| <!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="Source of the Rust file `/root/.cargo/git/checkouts/tantivy-65d0bbbddbbd5d02/433372d/src/indexer/log_merge_policy.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>log_merge_policy.rs - source</title><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../SourceSerif4-Regular.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../FiraSans-Regular.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../FiraSans-Medium.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../SourceCodePro-Regular.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../SourceSerif4-Bold.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../SourceCodePro-Semibold.ttf.woff2"><link rel="stylesheet" href="../../../normalize.css"><link rel="stylesheet" href="../../../rustdoc.css" id="mainThemeStyle"><link rel="stylesheet" href="../../../ayu.css" disabled><link rel="stylesheet" href="../../../dark.css" disabled><link rel="stylesheet" href="../../../light.css" id="themeStyle"><script id="default-settings" ></script><script src="../../../storage.js"></script><script defer src="../../../source-script.js"></script><script defer src="../../../source-files.js"></script><script defer src="../../../main.js"></script><noscript><link rel="stylesheet" href="../../../noscript.css"></noscript><link rel="alternate icon" type="image/png" href="../../../favicon-16x16.png"><link rel="alternate icon" type="image/png" href="../../../favicon-32x32.png"><link rel="icon" type="image/svg+xml" href="../../../favicon.svg"></head><body class="rustdoc source"><!--[if lte IE 11]><div class="warning">This old browser is unsupported and will most likely display funky things.</div><![endif]--><nav class="sidebar"><a class="sidebar-logo" href="../../../tantivy/index.html"><div class="logo-container"> |
| <img src="http://fulmicoton.com/tantivy-logo/tantivy-logo.png" alt="logo"></div></a></nav><main><div class="width-limiter"><nav class="sub"><a class="sub-logo-container" href="../../../tantivy/index.html"> |
| <img src="http://fulmicoton.com/tantivy-logo/tantivy-logo.png" alt="logo"></a><form class="search-form"><div class="search-container"><span></span><input class="search-input" name="search" autocomplete="off" spellcheck="false" placeholder="Click or press ‘S’ to search, ‘?’ for more options…" type="search"><div id="help-button" title="help" tabindex="-1"><a href="../../../help.html">?</a></div><div id="settings-menu" tabindex="-1"><a href="../../../settings.html" title="settings"><img width="22" height="22" alt="Change settings" src="../../../wheel.svg"></a></div></div></form></nav><section id="main-content" class="content"><div class="example-wrap"><pre class="src-line-numbers"><span id="1">1</span> |
| <span id="2">2</span> |
| <span id="3">3</span> |
| <span id="4">4</span> |
| <span id="5">5</span> |
| <span id="6">6</span> |
| <span id="7">7</span> |
| <span id="8">8</span> |
| <span id="9">9</span> |
| <span id="10">10</span> |
| <span id="11">11</span> |
| <span id="12">12</span> |
| <span id="13">13</span> |
| <span id="14">14</span> |
| <span id="15">15</span> |
| <span id="16">16</span> |
| <span id="17">17</span> |
| <span id="18">18</span> |
| <span id="19">19</span> |
| <span id="20">20</span> |
| <span id="21">21</span> |
| <span id="22">22</span> |
| <span id="23">23</span> |
| <span id="24">24</span> |
| <span id="25">25</span> |
| <span id="26">26</span> |
| <span id="27">27</span> |
| <span id="28">28</span> |
| <span id="29">29</span> |
| <span id="30">30</span> |
| <span id="31">31</span> |
| <span id="32">32</span> |
| <span id="33">33</span> |
| <span id="34">34</span> |
| <span id="35">35</span> |
| <span id="36">36</span> |
| <span id="37">37</span> |
| <span id="38">38</span> |
| <span id="39">39</span> |
| <span id="40">40</span> |
| <span id="41">41</span> |
| <span id="42">42</span> |
| <span id="43">43</span> |
| <span id="44">44</span> |
| <span id="45">45</span> |
| <span id="46">46</span> |
| <span id="47">47</span> |
| <span id="48">48</span> |
| <span id="49">49</span> |
| <span id="50">50</span> |
| <span id="51">51</span> |
| <span id="52">52</span> |
| <span id="53">53</span> |
| <span id="54">54</span> |
| <span id="55">55</span> |
| <span id="56">56</span> |
| <span id="57">57</span> |
| <span id="58">58</span> |
| <span id="59">59</span> |
| <span id="60">60</span> |
| <span id="61">61</span> |
| <span id="62">62</span> |
| <span id="63">63</span> |
| <span id="64">64</span> |
| <span id="65">65</span> |
| <span id="66">66</span> |
| <span id="67">67</span> |
| <span id="68">68</span> |
| <span id="69">69</span> |
| <span id="70">70</span> |
