Performance adjustment for Solid State Memory - Revision history

PoC: /* Recommended adjustments */ Better wording

2026-10-06T08:51:39Z

Recommended adjustments: Better wording

← Older revision		Revision as of 10:51, 6 October 2026
Line 86:		Line 86:
	Values printed in ''bold'' are changed (non-default) values.		Values printed in ''bold'' are changed (non-default) values.

	<blockquote>'''Note:''' These values are intended for small scale, or hobbyist systems. If these values hold up for heavy usage has not been established.</blockquote>		<blockquote>'''Note:''' These values are intended for small scale, or hobbyist systems. If these values hold up for heavy usage has not been established. Expect these values to change over time when additional experience has been gained.</blockquote>

	{\|class="wikitable"		{\|class="wikitable"

PoC: /* Work with Shared Pools */ Better wording

2026-10-06T08:43:50Z

Work with Shared Pools: Better wording

← Older revision		Revision as of 10:43, 6 October 2026
Line 30:		Line 30:
	\|*MACHINE		\|*MACHINE
	\|align="right"\|1		\|align="right"\|1
	\|align="right"\|~25<ref>This value is calculated by the system.</ref>		\|align="right"\|~25<ref>This value is actually calculated by the system.</ref>
	\|align="right"\|100		\|align="right"\|100
	\|align="right"\|10		\|align="right"\|10
Line 103:		Line 103:
	\|*MACHINE		\|*MACHINE
	\|align="right"\|1		\|align="right"\|1
	\|align="right"\|DFT<ref>A literal <tt>DFT</tt> isn't actually printed but can be used if the value has been changed prior.</ref>		\|align="right"\|DFT<ref>A literal <tt>DFT</tt> isn't actually printed but can be used to reset to the default value if it has been changed prior.</ref>
	\|align="right"\|'''50'''		\|align="right"\|'''50'''
	\|align="right"\|'''100'''		\|align="right"\|'''100'''

PoC: /* Recommended adjustments */ Footnote

2026-10-06T08:42:50Z

Recommended adjustments: Footnote

← Older revision		Revision as of 10:42, 6 October 2026
Line 103:		Line 103:
	\|*MACHINE		\|*MACHINE
	\|align="right"\|1		\|align="right"\|1
	\|align="right"\|~~25.49~~<ref>~~Use~~ literal <tt>*DFT</tt> ~~to reset to default,~~ if ~~unsure~~.</ref>		\|align="right"\|DFT<ref>A literal <tt>DFT</tt> isn't actually printed but can be used if the value has been changed prior.</ref>
	\|align="right"\|'''50'''		\|align="right"\|'''50'''
	\|align="right"\|'''100'''		\|align="right"\|'''100'''

PoC: Ready

2026-10-06T08:39:00Z

Ready

← Older revision		Revision as of 10:39, 6 October 2026
Line 1:		Line 1:
	~~{{FIXME\|Finish article}}~~
	OS/400 '''Performance adjustment for Solid State Memory''' sheds some light on how to tune a system in regard to the almost zero latency for this type of secondary storage.		OS/400 '''Performance adjustment for Solid State Memory''' sheds some light on how to tune a system in regard to the almost zero latency for this type of secondary storage.

PoC: /* Recommended adjustments */ Better wording

2026-10-06T08:38:38Z

Recommended adjustments: Better wording

← Older revision		Revision as of 10:38, 6 October 2026
Line 138:		Line 138:
	* Establish hard ''Size %'' limits to prevent pool starvation.		* Establish hard ''Size %'' limits to prevent pool starvation.
	* Allow for much higher faulting rates (''Faults/Second'') before taking action.		* Allow for much higher faulting rates (''Faults/Second'') before taking action.
	* Using higher scaling values still considers dynamic adjustment up to the raised ~~absolute maximum~~ values, and keeps the basic adjustment logic active.		* Using higher scaling values still considers dynamic adjustment up to the raised ''Acceptable Fault Target Threshold'' values, and keeps the basic adjustment logic active.

