Now lets look at using a tip from Dave Warburton to make an internal SATA HDD into an RDM for one of my Windows-based VMs.
My challenge was that I have a VM with a guest that I wanted to have a Raw Device Mapping (RDM) internal SATA HDD accessible to it, expect the device was an internal SATA device. Given that using the standard tools and reading some of the material available, it would have been easy to give up and quit since the SATA device was not attached to an FC or iSCSI SAN (such as my Iomega IX4 I bought from Amazon.com).
Image of internal SATA drive being added as a RDM with vClient
Thanks to Dave’s great post that I found, I was able to create a RDM of an internal SATA drive, present it to the existing VM running Windows 7 ultimate and it is now happy, as am I.
Pay close attention to make sure that you get the correct device name for the steps in Dave’s post (link is here).
For the device that I wanted to use, the device name was:
From the ESX command line I found the device I wanted to use which is:
t10.ATA_____ST1500LM0032D9YH148_____Z110S6M5
Then I used the following ESX shell command per Dave’s tip to create an RDM of an internal SATA HDD:
Then the next steps were to update an existing VM using vSphere client to use the newly created RDM.
Hint, Pay very close attention to your device naming, along with what you name the RDM and where you find it. Also, recommend trying or practicing on a spare or scratch device first, if something is messed up. I practiced on a HDD used for moving files around and after doing the steps in Dave’s post, added the RDM to an existing VM, started the VM and accessed the HDD to verify all was fine (it was). After shutting down the VM, I removed the RDM from it as well as from ESX, and then created the real RDM.
As per Dave’s tip, vSphere Client did not recognize the RDM per say, however telling it to look at existing virtual disks, select browse the data stores, and low and behold, the RDM I was looking for was there. The following shows an example of using vSphere to add the new RDM to one of my existing VMs.
In case you are wondering, why I want to make a non SAN HDD as a RDM vs. doing something else? Simple, the HDD in question is a 1.5TB HDD that has backups on that I want to use as is. The HDD is also bit locker protected and I want the flexibility to remove the device if I have to being accessible via a non-VM based Windows system.
Image of my VMware server with internal RDM and other items
Could I have had accomplished the same thing using a USB attached device accessible to the VM?
Yes, and in fact that is how I do periodic updates to removable media (HDD using Seagate Goflex drives) where I am not as concerned about performance.
While I back up off-site to Rackspace and AWS clouds, I also have a local disk based backup, along with creating periodic full Gold or master off-site copies. The off-site copies are made to removable Seagate Goflex SATA drives using a USB to SATA Goflex cable. I also have the Goflex eSATA to SATA cable that comes in handy to quickly attach a SATA device to anything with an eSATA port including my Lenovo X1.
As a precaution, I used a different HDD that contained data I was not concerned about if something went wrong to test to the process before doing it with the drive containing backup data. Also as a precaution, the data on the backup drive is also backed up to removable media and to my cloud provider.
Thanks again to both Dave and Duncan for their great tips; I hope that you find these and other material on their sites as useful as I do.
Meanwhile, time to get some other things done, as well as continue looking for and finding good work a rounds and tricks to use in my various projects, drop me a note if you see something interesting.
All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved
Recently I had these and some other questions and spent some time looking around, thus this post highlights some great information I have found for addressing the above VMware challenges and some others.
The SSD solution is via a post I found on fellow VMware vExpert Duncan Epping’s yellow-brick site which if you are into VMware or server virtualization in general, and particular a fan of high-availability in general or virtual specific, add Duncan’s site to your reading list. Duncan also has some great books to add to your bookshelves including VMware vSphere 5.1 Clustering Deepdive (Volume 1) and VMware vSphere 5 Clustering Technical Deepdive that you can find at Amazon.com.
Duncan’s post shows how to fake into thinking that a HDD was a SSD for testing or other purposes. Since I have some Seagate Momentus XT HHDDs that combine the capacity of a traditional HDD (and cost) with the read performance closer to a SSD (without the cost or capacity penalty), I was interested in trying Duncan’s tip (here is a link to his tip). Essential Duncan’s tip shows how to use esxcli storage nmp satp and esxcli storage core commands to make a non-SSD look like a SSD.
The commands that were used from the VMware shell per Duncan’s tip:
After all, if the HHDD is actually doing some of the work to boost and thus fool the OS or hypervisor that it is faster than a HDD, why not tell the OS or hypervisor in this case VMware ESX that it is a SSD. So far have not seen nor do I expect to notice anything different in terms of performance as that already occurred going from a 7,200RPM (7.2K) HDD to the HHDD.
