mirror of
https://github.com/alanorth/cgspace-notes.git
synced 2024-11-18 20:57:03 +01:00
289 lines
14 KiB
HTML
289 lines
14 KiB
HTML
<!DOCTYPE html>
|
|
<html lang="en" >
|
|
|
|
<head>
|
|
<meta charset="utf-8">
|
|
<meta name="viewport" content="width=device-width, initial-scale=1, shrink-to-fit=no">
|
|
|
|
|
|
<meta property="og:title" content="December, 2023" />
|
|
<meta property="og:description" content="2023-12-01 There is still high load on CGSpace and I don’t know why I don’t see a high number of sessions compared to previous days in the last few weeks $ for file in dspace.log.2023-11-[23]*; do echo "$file"; grep -a -oE 'session_id=[A-Z0-9]{32}' "$file" | sort | uniq | wc -l; done dspace.log.2023-11-20 22865 dspace.log.2023-11-21 20296 dspace.log.2023-11-22 19688 dspace.log.2023-11-23 17906 dspace.log.2023-11-24 18453 dspace.log.2023-11-25 17513 dspace.log.2023-11-26 19037 dspace.log.2023-11-27 21103 dspace.log.2023-11-28 23023 dspace.log.2023-11-29 23545 dspace." />
|
|
<meta property="og:type" content="article" />
|
|
<meta property="og:url" content="https://alanorth.github.io/cgspace-notes/2023-12/" />
|
|
<meta property="article:published_time" content="2023-12-01T08:48:36+03:00" />
|
|
<meta property="article:modified_time" content="2023-12-02T10:38:09+03:00" />
|
|
|
|
|
|
|
|
<meta name="twitter:card" content="summary"/>
|
|
<meta name="twitter:title" content="December, 2023"/>
|
|
<meta name="twitter:description" content="2023-12-01 There is still high load on CGSpace and I don’t know why I don’t see a high number of sessions compared to previous days in the last few weeks $ for file in dspace.log.2023-11-[23]*; do echo "$file"; grep -a -oE 'session_id=[A-Z0-9]{32}' "$file" | sort | uniq | wc -l; done dspace.log.2023-11-20 22865 dspace.log.2023-11-21 20296 dspace.log.2023-11-22 19688 dspace.log.2023-11-23 17906 dspace.log.2023-11-24 18453 dspace.log.2023-11-25 17513 dspace.log.2023-11-26 19037 dspace.log.2023-11-27 21103 dspace.log.2023-11-28 23023 dspace.log.2023-11-29 23545 dspace."/>
|
|
<meta name="generator" content="Hugo 0.121.0">
|
|
|
|
|
|
|
|
<script type="application/ld+json">
|
|
{
|
|
"@context": "http://schema.org",
|
|
"@type": "BlogPosting",
|
|
"headline": "December, 2023",
|
|
"url": "https://alanorth.github.io/cgspace-notes/2023-12/",
|
|
"wordCount": "529",
|
|
"datePublished": "2023-12-01T08:48:36+03:00",
|
|
"dateModified": "2023-12-02T10:38:09+03:00",
|
|
"author": {
|
|
"@type": "Person",
|
|
"name": "Alan Orth"
|
|
},
|
|
"keywords": "Notes"
|
|
}
|
|
</script>
|
|
|
|
|
|
|
|
<link rel="canonical" href="https://alanorth.github.io/cgspace-notes/2023-12/">
|
|
|
|
<title>December, 2023 | CGSpace Notes</title>
|
|
|
|
|
|
<!-- combined, minified CSS -->
|
|
|
|
<link href="https://alanorth.github.io/cgspace-notes/css/style.c6ba80bc50669557645abe05f86b73cc5af84408ed20f1551a267bc19ece8228.css" rel="stylesheet" integrity="sha256-xrqAvFBmlVdkWr4F+GtzzFr4RAjtIPFVGiZ7wZ7Ogig=" crossorigin="anonymous">
|
|
|
|
|
|
<!-- minified Font Awesome for SVG icons -->
|
|
|
|
<script defer src="https://alanorth.github.io/cgspace-notes/js/fontawesome.min.f5072c55a0721857184db93a50561d7dc13975b4de2e19db7f81eb5f3fa57270.js" integrity="sha256-9QcsVaByGFcYTbk6UFYdfcE5dbTeLhnbf4HrXz+lcnA=" crossorigin="anonymous"></script>
|
|
|
|
<!-- RSS 2.0 feed -->
|
|
|
|
|
|
|
|
|
|
</head>
|
|
|
|
<body>
|
|
|
|
|
|
<div class="blog-masthead">
|
|
<div class="container">
|
|
<nav class="nav blog-nav">
|
|
<a class="nav-link " href="https://alanorth.github.io/cgspace-notes/">Home</a>
|
|
</nav>
|
|
</div>
|
|
</div>
|
|
|
|
|
|
|
|
|
|
<header class="blog-header">
|
|
<div class="container">
|
|
<h1 class="blog-title" dir="auto"><a href="https://alanorth.github.io/cgspace-notes/" rel="home">CGSpace Notes</a></h1>