	== See also ==		== See also ==

PoC: /* Work with Shared Pools */ Reworked

2026-10-06T08:36:48Z

Work with Shared Pools: Reworked

← Older revision		Revision as of 10:36, 6 October 2026
Line 15:		Line 15:

	== Work with Shared Pools ==		== Work with Shared Pools ==
	The <code>wrkshrpool</code> command allows to adjust threshold values for the performance adjuster by pressing <code>F11</code>. You'll be presented with a table akin to the following. ~~Suggested adjustment~~ values ~~are shown below. Values printed in ''bold'' are changed~~ (~~non-default~~) ~~values.~~		The <code>wrkshrpool</code> command allows to adjust threshold values for the performance adjuster by pressing <code>F11</code>. You'll be presented with a table akin to the following. This table shows default values (for V4R5):

	{\|class="wikitable"		{\|class="wikitable"
	!colspan="2"\|		!colspan="2"\|
Line 32:		Line 31:
	\|*MACHINE		\|*MACHINE
	\|align="right"\|1		\|align="right"\|1
	\|align="right"\|25~~.49~~<ref>~~Use literal <tt>*DFT</tt> to reset to default, if unsure~~.</ref>		\|align="right"\|~25<ref>This value is calculated by the system.</ref>
	\|align="right"\|~~'''50'''~~		\|align="right"\|100
	\|align="right"\|~~'''100'''~~		\|align="right"\|10
	\|align="right"\|0		\|align="right"\|0
	\|align="right"\|~~'''100'''~~		\|align="right"\|10
	\|-		\|-
	\|*BASE		\|*BASE
Line 42:		Line 41:
	\|align="right"\|4.99		\|align="right"\|4.99
	\|align="right"\|100		\|align="right"\|100
	\|align="right"\|~~'''25'''~~		\|align="right"\|5
	\|align="right"\|~~'''~~5~~'''~~		\|align="right"\|0.5
	\|align="right"\|~~'''~~2000~~'''~~		\|align="right"\|2000
	\|-		\|-
	\|*INTERACT		\|*INTERACT
	\|align="right"\|2		\|align="right"\|2
	\|align="right"\|5		\|align="right"\|5
	\|align="right"\|~~'''25'''~~		\|align="right"\|100
	\|align="right"\|~~'''50'''~~		\|align="right"\|10
	\|align="right"\|~~'''10'''~~		\|align="right"\|2
	\|align="right"\|~~'''1000'''~~		\|align="right"\|100
	\|-		\|-
	\|*SPOOL		\|*SPOOL
	\|align="right"\|~~'''3'''~~		\|align="right"\|2
			\|align="right"\|1
			\|align="right"\|100
			\|align="right"\|5
	\|align="right"\|1		\|align="right"\|1
	\|align="right"\|~~'''10'''~~		\|align="right"\|100
	~~\|align="right"\|'''25'''~~
	~~\|align="right"\|'''5'''~~
	~~\|align="right"\|'''1000'''~~
	\|}		\|}

Line 69:		Line 68:
	* '''Thread''': A multiplier per (active) thread.		* '''Thread''': A multiplier per (active) thread.
	* '''Maximum''': If the pool's faulting rate exceeds this value, the adjuster considers the pool starved and starts aggressively moving memory into it from other pools.		* '''Maximum''': If the pool's faulting rate exceeds this value, the adjuster considers the pool starved and starts aggressively moving memory into it from other pools.

	~~The primary goals behind the suggested values are~~
	* Establish hard ''Size %'' limits to prevent pool starvation
	* Allow for much higher faulting rates (''Faults/Second'') before taking action

	=== Thread multiplier ===		=== Thread multiplier ===
Line 89:		Line 84:
	Because the absolute Maximum is capped at 1000, the math is clipped. The threshold stops scaling and locks firmly at 1000 faults/s.		Because the absolute Maximum is capped at 1000, the math is clipped. The threshold stops scaling and locks firmly at 1000 faults/s.