If you know how to decide what type of a HDD or SSD a device is by reading its sense code and model number information, you will recognize the circled device as a Seagate Momentus XT HHDD. This particular model is Seagate Momentus XT II 750GB with 8GB SLC nand flash SSD memory integrated inside the 2.5-inch drive device.
Normally the Seagate HHDDs appear to the host operating system or whatever it is attached to as a Momentus 7200 RPM SATA type disk drive. Since there are not special device drivers, controllers, adapters or anything else, essentially the Momentus XT type HHDD are plug and play. After a bit of time they start learning and caching things to boost read performance (read more about boosting read performance including Windows boot testing here).
Screen shot showing Seagate Momentus XT appearing as a SSD
Note that the HHDD (a Seagate Momentus XT II) is a 750GB 2.5” SATA drive that boost read performance with the current firmware. Seagate has hinted that there could be a future firmware version to enable write caching or optimization however, I have waited for a year.
Disclosure: Seagate gave me an evaluation copy of my first HHDD a couple of years ago and I then went on to buy several more from Amazon.com. I have not had a chance to try any Western Digital (WD) HHDDs yet, however I do have some of their HDDs. Perhaps I will hear something from them sometime in the future.
For those who are SSD fans or that actually have them, yes, I know SSD’s are faster all around and that is why I have some including in my Lenovo X1. Thus for write intensive go with a full SSD today if you can afford them as I have with my Lenovo X1 which enables me to save large files faster (less time waiting). However if you want the best of both worlds for lab or other system that is doing more reads vs. writes as well as need as much capacity as possible without breaking the budget, check out the HHDDs.
All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved
This is a follow-up companion post to the larger industry trends and perspectives series from earlier today (Part I, Part II and Part III) pertaining to today’s VMAX 10K enhancement and other announcements by EMC, and the industry myth of if large storage arrays or systems are dead.
The enhanced VMAX 10K scales from a couple of dozen up to 1,560 HDDs (or mix of HDD and SSDs). There can be a mix of 2.5 inch and 3.5 inch devices in different drive enclosures (DAE). There can be 25 SAS based 2.5 inch drives (HDD or SSD) in the 2U enclosure (see figure with cover panels removed), or 15 3.5 inch drives (HDD or SSD) in a 3U enclosure. As mentioned, there can be all 2.5 inch (including for vault drives) for up to 1,200 devices, all 3.5 inch drives for up to 960 devices, or a mix of 2.5 inch (2U DAE) and 3.5 inch (3U DAE) for a total of 1,560 drives.
Image courtesy EMC
Note carefully in the figure (courtesy of EMC) that the 2U 2.5 inch DAE and 3U 3.5 inch DAE along with the VMAX 10K are actually mounted in a 3rd cabinet or rack that is part of today’s announcement.
Also note that the DAE’s are still EMC; however as part of today’s announcement, certain third-party cabinets or enclosures such as might be found in a collocation (colo) or other data center environment can be used instead of EMC cabinets. The VMAX 10K can however like the VMAX 20K and 40K support external storage virtualized similar to what has been available from HDS (VSP/USP) and HP branded Hitachi equivalent storage, or using NetApp V-Series or IBM V7000 in a similar way.
As mentioned in one of the other posts, there are various software functionality bundles available. Note that SRDF is a separate license from the bundles to give customers options including RecoverPoint.
Check out the three post industry trends and perspectives posts here, here and here.
All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved
This is the third in a multi-part series of posts (read first post here and second post here) looking at what else EMC announced today in addition to an enhanced VMAX 10K and dispelling the myth that large storage arrays are dead (or at least for now).
In addition to the VMAX 10K specific updates, EMC also announced the release of a new version of their Enginuity storage software (firmware, storage operating system). Enginuity is supported across all VMAX platforms and features the following:
Replication enhancements include TimeFinder clone refresh, restore and four site SRDF for the VMAX 10K, along with think or thin support. This capability enables functionality across VMAX 10K, 40K or 20K using synchronous or asynchronous and extends earlier 3 site to 4 site and mix modes. Note that larger VMAX systems had the extended replication feature support with VMAX 10K now on par with those. Note that the VMAX can be enhanced with VPLEX in front of storage systems (local or wide area, in region HA and out of region DR) and RecoverPoint behind the systems supporting bi-synchronous (two-way), synchronous and asynchronous data protection (CDP, replication, snapshots).
Unisphere for VMAX 1.5 manages DMX along with VMware VAAI UNMAP and space reclamation, block zero and hardware clone enhancements, IPV6, Microsoft Server 2012 support and VFCache 1.5.