|
|
<p class="lead blog-description" dir="auto">Documenting day-to-day work on the <a href="https://cgspace.cgiar.org">CGSpace</a> repository.</p>
|
|
</div>
|
|
</header>
|
|
|
|
|
|
|
|
|
|
<div class="container">
|
|
<div class="row">
|
|
<div class="col-sm-8 blog-main">
|
|
|
|
|
|
|
|
|
|
<article class="blog-post">
|
|
<header>
|
|
<h2 class="blog-post-title" dir="auto"><a href="https://alanorth.github.io/cgspace-notes/2023-12/">December, 2023</a></h2>
|
|
<p class="blog-post-meta">
|
|
<time datetime="2023-12-01T08:48:36+03:00">Fri Dec 01, 2023</time>
|
|
in
|
|
<span class="fas fa-folder" aria-hidden="true"></span> <a href="/categories/notes/" rel="category tag">Notes</a>
|
|
|
|
|
|
</p>
|
|
</header>
|
|
<h2 id="2023-12-01">2023-12-01</h2>
|
|
<ul>
|
|
<li>There is still high load on CGSpace and I don’t know why
|
|
<ul>
|
|
<li>I don’t see a high number of sessions compared to previous days in the last few weeks</li>
|
|
</ul>
|
|
</li>
|
|
</ul>
|
|
<!-- raw HTML omitted -->
|
|
<div class="highlight"><pre tabindex="0" style="color:#f8f8f2;background-color:#272822;-moz-tab-size:4;-o-tab-size:4;tab-size:4;"><code class="language-console" data-lang="console"><span style="display:flex;"><span>$ <span style="color:#66d9ef">for</span> file in dspace.log.2023-11-<span style="color:#f92672">[</span>23<span style="color:#f92672">]</span>*; <span style="color:#66d9ef">do</span> echo <span style="color:#e6db74">"</span>$file<span style="color:#e6db74">"</span>; grep -a -oE <span style="color:#e6db74">'session_id=[A-Z0-9]{32}'</span> <span style="color:#e6db74">"</span>$file<span style="color:#e6db74">"</span> | sort | uniq | wc -l; <span style="color:#66d9ef">done</span>
|
|
</span></span><span style="display:flex;"><span>dspace.log.2023-11-20
|
|
</span></span><span style="display:flex;"><span>22865
|
|
</span></span><span style="display:flex;"><span>dspace.log.2023-11-21
|
|
</span></span><span style="display:flex;"><span>20296
|
|
</span></span><span style="display:flex;"><span>dspace.log.2023-11-22
|
|
</span></span><span style="display:flex;"><span>19688
|
|
</span></span><span style="display:flex;"><span>dspace.log.2023-11-23
|
|
</span></span><span style="display:flex;"><span>17906
|
|
</span></span><span style="display:flex;"><span>dspace.log.2023-11-24
|
|
</span></span><span style="display:flex;"><span>18453
|
|
</span></span><span style="display:flex;"><span>dspace.log.2023-11-25
|
|
</span></span><span style="display:flex;"><span>17513
|
|
</span></span><span style="display:flex;"><span>dspace.log.2023-11-26
|
|
</span></span><span style="display:flex;"><span>19037
|
|
</span></span><span style="display:flex;"><span>dspace.log.2023-11-27
|
|
</span></span><span style="display:flex;"><span>21103
|
|
</span></span><span style="display:flex;"><span>dspace.log.2023-11-28
|
|
</span></span><span style="display:flex;"><span>23023
|
|
</span></span><span style="display:flex;"><span>dspace.log.2023-11-29
|
|
</span></span><span style="display:flex;"><span>23545
|
|
</span></span><span style="display:flex;"><span>dspace.log.2023-11-30
|
|
</span></span><span style="display:flex;"><span>21298
|
|
</span></span></code></pre></div><ul>
|
|
<li>Even the number of unique IPs is not very high compared to the last week or so:</li>
|
|
</ul>
|
|
<div class="highlight"><pre tabindex="0" style="color:#f8f8f2;background-color:#272822;-moz-tab-size:4;-o-tab-size:4;tab-size:4;"><code class="language-console" data-lang="console"><span style="display:flex;"><span># awk <span style="color:#e6db74">'{print $1}'</span> /var/log/nginx/<span style="color:#f92672">{</span>access,library-access,oai,rest<span style="color:#f92672">}</span>.log.1 | sort | uniq | wc -l
|
|
</span></span><span style="display:flex;"><span>17023
