Condusiv Technologies Blog

Condusiv Technologies Blog

Blogging @Condusiv

The Condusiv blog shares insight into the issues surrounding system and application performance—and how I/O optimization software is breaking new ground in solving those issues.

National Mortgage Lender Eliminates Sluggish MS-SQL Applications with V-locity I/O Reduction Software

by Brian Morin 25. July 2017 06:01

I first chatted with Chuck Keith (Dir of Infrastructure, Supreme Lending) a couple years ago at VMworld. They had a custom-built loan application that sat on MS-SQL that was the most mission critical application to the business. The loan officers relied on it daily to do their jobs effectively. One problem – it was slow. 

 “Our common workloads are supported by our older Dell Compellent arrays, but all of our MS-SQL workloads are supported by newer Nimble storage arrays. As great as Nimble performs from a ‘cost per performance’ standpoint, it simply wasn’t enough with the growth of data and users we had been experiencing. Loan officers were complaining about slow queries taking five to ten minutes to run reports, and up to five seconds to advance from screen to screen within the loan origination system,” said Chuck Keith, Director of Infrastructure, Supreme Lending.

“At the time, we thought our only solution was to invest hundreds of thousands of dollars into new all-flash arrays to get the performance we needed. No matter how well your business is doing, no one wants to have a million-dollar conversation that’s not in budget. We needed to see how we could maximize performance on the hardware we already had, which led to a conversation with Condusiv,” said Keith.

“We examined a couple server-side caching players including Pernix Data and Infinio, but since Condusiv’s V-locity® I/O reduction software does so much more than server-side caching, its proof of concept came out the clear winner on both performance and price. And we didn’t have to add any additional hardware, since we already had a good amount of DRAM,” said Keith.

Keith continued, “Right off the bat, MS-SQL reporting that used to take five to ten minutes dropped to 30 seconds with V-locity, and all user complaints about sluggishness disappeared. We couldn’t believe it,” said Keith. Moreover, the typical 30-second load times to log into the software package dropped to ten seconds – a 3X improvement. The five-second wait to advance from screen to screen also disappeared, so that users could load each screen almost instantly.

“Not only did V-locity solve our ‘death by a thousand cuts’ issue of excessively small, tiny writes and reads from Windows VMs, but their DRAM caching engine provided huge gains on top of that by offloading a good percentage of hot reads from our underlying Nimble hybrid storage. It made a huge difference and gave back a big chunk of IOPS to our Nimble storage to be used for other things. We saved hundreds of thousands of dollars by being able to squeeze significantly more performance from the hardware stack we already have.” said Keith.

To read the full story on how V-locity I/O reduction software boosted their MS-SQL performance, read here: http://learn.condusiv.com/rs/246-QKS-770/images/CS_SupremeLending.pdf

Tags:

Performance

It’s Diskeeper Groundhog Day

by Brian Morin 12. July 2017 06:08

Every week, I find myself sending the same email to at least one Diskeeper® customer. Almost every time, it’s a new manager/director/VP who joins the company and hears Diskeeper is running on their physical servers or clients. This is how it goes:

Hi Christopher,

I’m the SVP of WW Sales here and received news XYZ company may not be renewing support on your Diskeeper licenses because of concerns with it on MS-SQL servers attached to SAN storage with SSDs.

Since you own these licenses, I wanted to reach out for a quick 15-min tech conversation only to make sure you understand what you have in the latest version. Many still have legacy ideas of Diskeeper when it was a “defrag” product and not applicable to the new world order of SSDs and modern SANs.

I guarantee the current version of our product will offload anywhere from 30-40% of your I/O traffic from your underlying storage to provide a nice performance boost and give some precious I/O headroom back to that subsystem. Many customers offload >50% of I/O by simply adding more memory, enabling them to sweat their storage assets significantly and use those IOPS for other things. It’s a free upgrade while you are active on your maintenance.

As a primer, you can read this case study we published last month with the University of Illinois in which we doubled performance of their SQL and Oracle applications sitting on all-flash arrays. And if you want the short, short summary of what the technology does now, here’s the 2-min video: https://www.youtube.com/watch?v=Ge-49YYPwBM. This is why Gartner named us Cool Vendor of the Year a couple years back.

The good news is that they have heard of Diskeeper. The bad news is that they still associate it with legacy versions that emphasized defragmentation applicable only to spinning disk. For those customers who virtualized and converted their licenses to V-locity®, we don’t run into this issue.

