential. Different vendors and products will implement to various degrees of extensibility SSD drive support, so look beyond the check box of feature, functionality. Dig in and understand how extensive and robust the SSD implementation is to meet your specific requirements.

Caveats of SSD drives in storage systems, arrays and appliances:

  • May not use full performance potential of nand flash SLC technology
  • Latency can be an issue for those who need extreme speed or performance
  • May not be the most innovative newest technology on the block
  • Fun for startup vendors, marketers and their fans to poke fun at
  • Not all vendors add value or optimization for endurance of drive SSD
  • Seen as not being technology advanced vs. legacy or mature systems

Note that different vendors will have various performance characteristics, some good for IOPs, others for bandwidth or throughput while others for latency or capacity. Look at different products to see how they will vary to meet your particular needs.

Cost comparisons are tricky. SSD in HDD form factors certainly cost more than raw flash dies, however PCIe cards and FTL (flash translation layer) controllers also cost more than flash chips by themselves. In other words, apples to apples comparisons are needed. In the future, ideally the baseboard or motherboard vendors will revise the layout to support nand flash (or its replacement) with DRAM DIMM type modules along with associated FTL and BIOS to handle the flash program/erase cycles (P/E) and wear leveling management, something that DRAM does not have to encounter. While that provides great location or locality of reference (figure 1), it is also a more complex approach that takes time and industry cooperation.

Locality of reference for memory and storage
Figure 1: Locality of reference for memory and storage

Certainly, for best performance, just like realty location matters and thus locality of reference comes into play. That is put the data as close to the server as possible, however when sharing is needed, then a different approach or a companion technique is required.

Here are some general thoughts about SSD:

  • Some customers and organizations get the value and role of SSD
  • Some see where SSD can replace HDD, others see where it compliments
  • Yet others are seeing the potential, however are moving cautiously
  • For many environments better than current performance is good enough
  • Environments with the need for speed need every bit of performance they can get
  • Storage systems and arrays or appliances continue to evolve including the media they use
  • Simply looking at how some storage arrays, systems and appliances have evolved, you can get an idea on how they might look in the future which could include not only SAS as a backend or target, also PCIe. After all, it was not that long ago where backend drive connections went from propriety to open parallel SCSI or SSA to Fibre Channel loop (or switched) to SAS.
  • Engineers and marketers tend to gravitate to newer products nand technology, which is good, as we need continued innovation on that front.
  • Customers and business people tend to gravitate towards deriving greatest value out of what is there for as long as possible.
  • Of course, both of the latter two points are not always the case and can be flip flopped.
  • Ultrahigh end environments and corner case applications will continue to push the limits and are target markets for some of the newer products and vendors.
  • Likewise, enterprise, mid market and other mainstream environments (outside of their corner case scenarios) will continue to push known technology to its limits as long as they can derive some business benefit value.

While not perfect, SSD in a HDD form factor with a SAS or SATA interface properly integrated by vendors into storage systems (or arrays or appliances) are a good fit for many environments today. Likewise, for some environments, new from the ground up SSD based solutions that leverage flash DIMM or daughter cards or PCIe flash cards are a fit. So to are PCIe flash cards either as a target, or as cache to complement storage system (arrays and appliances). Certainly, drive slots in arrays take up space for SSD, however so to does occupying PCIe space particularly in high density servers that require every available socket and slot for compute and DRAM memory. Thus, there are pros and cons, features and benefits of various approaches and which is best will depend on your needs and perhaps preferences, which may or may not be binary.

I agree that for some applications and solutions, non drive form factor SSD make sense while in others, compatibility has its benefits. Yet in other situations nand flash such as SLC combined with HDD and DRAM tightly integrated such as in my Momentus XT HHDD is good for laptops, however probably not a good fit for enterprise yet. Thus, SSD options and placements are not binary, of course, sometimes opinions and perspectives will be.

