Front cover

Acrobat bookmark

Introducing IBM Z System

Recovery Boost

Jannie Houlbjerg
Kazuhiro Nakajima
Paul Schouten

Redpaper
 Introducing IBM Z System Recovery Boost
This IBM® Redpaper publication introduces System Recovery Boost (SRB), which is a
firmware feature that was introduced with IBM z15™ and enhanced on IBM z16™ and IBM
z17™. SRB delivers substantially faster system shutdown and restart, short duration
Recovery Process Boosts (RPBs) for sysplex events, and fast catch-up of an accumulated
backlog of mission-critical workloads after specific events (such as system restart).

Note: SRB is a firmware feature that is available on IBM z15, IBM z16, and IBM z17
central processor complexes (CPCs), and it requires operating system support for use. It is
not available on older systems. Always check the latest firmware and software for available
SRB functions.

IBM Z® naming: The IBM Z server generations that are described in this paper are
available as the following machine types and models (MTMs):
򐂰 Machine Type 3931 (M/T 3931) Model A01, which is identified as IBM z16 Model A01
򐂰 Machine Type 3932 (MT 3932) Models A02/AGZ which are identified as IBM z16
Models A02, and IBM z16 Model AGZ.
򐂰 Machine Type 8561 (M/T 8561) Model T01, which is identified as IBM z15 Model T01.
򐂰 Machine Type 8562 (M/T 8562) Model T02, which is identified as IBM z15 model T02.
򐂰 Machine Type 9175 (M/T 9175) Model ME1, which is identified as IBM z17 model ME1.

Starting with IBM z15, System Recovery Boost can deliver higher processor capacity for a
limited time after an IPL, while shutting down a system, or during specific, short-term sysplex
recovery events. The increased capacity can be provided in one or more of the following
ways:
򐂰 In an LPAR on a sub-capacity machine, by utilizing the full speed for the general purpose
processors of the boosted partition (speed boost)
򐂰 Dispatching some work on z Integrated Information Processors (zIIP), even if the work is
not eligible for zIIP (zIIP boost)
򐂰 Configure online zIIPs that are in the standby state for the duration of the boost period
(zIIP boost)

Note: These three basic functions of System Recovery Boost continue to be fully
supported on the IBM z15 and above. System Recovery Boost Upgrade is not offered on
IBM z17. Customers who have already purchased System Recovery Boost Upgrade on
z15 or z16 can continue to use it.

© Copyright IBM Corp. 2020, 2022. All rights reserved. [Link]/redbooks 1

System Recovery Boost overview
SRB is a firmware feature that was introduced with IBM z15 and enhanced on IBM z16, and
IBM z17. It delivers improved overall system and application availability by reducing the
downtime that results from system shutdown and restart operations, and by using
short-duration RPBs.

SRB realizes the following benefits:

򐂰 During a planned or unplanned system restart:
– It shuts down the system substantially faster than any earlier IBM Z platform.
– It accelerates the initial program load (IPL) and performs restart and recovery of the
middleware environment and client workloads substantially faster than on any earlier
IBM Z platform.
– It delivers extra processor capacity so that mission-critical workloads can catch up and
work through a backlog after a downtime.
򐂰 During a Stand-alone Dump operation, SRB delivers extra capacity to shorten the duration
of the dump.
򐂰 During specific (IBM defined) events, SRB delivers extra processor capacity for a short
duration so that client mission-critical workloads can catch up and work through a backlog
after a downtime. For some of the predefined events, a client can control whether a boost
is initiated, but for most events, the boost is on by default.

System Recovery Boost delivery stages

SRB is enhanced with each new firmware level. At the time of writing, all SRB functions were
delivered in three stages:
򐂰 SRB Stage 1 was delivered with IBM z15 (GA September 2019 - driver 41). Stage 1
provided extra processing capacity and parallelism for an image that was shutting down or
being restarted by using the following methods:
– Central Processor (CP) Speed Boost: Running subcapacity CPs at full-capacity speed
during boost periods in boosting images only.
– IBM System z® Integrated Information Processor (zIIP) Boost: Making
general-purpose work available to run on zIIP processors during the boost periods in
boosting images only.
Also provided in SRB Stage 1 were the following features:
– IBM Geographically Dispersed Parallel Sysplex (IBM GDPS®) scripting and
performance and parallelism enhancements.
򐂰 SRB Stage 2 was delivered with MCL P46602.005 for IBM z15 Driver 41C (Bundle S29) or
later in addition to APARs for IBM z/OS® V2.R3 and V2.R4. SRB Stage 2 extends Stage 1
boost technologies to provide short-term RPBs, which include:
– Sysplex Partitioning Recovery
Boosts all surviving systems in the sysplex as they take on the extra workload of
sysplex partitioning-related recovery after planned or unplanned removal of a system
from the sysplex.
– CF Structure Recovery