Support for mix of 2.5 inch and 3.5 inch DAEs (disk array enclosures) along with new SAS drive support (high-performance and high-capacity, and various flash-based SSD or EFD).
The addition of a fourth dynamic tier within FAST for supporting third-party virtualized storage, along with compression of in-active, cold or stale data (manual or automatic) with 2 to 1 data footprint reduction (DFR) ratio. Note that EMC was one of early vendors to put compression into its storage systems on a block LUN basis in the CLARiiON (now VNX) along with NetApp and IBM (via their Storwize acquisition). The new fourth tier also means that third-party storage does not have to be the lowest tier in terms of performance or functionality.
Federated Tiered Storage (FTS) is now available on all EMC block storage systems including those with third-party storage attached in virtualization mode (e.g. VMAX). In addition to supporting tiering across its own products, and those of other vendors that have been virtualized when attached to a VMAX, ANSI T10 Data Integrity Field (DIF) is also supported. Read more about T10 DIF here, and here.
Front-end performance enhancements with host I/O limits (Quality of Service or QoS) for multi tenant and cloud environments to balance or prioritize IO across ports and users. This feature can balance based on thresholds for IOPS, bandwidth or both from the VMAX. Note that this feature is independent of any operating system based tool, utility, pathing driver or feature such as VMware DRS and Storage I/O control. Storage groups are created and mapped to specific host ports on the VMAX with the QoS performance thresholds applied to meet specific service level requirements or objectives.
For discussion (or entertainment) purpose, how about the question of if Enginuity qualifies or can be considered as a storage hypervisors (or storage virtualization or virtual storage)? After all, the VMAX is now capable of having third-party storage from other vendors attached to it, something that HDS has done for many years now. For those who feel a storage hypervisor, virtual storage or storage virtualization requires software running on Intel or other commodity based processors, guess what the VMAX uses for CPU processors (granted, you can’t simply download Enginuity software and run on a Dell, HP, IBM, Oracle or SuperMicro server).
I am guessing some of EMC competitors and their surrogates or others who like to play the storage hypervisor card game will be quick to tell you it is not based on various reasons or product comparisons, however you be the judge.
Back to the question of if, traditional high-end storage arrays are dead or dying (from part one in this series).
IMHO as mentioned not yet.
Granted like other technologies that have been declared dead or dying yet still in use (technology zombies), they continue to be enhanced, finding new customers, or existing customers using them in new ways, their roles are evolving, this still alive.
For some environments as has been the case over the past decade or so, there will be a continued migration from large legacy enterprise class storage systems to midrange or modular storage arrays with a mix of SSD and HDD. Thus, watch out for having a death grip not letting go of the past, while being careful about flying blind into the future. Do not be scared, be ready, do your homework with clouds, virtualization and traditional physical resources.
Likewise, there will be the continued migration for some from traditional mid-range class storage arrays to all flash-based appliances. Yet others will continue to leverage all the above in different roles aligned to where their specific features best serve the applications and needs of an organization.
In the case of high-end storage systems such as EMC VMAX (aka formerly known as DMX and Symmetrix before that) based on its Enginuity software, the hardware platforms will continue to evolve as will the software functionality. This means that these systems will evolve to handling more workloads, as well as moving into new environments from service providers to mid-range organizations where the systems were before out of their reach.
Smaller environments have grown larger as have their needs for storage systems while higher end solutions have scaled down to meet needs in different markets. What this means is a convergence of where smaller environments have bigger data storage needs and can afford the capabilities of scaled down or Right-sized storage systems such as the VMAX 10K.
Thus while some of the high-end systems may fade away faster than others, for those that continue to evolve being able to move into different adjacent markets or usage scenarios, they will be around for some time, at least in some environments.
Avoid confusing what is new and cool falling under industry adoption vs. what is productive and practical for customer deployment. Systems like the VMAX 10K are not for all environments or applications; however, for those who are open to exploring alternative solutions and approaches, it could open new opportunities.
If there is a high-end storage system platform (e.g. Enginuity) that continues to evolve, re-invent itself in terms of moving into or finding new uses and markets the EMC VMAX would be at or near the top of such list. For the other vendors of high-end storage system that are also evolving, you can have an Atta boy or Atta girl as well to make you feel better, loved and not left out or off of such list. ;)
Ok, nuff said for now.