For some situations PCIe, based cards in servers or appliances make sense, either as a target or as cache. Likewise for other scenarios drive format SSD make sense in servers and storage systems, appliances, arrays or other solutions. Thus while all of those approaches are used for storing binary digital data, the solutions of what to use when and where often will not be binary, that is unless your approach is to use one tool or technique for everything.

Here are some related links to learn more about SSD, where and when to use what:
Why SSD based arrays and storage appliances can be a good idea (Part I)
IT and storage economics 101, supply and demand
Researchers and marketers dont agree on future of nand flash SSD
Speaking of speeding up business with SSD storage
EMC VFCache respinning SSD and intelligent caching (Part I)
EMC VFCache respinning SSD and intelligent caching (Part II)
SSD options for Virtual (and Physical) Environments: Part I Spinning up to speed on SSD
SSD options for Virtual (and Physical) Environments, Part II: The call to duty, SSD endurance
SSD options for Virtual (and Physical) Environments Part III: What type of SSD is best for you?

Ok, nuff said for now.

Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press, 2011), The Green and Virtual Data Center (CRC Press, 2009), and Resilient Storage Networks (Elsevier, 2004)

twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2012 StorageIO and UnlimitedIO All Rights Reserved

Posted on

Why SSD based arrays and storage appliances can be a good idea (Part I)

This is the first of a two-part series, you can read part II here.

Robin Harris (aka @storagemojo) recently in a blog post asks a question and thinks solid state devices (SSDs) using SAS or SATA interface in traditional hard disk drive (HDD) form factors are a bad idea in storage arrays (e.g. storage systems or appliances). My opinion is that as with many things about storing, processing or moving binary digital data (e.g. 1s and 0s) the answer is not always clear. That is there may not be a right or wrong answer instead it depends on the situation, use or perhaps abuse scenario. For some applications or vendors, adding SSD packaged in HDD form factors to existing storage systems, arrays and appliances makes perfect sense, likewise for others it does not, thus it depends (more on that in a bit). While we are talking about SSD, Ed Haletky (aka @texiwill) recently asked a related question of Fix the App or Add Hardware, which could easily be morphed into a discussion of Fix the SSD, or Add Hardware. Hmmm, maybe a future post idea exists there.

Lets take a step back for a moment and look at the bigger picture of what prompts the question of what type of SSD to use where and when along as well as why various vendors want you to look at things a particular way. There are many options for using SSD that is packaged in various ways to meet diverse needs including here and here (see figure 1).

Various SSD packaging options
Figure 1: Various packaging and deployment options for SSD

The growing number of startup and established vendors with SSD enabled storage solutions vying to win your hearts, minds and budget is looking like the annual NCAA basketball tournament (aka March Madness and march metrics here and here). Some of vendors have or are adding SSD with SAS or SATA interfaces that plug into existing enclosures (drive slots). These SSDs have the same form factor of a 2.5 inch small form factor (SFF) or 3.5 inch HDDs with a SAS or SATA interface for physical and connectivity interoperability. Other vendors have added PCIe based SSD cards to their storage systems or appliances as a cache (read or read and write) or a target device similar to how these cards are installed in servers.

Simply adding SSD either in a drive form factor or as a PCIe card to a storage system or appliance is only part of a solution. Sure, the hardware should be faster than a traditional spinning HDD based solution. However, what differentiates the various approaches and solutions is what is done with the storage systems or appliances software (aka operating system, storage applications, management, firmware or micro code).

So are SSD based storage systems, arrays and appliances a bad idea?

If you are a startup or established vendor able to start from scratch with a clean sheet design not having to worry about interoperability and customer investment protection (technology, people skills, software tools, etc), then you would want to do something different. For example, leverage off the shelf components such as a PCIe flash SSD card in an industry standard server combined with your software for a solution. You could also use extra DRAM memory in those servers combined with PCIe flash SSD cards perhaps even with embedded HDDs for a backing or preservation medium.