2 Introducing IBM Z System Recovery Boost

 Boosts all systems participating in Coupling Facility (CF) structure recovery
processing, CF structure rebuild, duplexing failover, and reduplexing.
– CF Data Sharing Member Recovery
Boosts all systems participating in recovery from the termination of a CF data sharing
member.
– IBM HyperSwap® Recovery
Boosts all systems participating in a HyperSwap recovery process.
򐂰 SRB Stage 3 is delivered with the IBM z16 (Driver 51), and is also available for IBM z17
use cases. These use cases maximize service availability by using tailored, short-duration
boosts to mitigate the impact of recovery processes, which include:
– IBM SAN Volume Controller (IBM SVC) Dump Boost
– Middleware Region Startup Boost
– HyperSwap Configuration Load Boost
The new support for Stage 3 depends on z/OS PTFs that are only available on
z/OS V2.R4, z/OS V2.R5, z/OS V3.R1 and z/OS V3.R2.
This support includes a new IEASRB proc that you can use to enable or disable RPBs on
a system.
SRB Stage 3 also includes the following features:
– Displays output enhancements for D IPLINFO,BOOST,STATE.
– Improved monitoring for “potential” boosts, that is, boosts that were requested but
could not happen because boosts were disabled or boost time was unavailable.

System Recovery Boost use cases

SRB provides value for many use cases, including the following ones:
򐂰 Single-system IPL (planned and unplanned):
– Planned or rolling IPLs (for example, to install software maintenance and disruptive
system maintenance).
– Unplanned IPLs to recover after an operating system failure or “sick but not dead”
occurrence that required a system shutdown or restart.
򐂰 Multi-system IPL (planned and unplanned):
– Restart all images on a CPC after a planned CPC initial microcode load (IML) or
Power-on Reset (POR) (CPC non-concurrent upgrade).
– Restart all images on a CPC after an unplanned CPC failure after a CPC IML or POR.
– Start a sysplex after a sysplex-wide (or sysplex multi-system) failure or “sick but not
dead” occurrence that required a sysplex shutdown or restart.
򐂰 Disaster recovery (DR) or site switch:
– Planned DR test: Start the test systems at the DR site.
– Planned or unplanned site switch: Start the systems at the DR site.
򐂰 Stand-alone Dump processing
SRB provides boosted processor capacity to shorten the duration of the dump.
򐂰 RPBs (short duration) for helping with middleware recovery (in sysplex and non-sysplex
environments)

3
 SRB provides boosted processor capacity to mitigate the impact on workload processing
after short-term recovery events in a sysplex, and it restores normal steady-state sysplex
operation as quickly as possible.

System Recovery Boost functions

SRB is a firmware feature that is designed to provide extra temporary processing capacity to
logical partitions (LPARs) to accelerate shutdown, IPL, restart and recovery of the middleware
environment and client workloads; perform Stand-alone Dump operations; and provide
short-duration RPBs without increasing IBM software costs.

By default, SRB capacity is provided in the following ways:

򐂰 Speed Boost
By converting subcapacity CPs to full-capacity CPs for opted-in images1 during the boost
period.
򐂰 zIIP Boost
By dispatching general-purpose workloads to zIIPs (for IBM z/OS LPARs with allocated
zIIPs in the LPAR profile) during the boost period.
򐂰 GDPS Enhancement
By using firmware enhancements that support greater parallelism and performance
improvements in the hardware API services. These enhancements are used by
IBM GDPS to speed up the orchestration of shutdown and restart activities. The boost
capacity does not contribute to other IBM software license charges.

Figure 1 shows a typical SRB timeline for a z/OS system restart.

Note: The timeline can differ for other operating systems

Figure 1 z/OS typical System Recovery Boost timeline for z/OS restart

1 Supported operating system images that are enabled for boost and running in an LPAR.

4 Introducing IBM Z System Recovery Boost

System Recovery Boost exploitation and duration
The current exploitation and duration per system image is listed in Table 1 on page 5.

Table 1 System Recovery Boost exploitation and duration

Item z/OS z/TPFa IBM z/VM® IBM z/VSE b
21st Century VSEn

Function Speed Boost Speed Boost Speed Boost Speed Boost

zIIP Boost
GDPS Enhancement

Shutdown boost 30 min. 30 min. 30 min.c 30 min.

d c
Startup boost 60 min. 60 min. 60 min. 60 min.

Stand-alone Dump Up to 60 min.e N/Af N/Af Up to 60 min.

Boost

RPB Up to 30 min. (the N/Af N/Af N/Af

sum of boost times
for multiple
processes) over a
period of 24 hours.
a. Existing support for a function (called TPF Dynamic CPU) can be used to provide more CP capacity when needed.
b. IBM z16 A01 was the last IBM Z to support IBM z/VSE.
c. Second-level guests of z/VM (other than z/OS images) “inherit” the Speed Boost from z/VM during these z/VM
startup and shutdown periods. This situation applies to second-level z/TPF, z/VSE, 21st Century VSEn and
potentially Linux images. However, individual startups and shutdowns of guests (in isolation from z/VM image
startup and shutdown) are not boosted. Integrated Facility for Linux (IFL) always runs at full capacity, so no boost
is available for IFLs.
d. A maximum of 20 minutes might be spent in the catch-up phase after the system restarts.
e. SADMP does not use zIIP Boost.
f. N/A: Not available.

