From 5f477e0561b613038888a0fd7169f9b6dc11b118 Mon Sep 17 00:00:00 2001 From: Florian Fischer Date: Tue, 2 Apr 2019 11:51:20 +0200 Subject: add analyze and server_benchmark feature --analyze uses malt to trace the benchmarks behavior. It uses the run loop but the obtained results are not stored Benchmark.server_benchmark is used if only a server is started for each allocator and clients are used to measure its performance in the run loop. If server_benchmark is set to True the cmds are run with the system default allocator. Misc changes: * The global environment is no longer changed. Instead a custom env dict is passed to suprocesses containing LD_PRELOAD. * Failing cmds no longer skip the whole benchmark instead they now skip the malfunctioning allocator. * Fix default title in plot_single_arg an analyse run are not stored --- doc/Benchmarks.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'doc/Benchmarks.md') diff --git a/doc/Benchmarks.md b/doc/Benchmarks.md index 4ab0c02..4aeb8a4 100644 --- a/doc/Benchmarks.md +++ b/doc/Benchmarks.md @@ -127,7 +127,7 @@ for number_of_runs #### run hooks -* `preallocator_hook((alloc_name, alloc_definition), current_run, verbose)` is called +* `preallocator_hook((alloc_name, alloc_definition), current_run, environment, verbose)` is called if available once per allocator before any command is executed. This hook may be useful if you want to prepare stuff for each allocator. The mysql benchmark uses this hook to start the mysql server with the current allocator. -- cgit v1.2.3