Disclosure: EMC is not a StorageIO client; however, they have been in the past directly and via acquisitions that they have done. I am however a customer of EMC via my Iomega IX4 NAS (I never did get the IX2 that I supposedly won at EMCworld ;) ) that I bought on Amazon.com and indirectly via VMware products that I have, oh, and they did sent me a copy of the new book Human Face of Big Data (read more here).
All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved
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.
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
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 SASHDDs, along with fast SASHDDs, 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.
All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved
As luck or fate would turn out, I was in Nijkerk which is about an hour train ride from Amsterdam central station plus a free day in my schedule. After a morning train ride and nice walk from Amsterdam Central I arrived at the Tobacco Theatre (a former tobacco trading venue) where Ceph Day was underway, and in time for lunch of Krokettens sandwich.
Lets take a quick step back and address for those not familiar what is Ceph (Cephalanthera) and why it was worth spending a day to attend this event. Ceph is an open source distributed object scale out (e.g. cluster or grid) software platform running on industry standard hardware.
Ceph is used for deploying object storage, cloud storage and managed services, general purpose storage for research, commercial, scientific, high performance computing (HPC) or high productivity computing (commercial) along with backup or data protection and archiving destinations. Other software similar in functionality or capabilities to Ceph include OpenStack Swift, Basho Riak CS, Cleversafe, Scality and Caringo among others. There are also the tin wrapped software (e.g. appliances or pre-packaged) solutions such as Dell DX (Caringo), DataDirect Networks (DDN) WOS, EMC ATMOS and Centera, Amplidata and HDS HCP among others. From a service standpoint, these solutions can be used to build services similar Amazon S3 and Glacier, Rackspace Cloud files and Cloud Block, DreamHost DreamObject and HP Cloud storage among others.
At the heart of Ceph is RADOS a distributed object store that consists of peer nodes functioning as object storage devices (OSD). Data can be accessed via REST (Amazon S3 like) APIs, Libraries, CEPHFS and gateway with information being spread across nodes and OSDs using a CRUSH based algorithm (note Sage Weil is one of the authors of CRUSH: Controlled, Scalable, Decentralized Placement of Replicated Data). Ceph is scalable in terms of performance, availability and capacity by adding extra nodes with hard disk drives (HDD) or solid state devices (SSDs). One of the presentations pertained to DreamHost that was an early adopter of Ceph to make their DreamObjects (cloud storage) offering.
In addition to storage nodes, there are also an odd number of monitor nodes to coordinate and manage the Ceph cluster along with optional gateways for file access. In the above figure (via DreamHost), load balancers sit in front of gateways that interact with the storage nodes. The storage node in this example is a physical server with 12 x 3TB HDDs each configured as a OSD.
In the DreamHost example above, there are 90 storage nodes plus 3 management nodes, the total raw storage capacity (no RAID) is about 3PB (12 x 3TB = 36TB x 90 = 3.24PB). Instead of using RAID or mirroring, each objects data is replicated or copied to three (e.g. N=3) different OSDs (on separate nodes), where N is adjustable for a given level of data protection, for a usable storage capacity of about 1PB.
Note that for more usable capacity and lower availability, N could be set lower, or a larger value of N would give more durability or data protection at higher storage capacity overhead cost. In addition to using JBOD configurations with replication, Ceph can also be configured with a combination of RAID and replication providing more flexibility for larger environments to balance performance, availability, capacity and economics.
One of the benefits of Ceph is the flexibility to configure it how you want or need for different applications. This can be in a cost-effective hardware light configuration using JBOD or internal HDDs in small form factor generally available servers, or high density servers and storage enclosures with optional RAID adapters along with SSD. This flexibility is different from some cloud and object storage systems or software tools which take a stance of not using or avoiding RAID vs. providing options and flexibility to configure and use the technology how you see fit.
Here are some links to presentations from Ceph Day: Introduction and Welcome by Wido den Hollander Ceph: A Unified Distributed Storage System by Sage Weil Ceph in the Cloud by Wido den Hollander DreamObjects: Cloud Object Storage with Ceph by Ross Turk Cluster Design and Deployment by Greg Farnum Notes on Librados by Sage Weil
While at Ceph day, I was able to spend a few minutes with Sage Weil Ceph creator and founder of inktank.com to record a pod cast (listen here) about what Ceph is, where and when to use it, along with other related topics. Also while at the event I had a chance to sit down with Curtis (aka Mr. Backup) Preston where we did a simulcast video and pod cast. The simulcast involved Curtis recording this video with me as a guest discussing Ceph, cloud and object storage, backup, data protection and related themes while I recorded this pod cast.