| <span id="71">71</span> |
| <span id="72">72</span> |
| <span id="73">73</span> |
| <span id="74">74</span> |
| <span id="75">75</span> |
| <span id="76">76</span> |
| <span id="77">77</span> |
| <span id="78">78</span> |
| <span id="79">79</span> |
| <span id="80">80</span> |
| <span id="81">81</span> |
| <span id="82">82</span> |
| <span id="83">83</span> |
| <span id="84">84</span> |
| <span id="85">85</span> |
| <span id="86">86</span> |
| <span id="87">87</span> |
| <span id="88">88</span> |
| <span id="89">89</span> |
| <span id="90">90</span> |
| <span id="91">91</span> |
| <span id="92">92</span> |
| <span id="93">93</span> |
| <span id="94">94</span> |
| <span id="95">95</span> |
| <span id="96">96</span> |
| <span id="97">97</span> |
| <span id="98">98</span> |
| <span id="99">99</span> |
| <span id="100">100</span> |
| <span id="101">101</span> |
| <span id="102">102</span> |
| <span id="103">103</span> |
| <span id="104">104</span> |
| <span id="105">105</span> |
| <span id="106">106</span> |
| <span id="107">107</span> |
| <span id="108">108</span> |
| <span id="109">109</span> |
| <span id="110">110</span> |
| <span id="111">111</span> |
| <span id="112">112</span> |
| <span id="113">113</span> |
| <span id="114">114</span> |
| <span id="115">115</span> |
| <span id="116">116</span> |
| <span id="117">117</span> |
| <span id="118">118</span> |
| <span id="119">119</span> |
| <span id="120">120</span> |
| <span id="121">121</span> |
| <span id="122">122</span> |
| <span id="123">123</span> |
| <span id="124">124</span> |
| <span id="125">125</span> |
| <span id="126">126</span> |
| <span id="127">127</span> |
| <span id="128">128</span> |
| <span id="129">129</span> |
| <span id="130">130</span> |
| <span id="131">131</span> |
| <span id="132">132</span> |
| <span id="133">133</span> |
| <span id="134">134</span> |
| <span id="135">135</span> |
| <span id="136">136</span> |
| <span id="137">137</span> |
| <span id="138">138</span> |
| <span id="139">139</span> |
| <span id="140">140</span> |
| <span id="141">141</span> |
| <span id="142">142</span> |
| <span id="143">143</span> |
| <span id="144">144</span> |
| <span id="145">145</span> |
| <span id="146">146</span> |
| <span id="147">147</span> |
| <span id="148">148</span> |
| <span id="149">149</span> |
| <span id="150">150</span> |
| <span id="151">151</span> |
| <span id="152">152</span> |
| <span id="153">153</span> |
| <span id="154">154</span> |
| <span id="155">155</span> |
| <span id="156">156</span> |
| <span id="157">157</span> |
| <span id="158">158</span> |
| <span id="159">159</span> |
| <span id="160">160</span> |
| <span id="161">161</span> |
| <span id="162">162</span> |
| <span id="163">163</span> |
| <span id="164">164</span> |
| <span id="165">165</span> |
| <span id="166">166</span> |
| <span id="167">167</span> |
| <span id="168">168</span> |
| <span id="169">169</span> |
| <span id="170">170</span> |
| <span id="171">171</span> |
| <span id="172">172</span> |
| <span id="173">173</span> |
| <span id="174">174</span> |
| <span id="175">175</span> |
| <span id="176">176</span> |
| <span id="177">177</span> |
| <span id="178">178</span> |
| <span id="179">179</span> |
| <span id="180">180</span> |
| <span id="181">181</span> |
| <span id="182">182</span> |
| <span id="183">183</span> |
| <span id="184">184</span> |
| <span id="185">185</span> |
| <span id="186">186</span> |
| <span id="187">187</span> |
| <span id="188">188</span> |
| <span id="189">189</span> |
| <span id="190">190</span> |
| <span id="191">191</span> |
| <span id="192">192</span> |
| <span id="193">193</span> |
| <span id="194">194</span> |
| <span id="195">195</span> |
| <span id="196">196</span> |
| <span id="197">197</span> |
| <span id="198">198</span> |
| <span id="199">199</span> |
| <span id="200">200</span> |
| <span id="201">201</span> |
| <span id="202">202</span> |
| <span id="203">203</span> |
| <span id="204">204</span> |
| <span id="205">205</span> |
| <span id="206">206</span> |
| <span id="207">207</span> |
| <span id="208">208</span> |
| <span id="209">209</span> |
| <span id="210">210</span> |
| <span id="211">211</span> |
| <span id="212">212</span> |
| <span id="213">213</span> |
| <span id="214">214</span> |
| <span id="215">215</span> |
| <span id="216">216</span> |
| <span id="217">217</span> |
| <span id="218">218</span> |
| <span id="219">219</span> |
| <span id="220">220</span> |
| <span id="221">221</span> |
| <span id="222">222</span> |
| <span id="223">223</span> |
| <span id="224">224</span> |
| <span id="225">225</span> |
| <span id="226">226</span> |
| <span id="227">227</span> |