Other approaches might use a mix of DRAM, PCIe flash cards, as either a cache or target combined with some drive form factor SSDs. In other words, there is no right or wrong approach; sure, there are different technical merits that have advantages for various applications or environments. Likewise, people have preferences particular for technology focused who tend to like one approach vs. another. Thus, we have many options to leverage, use or abuse.

In his post, Robin asks a good question of if nand flash SSD were being put into a new storage system, why not use the PCIe backplane vs. using nand flash on DIMM vs. using drive formats, all of which are different packaging options (Figure 1). Some startups have gone the all backplane approach, some have gone with the drive form factor, some have gone with a mix and some even using HDDs in the background. Likewise some traditional storage system and array vendors who support a mix of SSD and HDD drive form factor devices also leverage PCIe cards, either as a server-based cache (e.g. EMC VFCahe) or installed as a performance accelerator module (e.g. NetApp PAM) in their appliances.

While most vendors who put SSD drive form factor drives into their storage systems or appliances (or serves for that matter) use them as data targets for creating LUNs or file systems, others use them for internal functionality. By internal functionality I mean instead of the SSD appearing as another drive or target, they are used exclusively by the storage system or appliance for caching or similar purposes. On storage systems, this can be to increase the size of persistent cache such as EMC on the CLARiiON and VNX (e.g. FAST Cache). Another use is on backup or dedupe target appliances where SSDs are used to store dictionary, index or meta data repositories as opposed to being a general data pool.

Part two of this post looks at the benefits and caveats of SSD in storage arrays.

Here are some related links to learn more about SSD, where and when to use what:
Why SSD based arrays and storage appliances can be a good idea (Part II)
IT and storage economics 101, supply and demand
Researchers and marketers don’t agree on future of nand flash SSD
Speaking of speeding up business with SSD storage
EMC VFCache respinning SSD and intelligent caching (Part I)
EMC VFCache respinning SSD and intelligent caching (Part II)
SSD options for Virtual (and Physical) Environments: Part I Spinning up to speed on SSD
SSD options for Virtual (and Physical) Environments, Part II: The call to duty, SSD endurance
SSD options for Virtual (and Physical) Environments Part III: What type of SSD is best for you?

Ok, nuff said for now, check part II.

Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press, 2011), The Green and Virtual Data Center (CRC Press, 2009), and Resilient Storage Networks (Elsevier, 2004)

twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2012 StorageIO and UnlimitedIO All Rights Reserved

Posted on

EMC VFCache respinning SSD and intelligent caching (Part II)

This is the second of a two part series pertaining to EMC VFCache, you can read the first part here.

In this part of the series, lets look at some common questions along with comments and perspectives.

Common questions, answers, comments and perspectives:

Why would EMC not just go into the same market space and mode as FusionIO, a model that many other vendors seam eager to follow? IMHO many vendors are following or chasing FusionIO thus most are selling in the same way perhaps to the same customers. Some of those vendors can very easily if they were not already also make a quick change to their playbook adding some new moves to reach broader audience. Another smart move here is that by taking a companion or complimentary approach is that EMC can continue selling existing storage systems to customers, keep those investments while also supporting competitors products. In addition, for those customers who are slow to adopt the SSD based techniques, this is a relatively easy and low risk way to gain confidence. Granted the disk drive was declared dead several years (and yes also several decades) ago, however it is and will stay alive for many years due to SSD helping to close the IO storage and performance gap.

Storage IO performance and capacity gap
Data center and storage IO performance capacity gap (Courtesy of Cloud and Virtual Data Storage Networking (CRC Press))

Has this been done before? There have been other vendors who have done LUN caching appliances in the past going back over a decade. Likewise there are PCIe RAID cards that support flash SSD as well as DRAM based caching. Even NetApp has had similar products and functionality with their PAM cards.