One of the interesting things I heard, or actually did not hear while at the Ceph Day event that I tend to hear at related conferences such as SNW is a focus on where and how to use, configure and deploy Ceph along with various configuration options, replication or copy modes as opposed to going off on erasure codes or other tangents. In other words, instead of focusing on the data protection protocol and algorithms, or what is wrong with the competition or other architectures, the Ceph Day focused was removing cloud and object storage objections and enablement.
Where do you get Ceph? You can get it here, as well as via 42on.com and inktank.com.
At the recent StorageExpo Holland event in Utrecht, I gave a couple of presentations, one on cloud, virtualization and storage networking trends, the other taking a deeper look at Solid State Devices (SSD’s). As in the past, StorageExpo Holland was great in a fantastic venue, with many large exhibits and great attendance which I heard was over 6,000 people over two days (excluding exhibitor vendors, vars, analysts, press and bloggers) which was several times larger than what was seen in Frankfurt at the SNW event.
Both presentations were very well attended and included lively interactive discussion during and after the sessions. The theme of my second talk was SSD, the question is not if, rather what to use where, how and when which brings us up to this post.
Often in technology what is old can be new, what is new can be seen as old, if you have seen, experienced or done something before you will have a sense of DejaVu and it might be evolutionary. On the other hand, if you have not seen, heard, experienced, or found a new audience, then it can be revolutionary or maybe even an industry first ;).
Technology evolves, gets improved on, matures, and can often go in cycles of adoption, deployment, refinement, retirement, and so forth. SSD in general has been an on again, off again type cycle technology for the past several decades except for the past six to seven years. Normally there is an up cycle tied to different events, servers not being fast enough or affordable so use SSD to help address performance woes, or drives and storage systems not being fast enough and so forth.
Btw, for those of you who think that the current SSD focused technology (nand flash) is new, it is in fact 25 years old and still evolving and far from reaching its full potential in terms of customer deployment opportunities.
Nand flash memory has helped keep SSD practical for the past several years riding the similar curve that is keeping hard disk drives (HDD’s) that they were supposed to replace alive. That is improved reliability, endurance or duty cycle, better annual failure rate (AFR), larger space capacity, lower cost, and enhanced interfaces, packaging, power and functionality.
DRAM historically at least for enterprise has been the main option for SSD based solutions using some form of data persistency. Data persistency options include battery backup combined with internal HDD’s to de stage information from the DRAM before power was lost. TMS (recently bought by IBM) was one of the early SSD vendors from the DRAM era that made the transition to flash including being one of the first many years ago to combine DRAM as a cache layer over nand flash as a persistency or de-stage layer. This would be an example of if you were not familiar with TMS back then and their capacities, you might think or believe that some more recent introductions are new and revolutionary, and perhaps they are in their own right or with enough caveats and qualifiers.
An emerging trend, which for some will be Dejavu, is that of using more DRAM in combination with nand flash SSD.
So is the future in the past? Some would say no, some will say yes, however IMHO there are lessons to learn and leverage from the past while looking and moving forward.
Early SSD’s were essentially RAM disks, that is a portion of main random access memory (RAM) or what we now call DRAM set aside as a non persistent (unless battery backed up) cache or device. Using a device driver, applications could use the RAM disk as though it were a normal storage system. Different vendors springing up with drivers for various platforms and disappeared as their need were reduced with faster storage systems, interfaces and ram disks drives supplied by vendors, not to mention SSD devices.
Oh, for you tech trivia types, there was also database machines from the late 80’s such as Briton Lee that would offload your database processing functions to a specialized appliance. Sound like Oracle ExaData I, II or III to anybody?
Ok, so we have seen this movie before, no worries, old movies or shows get remade, and unless you are nostalgic or cling to the past, sure some of the remakes are duds, however many can be quite good.
Same goes with the remake of some of what we are seeing now. Sure there is a generation that does not know nor care about the past, its full speed ahead and leverage what will get them there.
Thus we are seeing in memory databases again, some of you may remember the original series (pick your generation, platform, tool and technology) with each variation getting better. With 64 bit processor, 128 bit and beyond file system and addressing, not to mention ability for more DRAM to be accessed directly, or via memory address extension, combined with memory data footprint reduction or compression, there is more space to put things (e.g. no such thing as a data or information recession).
Lets also keep in mind that the best IO is the IO that you do not have to do, and that SSD which is an extension of the memory map plays by the same rules of real estate. That is location matters.
Thus, here we go again for some of you (DejaVu), while for others get ready for a new and exciting ride (new and revolutionary). We are back to the future with in memory database which while for a time will take some pressure from underlying IO systems until they once again out grow server memory addressing limits (or IT budgets).