	Using higher scaling values still considers dynamic adjustment up to the raised absolute maximum values, and keeps the basic adjustment logic active.		=== Recommended adjustments ===
			Values printed in ''bold'' are changed (non-default) values.

			<blockquote>'''Note:''' These values are intended for small scale, or hobbyist systems. If these values hold up for heavy usage has not been established.</blockquote>

			{\|class="wikitable"
			!colspan="2"\|
			!colspan="2"\|Size (%)
			!colspan="3"\|Faults/Second
			\|-
			!Pool
			!Priority
			!Minimum
			!Maximum
			!Minimum
			!Thread
			!Maximum
			\|-
			\|*MACHINE
			\|align="right"\|1
			\|align="right"\|25.49<ref>Use literal <tt>*DFT</tt> to reset to default, if unsure.</ref>
			\|align="right"\|'''50'''
			\|align="right"\|'''100'''
			\|align="right"\|0
			\|align="right"\|'''100'''
			\|-
			\|*BASE
			\|align="right"\|1
			\|align="right"\|4.99
			\|align="right"\|100
			\|align="right"\|'''25'''
			\|align="right"\|'''5'''
			\|align="right"\|'''2000'''
			\|-
			\|*INTERACT
			\|align="right"\|2
			\|align="right"\|5
			\|align="right"\|'''25'''
			\|align="right"\|'''50'''
			\|align="right"\|'''10'''
			\|align="right"\|'''1000'''
			\|-
			\|*SPOOL
			\|align="right"\|'''3'''
			\|align="right"\|1
			\|align="right"\|'''10'''
			\|align="right"\|'''25'''
			\|align="right"\|'''5'''
			\|align="right"\|'''1000'''
			\|}

			The primary goals behind the suggested values are:
			* Establish hard ''Size %'' limits to prevent pool starvation.
			* Allow for much higher faulting rates (''Faults/Second'') before taking action.
			* Using higher scaling values still considers dynamic adjustment up to the raised absolute maximum values, and keeps the basic adjustment logic active.

	== See also ==		== See also ==

PoC: /* Work with Shared Pools */ Priority

2026-10-06T08:05:43Z

Work with Shared Pools: Priority

← Older revision		Revision as of 10:05, 6 October 2026
Line 62:		Line 62:
	\|align="right"\|'''1000'''		\|align="right"\|'''1000'''
	\|}		\|}

			A pool's ''priority'' is a relative number from 1 to 14. Lower numbers mean higher priority for pools to be served with additional memory, while higher numbered pools are stripped from excess memory earlier.

	Some explanation to the meaning of the ''Faults/Second'' values:		Some explanation to the meaning of the ''Faults/Second'' values:

PoC: /* Thread multiplier */ Better wording

2026-10-06T07:54:48Z

Thread multiplier: Better wording

← Older revision		Revision as of 09:54, 6 October 2026
Line 75:		Line 75:
	Explanation by example: If one user is running an application in the INTERACT pool and causing 50 faults/second, that single user is experiencing a performance bottleneck. Contrary, if 100 people are using INTERACT simultaneously and causing the same 50 faults/second, that means each user is only experiencing 0.5 faults/second. No bottleneck.		Explanation by example: If one user is running an application in the INTERACT pool and causing 50 faults/second, that single user is experiencing a performance bottleneck. Contrary, if 100 people are using INTERACT simultaneously and causing the same 50 faults/second, that means each user is only experiencing 0.5 faults/second. No bottleneck.

	The system calculates a ''~~dynamic Maximum~~ = Minimum + (Thread Multiplier × Active Threads)''. If that value exceeds the absolute Maximum value, the latter is considered. Let's take an example of ''multiplier = 2''.		The system calculates a ''Dynamic Acceptable Fault Target Threshold = Minimum + (Thread Multiplier × Active Threads)''. If that value exceeds the absolute Maximum value, the latter is considered. Let's take an example of ''multiplier = 2''.