If you are a current Diskeeper customer and have difficulty educating new management, I suggest setting up a tech review between Condusiv and new team members. If you are running all-flash, an alternative approach others have taken is simply replacing their Diskeeper with SSDkeeper® so they don’t run into old “defrag” objections. The core features are identical and both auto-detect if the storage is HDD or SSD and apply the best optimization method.

Keep in mind, since Diskeeper now proactively eliminates excessively small tiny writes and reads in the first place, the whole concept of “defragmentation” is a dead concept for the most part except in some extenuating circumstances. An example would be a heavily fragmented volume on spinning disk that didn’t have Diskeeper on it and could use a one-time clean up. A good example of this is a new customer last week whose full backup was taking over a day to complete! After running Diskeeper on their physical servers, the backup time was cut in half.

Tags:

Defrag | Diskeeper | SAN | SSD, Solid State, Flash

Recently Discovered SSD Vulnerabilities Could Cripple Global Markets with Data Corruption if Exploited by Attackers

by Brian Morin 15. June 2017 10:38

Recently discovered multi-level cell (MLC) solid-state drive (SSD) vulnerabilities by researchers from Carnegie Mellon University, Seagate, and the Swiss Federal Institute of Technology in Zurich, reveal the first-ever security weakness of its kind against MLC SSDs that store much of the world’s data. Two different types of malicious attacks are reported to corrupt data, leaving much of the world’s data currently exposed while organizations search for answers.

If security experts and data protection experts didn’t have enough to worry about already, the latest discovery from Carnegie Mellon University has set off brand new alarms that could be far more crippling than the recent WannaCry virus or any ransomware attack. In this case, data is not infected or held hostage, but is lost entirely - not even the host SSD hardware can be salvaged after such an attack. This is not simply alarming to organizations that stand the most to lose like financial institutions, but we’re talking about real lives here if patient care is compromised as we saw earlier this month at hospitals across the UK.

In a recently published report by researchers from Carnegie Mellon University, Seagate, and the Swiss Federal Institute of Technology in Zurich, there are two types of malicious attacks that can corrupt data and shorten the lifespan of MLC SSDs – a write attack (“program interference”) and a read attack (“read disturb”). Both attacks inundate the SSD with a large number of operations over a short period of time, which can corrupt data, shorten lifespan, and render an SSD useless to store data in a reliable manner into the future. However, both attacks rely upon native read and write operations from the operating system to the solid-state drive, which is circumvented by Condusiv® I/O reduction software on Windows systems (V-locity®, SSDkeeper®, Diskeeper® 16).

The only reason this story has been covered lightly by the media and not sensationalized across headlines is because no one has died yet or lost a billion dollars. This is a new and very different kind of vulnerability. Protection from this kind of an attack is not something that can be addressed by traditional lines of defense like anti-virus software, firmware upgrades, or OS patches. Since it is cost prohibitive for organizations to “rip-and-replace” multi-cell SSDs with single-cell SSDs, they are forced to rely on data sets that have been “backed-up.” However, what good is restoring data to hardware that can no longer reliably store data?

By acting as the “gatekeeper” between the Windows OS and the underlying SSD device, Condusiv I/O reduction software solutions perform inline optimizations at the OS-level before data is physically written or read from the solid-state drive. As a result, Condusiv’s patented technology is the only known solution that can disrupt “program interference” write operation attacks as well as “read disturb” read operation attacks that would attempt to exploit SSD vulnerabilities and corrupt data. While most known for boosting performance of applications running on Windows systems while extending the longevity of SSDs, Condusiv solutions go a step further as the only line of defense against these malicious attacks.

Condusiv’s patented write optimization engine (IntelliWrite®) mitigates the first vulnerability, “program interference,” by disrupting the write pattern that would otherwise generate errors and corrupt data. IntelliWrite eliminates excessively small writes and subsequent reads by ensuring large, clean contiguous writes from Windows so write operations to solid-state devices are performed in the most efficient manner possible on Windows servers and PCs. An attack could only be successful in the rare instance of limited free space or zero free space on a volume that results in writes occurring natively, circumventing the benefit of IntelliWrite.

Condusiv’s second patented engine (IntelliMemory®) disrupts the second vulnerability, “read disturb,” by establishing a tier-0 caching strategy that leverages idle, available memory to serve hot reads. This renders the “read disturb” attack useless since the storage target for hot reads becomes memory instead of the SSD device. A “read disturb” attack could only be successful in the rare instance that a Windows system is memory constrained and has no idle, available memory to be leveraged for cache.

While organizations use Condusiv software on Windows systems to maintain peak performance and extend the longevity of their SSDs, they can trust Condusiv to protect against malicious attacks that would otherwise corrupt user data and bring great harm to their business and service to customers.