Delivering extra capacity by using System Recovery Boost

This section describes the ways in which extra capacity is delivered for SRB.

Speed Boost
When the CPC is configured as a subcapacity model, LPARs that are running in a boost
period can access the Speed Boost.

This feature requires operating system opt-in and support. At the time of writing, IBM z/OS,
IBM z/VM, z/VSE, 21st Century VSEn , and z/TPF can use the subcapacity boost. For more
information, see “Software support” on page 17.

5
 Note: Consider the following points:
򐂰 Speed Boost applies to general-purpose processors (CPs) only. All other engines run at
full capacity (IFLs, zIIPs, and Internal Coupling Facilities (ICFs)).
򐂰 The following subcapacity models are available:
– IBM z15 T01 subcapacity CP is available for up to 34 CPs with three subcapacity
levels, 4xx, 5xx, and 6xx, where xx is 1 - 34. Model 7xx is a full capacity CP model.
– IBM z15 T02 subcapacity CP is available for up to six CPs with 26 subcapacity
levels, A0x - Y0x, where x is 1 - 6. Model Z0x is a full capacity CP model.
– IBM z16 A01 subcapacity CP is available for up to 39 CPs with three subcapacity
levels, 4xx, 5xx, and 6xx, where xx is 1 - 39. Model 7xx is a full capacity CP model.
– IBM z17 ME1 subcapacity CP is available for up to 43 CPs with three subcapacity
levels, 4xx, 5xx and 6xx, where xx is 1 - 43. Model 7xx is a full capacity CP model.

System Recovery Boost by using Speed Boost example

Figure 2 shows an example of Speed Boost.

Figure 2 Subcapacity to full-capacity boost example (IBM z16 A01 shown)

In this example, three LPARs are defined in IBM z16 A01 model 403. In normal operation, all
work is dispatched on subcapacity CPs.

When LPAR c enters a boost period, work that is dispatched from LPAR z runs at CP7 (full
capacity). Other LPARs continue to be dispatched at CP4 (subcapacity). One boost period is
started at LPAR c shutdown, and a new boost period is started at IPL (of LPAR c). At the end
of the IPL boost period, LPAR c returns to normal operation at CP4 (subcapacity).

6 Introducing IBM Z System Recovery Boost

zIIP Boost
Normally, only zIIP eligible work (such as Distributed Relational Database Architecture
(DRDA) and IBM Db2® Utilities) is dispatched to zIIPs. During the SRB period, zIIP eligible
and general CP work is dispatched to available zIIPs for the boost opt-in z/OS images
(running in an LPAR).

Notes: Consider the following points:

򐂰 At the time of writing, z/OS uses the zIIP Boost feature.
򐂰 At least one zIIP entitlement must be available to use zIIP Boost.

In this period, the system can use following processors to run a CP workload:
򐂰 Entitled purchased CPs.
򐂰 Entitled purchased zIIPs.

If more logical zIIPs are available and configured in the LPAR profile while in the boost period,
the images bring more logical zIIP processors online to use the extra physical zIIP capacity.

After the boost period ends, the z/OS dispatching of work on CPs versus zIIPs returns to
normal.

Important: With proper configuration, z/OS can automatically bring extra logical
processors on at the start of a boost period (based on resources availability) and
automatically take them off again at the end of the boost period.

System Recovery Boost by using zIIP Boost example

Figure 3 shows an example of recovery boost by using zIIP Boost.

Figure 3 zIIP Boost (z/OS LPAR): IBM z16 A01 example

In this example, three LPARs are defined on the IBM z16 A01 model 703 with two zIIPs. Two
zIIPs are shared between LPAR b and LPAR c.

During normal operation, only zIIP eligible work is dispatched to the zIIPs. When LPAR enters
a boost period, general-purpose work and zIIP eligible work might be dispatched to the zIIPs.

7
 When the boost period ends, only zIIPs eligible work is dispatched to the zIIPs.

Planned shutdown boost

A z/OS system can signal that it wants to enter a boost for a planned shutdown by starting the
IEA Shut Down Boost Start (IEASDBS) PROC. Consider the following points:
򐂰 To use SRB to speed up shutdown, you start the proc IEASDBS to tell z/OS that a
shutdown is in progress and to begin the shutdown boost. If for some reason you want to
stop a shutdown boost before the 30-minute time limit, you can run proc IEABE to do so.
However, stopping a shutdown boost by using the IEABE proc will not allow you to use any
remaining boost time in the future, that is, the IEASDSBS proc cannot be re-invoked to
start the shutdown boost once again.
򐂰 In response to starting the PROC, which is driven manually or by way of automation, z/OS
opts in to the allowed boosts that are permitted by using a parmlib.
򐂰 The start and end of the boost period is signaled by a console message (event notification
facility (ENF) signal (84)) and cutting an SMF record. The start and end of the boost period
starts a new SMF interval.

In a sysplex, Workload Manager (WLM) sysplex routing starts to route work away from a
system after the shutdown PROC is started to accelerate shutdown.