	* Scenario A: The system is quiet (5 active threads)<br>		* Scenario A: The system is quiet (5 active threads)<br>

PoC: /* Work with Shared Pools */ Thread multiplier explained

2026-10-06T07:51:45Z

Work with Shared Pools: Thread multiplier explained

← Older revision		Revision as of 09:51, 6 October 2026
Line 43:		Line 43:
	\|align="right"\|100		\|align="right"\|100
	\|align="right"\|'''25'''		\|align="right"\|'''25'''
	\|align="right"\|0.5		\|align="right"\|'''5'''
	\|align="right"\|'''2000'''		\|align="right"\|'''2000'''
	\|-		\|-
Line 51:		Line 51:
	\|align="right"\|'''25'''		\|align="right"\|'''25'''
	\|align="right"\|'''50'''		\|align="right"\|'''50'''
	\|align="right"\|2		\|align="right"\|'''10'''
	\|align="right"\|'''1000'''		\|align="right"\|'''1000'''
	\|-		\|-
Line 59:		Line 59:
	\|align="right"\|'''10'''		\|align="right"\|'''10'''
	\|align="right"\|'''25'''		\|align="right"\|'''25'''
	\|align="right"\|1		\|align="right"\|'''5'''
	\|align="right"\|'''1000'''		\|align="right"\|'''1000'''
	\|}		\|}
Line 65:		Line 65:
	Some explanation to the meaning of the ''Faults/Second'' values:		Some explanation to the meaning of the ''Faults/Second'' values:
	* '''Minimum''': If a pool's faulting rate drops below this value, the adjuster views the pool as over-allocated and will begin to strip memory away from it to feed other pools.		* '''Minimum''': If a pool's faulting rate drops below this value, the adjuster views the pool as over-allocated and will begin to strip memory away from it to feed other pools.
	* '''Thread''': ~~The~~ multiplier ~~allocated~~ per active thread~~. The OS calculates active threads by evaluating only threads that have actually consumed CPU slices during the most recent tuning interval~~.		* '''Thread''': A multiplier per (active) thread.
	* '''Maximum''': If the pool's faulting rate exceeds this value, the adjuster considers the pool starved and starts aggressively moving memory into it from other pools.		* '''Maximum''': If the pool's faulting rate exceeds this value, the adjuster considers the pool starved and starts aggressively moving memory into it from other pools.

Line 71:		Line 71:
	* Establish hard ''Size %'' limits to prevent pool starvation		* Establish hard ''Size %'' limits to prevent pool starvation
	* Allow for much higher faulting rates (''Faults/Second'') before taking action		* Allow for much higher faulting rates (''Faults/Second'') before taking action

			=== Thread multiplier ===
			Explanation by example: If one user is running an application in the INTERACT pool and causing 50 faults/second, that single user is experiencing a performance bottleneck. Contrary, if 100 people are using INTERACT simultaneously and causing the same 50 faults/second, that means each user is only experiencing 0.5 faults/second. No bottleneck.

			The system calculates a ''dynamic Maximum = Minimum + (Thread Multiplier × Active Threads)''. If that value exceeds the absolute Maximum value, the latter is considered. Let's take an example of ''multiplier = 2''.

			* Scenario A: The system is quiet (5 active threads)<br>
			50 + (2 × 5) = 60 faults/s<br>
			Because only 5 threads are active, the baseline is 60 faults/s. If overall pool activity exceeds 60 faults/s, adjustment will kick in.
			* Scenario B: Peak hours (200 active threads)<br>
			50 + (2 × 200) = 450 faults/s<br>
			Now 200 threads are actively sharing the pool, and adjustment scales its tolerance up to 450 faults/sec before it considers the pool "starved" enough to warrant moving memory from elsewhere.
			* Scenario C: Extreme burst (600 active threads)<br>
			50 + (2 × 600) = 1250 faults/s<br>
			Because the absolute Maximum is capped at 1000, the math is clipped. The threshold stops scaling and locks firmly at 1000 faults/s.

			Using higher scaling values still considers dynamic adjustment up to the raised absolute maximum values, and keeps the basic adjustment logic active.