| <span id="228">228</span> |
| <span id="229">229</span> |
| <span id="230">230</span> |
| <span id="231">231</span> |
| <span id="232">232</span> |
| <span id="233">233</span> |
| <span id="234">234</span> |
| <span id="235">235</span> |
| <span id="236">236</span> |
| <span id="237">237</span> |
| <span id="238">238</span> |
| <span id="239">239</span> |
| <span id="240">240</span> |
| <span id="241">241</span> |
| <span id="242">242</span> |
| <span id="243">243</span> |
| <span id="244">244</span> |
| <span id="245">245</span> |
| <span id="246">246</span> |
| <span id="247">247</span> |
| <span id="248">248</span> |
| <span id="249">249</span> |
| <span id="250">250</span> |
| <span id="251">251</span> |
| <span id="252">252</span> |
| <span id="253">253</span> |
| <span id="254">254</span> |
| <span id="255">255</span> |
| <span id="256">256</span> |
| <span id="257">257</span> |
| <span id="258">258</span> |
| <span id="259">259</span> |
| <span id="260">260</span> |
| <span id="261">261</span> |
| <span id="262">262</span> |
| <span id="263">263</span> |
| <span id="264">264</span> |
| <span id="265">265</span> |
| <span id="266">266</span> |
| <span id="267">267</span> |
| <span id="268">268</span> |
| <span id="269">269</span> |
| <span id="270">270</span> |
| <span id="271">271</span> |
| <span id="272">272</span> |
| <span id="273">273</span> |
| <span id="274">274</span> |
| <span id="275">275</span> |
| <span id="276">276</span> |
| <span id="277">277</span> |
| <span id="278">278</span> |
| <span id="279">279</span> |
| <span id="280">280</span> |
| <span id="281">281</span> |
| <span id="282">282</span> |
| <span id="283">283</span> |
| <span id="284">284</span> |
| <span id="285">285</span> |
| <span id="286">286</span> |
| <span id="287">287</span> |
| <span id="288">288</span> |
| <span id="289">289</span> |
| <span id="290">290</span> |
| <span id="291">291</span> |
| <span id="292">292</span> |
| <span id="293">293</span> |
| <span id="294">294</span> |
| <span id="295">295</span> |
| <span id="296">296</span> |
| <span id="297">297</span> |
| <span id="298">298</span> |
| <span id="299">299</span> |
| <span id="300">300</span> |
| <span id="301">301</span> |
| <span id="302">302</span> |
| <span id="303">303</span> |
| <span id="304">304</span> |
| <span id="305">305</span> |
| <span id="306">306</span> |
| <span id="307">307</span> |
| <span id="308">308</span> |
| <span id="309">309</span> |
| <span id="310">310</span> |
| <span id="311">311</span> |
| <span id="312">312</span> |
| <span id="313">313</span> |
| <span id="314">314</span> |
| <span id="315">315</span> |
| <span id="316">316</span> |
| <span id="317">317</span> |
| <span id="318">318</span> |
| <span id="319">319</span> |
| <span id="320">320</span> |
| <span id="321">321</span> |
| <span id="322">322</span> |
| <span id="323">323</span> |
| <span id="324">324</span> |
| <span id="325">325</span> |
| <span id="326">326</span> |
| <span id="327">327</span> |
| <span id="328">328</span> |
| <span id="329">329</span> |
| <span id="330">330</span> |
| <span id="331">331</span> |
| <span id="332">332</span> |
| <span id="333">333</span> |
| <span id="334">334</span> |
| <span id="335">335</span> |
| <span id="336">336</span> |
| <span id="337">337</span> |
| <span id="338">338</span> |
| <span id="339">339</span> |
| <span id="340">340</span> |
| <span id="341">341</span> |
| <span id="342">342</span> |
| <span id="343">343</span> |
| <span id="344">344</span> |
| <span id="345">345</span> |
| <span id="346">346</span> |
| <span id="347">347</span> |
| <span id="348">348</span> |
| <span id="349">349</span> |
| <span id="350">350</span> |
| <span id="351">351</span> |
| <span id="352">352</span> |
| <span id="353">353</span> |
| <span id="354">354</span> |
| <span id="355">355</span> |
| <span id="356">356</span> |
| <span id="357">357</span> |
| <span id="358">358</span> |
| <span id="359">359</span> |
| <span id="360">360</span> |
| <span id="361">361</span> |
| <span id="362">362</span> |
| <span id="363">363</span> |
| <span id="364">364</span> |
| <span id="365">365</span> |
| <span id="366">366</span> |
| <span id="367">367</span> |
| <span id="368">368</span> |
| <span id="369">369</span> |
| <span id="370">370</span> |
| <span id="371">371</span> |
| <span id="372">372</span> |
| <span id="373">373</span> |
| <span id="374">374</span> |
| <span id="375">375</span> |
| <span id="376">376</span> |
| </pre><pre class="rust"><code><span class="kw">use </span>std::cmp; |
| |
| <span class="kw">use </span>itertools::Itertools; |
| |
| <span class="kw">use </span><span class="kw">super</span>::merge_policy::{MergeCandidate, MergePolicy}; |