All z/OS and middleware processing during the shutdown boost period benefits from higher
capacity CP processors or extra parallelism that is provided by zIIPs and allows CP work to
run on zIIPs.

Shutdown boost example

Figure 4 shows an example of a shutdown boost by using a subcapacity CP Speed Boost and
a zIIP Capacity Boost.

Figure 4 Example of a shutdown boost in a subcapacity model (IBM z16 A01 shown)

In this example, three LPARs are defined in the IBM z16 A01 model 403 with two zIIPs. Two
zIIPs are assigned to LPAR b and LPAR c. During normal operation, all CP work is dispatched
at subcapacity (CP4), but only zIIP eligible work is dispatched to zIIPs.

8 Introducing IBM Z System Recovery Boost

 Before the planned shutdown of LPAR c, the IEASDBS proc is started by an operator or
automation. This process starts the shutdown boost. CP work that is dispatched by LPAR c is
run at full-capacity (CP7) and a general-purpose workload is dispatched to zIIPs. LPAR a and
LPAR b continue in the normal operation at subcapacity (CP4), and the only zIIP eligible
workload is dispatched to zIIP.

IBM Geographically Dispersed Parallel Sysplex actions, performance, and

parallelism
GDPS drives Base Control Program internal interface (BCPii) hardware APIs for orchestrating
Capacity BackUp (CBU) activations, image activations, resets, and IPLs for multiple images in
many planned and unplanned DR site-switch scenarios.

Firmware changes on the Hardware Management Console (HMC) and Support Elements
(SEs) support greater parallelism and performance improvements in the hardware API
services, and GDPS has changed the processing and scripting to take advantage of the
firmware improvement. GDPS itself also does more work in parallel when possible.

For z/OS and GDPS support and requirements, see “Software support” on page 17.

Recovery Process Boost (short duration)

Notes:
򐂰 All these capabilities are available for IBM z16 and IBM z17 ME1.
򐂰 Some of these capabilities are available for IBM z15 with a specific (concurrently
installable) LPAR Microcode Change Level (MCL). For more information,
see IBM ResourceLink (an IBMid is required.)
򐂰 At the time of writing, z/OS can exploit these features. For more information, see
“Software support” on page 17.

With enhanced SRB support, IBM is extending boost technologies to provide short-term RPB
acceleration for specific sysplex recovery events.

Currently, these process recovery events often cause short-duration workload impacts or
workload spikes while the system is busy recovering. Recovery affects the normal execution
of the client workload until recovery processing completes.

The RPB is designed to provide boosted processor capacity to mitigate short-term recovery
impacts and restore steady-state sysplex operation as quickly as possible following specific
recovery events, and to provide boosted processor capacity for a short period following
restoration of steady-state operation to help with workload catch-up from the recovery event.

When the events occur, sometimes an RPB is automatically initiated, and sometimes more
configuration or setup is required to initiate the RPB, depending on what the event is.

When an event occurs, z/OS manages the RPBs internally with the operating system initiating
the boosts as these recovery events take place, and only on the images that are affected by
these events. For certain events, additional configuration or setup is required to initiate RPB.
If RPBs happen to “overlap” (a second RPB occurs before a first one uses its entire boost
period), then the overlapping boosts are merged and the boost period may be extended to
allow the full boost period for the second recovery process. For setup considerations, see
“z/OS” on page 12.

9
 z/OS supports a dynamic enable and disable capability for all the RPB candidates, which
provides more control over the applicability and usage of RPBs, perhaps at different times of
day or under different operating conditions. For more information, see “z/OS” on page 12.

Recovery Process Boost candidates

The SRB RPB provides boosted processor capacity and parallelism to accelerate the
following events:
򐂰 Sysplex partitioning
Boost all surviving systems in the sysplex as they take on the extra workload of sysplex
partitioning-related recovery after a planned or unplanned removal of a system from the
sysplex.
When a system in the sysplex is removed, the surviving systems must do a large amount
of recovery processing to clean up after the failed system; free up resources that were
held on the failed system; and perform other tasks.
򐂰 CF structure recovery
Boost all systems participating in CF structure recovery processing, such as CF structure
rebuild, duplexing failover, and reduplexing.
Recovering failed CF structures and their data can be a laborious process that requires
the participation of all systems that were using those CF structures, and it can apply to
many structures in cases like the loss of a CF image.
򐂰 CF data sharing member recovery
Boost all systems participating in recovery from disconnection from a CF lock structure
while lock resources were still held.
When a connected user is disconnected from a lock structure while holding lock resources
or is disconnected implicitly as the result of address space termination or a system being
removed from the sysplex, the other surviving members must do much recovery and
cleanup processing to free up locks and other data sharing resources that are held by the
failed member.
򐂰 IBM HyperSwap
Boost all systems participating in a HyperSwap recovery process.
HyperSwap processing is a coordinated, sysplex-wide recovery process that restores
access to direct access storage devices (DASDs) following the failure of a storage
controller. Its recovery time is sometimes limited by slow processing on one or more
participating systems.
򐂰 SVC Dump Boost
Boost the system on which SVC dump is taken to reduce system impact and expedite
diagnostic capture.
By default, SVC Dump Boost is not enabled. You must set a threshold to enable it. For
more information, see “z/OS” on page 12.