Does VFCache work with other PCIe SSD cards such as FusionIO? No, VFCache is a combination of software IO intercept and intelligent cache driver along with a PCIe SSD flash card (which could be supplied as EMC has indicated from different manufactures). Thus VFCache to be VFCache requires the EMC IO intercept and intelligent cache software driver.

Does VFCache work with other vendors storage? Yes, Refer to the EMC support matrix, however the product has been architected and designed to install and coexist into a customers existing environment which means supporting different EMC block storage systems as well as those from other vendors. Keep in mind that a main theme of VFCache is to compliment, coexist, enhance and protect customers investments in storage systems to improve their effectiveness and productivity as opposed to replacing them.

Does VFCache introduce a new point of vendor lockin or stickiness? Some will see or place this as a new form of vendor lockin, others assuming that EMC supports different vendors storage systems downstream as well as offer options for different PCIe flash cards and keeps the solution affordable will assert it is no more lockin that other solutions. In fact by supporting third party storage systems as opposed to replacing them, smart sales people and marketeers will place VFCache as being more open and interoperable than some other PCIe flash card vendors approach. Keep in mind that avoiding vendor lockin is a shared responsibility (read more here).

Does VFCache work with NAS? VFCache does not work with NAS (NFS or CIFS) attached storage.

Does VFCache work with databases? Yes, VFCache is well suited for little data (e.g. database) and traditional OLTP or general business application process that may not be covered or supported by other so called big data focused or optimized solutions. Refer to this EMC document (and this document here) for more information.

Does VFCache only work with little data? While VFCache is well suited for little data (e.g. databases, share point, file and web servers, traditional business systems) it also able to work with other forms of unstructured data.

Does VFCache need VMware? No, While VFCache works with VMware vSphere including a vCenter plug in, however it does not need a hypervisor and is practical in a physical machine (PM) as it is in a virtual machine (VM).

Does VFCache work with Microsoft Windows? Yes, Refer to the EMC support matrix for specific server operating systems and hypervisor version support.

Does VFCache work with other unix platforms? Refer to the EMC support matrix for specific server operating systems and hypervisor version support.

How are reads handled with VFCache? The VFCache software (driver if you prefer) intercepts IO requests to LUNs that are being cached performing a quick lookup to see if there is a valid cache entry in the physical VFCache PCIe card. If there is a cache hit the IO is resolved from the closer or local PCIe card cache making for a lower latency or faster response time IO. In the case of a cache miss, the VFCache driver simply passes the IO request onto the normal SCSI or block (e.g. iSCSI, SAS, FC, FCoE) stack for processing by the downstream storage system (or appliance). Note that when the requested data is retrieved from the storage system, the VFCache driver will based on caching algorithms determinations place a copy of the data in the PCIe read cache. Thus the real power of the VFCache is the software implementing the cache lookup and cache management functions to leverage the PCIe card that complements the underlying block storage systems.

How are writes handled with VFCache? Unless put into a write cache mode which is not the default, VFCache software simply passes the IO operation onto the IO stack for downstream processing by the storage system or appliance attached via a block interface (e.g. iSCSI, SAS, FC, FCoE). Note that as part of the caching algorithms, the VFCache software will make determinations of what to keep in cache based on IO activity requests similar to how cache management results in better cache effectiveness in a storage system. Given EMCs long history of working with intelligent cache algorithms, one would expect some of that DNA exists or will be leveraged further in future versions of the software. Ironically this is where other vendors with long cache effectiveness histories such as IBM, HDS and NetApp among others should also be scratching their collective heads saying wow, we can or should be doing that as well (or better).

Can VFCache be used as a write cache? Yes, while its default mode is to be used as a persistent read cache to compliment server and application buffers in DRAM along with enhance effectiveness of downstream storage system (or appliances) caches, VFCache can also be configured as a persistent write cache.

Does VFCache include FAST automated tiering between different storage systems? The first version is only a caching tool, however think about it a bit, where the software sits, what storage systems it can work with, ability to learn and understand IO paths and patterns and you can get an idea of where EMC could evolve it to, similar to what they have done with recoverpoint among other tools.

