Last active
December 3, 2018 02:51
-
-
Save mtrolle/96f55822122ecabd3cc46190a6dc18a5 to your computer and use it in GitHub Desktop.
High memory consumption, question asked on StackOverflow: https://stackoverflow.com/questions/53169751/ruby-memory-usage-gone-wild
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
require 'bundler/inline' | |
require 'json' | |
gemfile do | |
source 'https://rubygems.org' | |
gem 'rest-client' | |
gem 'nokogiri' | |
gem 'memory_profiler' | |
end | |
xml_base_url = 'http://noneed.dk/test.xml?date=' | |
auth_end_point = 'http://noneed.dk/session.php' | |
auth_payload = {"user" => "[email protected]", "password" => "secret"} | |
image_search_base_url = 'http://noneed.dk/images.php?id=' | |
image_base_url = 'http://noneed.dk/' | |
logger = Logger.new(STDOUT) | |
download_size = 0 | |
time_start = Time.now | |
requests = 0 | |
report = MemoryProfiler.report do | |
# Authenticates | |
response = RestClient::Request.execute({ | |
method: :post, | |
url: auth_end_point, | |
payload: auth_payload, | |
}) | |
cookie_jar = response.cookie_jar | |
logger.debug "Got a cookiejar - #{cookie_jar.cookies}" | |
download_size += response.body.bytesize | |
requests += 1 | |
# Run X days of data | |
1.times do |n| | |
date = (Time.now + n * 86400).strftime("%F") | |
logger.info "Downloads data for #{date}" | |
response = RestClient.get(xml_base_url + date) | |
download_size += response.body.bytesize | |
requests += 1 | |
logger.debug "Download completed with code #{response.code} with a total size of #{response.body.bytesize/1024}Kb." | |
# Parse downloaded XML and process data items | |
xml = Nokogiri::XML(response.body) | |
items = xml.xpath("//noneed//item") | |
logger.debug "-- found #{items.count} records in the file" | |
items.each do |item| | |
id = item.at("id").content | |
unless id.nil? | |
logger.info "Find images for (id:#{id})" | |
request = { | |
method: :post, | |
url: image_search_base_url + id, | |
cookies: cookie_jar | |
} | |
images = RestClient::Request.execute(request) | |
download_size += images.body.bytesize | |
requests += 1 | |
logger.debug "Download completed with code #{images.code} with a total size of #{images.body.bytesize}." | |
image_json = JSON.parse(images.body) | |
image_json['ids'].each do |img_id| | |
logger.debug "-- downloading image #{img_id}" | |
request = { | |
method: :post, | |
url: image_base_url + img_id.to_s, | |
cookies: cookie_jar | |
} | |
image = RestClient::Request.execute(request) | |
download_size += image.body.bytesize | |
requests += 1 | |
logger.debug "---- download status: #{image.code} with a total size of #{image.body.bytesize/1024.0/1024.0}Mb." | |
end | |
end | |
end | |
end | |
logger.info "Total download size: #{(download_size / 1024.0 / 1024.0).round(2)}Mb in #{Time.now - time_start} seconds through #{requests} requests." | |
end | |
report.pretty_print | |
logger.info "Completed!" |
https://stackoverflow.com/a/53574813/1977104
Using HTTP.rb results in:
Total download size: 96.92Mb through 118 unique requests.
Memory consumption:
Total allocated: 7107283 bytes (83437 objects)
Total retained: 44221 bytes (385 objects)
Code:
require 'bundler/inline'
require 'json'
require 'logger'
gemfile do
source 'https://rubygems.org'
ruby '2.5.3'
gem 'http', '~> 4.0.0'
gem 'nokogiri', '~> 1.8.3'
gem 'memory_profiler', '~> 0.9.11'
end
xml_base_url = 'http://noneed.dk/test.xml?date='
auth_end_point = 'http://noneed.dk/session.php'
auth_payload = {"user" => "[email protected]", "password" => "secret"}
image_search_base_url = 'http://noneed.dk/images.php?id='
image_base_url = 'http://noneed.dk/'
logger = Logger.new(STDOUT)
download_size = 0
time_start = Time.now
requests = 0
report = MemoryProfiler.report do
# Authenticates
response = HTTP.post(auth_end_point, form: auth_payload)
cookie_jar = response.cookies
logger.debug "Got a cookiejar - #{cookie_jar.cookies}"
download_size += response.content_length
requests += 1
# Run X days of data
1.times do |n|
date = (Time.now + n * 86400).strftime("%F")
logger.info "Downloads data for #{date}"
response = HTTP.get(xml_base_url + date)
download_size += response.content_length
requests += 1
logger.debug "Download completed with code #{response.code} with a total size of #{response.content_length/1024}Kb."
# Parse downloaded XML and process data items
xml = Nokogiri::XML(response.body)
items = xml.xpath("//noneed//item")
logger.debug "-- found #{items.count} records in the file"
items.each do |item|
id = item.at("id").content
unless id.nil?
logger.info "Find images for (id:#{id})"
images = HTTP.cookies(cookie_jar).post(image_search_base_url + id)
download_size += images.content_length
requests += 1
logger.debug "Download completed with code #{images.code} with a total size of #{images.content_length}."
image_json = JSON.parse(images.body)
image_json['ids'].each do |img_id|
logger.debug "-- downloading image #{img_id}"
image = HTTP.cookies(cookie_jar).post(image_base_url + img_id.to_s)
download_size += image.content_length
requests += 1
logger.debug "---- download status: #{image.code} with a total size of #{image.content_length/1024.0/1024.0}Mb."
end
end
end
end
logger.info "Total download size: #{(download_size / 1024.0 / 1024.0).round(2)}Mb in #{Time.now - time_start} seconds through #{requests} requests."
end
report.pretty_print
logger.info "Completed!"
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Setting ENV variable
RUBY_GC_HEAP_OLDOBJECT_LIMIT_FACTOR
to1.3
halves the memory usage.https://samsaffron.com/archive/2014/04/08/ruby-2-1-garbage-collection-ready-for-production