Blog Single Author Small

Uptime Institute Intelligence plans to release its 2019/2020 outages report shortly. This report will examine the types, causes and impacts of public outages, as well as further analyze the results of a recent Uptime survey on outages and impacts. The data will once again show that serious IT service interruptions are common and costly, with the impacts often causing serious disruption.

We have excluded one type of outage from the report: those caused by cyberattacks. Data integrity and cybersecurity is, of course, a very major issue that requires vigilant attention and investment, but it is not currently an area on which Uptime Institute researches and advises. Most security issues are data breaches; although they have serious consequences, they do not usually lead to a service interruption.

However, two forms of malicious attack can and often do lead to outages or at least a severe service degradation. The first is a Distributed Denial of Service (DDoS) attack, where a coordinated attempt is made to overwhelm a site with traffic. Uptime has tracked a number of these each year for many years, and security specialists say they are increasingly common. Even so, most organizations that are DDoS targets have developed effective countermeasures that minimize the threat. These measures include such techniques as packet filtering, load balancing and blocking suspect internet protocol addresses. As a result, DDoS attacks are showing up less frequently in our lists of outages.

The second type, ransomware, is emerging as a major problem and cause of outages. Ransomware attackers deny authorized users access to their own data; the hackers use malware to encrypt the user’s files and refuse to unlock them unless a ransom is paid. Often, operators have no choice but to take down all involved IT services in an attempt to recover access, restore from the last clean backup copy, and purge the systems of viruses. Outages can last days or weeks.

In the past two years, ransomware attacks have increased dramatically. The FBI investigated over 1,400 ransomware attacks in 2018. Government offices are a particular target. Kaspersky Research Labs, operated by security software supplier Kaspersky, identified 147 attacks on municipalities in 2019 (up 60%), in which the criminals demanded ransoms of $5.3 million. The IT Governance blog, based in the UK, recorded 19 major ransomware attacks globally in December 2019 alone.

Most US cities have now signed a charter never to pay a ransom to the criminals — but more importantly, most are now also upgrading their infrastructure and practices to prevent attacks. Some that have been targeted, however, have paid the ransom.

Perhaps the two most serious attacks in 2019 were the City of Baltimore, which refused to pay the ransom and budgeted $18 million to fix its problem; and the City of Atlanta, which also refused to pay the ransom and paid over $7 million to fully restore operations. The WannaCry virus attack in 2018 reportedly cost the UK National Health Service over $120 million (£92 million). And on New Year’s Eve 2019, Travelex’s currency trading went offline for two weeks due to a ransomware attack, costing it millions.

Preventing a ransomware attack has become — or should become — a very high priority for those concerned with resiliency. Addressing the risk may involve some stringent, expensive and inconvenient processes, such as multifactor security, since attackers will likely try to copy all passwords as well as encrypt files. In terms of the Uptime Institute Outage Severity Rating, many attacks quickly escalate to the most serious Category 4 or 5 levels — severe enough to costs millions and threaten the survival of the organization. Indeed, one North American health provider has struggled to recover after receiving a $14 million ransom demand.

All of this points to the obvious imperative: The availability and integrity of digital infrastructure, data and services is critical — in the fullest sense of the word — to almost all organizations today, and assessments of vulnerability need to span security, software, systems, power, networks and facilities. Weaknesses are likely to be exploited; sufficient investment and diligence in this area has become essential and must never waver. In hindsight we discover that almost all outages could have prevented with better management, processes and technology.

Members of the Uptime Institute Network can read more on this topic here.

Hardware refresh is the process of replacing older, less efficient servers with newer, more efficient ones with more compute capacity. However, there is a complication to the refresh cycle that is relatively recent: the slowing down of Moore’s law. There is still a very strong case for savings in energy when replacing servers that are up to nine years old. However, the case for refreshing more recent servers — say, up to three years old — may be far less clear, due to the stagnation witnessed in Moore’s law over the past few years.

Moore’s law refers to the observation made by Gordon Moore (co-founder of Intel) that the transistor count on microchips would double every two years. This implied that transistors would become smaller and faster, while drawing less energy. Over time, the doubling in performance per watt was observed to happen around every year and a half.

It is this doubling in performance per watt that underpins the major opportunity for increasing compute capacity while increasing efficiency through hardware refresh. But in the past five years, it has been harder for Intel (and immediate rival AMD) to maintain the pace of improvement. This raises the question: Are we still seeing these gains from recent and forthcoming generation of central processing units (CPUs)? If not, the hardware refresh case will be undermined … and suppliers are unlikely to be making that point too loudly.

To answer this question, Uptime Institute Intelligence analyzed performance data from the Standard Performance Evaluation Corporation (SPEC; https://www.spec.org/). The SPECpower dataset used contains energy performance results from hundreds of servers, based on the SPECpower server energy performance benchmark. To be able to track trends and eliminate potential outlier bias in reported servers (e.g., high-end servers versus volume servers), only dual-socket servers were considered in our analysis, for trend consistency. The dataset was then broken down into 18-month intervals (based on the published date of release of servers in SPECpower) and the performance averaged for each period. The results (server performance per watt) are shown in Figure 1, along with the trend line (polynomial, order 3).

The figure above shows how performance increases have started to plateau, particularly over the past two periods. The data suggests upgrading a 2015 server in 2019 might provide only a 20% boost in processing power for the same number of watts. In contrast, upgrading a 2008/2009 server in 2012 might have given a boost of 200% to 300%.

To further understand the reason behind this, we charted the way CPU technology (lithography) has evolved over time, along with performance and idle power consumption (see Figure 2).

Figure 2 reveals some interesting insights. During the beginning of the decade, the move from one CPU lithography to another, e.g., 65 nanometers (nm) to 45 nm, 45 nm to 32 nm, etc., presented major performance per watt gains (orange line), as well as substantial reduction in idle power consumption (blue line), thanks to the reduction in transistor size and voltage.

However, it is also interesting to see that the introduction of a larger number of cores to maintain performance gains produced a negative impact on idle power consumption. This can be seen briefly during the 45 nm lithography and very clearly in recent years with 14 nm.

Over the past few years, while lithography stagnated at 14 nm, the increase in performance per watt (when working with a full load) has been accompanied by a steady increase in idle power consumption (perhaps due to the increase in core count to achieve performance gains). This is one reason why the case for hardware refresh for more recent kit has become weaker: Servers in real-life deployments tend to spend a substantial part of their time in idle mode — 75% of the time, on average. As such, the increase in idle power may offset energy gains from performance.

This is an important point that will likely have escaped many buyers and operators: If a server spends a disproportionate amount of time in active idle mode — as is the case for most — the focus should be on active idle efficiency (e.g., choosing servers with lower core count) rather than just on higher server performance efficiency, while satisfying overall compute capacity requirements.

It is, of course, a constantly moving picture. The more recent introduction of the 7 nm lithography by AMD (Intel’s main competitor) should give Moore’s law a new lease of life for the next couple of years. However, it has become clear that we are starting to reach the limits of the existing approach to CPU design. Innovation and efficiency improvements will need to be based on new architectures, entirely new technologies and more energy-aware software design practices.

The full report Beyond PUE: Tackling IT’s wasted terawatts is available to members of the Uptime Institute Network here.