However for those who do not fall into a false sense of security, no fear, as there is no such thing as a data or information recession. Sure as the sun rises in the east and sets in the west, sooner or later those IO’s that were or are being kept in memory will need to be de-staged to persistent storage, either nand flash SSD, HDD or somewhere down the road PCM, mram and more.
There is another trend that with more IOs being cached, reads are moving to where they should resolve which is closer to the application or via higher up in the memory and IO pyramid or hierarchy (shown above).
Thus, we could see a shift over time to more writes and ugly IOs being sent down to the storage systems. Keep in mind that any cache historically provides temporal relieve, question is how long of a temporal relief or until the next new and revolutionary or DejaVu technology shows up.
Normally solid state devices (SSD) including non-persistent DRAM, and persistent nand flash are thought of in the context of performance including bandwidth or throughput, response time or latency, and IOPS or transactions. However there is another role where SSD are commonly used where the primary focus is not performance. Besides consumer devise such as iPhones, iPads, iPods, Androids, MP3, cell phones and digital cameras, the other use is for harsh environments.
Harsh environments include those (both commercial and government) where use of SSDs are a solution to vibration or other rough handling. These include commercial and military aircraft, telemetry and mobile command, control and communications, energy exploration among others.
What’s also probably not commonly thought about is that the vendors or solution providers for the above specialized environments include mainstream vendors including IBM (via their TMS acquisition) and EMC among others. Yes, EMC is involved with deploying SSD in different environments including all nand flash-based VNX systems.
In a normal IT environment, vibration should not be an issue for storage devices assuming quality solutions with good enclosures are used. However some environments that are pushing the limits on density may become more susceptible to vibration. Not all of those use cases will be SSD opportunities, however some that can leverage IO density along with tolerance to vibration will be a good fit.
Does that mean HDDs can not or should not be used in high density environments where vibration can be an issue?
That depends.
If the right drive enclosures, type of drive are used following manufactures recommendations, then all should be good. Keep in mind that there are many options to leverage SSD for various scenarios.
Which tool or technology to use when, where or how much will depend on the specific situation, or perhaps your preferences for a given product or approach.
This is the second (here is the firstSNW 2012 Waynes World) in a series of StorageIO industry trends and perspective audio blog and pod cast about Storage Networking World (SNW) Fall 2012 in Santa Clara California.
Given how at conference conversations tend to occur in the hallways, lobbies and bar areas of venues, what better place to have candid conversations with people from throughout the industry, some you know, some you will get to know better.
In this episode, I’m joined by my co-host Bruce Rave aka Bruce Ravid of Ravid & Associates as we catch up and visit with Chief Marketing Officer (CMO) of Starboard Storage Systems Karl Chen in the Santa Clara Hyatt (event venue) lobby bar area.
There are at least two different meanings for IOPs, which for those not familiar with the information technology (IT) and data storage meaning is Input/output Operations Per second (e.g. data movement activity). Another meaning for IOP that is the international organization for a participatory society (iopsociety.org), and their fundraising activity found here.
I recently came across a piece (here and here) talking about RAID and IOPs that had some interesting points; however, some generalizations could use some more comments. One of the interesting comments and assertions is that RAID writes increase with the number of drives in the parity scheme. Granted the specific implementation and configuration could result in an it depends type response.
Here are some more perspectives to the piece (here and here) as the sites comments seem to be restricted.
Keep in mind that such as with RAID 5 (or 6) performance, your IO size will have a bearing on if you are doing those extra back-end IOs. For example if you are writing a 32KB item that is accomplished by a single front-end IO from an applications server, and your storage system, appliance, adapter, software implementing and performing the RAID (or erasure coding for that matter) has a chunk size of say 8KB (e.g. the amount of data written to each back-end drive). Then a 5 drive R5 (e.g. 4+1) would in fact have five back-end IOPS (32KB / 8KB = 4 + 1 (8KB Parity)).
Otoh of the front end IOP were only 16KB (using whole numbers for simplicity, otherwise round-up), in the case of a write, there would be three back-end writes with the R5 (e.g. 2 + 1). Keep in mind the controller/software managing the RAID would (or should) try to schedule back-end IO with cache, read-head, write-behind, write-back, other forms of optimization etc.
In the piece (here and here), a good point is the understanding and factoring in IOPS is important, as is also latency or response time in addition to bandwidth or throughput, along with availability, they are all inter-related.