Note: SVC Dump Boost is only available on IBM z16 IBM z17 ME1.

򐂰 Customer-identified Middleware Region Boost for startup or restart

Boost the system on which a middleware instance is being restarted to expedite resource
recovery processing, release retained locks, and other items.
This boost is applicable to planned restarts; restarts after failure; and automated or z/OS
Automatic Restart Manager (ARM) driven restarts. SRB does not boost any system

10 Introducing IBM Z System Recovery Boost

 address space by default, and must be explicitly configured by the WLM service definition.
For more information, see “z/OS” on page 12.

Note: Customer-identified Middleware Restart Boost is available only on IBM z16 and
IBM z17.

򐂰 HyperSwap Configuration Load Boost

Boost the system in which the HyperSwap configuration and policy information are being
loaded or re-loaded.
This boost applies to both Copy Services Manager (CSM) and GDPS. HyperSwap
Configuration Load Boost is enabled by default. There are no thresholds or criteria that are
applied to the boost request based on the size or number of devices that are present in the
HyperSwap configuration.

Note: HyperSwap Configuration Load Boost is available only on IBM z16 and IBM z17.

Operational considerations
Here are several operational considerations:
򐂰 During an RPB period, WLM does not route work away from the system (as it does during
a shutdown boost) or toward the system (as it does during a startup boost). WLM ignores
short-duration recovery boosts for workload routing purposes.
򐂰 When bringing reserved logical zIIP processors online and offline at the start and end of
an RPB period, z/OS limits the number of “transient” zIIPs brought online and offline
automatically to at most two (more transient zIIPs during IPL and shutdown boost periods
may be configured).
򐂰 z/OS starts and ends a new IBM System Management Facility (SMF) interval during an
RPB period, but when two or more recovery processes boost “overlap”, they are merged
into a single boost period and a single SMF interval.
򐂰 z/OS issues ENF signals and console messages when starting, extending, or stopping an
RPB.
򐂰 For z/OS, a system command or PROC (IEABE) is provided to allow for early opt-out of an
IPL or shutdown boost if wanted.
򐂰 z/OS does not permit overlap between the RPBs and the longer image-level startup and
shutdown boosts:
– RPBs are not initiated while an image-level startup boost is still in progress because
the system is already boosted.
– If an RPB is in progress when a system image-level shutdown is initiated, then z/OS
“cancels” the in-progress RPB and initiates the shutdown boost period for system
shutdown.
– If more transient zIIPs were already online during the RPB, z/OS potentially must bring
more online for the shutdown boost, up to the full quota of reserved logical zIIPs.

Setting up the System Recovery Boost

SRB is a firmware feature for operating systems that are running in an LPAR, which requires
operating system support.

11
 Important: The base SRB capability is built in to the firmware and does not require
ordering any other features.

z/OS
You can configure a z/OS system-level parameter (IEASYSxx) to control whether a specific
z/OS image opts in to any of the available processor boosts, as shown in the following
example:
BOOST=SYSTEM | zIIP | SPEED | NONE

You can configure the RPB - SVC Dump by using RPBMINSZ in the CHNGDUMP parameter. For
more information, see Managing Recovery Process Boost.

You can configure the RPB - Customer-identified Middleware Restart Boost through your
WLM Service Definition. WLM specification is required to designate any Middleware Restart
Boost for started tasks (STCs) only. The boost is identified in WLM Classification Rules, with
Boost=Y | N.

For all the RPB candidates, you can configure these boosts as ENABLED or DISABLED by using
the IEASRB PROC, as shown in the following example:
S IEASRB,[CLASS=RP,]REQ=DISABLE|D to dynamically disable Recovery Process boost
S IEASRB,[CLASS=RP,]REQ=ENABLE|E to dynamically enable Recovery Process boost

For more information, see z/OS 2.5: System Recovery Boost and z/OS 3.1 System Recovery
Boost.

If you want to use offline zIIPs or extra zIIPs that are provided by the SRB record, you must
define reserved zIIPs in the image profile, as shown in Figure 5.

Figure 5 Reserved zIIPs definition window in the image profile

You also should review LPAR weights and storage allocation to ensure that they meet your
system requiremenCentury s.

12 Introducing IBM Z System Recovery Boost

21st Century VSE n and z/VSE
SRB is automatically enabled during IPL and Stand-alone Dump. The shutdown boost must
be enabled by running the SYSDEF SYSTEM command, as shown in the following example:
SYSDEF SYSTEM,BOOST=START

z/VM
SRB is enabled by default. It can be controlled by the FEATURES statement in the system
configuration file, and it can be ENABLED and DISABLED, as shown in the following example:
FEATURES ENABLE RECOVERY_BOOST
FEATURES ENABLE RECOVERY_BOOST

Monitoring System Recovery Boost

This section describes monitoring SRB for the following items:
򐂰 z/OS
򐂰 21st Century VSE n and z/VSE
򐂰 HMC

z/OS
The D IPLINFO,BOOST,STATE command shows an image’s current boost state, both for startup
and shutdown boosts, and the RPBs, including details such as time used, remaining time,
and other details within the last 24-hour window, as shown in Example 1.