Telestream Solves MS Exchange Timeouts and Boosts SQL with V-locity I/O Reduction Software

by Brian Morin 13. June 2017 05:12

Many first-time users of V-locity® I/O reduction software for virtual servers end up trying the software for more than boosting application performance, but to resolve “shadow IT issues” like timeouts, unexpected crashes, troublesome servers that need to be rebooted regularly, etc.


Often times, the underlying issue is in fact I/O related. By offloading I/O from  storage and optimizing the remaining I/O stream to be written and read as a large, clean sequential profile, the “shadow IT issues” that plague many environments simply disappear when trying V-locity. Condusiv has published previous case studies solving shadow IT issues on ERP systems and MS-SQL apps. For Telestream (a popular provider of software and hardware products for video capture, encoding, transcoding, and network-based delivery), it was users timing out from MS Exchange and getting disconnected from the email server.


Before considering adding another hybrid storage array, all-flash array, or expensive new servers that may or may not solve the problem, they gave V-locity a try first.


“As soon as we installed V-locity and the Exchange timeouts disappeared, we were elated that users were no longer getting disconnected from the email server. That made our purchase of V-locity I/O reduction software a ‘no brainer,’” said Allie McLachlan, Systems Administrator, Telestream.


McLachlan continued, “The most eye-opening experience was finding out how badly our system performance was being taxed by small, fractured, random I/O from Windows write inefficiencies and the “I/O blender” effect. We would have had no idea that was even an issue without trying V-locity to solve those root cause performance issues.”


To read the full story and how their MS-SQL apps were boosted by 50% as well, read here: http://learn.condusiv.com/rs/246-QKS-770/images/CS_Telestream.pdf


University of Illinois Doubles SQL and Oracle Performance on All-Flash Arrays with V-locity® I/O Reduction Software

by Brian Morin 19. May 2017 11:00

The University of Illinois, had already deployed an all-flash Dell Compellent storage array to support their hardest hitting application, AssetWorks AiM, that runs on Oracle. After a year in service, performance began to erode due to growth in users and overall workload. Other hard hitting MS-SQL applications supported by hybrid arrays were suffering performance degradation as well.

The one common denominator is that all these applications ran on Windows servers – Windows Server 2012R2.

“As we learned through this exercise with Condusiv’s V-locity I/O reduction software, we were getting hit really hard by thousands of excessively small, tiny writes and reads that dampened performance significantly,” said Greg Landes, Manager of Systems Services. “Everything was just slower due to Windows Server write inefficiencies that break writes down to be much smaller than they need to be, and forces the all-flash SAN to process far more I/O operations than necessary for any given workload.”

Landes continued, “When you have a dump truck but are only filling it a shovelful at a time before sending it on, you’re not getting near the payload you should get with each trip. That’s the exact effect we were getting with a surplus of unnecessarily small, fractured writes and subsequent reads, and it was really hurting our storage performance, even though we had a really fast ‘dump truck.’ We had no idea how much this was hurting us until we tried V-locity to address the root-cause problem to get more payload with every write. When you no longer have to process three small, fractured writes for something that only needs one write and a single I/O operation, everything is just faster.”

When testing the before-and-after effect on their production system, Greg and his team first measured without V-locity. It took 4 hours and 3 minutes to process 1.57TB of data, requiring 13,910,568 I/O operations from storage. After V-locity, the same system processed 2.1TB of data in 1 hour and 6 minutes, while only needing to process 2,702,479 I/O operations from underlying storage. “We processed half a terabyte more in a quarter of the time,” said Landes.

“Not only did V-locity dramatically help our write-heavy MS-SQL and Oracle Servers by increasing performance 50–100% on several workloads, we saw even bigger gains on our read heavy applications that could take advantage of V-locity’s patented DRAM caching engine, that put our idle, unused memory to good use. Since we had provisioned adequate memory for these I/O-intensive systems, we were well positioned to get the most from V-locity.”

“We thought we were getting the most performance possible from our systems, but it wasn’t until we used V-locity that we realized how inefficient these systems really are if you’re not addressing the root cause performance issues related to the I/O profile from Windows servers. By solving the issue of small, fractured, random I/O, we’ve been able to increase the efficiency of our infrastructure and, ultimately, our people,” said Landes.

Tags:

General | SAN | Success Stories | virtualization | V-Locity | Windows Server 2012

Month List

Calendar

<<  September 2017  >>
MoTuWeThFrSaSu
28293031123
45678910
11121314151617
18192021222324
2526272829301
2345678

View posts in large calendar