IBM z16 and Power10 Deliver Highest Reliability Among Mainstream Servers for 15th Consecutive Year
The IBM z16 mainframe lives up to its reputation for delivering “zero downtime.”
The latest z16 server, introduced in April 2022, delivers nine nines—99.9999999%—of uptime and reliability. This is just over 30 milliseconds of per server annual downtime, according to the results of the ITIC 2023 Global Server Hardware, Server OS Reliability Survey.
ITIC’s 2023 Global Server Hardware, Server OS Reliability independent web-based survey polled more than 1,800 corporations worldwide across 30 vertical market segments on the reliability, performance and security of the leading mainstream on-premises and cloud-based servers from January through mid-June 2023. To maintain objectivity, ITIC accepted no vendor sponsorship.
ITIC’s 2023 Global Server Hardware, Server OS Reliability survey also found that an 88% majority of the newest IBM Power10 server (shipping since September 2021) users say their organizations achieved eight nines—99.999999%—of uptime. This is 3.15 milliseconds of unplanned, per server, per annum outage time due to underlying system flaws or component failures. So, Power10 corporate enterprises spend just $7.18 per server/per year performing remediation due to unplanned server outages.
The IBM z16 and Power 10 server-specific uptime statistics were obtained by breaking out the results of more than 200 respondent organizations that deployed the z16 since it began shipping in April/May 2022. A 96% majority of these z16 enterprises say their businesses achieved nine nines—99.9999999%—of server uptime. This is the equivalent of a near-imperceptible 31.56 milliseconds of per server annual downtime due to any inherent flaws in the server hardware and its various components (see table 1).
An IBM spokesperson says that currently the IBM Z mainframe achieves an average of eight nines, or 99.999999%, reliability overall, and that statistic includes the various versions (the z13, z14, z15 and z16) of its mainframe enterprise system. IBM has not yet reviewed ITIC’s independent survey data on the z16 results.
To put these statistics into perspective: The latest z16 corporate enterprises and their IT managers spend mere pennies per server/per year performing remediation activities due to unplanned per server outages that occurred due to inherent system failures.
This is the 15th consecutive year that the IBM Z and IBM Power Systems have dominated with the best across-the-board uptime reliability ratings among 18 mainstream distributions.
Additionally, the z16 customers say their firms experienced a 20% to 30% improvement in overall reliability, performance, response times and critical security metrics versus older iterations of the zSystems platforms.
Previous versions of the IBM Z mainframe—the z13, z14 and z15—always delivered best-in-class reliability. ITIC’s 2023 Global Reliability study found that the aggregate average results from all z13, z14 and z15 customers ranged between seven and eight nines of uptime depending on the version, age, server configurations and specific use cases.
There is an order of magnitude of that distinguishes the “nines” of uptime and reliability. For example, four nines of uptime—which is the current acceptable level of uptime for many mainstream businesses—equals 52.56 minutes of unplanned annual per server downtime. In contrast, five nines of uptime is the equivalent of just 5.26 minutes of unplanned annual per server downtime.
As table 1 depicts, 99.99999% and 99.999999% represent 3.15 seconds and 3.15 milliseconds, respectively of unplanned per server annual outages due to server or component failures.
Table 1: Reliability/Uptime by the Numbers
Reliability % | Downtime per year | Downtime per month | Downtime per week |
90% (one nine) | 36.5 days | 72 hours | 16.8 hours |
95% | 18.25 days | 36 hours | 8.4 hours |
97% | 10.96 days | 21.6 hours | 5.04 hours |
98% | 7.30 days | 14.4 hours | 3.36 hours |
99% (two nines) | 3.65 days | 7.20 hours | 1.68 hours |
99.5% | 1.83 days | 3.60 hours | 50.4 minutes |
99.8% | 17.52 hours | 86.23 minutes | 20.16 minutes |
99.9% (three nines) | 8.76 hours | 43.8 minutes | 10.1 minutes |
99.95% | 4.38 hours | 21.56 minutes | 5.04 minutes |
99.99% (four nines) | 52.56 minutes | 4.32 minutes | 1.01 minutes |
99.999% (five nines) | 5.26 minutes | 25.9 seconds | 6.05 seconds |
99.9999% (six nines) | 31.5 seconds | 2.59 seconds | 0.605 seconds |
99.99999% (seven nines) | 3.15 seconds | 0.259 seconds | 0.0605 seconds |
99.999999% (eight nines) | 3.15 milliseconds | 26.25 milliseconds | 6.05 milliseconds |
99.9999999% (nine nines) | 31.56 milliseconds | 2.63 milliseconds | 606.9 microseconds |
Source: ITIC 2023 Global Server Hardware, Server OS Reliability Survey
The z16: A Quantum Leap Forward in Reliability, Performance and Cloud Functionality
The IBM Z mainframes have always delivered best-in-class reliability, performance and security. However, the z16 quite literally takes a quantum leap forward by providing advanced capabilities like on-chip AI inferencing and quantum-safe computing.
The IBM z16 and Power10 servers also delivered the strongest server security, experiencing the fewest number of successful data breaches, the least amount of downtime due to security-related incidents and the fastest mean time to detection (MTTD). ITIC’s latest 2023 Global Server Hardware Security Survey found that 97% of IBM z16 enterprises were able to detect, isolate and shut down attempted data breaches immediately to within the first 10 minutes. Additionally, 92% of IBM Power10 customers detected and repelled attempted hacks immediately to within the first 10 minutes. An organization’s ability to identify and thwart security breaches, minimizes downtime, saves money and mitigates risk.