Example 1 z/OS sample display for boost status

Sample 1:
IEE258I00.18.13 Boost State 899
Boost class: IPL
zIIP boost: active with 5 transient zIIP cores
Speed boost: active
Recovery Process Boosts: enabled at 09.34.54 on 03/24/2022
Recovery Process Boost Usage Information
zIIP boost: Total Avail: 30:00 Used: 00:00 Remaining: 30:00
Speed boost: Total Avail: 30:00 Used: 00:00 Remaining: 30:00

Total Available time will be refreshed in: [Link]

Recovery Process Boost Usage Since IPL

Actual: [Link] Potential_E: [Link] Potential: [Link]

In addition, the DISPLAY M=CPU command is enhanced with the following parameters (see
Example 2):
򐂰 I indicates zIIPs.
򐂰 B indicates (transient) boost zIIPs. This CPU was configured online at the start of the boost
period, and is configured offline when the boost ends.

13
 Example 2 CPU information for transient zIIPs
SY1 IEE174I 09.58.10 DISPLAY M 328
PROCESSOR STATUS
ID CPU SERIAL
00 + 0449D74381
01 + 1449D74381
02 +I 2449D74381
03 +B 3449D74381
04 +I 4449D74381

DISPLAY DUMP,OPTIONS can provide information about the RPBMINSZ threshold value that is
set to control boosts.

In addition, DISPLAY DUMP,INFO can provide information about dump sizes.

A number of IEA-messages are introduced with SRB. Messages are issued when a boost is
started and when a boost ends. These messages include information such as which type of
boost (Shutdown, IPL, or RPB) is activated. In an RPB situation, more information is
available, such as requester name (for example, ‘Sysplex partitioning’). Messages also are
issued if SRB cannot be activated due to an error or limits having been reached, or if SRB or
RPB is DISABLED. For more information, see z/OS 2.5: System Recovery Boost and z/OS 3.1
System Recovery Boost.

A new SMF interval starts whenever a boost starts or ends. SMF 90-40 is generated when a
boost event occurs (starting or stopping a boost). SMF 90-40 contains information about the
boost. SMF 90-40 is generated every 24 hour, and it contains summarized information about
RPB, such as enablement or disablement of state and usage. SMF types 30, 70-1, 72-3, and
89-1, 89-2, and 99-1 all receive a boost information byte that informs you whether a boost is
active, and if so, which type. During the boost, SMF records that contain capacity information,
such as 30, 70-1, 72-3, and 89, reflect the unboosted capacity of the image, not the effective
boosted capacity. For more information, see z/OS 2.5: MVS System Management Facilities
(SMF) and z/OS 3.1 MVS System Management Facilities (SMF).

21st Century VSE n and z/VSE

The SIR and the QUERY SYSTEM commands show an image’s current boost state.

HMC
When an LPAR is in the boost period, you can confirm the status of the SRB in the HMC or
SE Partition Image Details window, as shown in Figure 6 on page 15. During the boost
period, Processor Boost is shown as Active.

14 Introducing IBM Z System Recovery Boost

Figure 6 HMC Partition Image Details window

15
 Also, the processor boost status is shown in HMC Monitors Dashboard, as shown in Figure 7.

Figure 7 HMC Monitor Dashboard Window

Automation
Your automation product can be used in the following ways to automate and control SRB
activities:
򐂰 Dynamically modify LPAR weights, which might be needed to modify or “skew” the sharing
of physical zIIP capacity during a boost period.
򐂰 Drive the invocation of IEASDBS that indicates the beginning of a shutdown process.
򐂰 Use new composite hardware API reconfiguration actions.
򐂰 Control the level of parallelism that is present in the workload at start (for example, starting
middleware regions) and shutdown. Automation can pace or throttle these activities to
varying degrees. With boost, less pacing or more parallelism might be wanted.
򐂰 Automate the new z/OS messages that are issued at the start or end of boost periods to
take whatever actions are needed.
򐂰 Drive IEASRB proc invocations to enable or disable RPBs at certain times of day or as
otherwise needed.

Pricing
In this section, the available pricing options are described.

No additional charge functions

The following standard no additional charge IBM z15, IBM z16 and IBM z17 hardware
facilities are available:

16 Introducing IBM Z System Recovery Boost

 򐂰 Subcapacity to full-capacity boost for CPs
򐂰 zIIP Boost that uses a client’s entitled zIIPs
򐂰 GDPS scripting and firmware enhancements

Software pricing
A boost should not increase a customers’ IBM software costs regardless of whether the client
is using 4HRA Pricing, Solution Pricing, or Consumption-based Pricing.