Changing data access patterns and lifecycles
Evolving data access patterns and life cycles (more retention and reads)

Does VFCache mean all or nothing approach with EMC? While the complete VFCache solution comes from EMC (e.g. PCIe card and software), the solution will work with other block attached storage as well as existing EMC storage systems for investment protection.

Does VFCache support NAS based storage systems? The first release of VFCache only supports block based access, however the server that VFCache is installed in could certainly be functioning as a general purpose NAS (NFS or CIFS) server (see supported operating systems in EMC interoperability notes) in addition to being a database or other other application server.

Does VFCache require that all LUNs be cached? No, you can select which LUNs are cached and which ones are not.

Does VFCache run in an active / active mode? In the first release it is active passive, refer to EMC release notes for details.

Can VFCache be installed in multiple physical servers accessing the same shared storage system? Yes, however refer to EMC release notes on details about active / active vs. active / passive configuration rules for ensuring data integrity.

Who else is doing things like this? There are caching appliance vendors as well as others such as NetApp and IBM who have used SSD flash caching cards in their storage systems or virtualization appliances. However keep in mind that VFCache is placing the caching function closer to the application that is accessing it there by improving on the locality of reference (e.g. storage and IO effectiveness).

Does VFCache work with SSD drives installed in EMC or other storage systems? Check the EMC product support matrix for specific tested and certified solutions, however in general if the SSD drive is installed in a storage system that is supported as a block LUN (e.g. iSCSI, SAS, FC, FCoE) in theory it should be possible to work with VFCache. Emphasis, visit the EMC support matrix.
What type of flash is being used?

What type of nand flash SSD memory is EMC using in the PCIe card? The first release of VFCache is leveraging enterprise class SLC (Single Level Cell) nand flash which has been used in other EMC products for its endurance, long duty cycle to minnimize or eliminate concerns of wear and tear while meeting read and write performance. EMC has indicated that they will also as part of an industry trend leverage MLC along with Enterprise MLC (EMLC) technologies on a go forward basis.

Doesnt nand ssd flash cache wear out? While nand flash SSD can wear out over time due to extensive write use, the VFCache approach mitigates this by being primarily a read cache reducing the number or program / erase cycles (P/E cycles) that occur with write operations as well as initially leveraging longer duty cycle SLC flash. EMC also has several years experience from implementing wear leveling algorithms into the storage systems controllers to increase duty cycle and reduce wear on SLC flash which will play forward as MLC or Enterprise MLC (EMLC) techniques are leveraged. This differs from vendors who are positioning their SLC or MLC based flash PCIe SSD cards for mainly write operations which will cause more P/E cycles to occur at a faster rate reducing the duty or useful life of the device.

How much capacity does the VFCache PCIe card contain? The first release supports a 300GB card and EMC has indicated that added capacity and configuration options are in their plans.

Does this mean disks are dead? Contrary to popular industry folk lore (or wish) the hard disk drive (HDD) has plenty of life left part of which has been increased by being complimented by VFCache.

Various options and locations for SSD along with different usage scenarios
Various SSD locations, types, packaging and usage scenario options

Can VFCache work in blade servers? The VFCache software is transparent to blade, rack mount, tower or other types of servers. The hardware part of VFCache is a PCIe card which means that the blade server or system will need to be able to accommodate a PCIe card to compliment the PCIe based mezzaine IO card (e.g. iSCSI, SAS, FC, FCOE) used for accessing storage. What this means is that for blade systems or server vendors such as IBM who have a PCIe expansion module for their H series blade systems (it consumes a slot normally used by a server blade), PCIe cache cards like those being initially released by IBM could work, however check with the EMC interoperability matrix, as well as your specific blade server vendor for PCIe expansion capabilities. Given that EMC leverages Cisco UCS for their vBlocks, one would assume that those systems will also see VFCache modules in those systems. NetApp partners with Cisco using UCS in their FlexPods so you see where that could go as well along with potential other server vendors support including Dell, HP, IBM and Oracle among others.