| <span class="kw">use </span><span class="kw">crate</span>::core::SegmentMeta; |
| |
| <span class="kw">const </span>DEFAULT_LEVEL_LOG_SIZE: f64 = <span class="number">0.75</span>; |
| <span class="kw">const </span>DEFAULT_MIN_LAYER_SIZE: u32 = <span class="number">10_000</span>; |
| <span class="kw">const </span>DEFAULT_MIN_NUM_SEGMENTS_IN_MERGE: usize = <span class="number">8</span>; |
| <span class="kw">const </span>DEFAULT_MAX_DOCS_BEFORE_MERGE: usize = <span class="number">10_000_000</span>; |
| <span class="comment">// The default value of 1 means that deletes are not taken in account when |
| // identifying merge candidates. This is not a very sensible default: it was |
| // set like that for backward compatibility and might change in the near future. |
| </span><span class="kw">const </span>DEFAULT_DEL_DOCS_RATIO_BEFORE_MERGE: f32 = <span class="number">1.0f32</span>; |
| |
| <span class="doccomment">/// `LogMergePolicy` tries to merge segments that have a similar number of |
| /// documents. |
| </span><span class="attribute">#[derive(Debug, Clone)] |
| </span><span class="kw">pub struct </span>LogMergePolicy { |
| min_num_segments: usize, |
| max_docs_before_merge: usize, |
| min_layer_size: u32, |
| level_log_size: f64, |
| del_docs_ratio_before_merge: f32, |
| } |
| |
| <span class="kw">impl </span>LogMergePolicy { |
| <span class="kw">fn </span>clip_min_size(<span class="kw-2">&</span><span class="self">self</span>, size: u32) -> u32 { |
| cmp::max(<span class="self">self</span>.min_layer_size, size) |
| } |
| |
| <span class="doccomment">/// Set the minimum number of segments that may be merged together. |
| </span><span class="kw">pub fn </span>set_min_num_segments(<span class="kw-2">&mut </span><span class="self">self</span>, min_num_segments: usize) { |
| <span class="self">self</span>.min_num_segments = min_num_segments; |
| } |
| |
| <span class="doccomment">/// Set the maximum number docs in a segment for it to be considered for |
| /// merging. A segment can still reach more than max_docs, by merging many |
| /// smaller ones. |
| </span><span class="kw">pub fn </span>set_max_docs_before_merge(<span class="kw-2">&mut </span><span class="self">self</span>, max_docs_merge_size: usize) { |
| <span class="self">self</span>.max_docs_before_merge = max_docs_merge_size; |
| } |
| |
| <span class="doccomment">/// Set the minimum segment size under which all segment belong |
| /// to the same level. |
| </span><span class="kw">pub fn </span>set_min_layer_size(<span class="kw-2">&mut </span><span class="self">self</span>, min_layer_size: u32) { |
| <span class="self">self</span>.min_layer_size = min_layer_size; |
| } |
| |
| <span class="doccomment">/// Set the ratio between two consecutive levels. |
| /// |
| /// Segments are grouped in levels according to their sizes. |
| /// These levels are defined as intervals of exponentially growing sizes. |
| /// level_log_size define the factor by which one should multiply the limit |
| /// to reach a level, in order to get the limit to reach the following |
| /// level. |
| </span><span class="kw">pub fn </span>set_level_log_size(<span class="kw-2">&mut </span><span class="self">self</span>, level_log_size: f64) { |
| <span class="self">self</span>.level_log_size = level_log_size; |
| } |
| |
| <span class="doccomment">/// Set the ratio of deleted documents in a segment to tolerate. |
| /// |
| /// If it is exceeded by any segment at a log level, a merge |
| /// will be triggered for that level. |
| /// |
| /// If there is a single segment at a level, we effectively end up expunging |
| /// deleted documents from it. |
| /// |
| /// # Panics |
| /// |
| /// Panics if del_docs_ratio_before_merge is not within (0..1]. |
| </span><span class="kw">pub fn </span>set_del_docs_ratio_before_merge(<span class="kw-2">&mut </span><span class="self">self</span>, del_docs_ratio_before_merge: f32) { |
| <span class="macro">assert!</span>(del_docs_ratio_before_merge <= <span class="number">1.0f32</span>); |
| <span class="macro">assert!</span>(del_docs_ratio_before_merge > <span class="number">0f32</span>); |
| <span class="self">self</span>.del_docs_ratio_before_merge = del_docs_ratio_before_merge; |
| } |
| |
| <span class="kw">fn </span>has_segment_above_deletes_threshold(<span class="kw-2">&</span><span class="self">self</span>, level: <span class="kw-2">&</span>[<span class="kw-2">&</span>SegmentMeta]) -> bool { |
| level |
| .iter() |
| .any(|segment| deletes_ratio(segment) > <span class="self">self</span>.del_docs_ratio_before_merge) |
| } |
| } |
| |