|
|
</span></span><span style="display:flex;"><span># awk <span style="color:#e6db74">'{print $1}'</span> /var/log/nginx/<span style="color:#f92672">{</span>access,library-access,oai,rest<span style="color:#f92672">}</span>.log.2.gz | sort | uniq | wc -l
|
|
</span></span><span style="display:flex;"><span>17294
|
|
</span></span><span style="display:flex;"><span># awk <span style="color:#e6db74">'{print $1}'</span> /var/log/nginx/<span style="color:#f92672">{</span>access,library-access,oai,rest<span style="color:#f92672">}</span>.log.3.gz | sort | uniq | wc -l
|
|
</span></span><span style="display:flex;"><span>22057
|
|
</span></span><span style="display:flex;"><span># awk <span style="color:#e6db74">'{print $1}'</span> /var/log/nginx/<span style="color:#f92672">{</span>access,library-access,oai,rest<span style="color:#f92672">}</span>.log.4.gz | sort | uniq | wc -l
|
|
</span></span><span style="display:flex;"><span>32956
|
|
</span></span><span style="display:flex;"><span># awk <span style="color:#e6db74">'{print $1}'</span> /var/log/nginx/<span style="color:#f92672">{</span>access,library-access,oai,rest<span style="color:#f92672">}</span>.log.5.gz | sort | uniq | wc -l
|
|
</span></span><span style="display:flex;"><span>11415
|
|
</span></span><span style="display:flex;"><span># awk <span style="color:#e6db74">'{print $1}'</span> /var/log/nginx/<span style="color:#f92672">{</span>access,library-access,oai,rest<span style="color:#f92672">}</span>.log.6.gz | sort | uniq | wc -l
|
|
</span></span><span style="display:flex;"><span>15444
|
|
</span></span><span style="display:flex;"><span># awk <span style="color:#e6db74">'{print $1}'</span> /var/log/nginx/<span style="color:#f92672">{</span>access,library-access,oai,rest<span style="color:#f92672">}</span>.log.7.gz | sort | uniq | wc -l
|
|
</span></span><span style="display:flex;"><span>12648
|
|
</span></span></code></pre></div><ul>
|
|
<li>It doesn’t make any sense so I think I’m going to restart the server…
|
|
<ul>
|
|
<li>After restarting the server the load went down to normal levels… who knows…</li>
|
|
</ul>
|
|
</li>
|
|
<li>I started trying to see how I’m going to generate the fake statistics for the Alliance bitstream that was replaced
|
|
<ul>
|
|
<li>I exported all the statistics for the owningItem now:</li>
|
|
</ul>
|
|
</li>
|
|
</ul>
|
|
<div class="highlight"><pre tabindex="0" style="color:#f8f8f2;background-color:#272822;-moz-tab-size:4;-o-tab-size:4;tab-size:4;"><code class="language-console" data-lang="console"><span style="display:flex;"><span>$ chrt -b <span style="color:#ae81ff">0</span> ./run.sh -s http://localhost:8081/solr/statistics -a export -o /tmp/stats-export.json -f <span style="color:#e6db74">'owningItem:b5862bfa-9799-4167-b1cf-76f0f4ea1e18'</span> -k uid
|
|
</span></span></code></pre></div><ul>
|
|
<li>Importing them into DSpace Test didn’t show the statistics in the Atmire module, but I see them in Solr…</li>
|
|
</ul>
|
|
<h2 id="2023-12-02">2023-12-02</h2>
|
|
<ul>
|
|
<li>Export CGSpace to check for missing Initiative collection mappings</li>
|
|
<li>Start a harvest on AReS</li>
|
|
</ul>
|
|
<h2 id="2023-12-04">2023-12-04</h2>
|
|
<ul>
|
|
<li>Send a message to Altmetric support because the item IWMI highlighted last month still doesn’t show the attention score for the Handle after I tweeted it several times weeks ago</li>
|
|
<li>Spent some time writing a Python script to fix the literal MaxMind City JSON objects in our Solr statistics
|
|
<ul>
|
|
<li>There are about 1.6 million of these, so I exported them using solr-import-export-json with the query <code>city:com*</code> but ended up finding many that have missing bundles, container bitstreams, etc:</li>
|
|
</ul>
|
|
</li>
|
|
</ul>
|
