Page replacement algorithm

In a computer operating system that uses paging for virtual memory memory management, page replacement algorithms decide which memory pages to page out (swap out, write to disk) when a page of memory needs to be allocated. Paging happens when a page fault occurs and a free page cannot be used to satisfy the allocation, either because there are none, or because the number of free pages is lower than some threshold.

When the page that was selected for replacement and paged out is referenced again it has to be paged in (read in from disk), and this involves waiting for I/O completion. This determines the quality of the page replacement algorithm: the less time waiting for page-ins, the better the algorithm. A page replacement algorithm looks at the limited information about accesses to the pages provided by hardware, and tries to guess which pages should be replaced to minimize the total number of page misses, while balancing this with the costs (primary storage and processor time) of the algorithm itself.

History

Page replacement algorithms were a hot topic of research and debate in the 1960s and 1970s. That mostly ended with the development of sophisticated LRU approximations and working set algorithms. Since then, some basic assumptions made by the traditional page replacement algorithms were invalidated, resulting in a revival of research. In particular, the following trends in the behavior of underlying hardware and user-level software has affected the performance of page replacement algorithms:

    * Size of primary storage has increased by multiple orders of magnitude. With several gigabytes of primary memory, algorithms that require a periodic check of each and every memory frame are becoming less and less practical.
    * Memory hierarchies have grown taller. The cost of a CPU cache miss is far more expensive. This exacerbates the previous problem.
    * Locality of reference of user software has weakened. This is mostly attributed to the spread of object-oriented programming techniques that favor large numbers of small functions, use of sophisticated data structures like trees and hash tables that tend to result in chaotic memory reference patterns, and the advent of garbage collection that drastically changed memory access behavior of applications.

Requirements for page replacement algorithms have changed due to differences in operating system kernel architectures. In particular, most modern OS kernels have unified virtual memory and file system caches, requiring the page replacement algorithm to select a page from among the pages of both user program virtual address spaces and cached files. The latter pages have specific properties. For example, they can be locked, or can have write ordering requirements imposed by journaling. Moreover, as the goal of page replacement is to minimize total time waiting for memory, it has to take into account memory requirements imposed by other kernel sub-systems that allocate memory. As a result, page replacement in modern kernels (Linux, FreeBSD, and Solaris) tends to work at the level of a general purpose kernel memory allocator, rather than at the higher level of a virtual memory subsystem.

Local vs. global replacement

Replacement algorithms can be local or global.

When a process incurs a page fault, a local page replacement algorithm selects for replacement some page that belongs to that same process (or a group of processes sharing a memory partition). A global replacement algorithm is free to select any page in memory.

Local page replacement assumes some form of memory partitioning that determines how many pages are to be assigned to a given process or a group of processes. Most popular forms of partitioning are fixed partitioning and balanced set algorithms based on the working set model. The advantage of local page replacement is its scalability: each process can handle its page faults independently without contending for some shared global data structure.

Precleaning

Most replacement algorithms simply return the target page as their result. This means that if target page is dirty (that is, contains data that have to be written to the stable storage before page can be reclaimed), I/O has to be initiated to send that page to the stable storage (to clean the page). In the early days of virtual memory, time spent on cleaning was not of much concern, because virtual memory was first implemented on systems with full duplex channels to the stable storage, and cleaning was customarily overlapped with paging. Contemporary commodity hardware, on the other hand, does not support full duplex transfers, and cleaning of target pages becomes an issue.

To deal with this situation, various precleaning policies are implemented. Precleaning is the mechanism that starts I/O on dirty pages that are (likely) to be replaced soon. The idea is that by the time the precleaned page is actually selected for the replacement, the I/O will complete and the page will be clean. Precleaning assumes that it is possible to identify pages that will be replaced next. Precleaning that is too eager can waste I/O bandwidth by writing pages that manage to get re-dirtied before being selected for replacement.

Anticipatory paging

Some systems use demand paging -- waiting until a page is actually requested before loading it into RAM.

Other systems attempt to reduce latency by guessing which pages not in RAM are likely to be needed soon, and pre-loading such pages into RAM, before that page is requested. (This is often in combination with pre-cleaning, which guesses which pages currently in RAM are not likely to be needed soon, and pre-writing them out to storage).

When a page fault occurs, "anticipatory paging" systems will not only bring in the referenced page, but also the next few consecutive pages (analogous to a prefetch input queue in a CPU).

The swap prefetch mechanism goes even further in loading pages (even if they are not consecutive) that are likely to be needed soon.

The theoretically optimal page replacement algorithm

The theoretically optimal page replacment algorithm (also known as OPT, clairvoyant replacement algorithm, or Belady's optimal page replacement policy) is an algorithm that works as follows: when a page needs to be swapped in, the operating system swaps out the page whose next use will occur farthest in the future. For example, a page that is not going to be used for the next 6 seconds will be swapped out over a page that is going to be used within the next 0.4 seconds.

This algorithm cannot be implemented in the general purpose operating system because it is impossible to compute reliably how long it will be before a page is going to be used, except when all software that will run on a system is either known beforehand and is amenable to the static analysis of its memory reference patterns, or only a class of applications allowing run-time analysis is allowed. Despite this limitation, algorithms exist[citation needed] that can offer near-optimal performance — the operating system keeps track of all pages referenced by the program, and it uses those data to decide which pages to swap in and out on subsequent runs. This algorithm can offer near-optimal performance, but not on the first run of a program, and only if the program's memory reference pattern is relatively consistent each time it runs.

Analysis of the paging problem has also been done in the field of online algorithms. Efficiency of randomized online algorithms for the paging problem is measured using amortized analysis.

Not recently used

The not recently used (NRU) page replacement algorithm is an algorithm that favours keeping pages in memory that have been recently used. This algorithm works on the following principle: when a page is referenced, a referenced bit is set for that page, marking it as referenced. Similarly, when a page is modified (written to), a modified bit is set. The setting of the bits is usually done by the hardware, although it is possible to do so on the software level as well.

At a certain fixed time interval, the clock interrupt triggers and clears the referenced bit of all the pages, so only pages referenced within the current clock interval are marked with a referenced bit. When a page needs to be replaced, the operating system divides the pages into four classes:

    * Class 0: not referenced, not modified
    * Class 1: not referenced, modified
    * Class 2: referenced, not modified
    * Class 3: referenced, modified

Although it does not seem possible for a page to be not referenced yet modified, this happens when a class 3 page has its referenced bit cleared by the clock interrupt. The NRU algorithm picks a random page from the lowest category for removal. Note that this algorithm implies that a modified (within clock interval) but not referenced page is less important than a not modified page that is intensely referenced.