| <span class="kw">fn </span>deletes_ratio(segment: <span class="kw-2">&</span>SegmentMeta) -> f32 { |
| <span class="kw">if </span>segment.max_doc() == <span class="number">0 </span>{ |
| <span class="kw">return </span><span class="number">0f32</span>; |
| } |
| segment.num_deleted_docs() <span class="kw">as </span>f32 / segment.max_doc() <span class="kw">as </span>f32 |
| } |
| |
| <span class="kw">impl </span>MergePolicy <span class="kw">for </span>LogMergePolicy { |
| <span class="kw">fn </span>compute_merge_candidates(<span class="kw-2">&</span><span class="self">self</span>, segments: <span class="kw-2">&</span>[SegmentMeta]) -> Vec<MergeCandidate> { |
| <span class="kw">let </span>size_sorted_segments = segments |
| .iter() |
| .filter(|seg| seg.num_docs() <= (<span class="self">self</span>.max_docs_before_merge <span class="kw">as </span>u32)) |
| .sorted_by_key(|seg| std::cmp::Reverse(seg.max_doc())) |
| .collect::<Vec<<span class="kw-2">&</span>SegmentMeta>>(); |
| |
| <span class="kw">if </span>size_sorted_segments.is_empty() { |
| <span class="kw">return </span><span class="macro">vec!</span>[]; |
| } |
| |
| <span class="kw">let </span><span class="kw-2">mut </span>current_max_log_size = f64::MAX; |
| <span class="kw">let </span><span class="kw-2">mut </span>levels = <span class="macro">vec!</span>[]; |
| <span class="kw">for </span>(<span class="kw">_</span>, merge_group) <span class="kw">in </span><span class="kw-2">&</span>size_sorted_segments.into_iter().group_by(|segment| { |
| <span class="kw">let </span>segment_log_size = f64::from(<span class="self">self</span>.clip_min_size(segment.num_docs())).log2(); |
| <span class="kw">if </span>segment_log_size < (current_max_log_size - <span class="self">self</span>.level_log_size) { |
| <span class="comment">// update current_max_log_size to create a new group |
| </span>current_max_log_size = segment_log_size; |
| } |
| <span class="comment">// return current_max_log_size to be grouped to the current group |
| </span>current_max_log_size |
| }) { |
| levels.push(merge_group.collect::<Vec<<span class="kw-2">&</span>SegmentMeta>>()); |
| } |
| |
| levels |
| .iter() |
| .filter(|level| { |
| level.len() >= <span class="self">self</span>.min_num_segments |
| || <span class="self">self</span>.has_segment_above_deletes_threshold(level) |
| }) |
| .map(|segments| MergeCandidate(segments.iter().map(|<span class="kw-2">&</span>seg| seg.id()).collect())) |
| .collect() |
| } |
| } |
| |
| <span class="kw">impl </span>Default <span class="kw">for </span>LogMergePolicy { |
| <span class="kw">fn </span>default() -> LogMergePolicy { |
| LogMergePolicy { |
| min_num_segments: DEFAULT_MIN_NUM_SEGMENTS_IN_MERGE, |
| max_docs_before_merge: DEFAULT_MAX_DOCS_BEFORE_MERGE, |
| min_layer_size: DEFAULT_MIN_LAYER_SIZE, |
| level_log_size: DEFAULT_LEVEL_LOG_SIZE, |
| del_docs_ratio_before_merge: DEFAULT_DEL_DOCS_RATIO_BEFORE_MERGE, |
| } |
| } |
| } |
| |
| <span class="attribute">#[cfg(test)] |
| </span><span class="kw">mod </span>tests { |
| <span class="kw">use </span>once_cell::sync::Lazy; |
| |
| <span class="kw">use super</span>::<span class="kw-2">*</span>; |
| <span class="kw">use </span><span class="kw">crate</span>::core::{SegmentId, SegmentMeta, SegmentMetaInventory}; |
| <span class="kw">use </span><span class="kw">crate</span>::indexer::merge_policy::MergePolicy; |
| <span class="kw">use </span><span class="kw">crate</span>::schema; |
| <span class="kw">use </span><span class="kw">crate</span>::schema::INDEXED; |
| |
| <span class="kw">static </span>INVENTORY: Lazy<SegmentMetaInventory> = Lazy::new(SegmentMetaInventory::default); |
| |
| <span class="kw">use </span><span class="kw">crate</span>::Index; |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>create_index_test_max_merge_issue_1035() -> <span class="kw">crate</span>::Result<()> { |
| <span class="kw">let </span><span class="kw-2">mut </span>schema_builder = schema::Schema::builder(); |
| <span class="kw">let </span>int_field = schema_builder.add_u64_field(<span class="string">"intval"</span>, INDEXED); |
| <span class="kw">let </span>schema = schema_builder.build(); |
| |
| <span class="kw">let </span>index = Index::create_in_ram(schema); |
| |
| { |
| <span class="kw">let </span><span class="kw-2">mut </span>log_merge_policy = LogMergePolicy::default(); |
| log_merge_policy.set_min_num_segments(<span class="number">1</span>); |
| log_merge_policy.set_max_docs_before_merge(<span class="number">1</span>); |
| log_merge_policy.set_min_layer_size(<span class="number">0</span>); |
| |
| <span class="kw">let </span><span class="kw-2">mut </span>index_writer = index.writer_for_tests()<span class="question-mark">?</span>; |
