mirror of
https://github.com/edg-l/edlang.git
synced 2024-11-14 03:58:23 +00:00
109 lines
12 KiB
HTML
109 lines
12 KiB
HTML
<!DOCTYPE html><html lang="en"><head><meta charset="utf-8"><meta name="viewport" content="width=device-width, initial-scale=1.0"><meta name="generator" content="rustdoc"><meta name="description" content="Notes on `sharded-slab`’s implementation and design."><title>sharded_slab::implementation - Rust</title><link rel="preload" as="font" type="font/woff2" crossorigin href="../../static.files/SourceSerif4-Regular-46f98efaafac5295.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../static.files/FiraSans-Regular-018c141bf0843ffd.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../static.files/FiraSans-Medium-8f9a781e4970d388.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../static.files/SourceCodePro-Regular-562dcc5011b6de7d.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../static.files/SourceCodePro-Semibold-d899c5a5c4aeb14a.ttf.woff2"><link rel="stylesheet" href="../../static.files/normalize-76eba96aa4d2e634.css"><link rel="stylesheet" href="../../static.files/rustdoc-ac92e1bbe349e143.css"><meta name="rustdoc-vars" data-root-path="../../" data-static-root-path="../../static.files/" data-current-crate="sharded_slab" data-themes="" data-resource-suffix="" data-rustdoc-version="1.76.0 (07dca489a 2024-02-04)" data-channel="1.76.0" data-search-js="search-2b6ce74ff89ae146.js" data-settings-js="settings-4313503d2e1961c2.js" ><script src="../../static.files/storage-f2adc0d6ca4d09fb.js"></script><script defer src="../sidebar-items.js"></script><script defer src="../../static.files/main-305769736d49e732.js"></script><noscript><link rel="stylesheet" href="../../static.files/noscript-feafe1bb7466e4bd.css"></noscript><link rel="alternate icon" type="image/png" href="../../static.files/favicon-16x16-8b506e7a72182f1c.png"><link rel="alternate icon" type="image/png" href="../../static.files/favicon-32x32-422f7d1d52889060.png"><link rel="icon" type="image/svg+xml" href="../../static.files/favicon-2c020d218678b618.svg"></head><body class="rustdoc mod"><!--[if lte IE 11]><div class="warning">This old browser is unsupported and will most likely display funky things.</div><![endif]--><nav class="mobile-topbar"><button class="sidebar-menu-toggle">☰</button></nav><nav class="sidebar"><div class="sidebar-crate"><h2><a href="../../sharded_slab/index.html">sharded_slab</a><span class="version">0.1.7</span></h2></div><h2 class="location"><a href="#">Module implementation</a></h2><div class="sidebar-elems"><h2><a href="../index.html">In crate sharded_slab</a></h2></div></nav><div class="sidebar-resizer"></div>
|
||
<main><div class="width-limiter"><nav class="sub"><form class="search-form"><span></span><div id="sidebar-button" tabindex="-1"><a href="../../sharded_slab/all.html" title="show sidebar"></a></div><input class="search-input" name="search" aria-label="Run search in the documentation" autocomplete="off" spellcheck="false" placeholder="Click or press ‘S’ to search, ‘?’ for more options…" type="search"><div id="help-button" tabindex="-1"><a href="../../help.html" title="help">?</a></div><div id="settings-menu" tabindex="-1"><a href="../../settings.html" title="settings"><img width="22" height="22" alt="Change settings" src="../../static.files/wheel-7b819b6101059cd0.svg"></a></div></form></nav><section id="main-content" class="content"><div class="main-heading"><h1>Module <a href="../index.html">sharded_slab</a>::<wbr><a class="mod" href="#">implementation</a><button id="copy-path" title="Copy item path to clipboard"><img src="../../static.files/clipboard-7571035ce49a181d.svg" width="19" height="18" alt="Copy item path"></button></h1><span class="out-of-band"><a class="src" href="../../src/sharded_slab/implementation.rs.html#4-138">source</a> · <button id="toggle-all-docs" title="collapse all docs">[<span>−</span>]</button></span></div><details class="toggle top-doc" open><summary class="hideme"><span>Expand description</span></summary><div class="docblock"><p>Notes on <code>sharded-slab</code>’s implementation and design.</p>
|
||
<h2 id="design"><a href="#design">Design</a></h2>
|
||
<p>The sharded slab’s design is strongly inspired by the ideas presented by
|
||
Leijen, Zorn, and de Moura in <a href="https://www.microsoft.com/en-us/research/uploads/prod/2019/06/mimalloc-tr-v1.pdf">Mimalloc: Free List Sharding in
|
||
Action</a>. In this report, the authors present a novel design for a
|
||
memory allocator based on a concept of <em>free list sharding</em>.</p>
|
||
<p>Memory allocators must keep track of what memory regions are not currently
|
||
allocated (“free”) in order to provide them to future allocation requests.