What about benchmarks? EMC has released some technical documents that show performance improvements in Oracle environments such as this here. Hopefully we will see EMC also release other workloads for different applications including Microsoft Exchange Solutions Proven (ESRP) along with SPC similar to what IBM recently did with their systems among others.

How do the first EMC supplied workload simulations compare vs. other PCIe cards? This is tough to gauge as many SSD solutions and in particular PCIe cards are doing apples to oranges comparisons. For example to generate a high IOPs rating for marketing purposes, most SSD solutions are stress performance tested at 512 bytes or 1/2 of a KByte or at least 1/8 of a small 4Kbyte IO. Note that operating systems such as Windows are moving to 4Kbyte page allocation size to align with growing IO sizes with databases moving from the old average of 4Kbytes to 8Kbytes and larger. What is important to consider is what is the average IO size and activity profile (e.g. reads vs. writes, random vs. sequential) for your applications. If your application is doing ultra small 1/2 Kbyte IOs, or even smaller 64 byte IOs (which should be handled by better application or file system caching in DRAM), then the smaller IO size and record setting examples will apply. However if your applications are more mainstream or larger, then those smaller IO size tests should be taken with a grain of salt. Also keep latency in mind that many target or oppourtunity applications for VFCache are response time sensitive or can benefit by the improved productivity they enable.

What is locality of reference? Locality of reference refers to how close data is to where it is being requested or accessed from. The closer the data to the application requesting the faster the response time or quick the work gets done. For example in the figure below L1/L2/L3 on board processor caches are the fastest, yet smallest while closest to the application running on the server. At the other extreme further down the stack, storage becomes large capacity, lower cost, however lower performing.

Locality of reference data and storage memory

What does cache effectiveness vs. cache utilization mean? Cache utilization is an indicator of how much the available cache capacity is being used however it does not give an indicator of if the cache is being well used or not. For example, cache could be 100 percent used, however there could be a low hit rate. Thus cache effectiveness is a gauge of how well the available cache is being used to improve performance in terms of more work being done (IOPS or bandwidth) or lower of latency and response time.

Isnt more cache better? More cache is not better, it is how the cache is being used, this is a message that I would be disappointed in HDS if they were not to bring up as a point of messaging (or rebuttal) given their history of emphasis cache effectiveness vs. size or quantity (Hu, that is a hint btw ;).

What is the performance impact of VFCache on the host server? EMC is saying greatest of 5 percent or less CPU consumption which they claim is several times less than the competitions worst scenario, as well as claiming 512MB to 1GB of DRM on the server vs. several times that of their competitors. The difference could be expected to be via more off load functioning including flash translation layer (FTL), wear leveling and other optimization being handled by the PCIe card vs. being handled in the servers memory and using host server CPU cycles.

How does this compare to what NetApp or IBM does? NetApp, IBM and others have done caching with SSD in their storage systems, or leveraging third party PCIe SSD cards from different vendors to be installed in servers to be used as a storage target. Some vendors such as LSI have done caching on the PCIe cards (e.g. CacheCaid which in theory has a similar software caching concept to VFCache) to improve performance and effectiveness across JBOD and SAS devices.

What about stale (old or invalid) reads, how does VFCache handle or protect against those? Stale reads are handled via the VFCache management software tool or driver which leverages caching algorithms to decide what is valid or invalid data.

How much does VFCache cost? Refer to EMC announcement pricing, however EMC has indicated that they will be competitive with the market (supply and demand).

If a server shutdowns or reboots, what happens to the data in the VFCache? Being that the data is in non volatile SLC nand flash memory, information is not lost when the server reboots or loses power in the case of a shutdown, thus it is persistent. While exact details are not know as of this time, it is expected that the VFCache driver and software do some form of cache coherency and validity check to guard against stale reads or discard any other invalid cache entries.