| index_writer.set_merge_policy(Box::new(log_merge_policy)); |
| |
| <span class="comment">// after every commit the merge checker is started, it will merge only segments with 1 |
| // element in it because of the max_merge_size. |
| </span>index_writer.add_document(<span class="macro">doc!</span>(int_field=><span class="number">1_u64</span>))<span class="question-mark">?</span>; |
| index_writer.commit()<span class="question-mark">?</span>; |
| |
| index_writer.add_document(<span class="macro">doc!</span>(int_field=><span class="number">2_u64</span>))<span class="question-mark">?</span>; |
| index_writer.commit()<span class="question-mark">?</span>; |
| |
| index_writer.add_document(<span class="macro">doc!</span>(int_field=><span class="number">3_u64</span>))<span class="question-mark">?</span>; |
| index_writer.commit()<span class="question-mark">?</span>; |
| |
| index_writer.add_document(<span class="macro">doc!</span>(int_field=><span class="number">4_u64</span>))<span class="question-mark">?</span>; |
| index_writer.commit()<span class="question-mark">?</span>; |
| |
| index_writer.add_document(<span class="macro">doc!</span>(int_field=><span class="number">5_u64</span>))<span class="question-mark">?</span>; |
| index_writer.commit()<span class="question-mark">?</span>; |
| |
| index_writer.add_document(<span class="macro">doc!</span>(int_field=><span class="number">6_u64</span>))<span class="question-mark">?</span>; |
| index_writer.commit()<span class="question-mark">?</span>; |
| |
| index_writer.add_document(<span class="macro">doc!</span>(int_field=><span class="number">7_u64</span>))<span class="question-mark">?</span>; |
| index_writer.commit()<span class="question-mark">?</span>; |
| |
| index_writer.add_document(<span class="macro">doc!</span>(int_field=><span class="number">8_u64</span>))<span class="question-mark">?</span>; |
| index_writer.commit()<span class="question-mark">?</span>; |
| } |
| |
| <span class="kw">let </span>_segment_ids = index |
| .searchable_segment_ids() |
| .expect(<span class="string">"Searchable segments failed."</span>); |
| |
| <span class="kw">let </span>reader = index.reader().unwrap(); |
| <span class="kw">let </span>searcher = reader.searcher(); |
| <span class="kw">let </span>segment_readers = searcher.segment_readers(); |
| <span class="kw">for </span>segment <span class="kw">in </span>segment_readers { |
| <span class="kw">if </span>segment.num_docs() > <span class="number">2 </span>{ |
| <span class="macro">panic!</span>(<span class="string">"segment can't have more than two segments"</span>); |
| } <span class="comment">// don't know how to wait for the merge, then it could be a simple eq |
| </span>} |
| <span class="prelude-val">Ok</span>(()) |
| } |
| |
| <span class="kw">fn </span>test_merge_policy() -> LogMergePolicy { |
| <span class="kw">let </span><span class="kw-2">mut </span>log_merge_policy = LogMergePolicy::default(); |
| log_merge_policy.set_min_num_segments(<span class="number">3</span>); |
| log_merge_policy.set_max_docs_before_merge(<span class="number">100_000</span>); |
| log_merge_policy.set_min_layer_size(<span class="number">2</span>); |
| log_merge_policy |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_log_merge_policy_empty() { |
| <span class="kw">let </span>y = Vec::new(); |
| <span class="kw">let </span>result_list = test_merge_policy().compute_merge_candidates(<span class="kw-2">&</span>y); |
| <span class="macro">assert!</span>(result_list.is_empty()); |
| } |
| |
| <span class="kw">fn </span>create_random_segment_meta(num_docs: u32) -> SegmentMeta { |
| INVENTORY.new_segment_meta(SegmentId::generate_random(), num_docs) |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_log_merge_policy_pair() { |
| <span class="kw">let </span>test_input = <span class="macro">vec!</span>[ |
| create_random_segment_meta(<span class="number">10</span>), |
| create_random_segment_meta(<span class="number">10</span>), |
| create_random_segment_meta(<span class="number">10</span>), |
| ]; |
| <span class="kw">let </span>result_list = test_merge_policy().compute_merge_candidates(<span class="kw-2">&</span>test_input); |
| <span class="macro">assert_eq!</span>(result_list.len(), <span class="number">1</span>); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_log_merge_policy_levels() { |
| <span class="comment">// multiple levels all get merged correctly |
| // 2 MergeCandidates expected: |
| // * one with the 6 * 10-docs segments |
| // * one with the 3 * 1000-docs segments |
| // no MergeCandidate expected for the 2 * 10_000-docs segments as min_merge_size=3 |