Also very important is to keep in mind the size of the IOP, read and write, random, sequential etc.
RAID along with erasure coding is a balancing act between performance, availability, space capacity and economics aligned to different application needs.
RAID 0 (R0) actually has a big impact on performance, no penalty on writes; however, it has no availability protection benefit and in fact can be a single point of failure (e.g. loss of a HDD or SSD) impacts the entire R0 group. However, for static items, or items that are being journaled and protected on some other medium/RAID/protection scheme, R0 is used more than people realize for scratch/buffer/transient/read cache types of applications. Keep in mind that it is a balance of all performance and capacity with the exposure of no availability as opposed to other approaches. Thus, do not be scared of R0, however also do not get burned or hurt with it either, treat it with respect and can be effective for something’s.
Also mentioned in the piece was that SSD based servers will perform vastly better than SATA or SAS based ones. I am assuming that the authors meant to say better than SAS or SATA DAS based HDDs?
Keep in mind that unless you are using a PCIe nand flash SSD card as a target or cache or RAID card, most SSD drives today are either SAS or SATA (being the more common) along with moving from 3Gb SAS or SATA to 6Gb SAS & SATA.
Also while HDD and SSDs can do a given number of reads or writes per second, those will vary based on the size of the IO, read, write, random, sequential. However what can have the biggest impact and where I have seen too many people or environments get into a performance jam is when assuming that those IOP numbers per HDD or SSD are a given. For example assuming that 100-140, IOPs (regardless of size, type, etc.) can be achieved as a limiting factor is the type of interface and controller/adapter being used.
I have seen fast HDDs and SSDs deliver sub-par performance or not meeting expectations fast interfaces such as iSCSI/SAS/SATA/FC/FCoE/IBA or other interfaces due to bottlenecks in the adapter card, storage system / appliance / controller / software. In some cases you may see more effective IOPs or reads, writes or both, while on other implementations you may see lower than expected due to internal implementation bottlenecks or architectural designs. Hint, watch out for solutions where the vendor tries to blame poor performance on the access network (e.g. SAS, iSCSI, FC, etc.) particular if you know that those are not bottlenecks.
In terms of fund-raising, if you feel so compelled, send a gift, donation, sponsorship, project, buy some books, piece of work, assignment, research project, speaking, keynote, web cast, video or seminar event my way and just like professional fund-raisers, or IOPS vendors, StorageIO accept visa, Master Card, American express, Pay Pal, check and traditional POs.
As for this site and comments, outside of those caught in the spam trap, courteous perspectives and discussions are welcome.
All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved
In the spirit of Halloween and zombies season, a couple of thoughts come to mind about vendor tricks and treats. This is an industry trends and perspectives post, part of an ongoing series looking at various technology and fun topics.
The first trick or treat game pertains to the blame game; you know either when something breaks, or at the other extreme, before you have even made a decision to buy something. The trick or treat game for decision-making goes something like this.
Vendor “A” says products succeed with their solution while failure results with a solution from “B” when doing “X”. Otoh, vendor “B” claims that “X” will fail when using a solution from vendor “A”. In fact, you can pick what you want to substitute for “X”, perhaps VDI, PCIe, Big Data, Little Data, Backup, Archive, Analytics, Private Cloud, Public Cloud, Hybrid Cloud, eDiscovery you name it.
This is not complicated math or big data problem requiring a high-performance computing (HPC) platform. A HPC Zetta-Flop processing ability using 512 bit addressing of 9.9 (e.g. 1 nine) PettaBytes of battery-backed DRAM and an IO capability of 9.99999 (e.g. 5 9’s) trillion 8 bit IOPS to do table pivots or runge kutta numerical analysis, map reduce, SAS or another modeling with optional iProduct or Android interface are not needed.
StorageIO images of touring Texas Advanced Computing (e.g. HPC) Center
Can you solve this equation? Hint it does not need a PhD or any other advanced degree. Another hint, if you have ever been at any side of the technology product and services decision-making table, regardless of the costume you wore, you should know the answer.
Of course the question of would “X” fail regardless of who or what “A” or “B” let alone a “C”, “D” or “F”? In other words, it is not the solution, technology, vendor or provider, rather the problem or perhaps even lack thereof that is the issue. Or is it a case where there is a solution from “A”, “B” or any others that is looking for a problem, and if it is the wrong problem, there can be a wrong solution thus failure?