Software support
At the time of writing, the following software is supported by SRB:
򐂰 IBM z/OS: V2R3, V2R4, V2R5, z/OS V3R1, and z/OS V3R2 with PTFs. Some of the RPBs
that are provided in Stage 2 have support in z/OS V2R3. The new Stage 3 RPBs require
z/OS V2R4 or later.

Note: z/OS APARs are associated with the FIXCAT for SRB (the FIXCAT name is
[Link]).

򐂰 IBM GDPS: V4R2, V4R3, and V4R4.

򐂰 IBM z/VM: V7.1 with PTFs, V7.2, and V7.3.
򐂰 IBM z/TPF: V1.1 with PTFs.
򐂰 IBM zVSE 6.2 with PTFs and 21st Century Software VSEn V6.3.

Note: IBM z16 A01 is the last IBM Z family that supports IBM zVSE 6.2.

IBM Z processor characterization (engine types)

An overview of image modes, supported engine types, and operating systems on IBM z15,
IBM z16, and IBM z17 is shown in Table 2.

Table 2 Image modes that are supported on IBM z15 and IBM z16
Image mode Engine type Operating system Second-level guest
(configurable) (primary)

General CP and zIIP 򐂰 z/OS (CP and zIIP) N/A

򐂰 z/VSE (CP)
򐂰 21st Century VSEn (CP)
򐂰 z/TPF (CP)

CF ICF or CP Coupling Facility Control N/A

Code (CFCC)

Linux only IFL or CP Linux on IBM Z (CP or IFL) Linux on IBM Z

Kernel-based Virtual under KVM (CP or IFL)
Machine (KVM) (CP or IFL)

17
 Image mode Engine type Operating system Second-level guest
(configurable) (primary)

z/VM IFL, CP, zIIP, z/VM (IFL or CP) 򐂰 Linux on IBM Z (CP or
and ICF IFL)
򐂰 CFCC (CP or ICF)
򐂰 z/OS (CP and zIIP)
򐂰 z/VSE (CP)
򐂰 21st Century VSEn (CP)
򐂰 z/TPF (CP)

Secure IFL or CP Appliance Software IFL or CP

Service
Container

Processor unit characterization

Consider the following points:
򐂰 CP, which is the general-purpose processor, supports running the z/OS, 21st Century VSEn ,
z/VSE, z/VM, z/TPF, and Linux on IBM Z operating systems. It can also run CFCC.
– For IBM z15 T01 and IBM z16 A01, and IBM z17 CP can run at subcapacity levels
CP4, CP5, and CP6, or at full-capacity (CP7).
– For IBM z15 T02, and IBM z17 A02/AGZ, CPs (up to six) can run at subcapacity levels
CP-A - CP-Y, with CP-Z for a full capacity CP.
All other engines run at full speed.
򐂰 zIIP is an “offload processor” for a workload that supports applications, such as Db2 and
z/OS Container Extensions (z/CX). It can also be used for z/OS during SRB periods for
running a general-purpose workload.
򐂰 IFL is a processor for use by z/VM for Linux guests and Linux on IBM Z operating systems,
and the KVM supervisor (that is based on the Linux kernel). The KVM hypervisor is part of
supported Linux on IBM Z distributions.
򐂰 ICF is a processor for use by the CFCC.

18 Introducing IBM Z System Recovery Boost

Authors
This paper was produced by a team of specialists from around the world working at
IBM Redbooks, Poughkeepsie Center.

Jannie Houlbjerg is a Systems Programmer working at JN Data in Denmark. She has more
than 20 years of experience in the IBM® Z field. Her areas of expertise include IBM Z
hardware and infrastructure, IBM Parallel Sysplex®, connectivity, performance, IBM GDPS,
and technical project management and documentation. Jannie has co-authored several
IBM Redbooks® publications.

Kazuhiro Nakajima is a Senior IT Specialist at IBM Japan. He has more than 30 years at
IBM Japan, and has been active as an advanced subject matter expert (SME) of IBM Z
products for over 20 years. His areas of expertise include IBM Z hardware, performance,
z/OS, and connectivity. Kazuhiro has co-authored several IBM Z configuration setup
IBM Redbooks publications, from IBM zEC12 to IBM z14®.

Paul Schouten is an IBM Z Client Technical Specialist who is based in Sydney, Australia.
During his 40 years supporting mainframe systems, he has performed several roles, including
Certified IT Architect, Systems Software Developer, and Systems Programming. He has
extensive experience developing and documenting high availability (HA) solutions for
IBM Enterprise customers.

The project that created this IBM Redpaper publication was managed by Octavian Lascu,
Redbooks Project Leader, Poughkeepise Center.

Thanks to the following people for their contributions to this project:

Robert Haimowitz, Bill White, and Ewerson Palacio

IBM Redbooks, Poughkeepsie Center

Dave Surman, Peter Relson, and Bill Lamastro

IBM Poughkeepsie

Now you can become a published author, too!

Here's an opportunity to spotlight your skills, grow your career, and become a published
author—all at the same time! Join an IBM Redbooks residency project and help write a book
in your area of expertise, while honing your experience using leading-edge technologies. Your
efforts will help to increase product acceptance and customer satisfaction, as you expand
your network of technical contacts and relationships. Residencies run from two to six weeks
in length, and you can participate either in person or as a remote resident working from your
home base.