| </span><span class="kw">let </span>test_input = <span class="macro">vec!</span>[ |
| create_random_segment_meta(<span class="number">10</span>), |
| create_random_segment_meta(<span class="number">10</span>), |
| create_random_segment_meta(<span class="number">10</span>), |
| create_random_segment_meta(<span class="number">1_000</span>), |
| create_random_segment_meta(<span class="number">1_000</span>), |
| create_random_segment_meta(<span class="number">1_000</span>), |
| create_random_segment_meta(<span class="number">10_000</span>), |
| create_random_segment_meta(<span class="number">10_000</span>), |
| create_random_segment_meta(<span class="number">10</span>), |
| create_random_segment_meta(<span class="number">10</span>), |
| create_random_segment_meta(<span class="number">10</span>), |
| ]; |
| <span class="kw">let </span>result_list = test_merge_policy().compute_merge_candidates(<span class="kw-2">&</span>test_input); |
| <span class="macro">assert_eq!</span>(result_list.len(), <span class="number">2</span>); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_log_merge_policy_within_levels() { |
| <span class="comment">// multiple levels all get merged correctly |
| </span><span class="kw">let </span>test_input = <span class="macro">vec!</span>[ |
| create_random_segment_meta(<span class="number">10</span>), <span class="comment">// log2(10) = ~3.32 (> 3.58 - 0.75) |
| </span>create_random_segment_meta(<span class="number">11</span>), <span class="comment">// log2(11) = ~3.46 |
| </span>create_random_segment_meta(<span class="number">12</span>), <span class="comment">// log2(12) = ~3.58 |
| </span>create_random_segment_meta(<span class="number">800</span>), <span class="comment">// log2(800) = ~9.64 (> 9.97 - 0.75) |
| </span>create_random_segment_meta(<span class="number">1000</span>), <span class="comment">// log2(1000) = ~9.97 |
| </span>create_random_segment_meta(<span class="number">1000</span>), |
| ]; <span class="comment">// log2(1000) = ~9.97 |
| </span><span class="kw">let </span>result_list = test_merge_policy().compute_merge_candidates(<span class="kw-2">&</span>test_input); |
| <span class="macro">assert_eq!</span>(result_list.len(), <span class="number">2</span>); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_log_merge_policy_small_segments() { |
| <span class="comment">// segments under min_layer_size are merged together |
| </span><span class="kw">let </span>test_input = <span class="macro">vec!</span>[ |
| create_random_segment_meta(<span class="number">1</span>), |
| create_random_segment_meta(<span class="number">1</span>), |
| create_random_segment_meta(<span class="number">1</span>), |
| create_random_segment_meta(<span class="number">2</span>), |
| create_random_segment_meta(<span class="number">2</span>), |
| create_random_segment_meta(<span class="number">2</span>), |
| ]; |
| <span class="kw">let </span>result_list = test_merge_policy().compute_merge_candidates(<span class="kw-2">&</span>test_input); |
| <span class="macro">assert_eq!</span>(result_list.len(), <span class="number">1</span>); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_log_merge_policy_all_segments_too_large_to_merge() { |
| <span class="kw">let </span>eight_large_segments: Vec<SegmentMeta> = |
| std::iter::repeat_with(|| create_random_segment_meta(<span class="number">100_001</span>)) |
| .take(<span class="number">8</span>) |
| .collect(); |
| <span class="macro">assert!</span>(test_merge_policy() |
| .compute_merge_candidates(<span class="kw-2">&</span>eight_large_segments) |
| .is_empty()); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_large_merge_segments() { |
| <span class="kw">let </span>test_input = <span class="macro">vec!</span>[ |
| create_random_segment_meta(<span class="number">1_000_000</span>), |
| create_random_segment_meta(<span class="number">100_001</span>), |
| create_random_segment_meta(<span class="number">100_000</span>), |
| create_random_segment_meta(<span class="number">1_000_001</span>), |
| create_random_segment_meta(<span class="number">100_000</span>), |
| create_random_segment_meta(<span class="number">100_000</span>), |
| create_random_segment_meta(<span class="number">1_500_000</span>), |
| ]; |
| <span class="kw">let </span>result_list = test_merge_policy().compute_merge_candidates(<span class="kw-2">&</span>test_input); |
| <span class="comment">// Do not include large segments |
| </span><span class="macro">assert_eq!</span>(result_list.len(), <span class="number">1</span>); |
| <span class="macro">assert_eq!</span>(result_list[<span class="number">0</span>].<span class="number">0</span>.len(), <span class="number">3</span>); |
| |