ITIC’s 2023 survey data found that 84% of respondent enterprises cited security issues as the top cause of unplanned downtime. And 67% of respondents cite human error as the cause of unplanned server and application outages. Human error encompasses everything from accidentally disconnecting a server, to misconfiguration issues and incompatibilities among disparate hardware and application and server OS software.
IBM z16 Incorporates On-Chip AI Inferencing and Quantum-Safe Security
The IBM z16 utilizes the Telum processor, which Big Blue unveiled in August 2021. Telum is IBM’s first processor that contains on-chip acceleration for AI inferencing; it works while a transaction is in progress. Telum delivers AI and cyber resiliency to on-premises data centers and hybrid cloud environments using on-chip AI inferencing that assists organizations in gleaning insights in real-time.
The AI on-chip inferencing, which is available at no extra cost, is a game changer. It can deliver up to 300 billion deep learning inference operations per day with 1ms response time.
To cite two examples, AI on-chip inferencing can assist customers in preventing fraud before it happens by scoring up to 100% of transactions in real-time without impacting service level agreements (SLAs). It also helps companies keep up to date on fast-changing regulatory issues. IBM says the AI on-chip inferencing can also assist companies with compliance: It automates the process enabling firms to cut audit preparation time from one month to one week to maintain compliance, thus avoiding fines and penalties.
IBM executives say AI on-chip inferencing combined with its quantum-safe computing capabilities can assist enterprises in combating fraud, in credit approval, claims and settlements, and in financial trading. The servers conduct inferencing at the same speed as transactions. Since 2017, IBM consistently improved the performance and efficiency of its AI chips, boosting power performance by 2.5 times each year. Most recently, IBM says its goal is “to continue achieve 1,000 times better performance by 2029.”
Rock Solid Security
The IBM Z has always proactively delivered unparalleled security. It is indisputably the most secure platform in the industry with the inclusion of pervasive encryption, System Recovery Boost on-chip security, specialized crypto cards and accompanying software. These are all extremely crucial since security hacks like ransomware, email phishing schemes and targeted data breaches have surged by 84% in the past three years.
The z16 takes the pervasive encryption introduced in the z14 model and z15 System Recovery Boost features and turbo charges them with the quantum-safe cryptographic security. The z14 pervasive encryption model provided security at every layer of the stack. The z15 System Recovery Boost capability allowed businesses to drastically reduce the time it takes to shut down, restart and process the backlog that occurred during a system outage. The z16 quantum-safe cryptographic security was developed in-house by IBM Research.
Cryptography is the process of encrypting and protecting data so that only the person who has the right secret key can decrypt it. Simply put, quantum cryptography is as close to unbreakable or impenetrable encryption as a system can get. It uses quantum mechanics to secure and transmit data in a way that cannot be hacked (at least not yet).
Users, Analysts Weigh in on the “Nines” of Reliability
The IBM Z and Power Systems servers are particularly popular among key vertical markets like banking and finance, government, healthcare and universities that demand the highest reliability, observes Rob Enderle, president and principal analyst at the Bend, Oregon-based Enderle Group.
“IBM has really stepped up its game with AI on-chip inferencing and quantum safe computing. These features are state-of-the-art and the z16 is the undisputed server leader in terms of these capabilities,” Enderle says. “Together they make the IBM z16 the most reliable and secure server for on-premises data centers, the network edge and the hybrid cloud.”
Customers agree.
“The IBM Z mainframe has always been an incredibly reliable server and the newest z16 is the most resilient yet. We’ve had no perceptible downtime,” says the VP of IT at a New York City-based investment banking firm which is a longtime IBM shop. He notes that his transaction-based organization demands the highest levels of eight and nine nines of uptime and availability that the z16 and the Power10 servers deliver. “We have zero tolerance for downtime for any reason,” the IT executive says, adding, “Time is money for us. If our servers fail during the middle of a transaction, we would potentially incur losses of millions of dollars per minute. The IBM z16 and Power10 servers both deliver rock solid stability.”
Reliability and security are also of paramount importance for hospitals and healthcare organizations.
“There’s nothing more crucial to us than safeguarding the data privacy of our patients, clients, partners and employees,” notes the chief information security officer at a large hospital based in Texas. “We simply cannot afford even a single lapse or breach. While no system is 100% foolproof, the z16 is incredibly solid and difficult to hack,” the CISO says. “Hackers are always knocking on the door. The z16’s quantum-safe cryptography represents our best chance to recognize an attempted security breach and repel the attack.”
IBM Z Fast Facts
- The “Z” in the IBM z Systems stands for “zero downtime.”
- IBM Z platform experienced 3x growth in the last decade.
- The IBM Z platform supports 67 of the Fortune 100 firms.
- The IBM Z mainframe is used in 45 out of 50 of the world’s top banks.
- IBM Z is in eight of the top 10 insurance companies.
- IBM Z is deployed by four out of the five top airlines.
- IBM Z is used by seven out of 10 top global retailers.
- IBM Z is in use by eight of the top 10 telecommunications providers.
- 24 of the top 25 countries by GDP have an IBM Z mainframe.
- Currently, more than 1,000 ISVs and open-source solutions are now on the platforms supporting every part of their product and services stacks.