{"id":100438,"date":"2021-06-04T16:22:49","date_gmt":"2021-06-04T14:22:49","guid":{"rendered":"https:\/\/prohoster.info\/blog\/novosti-interneta\/vypusk-cache-bench-0-1-0-dlya-issledovaniya-effektivnosti-keshirovaniya-fajlov-pri-nehvatke-pamyati"},"modified":"2021-06-04T16:22:49","modified_gmt":"2021-06-04T14:22:49","slug":"vypusk-cache-bench-0-1-0-dlya-issledovaniya-effektivnosti-keshirovaniya-fajlov-pri-nehvatke-pamyati","status":"publish","type":"post","link":"https:\/\/prohoster.info\/nl\/blog\/news\/vypusk-cache-bench-0-1-0-dlya-issledovaniya-effektivnosti-keshirovaniya-fajlov-pri-nehvatke-pamyati","title":{"rendered":"Uitgave van cache-bench 0.1.0 voor het onderzoeken van de effici\u00ebntie van bestands caching bij geheugen tekort","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"
cache-bench \u2014 is a Python script that allows you to assess the impact of virtual memory settings (vm.swappiness, vm.watermark_scale_factor, Multigenerational LRU Framework, and others) on the performance of executing tasks that depend on caching file read operations under memory scarcity. The code is open under the CC0 license. <\/p>\n
The main method of use \u2014 reading files from a specified directory in random order and adding them to a list until a specified number of mebibytes has been read. Two operating modes are available: <\/p>\n
\n
The first \u2014 auxiliary \u2014 is used to create a directory of a specified size. In this directory, a certain number of mebibyte files with random names are created.\n
The second mode \u2014 main \u2014 is the mode for reading files from the specified directory in random order. During reading, the amount of memory used by the script increases, and the speed of reading the specified volume of files depends on the volume of cached file pages. <\/ul>\n
Een onderdeel van het project is ook het ondersteunende script drop-cache, dat wordt aanbevolen om v\u00f3\u00f3r het begin van de test uit te voeren. Tijdens de werking van het script in leermodus worden de totale werktijd, de gemiddelde leessnelheid en de naam van het laatst gelezen bestand weergegeven. Het script biedt ook de mogelijkheid om de resultaten naar een bestand met tijdstempels te loggen. \n Bron: opennet.ru<\/a> <\/p>","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"excerpt":{"rendered":"