| Commit message (Collapse) | Author | Age | Files | Lines | |
|---|---|---|---|---|---|
| * | fix and adjust to mysql installations on Ubuntu 18.04 | Florian Fischer | 2019-08-11 | 1 | -7/+8 |
| | | |||||
| * | use new location of bumpptr | Florian Fischer | 2019-08-11 | 1 | -1/+1 |
| | | |||||
| * | make bump pointer allocator available through src.allocators.bumpptr | Florian Fischer | 2019-08-11 | 1 | -1/+1 |
| | | |||||
| * | don't copy benchmark.allocators again | Florian Fischer | 2019-08-10 | 1 | -6/+0 |
| | | |||||
| * | print malloc_stats to stdout | Florian Fischer | 2019-08-10 | 1 | -1/+4 |
| | | |||||
| * | add facts to dataref export | Florian Fischer | 2019-07-31 | 5 | -11/+11 |
| | | |||||
| * | add barrier to larson benchmark | Florian Fischer | 2019-07-01 | 1 | -0/+10 |
| | | | | | | | The barrier prevents worker thread from doing work before the main thread starts the timing. This behaviour was mentioned in the paper: Mostly Lock-Free Malloc by Dave Dice, Alex Garthwaite | ||||
| * | fix realloc micro benchmark for allocators returning null for realloc(ptr, 0) | Florian Fischer | 2019-06-27 | 1 | -1/+1 |
| | | |||||
| * | apply some flake8 hints | Florian Fischer | 2019-06-19 | 6 | -63/+45 |
| | | |||||
| * | use sane iterations (100 -> 10000) | Florian Fischer | 2019-05-27 | 1 | -3/+3 |
| | | |||||
| * | don't break if a result is NaN | Florian Fischer | 2019-05-21 | 1 | -4/+4 |
| | | |||||
| * | add ttest1 from ptmalloc | Florian Fischer | 2019-05-15 | 5 | -0/+685 |
| | | |||||
| * | introduce server concept to Benchmark | Florian Fischer | 2019-05-15 | 2 | -104/+27 |
| | | | | | | | | | | | | | A benchmark object can specify a list of cmds to execute as "servers" in the member attribute server_cmds. Servers are started and terminated through Popen objects. This requires the server cmds to not daemonize so the server can be terminated through the Popen object. For each started server cmd a shutdown function is registered with atexit to terminate all servers even if a exception occurs. Use the new server concept in httpd and mysql benchmarks | ||||
| * | add php to httpd benchmark | Florian Fischer | 2019-05-15 | 8 | -75/+2666 |
| | | | | | | | | | | restructure httpd and php-fpm setup OBJDIR/etc holds configs OBJDIR/run holds pid files OBJDIR/log holds all log files don't daemonize nginx | ||||
| * | fix ylabel for llc miss plot | Florian Fischer | 2019-05-14 | 1 | -1/+1 |
| | | |||||
| * | add dataref exports | Florian Fischer | 2019-05-08 | 4 | -0/+31 |
| | | |||||
| * | use bumpptr in loop benchmark | Florian Fischer | 2019-04-28 | 1 | -0/+4 |
| | | |||||
| * | use new barplot function | Florian Fischer | 2019-04-15 | 1 | -13/+3 |
| | | |||||
| * | improve descriptive statistics, csv-export and add general barplot function | Florian Fischer | 2019-04-13 | 3 | -52/+20 |
| | | |||||
| * | improve httpd Makefile and config | Florian Fischer | 2019-04-13 | 2 | -3/+2 |
| | | |||||
| * | fix still running check | Florian Fischer | 2019-04-13 | 1 | -1/+18 |
| | | |||||
| * | add check if nginx is running before trying to terminate | Florian Fischer | 2019-04-13 | 1 | -7/+9 |
| | | |||||
| * | adjust absurd concurrency | Florian Fischer | 2019-04-13 | 1 | -1/+1 |
| | | |||||
| * | fix normalized plots | Florian Fischer | 2019-04-10 | 1 | -1/+1 |
| | | |||||
| * | add normalized time plot | Florian Fischer | 2019-04-10 | 1 | -0/+8 |
| | | |||||
| * | dj_trace: make tex table standalone | Florian Fischer | 2019-04-10 | 1 | -1/+5 |
| | | |||||
| * | use autoticks for loop plots | Florian Fischer | 2019-04-10 | 1 | -2/+4 |
| | | |||||
| * | add real simple realloc benchmark | Florian Fischer | 2019-04-02 | 3 | -0/+78 |
| | | |||||
| * | add real simple webserver benchmark using nginx and ab | Florian Fischer | 2019-04-02 | 4 | -0/+183 |
| | | |||||
| * | add analyze and server_benchmark feature | Florian Fischer | 2019-04-02 | 1 | -4/+4 |
| | | | | | | | | | | | | | | | | | | | | | | | --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 | ||||
| * | fix indent in loop.c | Florian Fischer | 2019-04-02 | 1 | -1/+1 |
| | | |||||
| * | add export_to_csv and use it in the loop benchmark | Florian Fischer | 2019-03-25 | 1 | -0/+3 |
| | | |||||
| * | move benchmark definitions into src/benchmarks | Florian Fischer | 2019-03-25 | 6 | -0/+798 |
| | | | | | bench now loads all *.py files from src/benchmarks as benchmarks | ||||
| * | rework build system #2: call make before executing any benchmark | Florian Fischer | 2019-02-02 | 4 | -4/+9 |
| | | | | | | | Make scans the project directory for Makefiles and executes them. The targets should be build by the new targets/Makefile. All included Makefiles are now "quiet" by default. | ||||
| * | rework build system #1 | Florian Fischer | 2019-02-01 | 12 | -0/+851 |
| | | | | | | each benchmark has its own Makefile which must put it's binaries into OBJDIR which is added to the PATH during execution. | ||||
| * | move source code to src/ | Florian Fischer | 2019-01-15 | 7 | -0/+1783 |
 |
index : allocbench | |
| benchmark tool for POSIX memory allocators |
| aboutsummaryrefslogtreecommitdiff |