Industry trends and perspectives

What will EMC do with VFCache in the future and on a larger scale such as an appliance? EMC via its own internal development and via acquisitions has demonstrated ability to use various clustered techniques such as RapidIO for VMAX nodes, InfiniBand for connecting Isilon  nodes. Given an industry trend with several startups using PCIe flash cards installed in a server that then functions as a IO storage system, it seems likely given EMCs history and experience with different storage systems, caching, and interconnects that they could do something interesting. Perhaps Oracle Exadata III (Exadata I was HP, Exadata II was Sun/Oracle) could be an EMC based appliance (That is pure speculation btw)?

EMC has already shown how it can use SSD drives as a cache extension in VNX and CLARiiON servers ( FAST CACHE ) in addition to as a target or storage tier combined with Fast for tiering. Given their history with caching algorithms, it would not be surprising to see other instantiations of the technology deployed in complimentary ways.

Finally, EMC is showing that it can use nand flash SSD in different ways, various packaging forms to apply to diverse applications or customer environments. The companion or complimentary approach EMC is currently taking contrasts with some other vendors who are taking an all or nothing, its all SSD as disk is dead approach. Given the large installed base of disk based systems EMC as well as other vendors have in place, not to mention the investment by those customers, it makes sense to allow those customers the option of when, where and how they can leverage SSD technologies to coexist and complement their environments. Thus with VFCache, EMC is using SSD as a cache enabler to discuss the decades old and growing storage IO to capacity performance gap in a force multiplier model that spreads the cost over more TBytes, PBytes or EBytes while increasing the overall benefit, in other words effectiveness and productivity.

Additional related material:
Part I: EMC VFCache respinning SSD and intelligent caching
IT and storage economics 101, supply and demand
2012 industry trends perspectives and commentary (predictions)
Speaking of speeding up business with SSD storage
New Seagate Momentus XT Hybrid drive (SSD and HDD)
Are Hard Disk Drives (HDDs) getting too big?
Unified storage systems showdown: NetApp FAS vs. EMC VNX
Industry adoption vs. industry deployment, is there a difference?
Two companies on parallel tracks moving like trains offset by time: EMC and NetApp
Data Center I/O Bottlenecks Performance Issues and Impacts
From bits to bytes: Decoding Encoding
Who is responsible for vendor lockin
EMC VPLEX: Virtual Storage Redefined or Respun?
EMC interoperabity support matrix

Ok, nuff said for now, I think I see some storm clouds rolling in…

Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press, 2011), The Green and Virtual Data Center (CRC Press, 2009), and Resilient Storage Networks (Elsevier, 2004)

twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2012 StorageIO and UnlimitedIO All Rights Reserved

Posted on

EMC VFCache respinning SSD and intelligent caching (Part I)

This is the first part of a two part series covering EMC VFCache, you can read the second part here.

EMC formerly announced VFCache (aka Project Lightning) an IO accelerator product that comprises a PCIe nand flash card (aka Solid State Device or SSD) and intelligent cache management software. In addition EMC is also talking about the next phase of the flash business unit and project Thunder. The approach EMC is taking with vFCache should not be a surprise given their history of starting out with memory and SSD evolving it into an intelligent cache optimized storage solution.

Storage IO performance and capacity gap
Data center and storage IO performance capacity gap (Courtesy of Cloud and Virtual Data Storage Networking (CRC Press))

Could we see the future of where EMC will take VFCache along with other possible solutions already being hinted at by the EMC flash business unit by looking where they have been already?

Likewise by looking at the past can we see the future or how VFCache and sibling product solutions could evolve?

After all, EMC is no stranger to caching with both nand flash SSD (e.g. FLASH CACHE, FAST and SSD drives) along with DRAM based across their product portfolio not too mention being a core part of their company founding products that evolved into HDDs and more recent nand flash SSDs among others.