|
||
The term <a href="https://en.wikipedia.org/wiki/Free_list"><em>free list</em></a> refers to a technique for performing this
|
||
bookkeeping, where each free block stores a pointer to the next free block,
|
||
forming a linked list. The memory allocator keeps a pointer to the most
|
||
recently freed block, the <em>head</em> of the free list. To allocate more memory,
|
||
the allocator pops from the free list by setting the head pointer to the
|
||
next free block of the current head block, and returning the previous head.
|
||
To deallocate a block, the block is pushed to the free list by setting its
|
||
first word to the current head pointer, and the head pointer is set to point
|
||
to the deallocated block. Most implementations of slab allocators backed by
|
||
arrays or vectors use a similar technique, where pointers are replaced by
|
||
indices into the backing array.</p>
|
||
<p>When allocations and deallocations can occur concurrently across threads,
|
||
they must synchronize accesses to the free list; either by putting the
|
||
entire allocator state inside of a lock, or by using atomic operations to
|
||
treat the free list as a lock-free structure (such as a <a href="https://en.wikipedia.org/wiki/Treiber_stack">Treiber stack</a>). In
|
||
both cases, there is a significant performance cost — even when the free
|
||
list is lock-free, it is likely that a noticeable amount of time will be
|
||
spent in compare-and-swap loops. Ideally, the global synchronzation point
|
||
created by the single global free list could be avoided as much as possible.</p>
|
||
<p>The approach presented by Leijen, Zorn, and de Moura is to introduce
|
||
sharding and thus increase the granularity of synchronization significantly.
|
||
In mimalloc, the heap is <em>sharded</em> so that each thread has its own
|
||
thread-local heap. Objects are always allocated from the local heap of the
|
||
thread where the allocation is performed. Because allocations are always
|
||
done from a thread’s local heap, they need not be synchronized.</p>
|
||
<p>However, since objects can move between threads before being deallocated,
|
||
<em>deallocations</em> may still occur concurrently. Therefore, Leijen et al.
|
||
introduce a concept of <em>local</em> and <em>global</em> free lists. When an object is
|
||
deallocated on the same thread it was originally allocated on, it is placed
|
||
on the local free list; if it is deallocated on another thread, it goes on
|
||
the global free list for the heap of the thread from which it originated. To
|
||
allocate, the local free list is used first; if it is empty, the entire
|
||
global free list is popped onto the local free list. Since the local free
|
||
list is only ever accessed by the thread it belongs to, it does not require
|
||
synchronization at all, and because the global free list is popped from
|
||
infrequently, the cost of synchronization has a reduced impact. A majority
|
||
of allocations can occur without any synchronization at all; and
|
||
deallocations only require synchronization when an object has left its
|
||
parent thread (a relatively uncommon case).</p>
|
||
<h2 id="implementation"><a href="#implementation">Implementation</a></h2>
|
||
<p>A slab is represented as an array of <a href="https://docs.rs/sharded-slab/latest/sharded_slab/trait.Config.html#associatedconstant.MAX_THREADS"><code>MAX_THREADS</code></a> <em>shards</em>. A shard
|
||
consists of a vector of one or more <em>pages</em> plus associated metadata.