	== See also ==		== See also ==

PoC: Better wording: Paging ≠ Faulting

2026-10-06T07:30:25Z

Better wording: Paging ≠ Faulting

← Older revision		Revision as of 09:30, 6 October 2026
Line 8:		Line 8:
	Today, disks are largely replaced with solid state, '''[[wikipedia:Flash memory\|flash based memory]]'''. It has no moving mechanical parts, eliminates the accompanying access latency, generates no noise, draws less power, generates less heat, and often uses less physical space. Older AS/400 systems can benefit from the [[ZuluSCSI]] parallel SCSI disk emulator.		Today, disks are largely replaced with solid state, '''[[wikipedia:Flash memory\|flash based memory]]'''. It has no moving mechanical parts, eliminates the accompanying access latency, generates no noise, draws less power, generates less heat, and often uses less physical space. Older AS/400 systems can benefit from the [[ZuluSCSI]] parallel SCSI disk emulator.

	OS/400 features a so called '''performance adjustment''' function, which automatically splits and shifts available memory around between memory pools according to the current workload, the goal is to minimize paging ~~activtiy~~. The default threshold values when, and how much memory is moved around are based on the relatively high latency of rotating disk drives. One particular data point is the ''~~paging~~ rate'', essentially how quickly the system tries to bring in data from secondary storage (disk) into primary storage (RAM) for processing. The higher the ~~paging~~ rate, the more aggressive memory is moved between pools.		OS/400 features a so called '''performance adjustment''' function, which automatically splits and shifts available memory around between memory pools according to the current workload, the goal is to minimize paging activity. The default threshold values when, and how much memory is moved around are based on the relatively high latency of rotating disk drives. One particular data point is the ''faulting rate'', essentially how quickly the system tries to bring in data from secondary storage (disk) into primary storage (RAM) for processing. The higher the faulting rate, the more aggressive memory is moved between pools.

	Solid state memory allows very high paging rates, impossible with spinning disk drives, but without introducing excessive latency. The performance adjust doesn't base adjustment calculations on latency, but on ~~paging~~ rate. On a system with much disk activity, this can lead to memory starvation of less active pools, and frequent invalidation of in-memory cached data due to quick reassignments of memory.		<blockquote>'''Note:''' Despite the word ''fault'' seemingly indicating a fatal condition, it isn't. A [[wikipedia:Page fault\|page fault]] is a mere indicator that a requested memory location isn't in main storage and a different code path has to be taken to bring it into main storage before processing can commence. Also, a single page fault can result in multiple memory pages being copied into main storage at once.</blockquote>

			Solid state memory allows very high paging rates, impossible with spinning disk drives, but without introducing excessive latency. The performance adjust doesn't base adjustment calculations on latency, but on faulting rate. On a system with much disk activity, this can lead to memory starvation of less active pools, and frequent invalidation of in-memory cached data due to quick reassignments of memory.

	== Work with Shared Pools ==		== Work with Shared Pools ==
Line 62:		Line 64:

	Some explanation to the meaning of the ''Faults/Second'' values:		Some explanation to the meaning of the ''Faults/Second'' values:
	* '''Minimum''': If a pool's ~~paging~~ rate drops below this value, the adjuster views the pool as over-allocated and will begin to strip memory away from it to feed other pools.		* '''Minimum''': If a pool's faulting rate drops below this value, the adjuster views the pool as over-allocated and will begin to strip memory away from it to feed other pools.
	* '''Thread''': The multiplier allocated per active thread. The OS calculates active threads by evaluating only threads that have actually consumed CPU slices during the most recent tuning interval.		* '''Thread''': The multiplier allocated per active thread. The OS calculates active threads by evaluating only threads that have actually consumed CPU slices during the most recent tuning interval.
	* '''Maximum''': If the pool's ~~paging~~ rate exceeds this value, the adjuster considers the pool starved and starts aggressively moving memory into it from other pools.		* '''Maximum''': If the pool's faulting rate exceeds this value, the adjuster considers the pool starved and starts aggressively moving memory into it from other pools.

