About pseudo swap

[한국 휴렛팩커드]

I wanna know correct mechanism of pseudo swap
Here is some document about psedo swap.

>Pseudo swap is HP's solution for large memory customers who do not wish to
>purchase a large amount of swap space. The justification for purchasing large
>memory systems is to prevent paging and swapping, therefore, the argument
>becomes "Why purchase a lot of swap space if the system is not expected to page
>or swap?"
>Pseudo swap is swap space which the operating systems recognizes, but in
>reality it does not exist. Pseudo swap is make-believe swap space. It does not
>exist in memory, it does not exist on disk, it does not exist anywhere.
>However, the operating system does recognize it, which means more swap space
>can be reserved than physically exists.


I understand this document.
Then, Is there only one profit in "saving disk area" through of using the pseudo swap?
Some customer says the pseudo swap gave them more performacne, the others customer says oppositely.

I guess It is more helpful some system that has a large physical memory with non-heavy load and save the swap disk space.
When one process start in system, o/s should guarenty phyiscal memory space(or virtual mem) and resevered area in swap device to prepare space in page fault situation commonly. Where could it possible reserved area ,in the system adapted pseudo swap?

Is it physical memory or device swap disk?
If there is performance gain through using pseudo swap, it could possible that resevered area will be set in physical memory.
Except these reason, How could it possible gain performance improvement?

Anyone help me~

[Clemens van Everdingen]

Hi,

It is always difficult to tell what is the performance gain is in particular configurations.

I have the same document as you displayed a part of in your question.
Is that the complete info you have or do you have the rest of it to ?

this is the rest of it !

------------------------------------------
The purpose of pseudo swap is to allow more processes to run in memory, than
could be supported by the swap device(s). Swap devices refer to both device
swap or filesystem swap. It allows the operating system(specifically the kernel
variable swap_avail) to recognize more swap space, thereby allowing additional
processes to start when all of the physical swap has been reserved. By having
the operating system recognize more swap space than physically exists, large
memory customers can now operate without having to purchase large amounts of
swap space which they will most likely never use.

The size of pseudo swap is dependent on the amount of memory in the system.
Specifically, the size is 75% of physical memory. This means the swap_avail
variable will have an additional amount(75% of physical memory) added to its
content. This additional amount allows more processes to start when all of the
physical swap has been reserved.

Pseudo swap is enabled through the tunable kernel parameter called swapmem_on.
If the value for swapmem_on is 1, then psuedo swap is turned on or enabled. The
percentage of physical memory that pseudo swap adds to swap_avail is not a
tunable kernel parameter and is always 75%. This information is valid for all
versions of HP-UX 10.X and 11.0
---------------------------------------------

I found an interesting on-line doc about configuring swap and the three type of swap.

http://www.docs.hp.com/cgi-bin/fsearch/framedisplay?top=/hpux/onlinedocs/B2355-90672/B2355-90672_top.html&con=/hpux/onlinedocs/B2355-90672/00/00/64-con.html&toc=/hpux/onlinedocs/B2355-90672/00/00/64-toc.html&searchterms=pseudo%7cswap&queryid=20020423-232320

It probably will be a bit experimenting in finding the best swap configuration for your system !

Regards,
C.

[Tore_1]

Hpux requires requieres every process to reserve swap space for its memory regions.

So if you have say 9G virtual memory, you need to reserve 9G swap space.

Obviously, you never actually need 9G swap, because if the swap/paging rate came close to that amount your system would be unusable.

What you want is to trick the system to think you have enough swap space for reservation purposes without actually having to waste a lot of disk space you will never actually use.

Pseudo swap is this mechanism. When turned on (with swapmem_on kernel parameter), the system thinks it has an extra 75% of available memory extra for swap purposes.

No paging/swapping will ever take place in ram.
So : configure enough swap space on disk to cover your actual swap usage.

[Tom Geudens]

Hi,
Take a look at this document http://h21007.www2.hp.com/dspp/files/unprotected/devresource/Docs/TechPapers/UXPerfCookBook.pdf
It's a great document that covers a lot of performance issues ... pseudoswap amongst them.

Hope this helps,
Tom

[Michael Tully]

Hi,

Here is extract from the /usr/share/doc/mem_mgt.txt file on one of my HPUX 11 systems, that might explain it a bit better.


Pseudo-Swap Space
-----------------

System memory used for swap space is called pseudo-swap space. It allows users to execute processes in memory without allocating physical
swap. Pseudo-swap is controlled by an operating-system parameter; by default, swapmem_on is set to 1, enabling pseudo-swap.

Typically, when the system executes a process, swap space is reserved for the entire process, in case it must be paged out. According to this model, to run one gigabyte of processes, the system would have to have one gigabyte of configured swap space. Although this protects the system from running out of swap space, disk space reserved for swap is under-utilized if minimal or no swapping occurs.

To avoid such waste of resources, HP-UX is configured to access up to three-quarters of system memory capacity as pseudo-swap. This means that system memory serves two functions: as process-execution space and as swap space. By using pseudo-swap space, a one-gigabyte memory system with one-gigabyte of swap can run up to 1.75 GB of processes. As before, if a process attempts to grow or be created beyond this extended threshold, it will fail.

When using pseudo swap for swap, the pages are locked; as the amount of pseudo-swap increases, the amount of lockable memory decreases.

For factory-floor systems (such as controllers), which perform best when the entire application is resident in memory, pseudo-swap space can be used to enhance performance: you can either lock the application in memory or make sure the total number of processes created does not exceed three-quarters of system memory.

Pseudo-swap space is set to a maximum of three-quarters of system memory because the system can begin paging once three-quarters of system available memory has been used. The unused quarter of memory allows a buffer between the system and the swapper to give the system
computational flexibility.

When the number of processes created approaches capacity, the system might exhibit thrashing and a decrease in system response time. If necessary, you can disable pseudo-swap space by setting the tunable parameter swapmem_on in /usr/conf/master.d/core-hpux to zero.

At the head of a doubly linked list of regions that have pseudo-swap allocated is a null terminated list called pswaplist.

[Steven Sim Kok Leong]

Hi,

From the HP-UX 10.X memory management paper:

http://www.ussg.iu.edu/usail/external/tuning/mem_mgmt

Pseudo-swap was introduced, apart from simply faster performance than device swap because memory fetches are faster than disk fetches, mainly as a more flexible alternative (swap space can be increased or reduced upon need) to wasting device swap (swap space is fixed in size regardless of whether it is used or not at any point in time).

However, one disadvantage is that if pseudo-swap reservation is
enabled, it does not allow lockable memory to exceed 3/4 of available memory on a Series 800 and 7/8 of available memory on a Series 700 system. On systems using pseudo-swap, as the amount of pseudo-swap increases, the amount of lockable memory decreases. These limits can be altered using the unlockable_mem parameter.

Pseudo-swap space is set to a maximum of three-quarters of system memory because the system can begin paging once three-quarters of system available memory has been used. The unused quarter of memory allows a buffer between the system and the swapper to give the system more breathing room.

Disk space has fallen in price but memory price has gone up recently and is expected to go up more. Depending on your needs, you have to weigh the trade-offs and decide on the most const-effective configuration.

Hope this helps. Regards.

Steven Sim Kok Leong