| <span class="comment">// Making sure merge policy points to the correct index of the original input |
| </span><span class="macro">assert_eq!</span>(result_list[<span class="number">0</span>].<span class="number">0</span>[<span class="number">0</span>], test_input[<span class="number">2</span>].id()); |
| <span class="macro">assert_eq!</span>(result_list[<span class="number">0</span>].<span class="number">0</span>[<span class="number">1</span>], test_input[<span class="number">4</span>].id()); |
| <span class="macro">assert_eq!</span>(result_list[<span class="number">0</span>].<span class="number">0</span>[<span class="number">2</span>], test_input[<span class="number">5</span>].id()); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_merge_single_segment_with_deletes_below_threshold() { |
| <span class="kw">let </span><span class="kw-2">mut </span>test_merge_policy = test_merge_policy(); |
| test_merge_policy.set_del_docs_ratio_before_merge(<span class="number">0.25f32</span>); |
| <span class="kw">let </span>test_input = <span class="macro">vec!</span>[create_random_segment_meta(<span class="number">40_000</span>).with_delete_meta(<span class="number">10_000</span>, <span class="number">1</span>)]; |
| <span class="kw">let </span>merge_candidates = test_merge_policy.compute_merge_candidates(<span class="kw-2">&</span>test_input); |
| <span class="macro">assert!</span>(merge_candidates.is_empty()); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_merge_single_segment_with_deletes_above_threshold() { |
| <span class="kw">let </span><span class="kw-2">mut </span>test_merge_policy = test_merge_policy(); |
| test_merge_policy.set_del_docs_ratio_before_merge(<span class="number">0.25f32</span>); |
| <span class="kw">let </span>test_input = <span class="macro">vec!</span>[create_random_segment_meta(<span class="number">40_000</span>).with_delete_meta(<span class="number">10_001</span>, <span class="number">1</span>)]; |
| <span class="kw">let </span>merge_candidates = test_merge_policy.compute_merge_candidates(<span class="kw-2">&</span>test_input); |
| <span class="macro">assert_eq!</span>(merge_candidates.len(), <span class="number">1</span>); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_merge_segments_with_deletes_above_threshold_all_in_level() { |
| <span class="kw">let </span><span class="kw-2">mut </span>test_merge_policy = test_merge_policy(); |
| test_merge_policy.set_del_docs_ratio_before_merge(<span class="number">0.25f32</span>); |
| <span class="kw">let </span>test_input = <span class="macro">vec!</span>[ |
| create_random_segment_meta(<span class="number">40_000</span>).with_delete_meta(<span class="number">10_001</span>, <span class="number">1</span>), |
| create_random_segment_meta(<span class="number">40_000</span>), |
| ]; |
| <span class="kw">let </span>merge_candidates = test_merge_policy.compute_merge_candidates(<span class="kw-2">&</span>test_input); |
| <span class="macro">assert_eq!</span>(merge_candidates.len(), <span class="number">1</span>); |
| <span class="macro">assert_eq!</span>(merge_candidates[<span class="number">0</span>].<span class="number">0</span>.len(), <span class="number">2</span>); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_merge_segments_with_deletes_above_threshold_different_level_not_involved() { |
| <span class="kw">let </span><span class="kw-2">mut </span>test_merge_policy = test_merge_policy(); |
| test_merge_policy.set_del_docs_ratio_before_merge(<span class="number">0.25f32</span>); |
| <span class="kw">let </span>test_input = <span class="macro">vec!</span>[ |
| create_random_segment_meta(<span class="number">100</span>), |
| create_random_segment_meta(<span class="number">40_000</span>).with_delete_meta(<span class="number">10_001</span>, <span class="number">1</span>), |
| ]; |
| <span class="kw">let </span>merge_candidates = test_merge_policy.compute_merge_candidates(<span class="kw-2">&</span>test_input); |
| <span class="macro">assert_eq!</span>(merge_candidates.len(), <span class="number">1</span>); |
| <span class="macro">assert_eq!</span>(merge_candidates[<span class="number">0</span>].<span class="number">0</span>.len(), <span class="number">1</span>); |
| <span class="macro">assert_eq!</span>(merge_candidates[<span class="number">0</span>].<span class="number">0</span>[<span class="number">0</span>], test_input[<span class="number">1</span>].id()); |
| } |
| } |
| </code></pre></div> |
| </section></div></main><div id="rustdoc-vars" data-root-path="../../../" data-current-crate="tantivy" data-themes="ayu,dark,light" data-resource-suffix="" data-rustdoc-version="1.66.0-nightly (5c8bff74b 2022-10-21)" ></div></body></html> |