Industry trends and perspectives

Unlike others who also offer PCIe SSD cards such as FusionIO with a focus on eliminating SANs or other storage (read their marketing), EMC not surprisingly is marching to a different beat. The beat EMC is marching too or perhaps leading by example for others to follow is that of going mainstream and using PCIe SSD cards as a cache to compliment theirs as well as other vendors storage systems vs. replacing them. This is similar to what EMC and other mainstream storage vendors have done in the past such as with SSD drives being used as flash cache extension on CLARiiON or VNX based systems as well as target or storage tier.

Various options and locations for SSD along with different usage scenarios
Various SSD locations, types, packaging and usage scenario options

Other vendors including IBM, NetApp and Oracle among others have also leveraged various packaging options of Single Level Cell (SLC) or Multi Level Cell (MLC) flash as caches in the past. A different example of SSD being used as a cache is the Seagate Momentus XT which is a desktop, workstation consumer type device. Seagate has shipped over a million of the Momentus XT which use SLC flash as a cache to compliment and enhance the integrated HDD performance (a 750GB with 8GB SLC memory is in the laptop Im using to type this with).

One of the premises of solutions such as those mentioned above for caching is to discuss changing data access patterns and life cycles shown in the figure below.

Changing data access patterns and lifecycles
Evolving data access patterns and life cycles (more retention and reads)

Put a different way, instead of focusing on just big data or corner case (granted some of those are quite large) or ultra large cloud scale out solutions, EMC with VFCache is also addressing their core business which includes little data. What will be interesting to watch and listen too is how some vendors will start to jump up and down saying that they have done or enabling what EMC is announcing for some time. In some cases those vendors will be rightfully doing and making noise on something that they should have made noise about before.

EMC is bringing the SSD message to the mainstream business and storage marketplace showing how it is a compliment to, vs. a replacement of existing storage systems. By doing so, they will show how to spread the cost of SSD out across a larger storage capacity footprint boosting the effectiveness and productive of those systems. This means that customers who install the VFCache product can accelerate the performance of both their existing EMC as well as storage systems from other vendors preserving their technology along with people skills investment.

 

Key points of VFCache

  • Combines PCIe SLC nand flash card (300GB) with intelligent caching management software driver for use in virtualized and traditional servers

  • Making SSD complimentary to existing installed block based disk (and or SSD) storage systems to increase their effectiveness

  • Providing investment protection while boosting productivity of existing EMC and third party storage in customer sites

  • Brings caching closer to the application where the data is accessed while leverage larger scale direct attached and SAN block storage

  • Focusing message for SSD back on to little data as well as big data for mainstream broad customer adoption scenarios

  • Leveraging benefit and strength of SSD as a read cache and scalable of underlying downstream disk for data storage

  • Reducing concerns around SSD endurance or duty cycle wear and tear by using as a read cache

  • Off loads underlying storage systems from some read requests enabling them to do more work for other servers

Additional related material:
Part II: EMC VFCache respinning SSD and intelligent caching
IT and storage economics 101, supply and demand
2012 industry trends perspectives and commentary (predictions)
Speaking of speeding up business with SSD storage
New Seagate Momentus XT Hybrid drive (SSD and HDD)
Are Hard Disk Drives (HDDs) getting too big?
Unified storage systems showdown: NetApp FAS vs. EMC VNX
Industry adoption vs. industry deployment, is there a difference?
Two companies on parallel tracks moving like trains offset by time: EMC and NetApp
Data Center I/O Bottlenecks Performance Issues and Impacts
From bits to bytes: Decoding Encoding
Who is responsible for vendor lockin
EMC VPLEX: Virtual Storage Redefined or Respun?
EMC interoperabity support matrix

Ok, nuff said for now, I think I see some storm clouds rolling in…

Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press, 2011), The Green and Virtual Data Center (CRC Press, 2009), and Resilient Storage Networks (Elsevier, 2004)

twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2012 StorageIO and UnlimitedIO All Rights Reserved