	The primary goals behind the suggested values are		The primary goals behind the suggested values are
	* Establish hard ''Size %'' limits to prevent pool starvation		* Establish hard ''Size %'' limits to prevent pool starvation
	* Allow for much higher ~~paging~~ rates (''Faults/Second'') before taking action		* Allow for much higher faulting rates (''Faults/Second'') before taking action

	== See also ==		== See also ==

← Older revision		Revision as of 10:43, 6 October 2026
Line 30:		Line 30:
	\|*MACHINE		\|*MACHINE
	\|align="right"\|1		\|align="right"\|1
	\|align="right"\|~25<ref>This value is calculated by the system.</ref>		\|align="right"\|~25<ref>This value is actually calculated by the system.</ref>
	\|align="right"\|100		\|align="right"\|100
	\|align="right"\|10		\|align="right"\|10
Line 103:		Line 103:
	\|*MACHINE		\|*MACHINE
	\|align="right"\|1		\|align="right"\|1
	\|align="right"\|DFT<ref>A literal <tt>DFT</tt> isn't actually printed but can be used if the value has been changed prior.</ref>		\|align="right"\|DFT<ref>A literal <tt>DFT</tt> isn't actually printed but can be used to reset to the default value if it has been changed prior.</ref>
	\|align="right"\|'''50'''		\|align="right"\|'''50'''
	\|align="right"\|'''100'''		\|align="right"\|'''100'''

← Older revision		Revision as of 10:42, 6 October 2026
Line 103:		Line 103:
	\|*MACHINE		\|*MACHINE
	\|align="right"\|1		\|align="right"\|1
	\|align="right"\|~~25.49~~<ref>~~Use~~ literal <tt>*DFT</tt> ~~to reset to default,~~ if ~~unsure~~.</ref>		\|align="right"\|DFT<ref>A literal <tt>DFT</tt> isn't actually printed but can be used if the value has been changed prior.</ref>
	\|align="right"\|'''50'''		\|align="right"\|'''50'''
	\|align="right"\|'''100'''		\|align="right"\|'''100'''

← Older revision		Revision as of 10:36, 6 October 2026
Line 15:		Line 15:

	== Work with Shared Pools ==		== Work with Shared Pools ==
	The <code>wrkshrpool</code> command allows to adjust threshold values for the performance adjuster by pressing <code>F11</code>. You'll be presented with a table akin to the following. ~~Suggested adjustment~~ values ~~are shown below. Values printed in ''bold'' are changed~~ (~~non-default~~) ~~values.~~		The <code>wrkshrpool</code> command allows to adjust threshold values for the performance adjuster by pressing <code>F11</code>. You'll be presented with a table akin to the following. This table shows default values (for V4R5):

	{\|class="wikitable"		{\|class="wikitable"
	!colspan="2"\|		!colspan="2"\|
Line 32:		Line 31:
	\|*MACHINE		\|*MACHINE
	\|align="right"\|1		\|align="right"\|1
	\|align="right"\|25~~.49~~<ref>~~Use literal <tt>*DFT</tt> to reset to default, if unsure~~.</ref>		\|align="right"\|~25<ref>This value is calculated by the system.</ref>
	\|align="right"\|~~'''50'''~~		\|align="right"\|100
	\|align="right"\|~~'''100'''~~		\|align="right"\|10
	\|align="right"\|0		\|align="right"\|0
	\|align="right"\|~~'''100'''~~		\|align="right"\|10
	\|-		\|-
	\|*BASE		\|*BASE
Line 42:		Line 41:
	\|align="right"\|4.99		\|align="right"\|4.99
	\|align="right"\|100		\|align="right"\|100
	\|align="right"\|~~'''25'''~~		\|align="right"\|5
	\|align="right"\|~~'''~~5~~'''~~		\|align="right"\|0.5
	\|align="right"\|~~'''~~2000~~'''~~		\|align="right"\|2000
	\|-		\|-
	\|*INTERACT		\|*INTERACT
	\|align="right"\|2		\|align="right"\|2
	\|align="right"\|5		\|align="right"\|5
	\|align="right"\|~~'''25'''~~		\|align="right"\|100
	\|align="right"\|~~'''50'''~~		\|align="right"\|10
	\|align="right"\|~~'''10'''~~		\|align="right"\|2
	\|align="right"\|~~'''1000'''~~		\|align="right"\|100
	\|-		\|-
	\|*SPOOL		\|*SPOOL
	\|align="right"\|~~'''3'''~~		\|align="right"\|2
			\|align="right"\|1
			\|align="right"\|100
			\|align="right"\|5
	\|align="right"\|1		\|align="right"\|1
	\|align="right"\|~~'''10'''~~		\|align="right"\|100
	~~\|align="right"\|'''25'''~~
	~~\|align="right"\|'''5'''~~
	~~\|align="right"\|'''1000'''~~
	\|}		\|}

