gitlab-org--gitlab-foss/scripts/insert-rspec-profiling-data
Stan Hu f11030173b Batch insert CI rspec_profiling data
Instead of inserting a row after each example to an external database,
we save the CI profiling reports into the `rspec_profiling` directory
and insert the data in the update-tests-metadata CI stage.  This should
make each spec run faster and also reduce the number of PostgreSQL
connections needed by concurrent CI builds.

`scripts/insert-rspec-profiling-data` also inserts one file at a time
via the PostgreSQL COPY command for faster inserts. The one side effect
is that the `created_at` and `updated_at` timestamps aren't available
since they aren't generated in the CSV.

Closes https://gitlab.com/gitlab-org/gitlab-ee/issues/10154
2019-03-12 09:51:37 +00:00

47 lines
1.2 KiB
Ruby
Executable file

#!/usr/bin/env ruby
require 'csv'
require 'rspec_profiling'
require 'postgres-copy'
module RspecProfiling
module Collectors
class PSQL
def establish_connection
# This disables the automatic creation of the database and
# table. In the future, we may want a way to specify the host of
# the database to connect so that we can call #install.
Result.establish_connection(results_url)
end
def prepared?
connection.data_source_exists?(table)
end
def results_url
ENV['RSPEC_PROFILING_POSTGRES_URL']
end
class Result < ActiveRecord::Base
acts_as_copy_target
end
end
end
end
def insert_data(path)
puts "#{Time.now} Inserting CI stats..."
collector = RspecProfiling::Collectors::PSQL.new
collector.install
files = Dir[File.join(path, "*.csv")]
files.each do |filename|
puts "#{Time.now} Inserting #{filename}..."
result = RspecProfiling::Collectors::PSQL::Result.copy_from(filename)
puts "#{Time.now} Inserted #{result.cmd_tuples} lines in #{filename}, DB response: #{result.cmd_status}"
end
end
insert_data('rspec_profiling') if ENV['RSPEC_PROFILING_POSTGRES_URL'].present?