IBM Power and z Systems Platforms Show Renewed Excitement
Granted, 20 consecutive quarters of posting negative revenue numbers is enough to get even the most diehard mainframe bigot down. If you ran your life like that your house and your car would have been seized by the bank months ago.
Toward the end of June, however, both z and Power had some good news. First, IBM announced that corporate enterprise users ranked the IBM z Systems enterprise servers as the most reliable hardware platform available on the market today. In its enterprise server category, the survey also found that IBM Power Systems achieved the highest levels of reliability and uptime when compared with 14 server hardware options and 11 server hardware virtualization platforms.
The results were compiled and reported by the ITIC 2017 Global Server Hardware and Server OS Reliability survey, which polled 750 organizations worldwide during April/May 2017. Also among the survey finding:
- IBM z Systems Enterprise mainframe class systems, had zero percent incidents of more than four hours of per server/per annum downtime of any hardware platform. Specifically, IBM z Systems mainframe-class servers exhibit true mainframe fault tolerance, experiencing just 0.96 minutes of minutes of unplanned per-server, per-annual downtime. That equates to eight seconds per month of “blink and you miss it,” or two seconds of unplanned weekly downtime. This is an improvement over the 1.12 minutes of per-server/per-annum downtime z Systems servers recorded in ITIC’s 2016—2017 Reliability Poll nine months ago.
- IBM Power Systems has the least amount of unplanned downtime, with 2.5 minutes per server/per year of any mainstream Linux server platforms.
- IBM and the Linux operating system distributions were either first or second in every reliability category, including virtualization and security.
The survey also highlighted market reliability trends. For nearly all companies surveyed, having four nines (99.99%) of availability, equating to less than one hour of system downtime per year was a key factor in its decision.
Then consider the increasing costs of downtime. Nearly all survey respondents claimed that one hour of downtime costs them more than $150k with one-third estimating that the same will cost their business up to $400k.
With so much activity going on 24×7, for an increasing number of businesses, 4 nines of availability is no longer sufficient. These businesses are adopting carrier levels of availability; 5 nines or 6 nines (or 99.999 to 99.9999 percent) availability, which translates to downtime per year of 30 seconds (6 nines) or 5 minutes (5 nines) of downtime per year.
According to ITIC’s 2016 report: IBM’s zl Systems Enterprise mainframe customers reported the least amount of unplanned downtime and the highest percentage of 5 nines (99.999%) uptime of any server hardware platform.
IBM just recently announced that according to results from International Data Corporation (IDC) Worldwide Quarterly Server Tracker (June, 2017) IBM exceeded market growth by 3x compared with the total Linux server market, which grew at 6 percent. The improved performances are the result of success across IBM Power Systems including IBM’s OpenPOWER LC servers and IBM Power Systems running SAP HANA as well as the OpenPOWER-Ready servers developed through the OpenPOWER Foundation.
As IBM explains it: Power Systems market share growth is underpinned by solutions that handle fast growing applications, like the deep learning capabilities within the POWER8 architecture. In addition these are systems that expand IBM’s Linux server portfolio, which have been co-developed with fellow members of the OpenPOWER Foundation
Now all that’s needed is IBM’s sales and marketing teams to translate this into revenue. Between that and the new systems IBM has been hinting at for the past year maybe the consecutive quarterly losses might come to an end this year.