Another trick or treat game is vendors public relations (PR) or analyst relations (AR) people to ask for one thing and delivery or ask another. For example, some vendor, service provider, their marketing AR and PR people or surrogates make contact wanting to tell of various success and failure story. Of course, this is usually their success and somebody else’s failure, or their victory over something or someone who sometimes can be interesting. Of course, there are also the treats to get you to listen to the above, such as tempt you with a project if you meet with their subject, which may be a trick of a disappearing treat (e.g. magic, poof it is gone after the discussion).
There are another AR and PR trick and treat where they offer on behalf of their representative organization or client to a perspective or exclusive insight on their competitor. Of course, the treat from their perspective is that they will generously expose all that is wrong with what a competitor is saying about their own (e.g. the competitors) product.
Let me get this straight, I am not supposed to believe what somebody says about his or her own product, however, supposed to believe what a competitor says is wrong with the competition’s product, and what is right with his or her own product.
Hmm, ok, so let me get this straight, a competitor say “A” wants to tell me what somebody say from “B” has told me is wrong and I should schedule a visit with a truth squad member from “A” to get the record set straight about “B”?
Does that mean then that I go to “B” for a rebuttal, as well as an update about “A” from “B”, assuming that what “A” has told me is also false about themselves, and perhaps about “B” or any other?
Too be fair, depending on your level of trust and confidence in either a vendor, their personal or surrogates, you might tend to believe more from them vs. others, or at least until you been tricked after given treats. There may be some that have been tricked, or they tried applying to many treats to present a story that behind the costume might be a bit scary.
Having been through enough of these, and I candidly believe that sometimes “A” or “B” or any other party actually do believe that they have more or better info about their competitor and that they can convince somebody about what their competitor is doing better than the competitor can. I also believe that there are people out there who will go to “A” or “B” and believe what they are told by based on their preference, bias or interests.
When I hear from vendors, VARs, solution or service providers and others, it’s interesting hearing point, counterpoint and so forth, however if time is limited, I’am more interested in hearing from such as “A” about them, what they are doing, where success, where challenges, where going and if applicable, under NDA go into more detail.
Customer success stories are good, however again, if interested in what works, what kind of works, or what does not work, chances are when looking for G2 vs. GQ, a non-scripted customer conversation or perspective of the good, the bad and the ugly is preferred, even if under NDA. Again, if time is limited which it usually is, focus on what is being done with your solution, where it is going and if compelled send follow-up material that can of course include MUD and FUD about others if that is your preference.
Then there is when during a 30 minute briefing, the vendor or solution provider is still talking about trends, customer pain points, what competitors are doing at 21 minutes into the call with no sign of an announcement, update or news in site
Lets not forget about the trick where the vendor marketing or PR person reaches out and says that the CEO, CMO, CTO or some other CxO or Chief Jailable Officer (CJO) wants to talk with you. Part of the trick is when the CxO actually makes it to the briefing and is not ready, does not know why the call is occurring, or, thinks that a request for an audience has been made with them for an interview or something else.
A treat is when 3 to 4 minutes into a briefing, the vendor or solution provider has already framed up what and why they are doing something. This means getting to what they are announcing or planning on doing and getting into a conversation to discuss what they are doing and making good follow-up content and resources available.
Sometimes a treat is when a briefer goes on autopilot nailing their script for 29 of a 30 minute session then use the last-minute to ask if there are any questions. The reason autopilot briefings can be a treat is when they are going over what is in the slide deck, webex, or press release thus affording an opportunity to get caught up on other things while talk at you. Hmm, perhaps need to consider playing some tricks in reward for those kind of treats? ;)
Do not be scared, not everybody is out to trick you with treats, and not all treats have tricks attached to them. Be prepared, figure out who is playing tricks with treats, and who has treats without tricks.
Oh, and as a former IT customer, vendor and analyst, one of my favorites is contact information of my dogs to vendors who require registration on their websites for basic things such as data sheets. Another is supplying contact information of competing vendors sales reps to vendors who also require registration for basic data sheets or what should otherwise be generally available information as opposed to more premium treats. Of course there are many more fun tricks, however lets leave those alone for now.
Note: Zombie voting rules apply which means vote early, vote often, and of course vote for those who cannot include those that are dead (real or virtual).
Where To Learn More
View additiona related material via the following links.
All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO. All Rights Reserved. StorageIO is a registered Trade Mark (TM) of Server StorageIO.
Following up from my last post over at InfoStor about metrics that matter, here is a link to a new piece that I did on storage vendors benchmarking and related topics. This new post looked at an storage performance council (SPC1) benchmark that HP did with their P10000 (e.g. 3PAR) storage system under assertions by some in the industry that they were short stroking to meet better performance.
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?
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.