|
<pre tabindex="0"><code>city:com* AND -bundleName:[* TO *] AND -containerBitstream:[* TO *] AND -file_id:[* TO *] AND -owningItem:[* TO *] AND -version_id:[* TO *]
|
|
</code></pre><ul>
|
|
<li>(Note the negation to find fields that are missing)</li>
|
|
<li>I don’t know what I want to do with these yet</li>
|
|
</ul>
|
|
<h2 id="2023-12-05">2023-12-05</h2>
|
|
<ul>
|
|
<li>I finished the <code>fix_maxmind_stats.py</code> script and fixed 1.6 million records and imported them on CGSpace after testing on DSpace 7 Test</li>
|
|
<li>Altmetric said there was a glitch regarding the Handle and DOI linking and they successfully re-scraped the item page and linked them
|
|
<ul>
|
|
<li>They sent me a list of current production IPs and I notice that some of them are in our nginx bot network list:</li>
|
|
</ul>
|
|
</li>
|
|
</ul>
|
|
<div class="highlight"><pre tabindex="0" style="color:#f8f8f2;background-color:#272822;-moz-tab-size:4;-o-tab-size:4;tab-size:4;"><code class="language-console" data-lang="console"><span style="display:flex;"><span>$ <span style="color:#66d9ef">for</span> network in <span style="color:#66d9ef">$(</span>csvcut -c network /tmp/ips.csv | sed 1d | sort -u<span style="color:#66d9ef">)</span>; <span style="color:#66d9ef">do</span> grepcidr $network ~/src/git/rmg-ansible-public/roles/dspace/files/nginx/bot-networks.conf; <span style="color:#66d9ef">done</span>
|
|
</span></span><span style="display:flex;"><span>108.128.0.0/13 'bot';
|
|
</span></span><span style="display:flex;"><span>46.137.0.0/16 'bot';
|
|
</span></span><span style="display:flex;"><span>52.208.0.0/13 'bot';
|
|
</span></span><span style="display:flex;"><span>52.48.0.0/13 'bot';
|
|
</span></span><span style="display:flex;"><span>54.194.0.0/15 'bot';
|
|
</span></span><span style="display:flex;"><span>54.216.0.0/14 'bot';
|
|
</span></span><span style="display:flex;"><span>54.220.0.0/15 'bot';
|
|
</span></span><span style="display:flex;"><span>54.228.0.0/15 'bot';
|
|
</span></span><span style="display:flex;"><span>63.32.242.35/32 'bot';
|
|
</span></span><span style="display:flex;"><span>63.32.0.0/14 'bot';
|
|
</span></span><span style="display:flex;"><span>99.80.0.0/15 'bot'
|
|
</span></span></code></pre></div><ul>
|
|
<li>I will remove those for now so that Altmetric doesn’t have any unexpected issues harvesting</li>
|
|
</ul>
|
|
<!-- raw HTML omitted -->
|
|
|
|
|
|
|
|
|
|
|
|
|
|
</article>
|
|
|
|
|
|
|
|
</div> <!-- /.blog-main -->
|
|
|
|
<aside class="col-sm-3 ml-auto blog-sidebar">
|
|
|
|
|
|
|
|
<section class="sidebar-module">
|
|
<h4>Recent Posts</h4>
|
|
<ol class="list-unstyled">
|
|
|
|
|
|
<li><a href="/cgspace-notes/2023-12/">December, 2023</a></li>
|
|
|
|
<li><a href="/cgspace-notes/2023-11/">November, 2023</a></li>
|
|
|
|
<li><a href="/cgspace-notes/2023-10/">October, 2023</a></li>
|
|
|
|
<li><a href="/cgspace-notes/2023-09/">September, 2023</a></li>
|
|
|
|
<li><a href="/cgspace-notes/2023-08/">August, 2023</a></li>
|
|
|
|
</ol>
|
|
</section>
|
|
|
|
|
|
|
|
|
|
<section class="sidebar-module">
|
|
<h4>Links</h4>
|
|
<ol class="list-unstyled">
|
|
|
|
<li><a href="https://cgspace.cgiar.org">CGSpace</a></li>
|
|
|
|
<li><a href="https://dspacetest.cgiar.org">DSpace Test</a></li>
|
|
|
|
<li><a href="https://github.com/ilri/DSpace">CGSpace @ GitHub</a></li>
|
|
|
|
</ol>
|
|
</section>
|
|
|
|
</aside>
|
|
|
|
|
|
</div> <!-- /.row -->
|
|
</div> <!-- /.container -->
|
|
|
|
|
|
|
|
<footer class="blog-footer">
|
|
<p dir="auto">
|
|
|
|
Blog template created by <a href="https://twitter.com/mdo">@mdo</a>, ported to Hugo by <a href='https://twitter.com/mralanorth'>@mralanorth</a>.
|
|
|
|
</p>
|
|
<p>
|
|
<a href="#">Back to top</a>
|
|
</p>
|
|
</footer>
|
|
|
|
|
|
</body>
|
|
|
|
</html>
|