<img height="1" width="1" src="https://www.facebook.com/tr?id=1953097804934218&amp;ev=PageView &amp;noscript=1">

Blog

Managing Shadow IT Risks by Building IT Resources for the Future

Shadow IT is a double-edged sword: It’s the greatest opportunity for innovation your company has, if the shadow IT risks don’t cut into your business first.

After all, cyber threats will very quickly wipe out any upsides shadow applications can deliver.

Topics: Security Tips

Shadow Technologies Drop Security Risks and Drive Business Value — if You Let Them

Shadow technologies can send a chill down the spine of any IT professional tasked with keeping an organization secure.

Topics: Security Tips

Three Benefits of Shadow IT — And How to Harness Them

What is shadow IT?

It helps to first define shadow IT, sometimes known as dark IT. Most would start with a rundown of the network security risks it presents, but a more helpful shadow IT definition would explain it as something that’s already happening in your organization.

Topics: Security Tips

Purchasing SSDs in Spring 2017? Here's what you need to know.

If you want to see the concept of supply and demand in action, look no further than today's storage and memory market. You may have heard rumblings about a dearth of enterprise SSDs in the offing, and those rumblings have come to pass.

Here's what you need to know if you plan on purchasing enterprise SSDs or server-grade memory in the next 4-6 months.

Topics: Data Center Tips Infrastructure

7 PowerCLI Learning and Coding Tools I Learned about at VMworld 2016 US

With VMworld 2016 US coming to a close, there’s no time like the present to review one of the major tracks from the conference. Up first, one of the main pillars of VMware automation and scripting: PowerCLI.

Topics: Tips

Get an in-browser remote desktop with Mojolicious and noVNC

Note: This is an excerpt from my blog post originally published on PerlTricks.com

Topics: Tips

The 7 Biggest Data Center Migration Mistakes (And How to Avoid Them)

Topics: Data Center Tips

How VMware Virtual SAN 6.1 Can Support Your Remote Applications And PoPs

With the ecommerce industry growing each year, international business is no longer an enterprise-only sport. With small and midsize companies entering the global footprint game, their IT infrastructure needs to follow suit as they seek to engage and keep customers around the world.

Topics: Networking Tips

5 Key Questions: Replication as a Service

In a previous post, we highlighted 5 Key Questions to Ask Your BaaS Provider. In this post, we’ll take a look at the solution one step further on the Business Continuity/Disaster Recovery continuum: Replication as a Service.

Defining Replication as a Service

It’s important to have a common understanding of a service so that everyone shares the same expectations. Nothing takes a conversation sideways faster than everyone working with different definitions of the same product.

At ServerCentral, Replication as a Service is ServerCentral-operated hardware and software that replicate and recover applications and data from a customer premise to one or more of our data centers.

Replication differs from backups in that it involves the frequent updating of data between multiple systems, whereas backups save a copy of data that remains unchanged for a period of time.

Topics: Tips

Scaling ZFS on Linux to many CPUs

In February 2015, I posted the first pull request for a port of Prakash Surya's multilist and ARC re-work to ZFS on Linux. The goal was to reduce the lock contention on arcs_mtx, a single mutex embedded within each of the per-state ARC lists. The new multilist facility provided as part of this pull request includes an almost drop-in replacement to the standard linked list typelist_t.  Rather than maintaining a single lock for a single linked list (per ARC state), the lists were split up into a number of sub-lists, each of which had their own mutex.

The benchmark used for testing this work consists of numerous concurrent 4K reads of 100% cached data.  In the original OpenZFS ARC implementation, with a single arcs_mtx lock, the benchmark didn't scale well as additional reader tasks were added. There was a great deal of contention on the single mutex.  (The before-and-after results for illumos are described here.)

Given ZoL's divergent development with respect to the "upstream" OpenZFS code (from illumos), porting this patch required dealing with a number of conflicts which developed over time. Some of the issues are documented in the final commit.

Once the code was ported and in working condition, my next step was to try to duplicate the benchmark results under Linux. My initial results were not encouraging: The performance wasn't improved much at all and in some cases, was even worse. My benchmarking was also handicapped by the lack of access to sufficiently "big" hardware. The largest system which I had direct access to was a 2x6-core Opteron (2-node NUMA system) with only 64GiB RAM. I began using large spot instances on Amazon EC2 to run the tests but it wasn't very convenient. It also brought to light the differences in the locking primitives under a virtualized (Xen) environment as opposed to running on bare metal.

I was eventually put in touch with the good people at ServerCentral, who, in the name of furthering the ZoL development effort, gave me access to a dedicated server with 4 E7-4850 CPUs, each of which has 10 cores and 2 threads per core. The system has 80 threads available. Backing it is 512GiB of RAM and a bunch of hard drives in several JBODs.  In short, it's a perfect system on which to perform this type of testing.

Using this 4xE7 system, not only was I able to find some (rather trivial) bottlenecks which greatly improved the performance of the benchmark mentioned above, but I also found several other similar bottlenecks, some of which have been fixed, some of which have not yet.

In subsequent postings, I'll outline some of the specific bottlenecks I encountered and their fixes, if any. Pretty much any scaling-related fix or issue I posted or commented on regarding ZoL (zfs or spl repositories) were discovered through testing on the E7 system.

- Tim

This guest post was published with permission from Tim Chase. It originally appeared here.

Topics: Tips