Find out more about the residency program, browse the residency index, and apply online at:
[Link]/redbooks/[Link]

19
Stay connected to IBM Redbooks
򐂰 Look for us on LinkedIn:
[Link]
򐂰 Explore new Redbooks publications, residencies, and workshops with the IBM Redbooks
weekly newsletter:
[Link]
򐂰 Stay current on recent Redbooks publications with RSS Feeds:
[Link]

20 Introducing IBM Z System Recovery Boost

Notices

This information was developed for products and services offered in the US. This material might be available
from IBM in other languages. However, you may be required to own a copy of the product or product version in
that language in order to access it.

IBM may not offer the products, services, or features discussed in this document in other countries. Consult
your local IBM representative for information on the products and services currently available in your area. Any
reference to an IBM product, program, or service is not intended to state or imply that only that IBM product,
program, or service may be used. Any functionally equivalent product, program, or service that does not
infringe any IBM intellectual property right may be used instead. However, it is the user’s responsibility to
evaluate and verify the operation of any non-IBM product, program, or service.

IBM may have patents or pending patent applications covering subject matter described in this document. The
furnishing of this document does not grant you any license to these patents. You can send license inquiries, in
writing, to:
IBM Director of Licensing, IBM Corporation, North Castle Drive, MD-NC119, Armonk, NY 10504-1785, US

INTERNATIONAL BUSINESS MACHINES CORPORATION PROVIDES THIS PUBLICATION “AS IS”

WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESS OR IMPLIED, INCLUDING, BUT NOT LIMITED
TO, THE IMPLIED WARRANTIES OF NON-INFRINGEMENT, MERCHANTABILITY OR FITNESS FOR A
PARTICULAR PURPOSE. Some jurisdictions do not allow disclaimer of express or implied warranties in
certain transactions, therefore, this statement may not apply to you.

This information could include technical inaccuracies or typographical errors. Changes are periodically made
to the information herein; these changes will be incorporated in new editions of the publication. IBM may make
improvements and/or changes in the product(s) and/or the program(s) described in this publication at any time
without notice.

Any references in this information to non-IBM websites are provided for convenience only and do not in any
manner serve as an endorsement of those websites. The materials at those websites are not part of the
materials for this IBM product and use of those websites is at your own risk.

IBM may use or distribute any of the information you provide in any way it believes appropriate without
incurring any obligation to you.

The performance data and client examples cited are presented for illustrative purposes only. Actual
performance results may vary depending on specific configurations and operating conditions.

Information concerning non-IBM products was obtained from the suppliers of those products, their published
announcements or other publicly available sources. IBM has not tested those products and cannot confirm the
accuracy of performance, compatibility or any other claims related to non-IBM products. Questions on the
capabilities of non-IBM products should be addressed to the suppliers of those products.

Statements regarding IBM’s future direction or intent are subject to change or withdrawal without notice, and
represent goals and objectives only.

This information contains examples of data and reports used in daily business operations. To illustrate them
as completely as possible, the examples include the names of individuals, companies, brands, and products.
All of these names are fictitious and any similarity to actual people or business enterprises is entirely
coincidental.

COPYRIGHT LICENSE:

This information contains sample application programs in source language, which illustrate programming
techniques on various operating platforms. You may copy, modify, and distribute these sample programs in
any form without payment to IBM, for the purposes of developing, using, marketing or distributing application
programs conforming to the application programming interface for the operating platform for which the sample
programs are written. These examples have not been thoroughly tested under all conditions. IBM, therefore,
cannot guarantee or imply reliability, serviceability, or function of these programs. The sample programs are
provided “AS IS”, without warranty of any kind. IBM shall not be liable for any damages arising out of your use
of the sample programs.

© Copyright IBM Corp. 2020, 2022. All rights reserved. 21

Trademarks
IBM, the IBM logo, and [Link] are trademarks or registered trademarks of International Business Machines
Corporation, registered in many jurisdictions worldwide. Other product and service names might be
trademarks of IBM or other companies. A current list of IBM trademarks is available on the web at “Copyright
and trademark information” at [Link]

The following terms are trademarks or registered trademarks of International Business Machines Corporation,
and might also be trademarks or registered trademarks in other countries.
Db2® IBM z16™ z/VM®
GDPS® Parallel Sysplex® z/VSE®
HyperSwap® Redbooks® z15™
IBM® Redbooks (logo) ® z16™
IBM Z® System z®
IBM z14® z/OS®

The following terms are trademarks of other companies:

The registered trademark Linux® is used pursuant to a sublicense from the Linux Foundation, the exclusive
licensee of Linus Torvalds, owner of the mark on a worldwide basis.

Other company, product, or service names may be trademarks or service marks of others.

22 Introducing IBM Z System Recovery Boost

Back cover

REDP-5563-02

ISBN 0738460796

Printed in U.S.A.

®
[Link]/redbooks