It’s not how much you have, its how storage I/O work gets done that matters
Following last weeks VMworld event in San Francisco where among other announcements including this one around Virtual SAN (VSAN) along with Software Defined Storage (SDS), EMC today made several announcements.
Today’s EMC announcements include:
- The new VNX MCx (Multi Core optimized) family of storage systems
- VSPEX proven infrastructure portfolio enhancements
- Availability of ViPR Software Defined Storage (SDS) platform (read more from earlier posts here, here and here)
- Statement of direction preview of Project Nile for elastic cloud storage platform
- XtremSW server cache software version 2.0 with enhanced management and support for VMware, AIX and Oracle RAC
Summary of the new EMC VNX MCx storage systems include:
- More processor cores, PCIe Gen 3 (faster bus), front-end and back-end IO ports, DRAM and flash cache (as well as drives)
- More 6Gb/s SAS back-end ports to use more storage devices (SAS and SATA flash SSD, fast HDD and high-capacity HDD)
- MCx – Multi-core optimized with software rewritten to make use of threads and resources vs. simply using more sockets and cores at higher clock rates
- Data Footprint Reduction (DFR) capabilities including block compression and dedupe, file dedupe and thin provisioning
- Virtual storage pools that include flash SSD, fast HDD and high-capacity HDD
- Block (iSCSI, FC and FCoE) and NAS file (NFS, pNFS, CIFS) front-end access with object access via Atmos Virtual Edition (VE) and ViPR
- Entry level pricing starting at below $10,000 USD
What is this MCx stuff, is it just more hardware?
While there is more hardware that can be used in different configurations, the key or core (pun intended) around MCx is that EMC has taken the time and invested in reworking the internal software of the VNX that has its roots going back to the Data General CLARRiON EMC acquired. This is similar to an effort EMC made a few years back when it overhauled what is now known as the VMAX from the Symmetric into the DMX. That effort expanded from a platform or processor port to re-architecting and software optimizing (rewrite portions) to leverage new and emerging hardware capabilities more effectively.
With MCx EMC is doing something similar in that core portions of the VNX software have been re-architected and written to take advantage of more threads and cores being available to do work more effectively. This is not all that different from what occurs (or should) with upper level applications that eventually get rewritten to leverage underlying new capabilities to do more work faster and leverage technologies in a more cost-effective way. MCx also leverages flash as a primary medium with data than being moved (256MB chunks) down into lower tiers of storage (SSD and HDD drives).
ENC VNX has had in the past FLASH Cache which enables SSD drives to be used as an extension of main cache as well as using drive targets. Thus while MCx can and does leverage more and faster core as would most any software, it is also able to leverage those cores and threads in a more effective way. After all, it’s not just how many processors, sockets, cores, threads, L1/L2 cache, DRAM, flash SSD and other resources, its how effective you use them. Also keep in mind that a bit of flash in the right place used effectively can go a long way vs. having a lot of cache in the wrong place or not used optimally that will end up costing a lot of cash.
Moving forward this means that EMC should be able to further refine and optimize other portions of the VNX software not yet updated to make further benefit of new hardware platforms and capabilities.
Does this mean EMC is catching up with newer vendors?
Similar to more of something is not always better, its how those items are used that matters, just because something is new does not mean its better or faster. That will manifest itself when they are demonstrated and performance results shown. However key is showing the performance across different workloads that have relevance to your needs and that convey metrics that matter with context.
Context matters including type and size of work being done, number of transactions, IOPs, files or videos served, pages processed or items rendered per unit of time, or response time and latency (aka wait or think time), along with others. Thus some newer systems may be faster on paper, powerpoint, WebEx, You tube or via some benchmarks, however what is the context and how do they compare to others on an apples to apples basis.
What are some other enhancements or features?
Leveraging of FAST VP (Fully Automated Storage Tiering for Virtual Pools) with improved MCx software
Increases the effectiveness of available hardware resources (processors, cores, DRAM, flash, drives, ports)
Active active LUNs accessible by both controllers as well as legacy AULA support
What does then new VNX MCx family look like?
Is VNX MCx all about supporting VMware?
Interesting that if you read behind the lines, listen closely to the conversations, ask the right questions you will realize that while VMware is an important workload or environment to support, it is not the only one targeted for VNX. Likewise if you listen and look beyond what is normally amplified in various conversations you will find that systems such as VNX are being deployed as back-end storage in cloud (public, private, hybrid) environments for use with technologies such as OpenStack or object based solutions (visit www.objectstoragecenter.com for more on object storage systems and access)..
There is a common myth that the cloud and service providers all use white box commodity hardware including JBOD for their systems which some do, however some are also using systems such as VNX among others. In some of these scenarios the VNX type systems are or will be deployed in large numbers essentially consolidating the functions of what had been done by even larger number of JBOD based systems. This is where some of you will have a DejaVu or back to the future moment from the mid 90s when there was an industry movement to combine all the DAS and JBOD into larger storage systems. Don’t worry if you are not yet reading about this trend in your favorite industry rag or analyst briefing notes, however ask or look around and you might be surprised at what is occurring, granted it might be another year or two before you read about it (just saying ;).
What that means is that VNX MCx is also well positioned for working with ViPR or Atmos Virtual Edition among other cloud and object storage stacks. VNX MCx is also well positioned for its new low-cost of entry for general purpose workloads and applications ranging from file sharing, email, web, database along with demanding high performance, low latency with large amounts of flash SSD. In addition to being used for general purpose storage, VNX MCx will also complement data protection solutions for backup/restore, BC, DR and archiving such as Data Domain, Avamar and Networker among others. Speaking of server virtualization, EMC also has tools for working with Hyper-V, Xen and KVM in addition to VMware.
If there is an all flash VNX MCx doesn’t that compete with XtremIO?
Yes there are all flash VNX MCx just as there have been all flash VNX before, however these will be positioned for different use case scenarios by EMC and their partners to avoid competing head to head with XtremIO. Thus EMC will need to be diligent in being very clear to its own sales and marketing forces as well as those of partners and customers of what to use when, where, why and how.
General thoughts and closing comments
The VNX MCx is a good set of enhancements by EMC and an example of how it’s not as important of how more you have, rather how you can use it to be more effective.
Ok, nuff said (fow now).
All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2016 Server StorageIO and UnlimitedIO LLC All Rights Reserved