Line 69:		Line 68:
	* '''Thread''': A multiplier per (active) thread.		* '''Thread''': A multiplier per (active) thread.
	* '''Maximum''': If the pool's faulting rate exceeds this value, the adjuster considers the pool starved and starts aggressively moving memory into it from other pools.		* '''Maximum''': If the pool's faulting rate exceeds this value, the adjuster considers the pool starved and starts aggressively moving memory into it from other pools.

	~~The primary goals behind the suggested values are~~
	* Establish hard ''Size %'' limits to prevent pool starvation
	* Allow for much higher faulting rates (''Faults/Second'') before taking action

	=== Thread multiplier ===		=== Thread multiplier ===
Line 89:		Line 84:
	Because the absolute Maximum is capped at 1000, the math is clipped. The threshold stops scaling and locks firmly at 1000 faults/s.		Because the absolute Maximum is capped at 1000, the math is clipped. The threshold stops scaling and locks firmly at 1000 faults/s.

	Using higher scaling values still considers dynamic adjustment up to the raised absolute maximum values, and keeps the basic adjustment logic active.		=== Recommended adjustments ===
			Values printed in ''bold'' are changed (non-default) values.

			<blockquote>'''Note:''' These values are intended for small scale, or hobbyist systems. If these values hold up for heavy usage has not been established.</blockquote>

			{\|class="wikitable"
			!colspan="2"\|
			!colspan="2"\|Size (%)
			!colspan="3"\|Faults/Second
			\|-
			!Pool
			!Priority
			!Minimum
			!Maximum
			!Minimum
			!Thread
			!Maximum
			\|-
			\|*MACHINE
			\|align="right"\|1
			\|align="right"\|25.49<ref>Use literal <tt>*DFT</tt> to reset to default, if unsure.</ref>
			\|align="right"\|'''50'''
			\|align="right"\|'''100'''
			\|align="right"\|0
			\|align="right"\|'''100'''
			\|-
			\|*BASE
			\|align="right"\|1
			\|align="right"\|4.99
			\|align="right"\|100
			\|align="right"\|'''25'''
			\|align="right"\|'''5'''
			\|align="right"\|'''2000'''
			\|-
			\|*INTERACT
			\|align="right"\|2
			\|align="right"\|5
			\|align="right"\|'''25'''
			\|align="right"\|'''50'''
			\|align="right"\|'''10'''
			\|align="right"\|'''1000'''
			\|-
			\|*SPOOL
			\|align="right"\|'''3'''
			\|align="right"\|1
			\|align="right"\|'''10'''
			\|align="right"\|'''25'''
			\|align="right"\|'''5'''
			\|align="right"\|'''1000'''
			\|}

			The primary goals behind the suggested values are:
			* Establish hard ''Size %'' limits to prevent pool starvation.
			* Allow for much higher faulting rates (''Faults/Second'') before taking action.
			* Using higher scaling values still considers dynamic adjustment up to the raised absolute maximum values, and keeps the basic adjustment logic active.

	== See also ==		== See also ==