|
||
Finally, a page consists of an array of <em>slots</em>, head indices for the local
|
||
and remote free lists.</p>
|
||
<div class="example-wrap"><pre class="language-text"><code>┌─────────────┐
|
||
│ shard 1 │
|
||
│ │ ┌─────────────┐ ┌────────┐
|
||
│ pages───────┼───▶│ page 1 │ │ │
|
||
├─────────────┤ ├─────────────┤ ┌────▶│ next──┼─┐
|
||
│ shard 2 │ │ page 2 │ │ ├────────┤ │
|
||
├─────────────┤ │ │ │ │XXXXXXXX│ │
|
||
│ shard 3 │ │ local_head──┼──┘ ├────────┤ │
|
||
└─────────────┘ │ remote_head─┼──┐ │ │◀┘
|
||
... ├─────────────┤ │ │ next──┼─┐
|
||
┌─────────────┐ │ page 3 │ │ ├────────┤ │
|
||
│ shard n │ └─────────────┘ │ │XXXXXXXX│ │
|
||
└─────────────┘ ... │ ├────────┤ │
|
||
┌─────────────┐ │ │XXXXXXXX│ │
|
||
│ page n │ │ ├────────┤ │
|
||
└─────────────┘ │ │ │◀┘
|
||
└────▶│ next──┼───▶ ...
|
||
├────────┤
|
||
│XXXXXXXX│
|
||
└────────┘
|
||
</code></pre></div>
|
||
<p>The size of the first page in a shard is always a power of two, and every
|
||
subsequent page added after the first is twice as large as the page that
|
||
preceeds it.</p>
|
||
<div class="example-wrap"><pre class="language-text"><code>
|
||
pg.
|
||
┌───┐ ┌─┬─┐
|
||
│ 0 │───▶ │ │
|
||
├───┤ ├─┼─┼─┬─┐
|
||
│ 1 │───▶ │ │ │ │
|
||
├───┤ ├─┼─┼─┼─┼─┬─┬─┬─┐
|
||
│ 2 │───▶ │ │ │ │ │ │ │ │
|
||
├───┤ ├─┼─┼─┼─┼─┼─┼─┼─┼─┬─┬─┬─┬─┬─┬─┬─┐
|
||
│ 3 │───▶ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │
|
||
└───┘ └─┴─┴─┴─┴─┴─┴─┴─┴─┴─┴─┴─┴─┴─┴─┴─┘
|
||
</code></pre></div>
|
||
<p>When searching for a free slot, the smallest page is searched first, and if
|
||
it is full, the search proceeds to the next page until either a free slot is
|
||
found or all available pages have been searched. If all available pages have
|
||
been searched and the maximum number of pages has not yet been reached, a
|
||
new page is then allocated.</p>
|
||
<p>Since every page is twice as large as the previous page, and all page sizes
|
||
are powers of two, we can determine the page index that contains a given
|
||
address by shifting the address down by the smallest page size and
|
||
looking at how many twos places necessary to represent that number,
|
||
telling us what power of two page size it fits inside of. We can
|
||
determine the number of twos places by counting the number of leading
|
||
zeros (unused twos places) in the number’s binary representation, and
|
||
subtracting that count from the total number of bits in a word.</p>
|
||
<p>The formula for determining the page number that contains an offset is thus:</p>
|
||
|
||
<div class="example-wrap ignore"><a href="#" class="tooltip" title="This example is not tested">ⓘ</a><pre class="rust rust-example-rendered"><code>WIDTH - ((offset + INITIAL_PAGE_SIZE) >> INDEX_SHIFT).leading_zeros()</code></pre></div>
|
||
<p>where <code>WIDTH</code> is the number of bits in a <code>usize</code>, and <code>INDEX_SHIFT</code> is</p>
|
||
|
||
<div class="example-wrap ignore"><a href="#" class="tooltip" title="This example is not tested">ⓘ</a><pre class="rust rust-example-rendered"><code>INITIAL_PAGE_SIZE.trailing_zeros() + <span class="number">1</span>;</code></pre></div>
|
||
</div></details></section></div></main></body></html> |