wangziqi2016 / index-microbench Goto Github PK

C++ 79.67% Python 0.36% Makefile 0.40% C 17.02% Shell 0.09% M4 0.53% TeX 1.62% Objective-C 0.30% Batchfile 0.01%

index-microbench's Introduction

index-microbench

Generate Workloads

Download YCSB

curl -O --location https://github.com/brianfrankcooper/YCSB/releases/download/0.11.0/ycsb-0.11.0.tar.gz
tar xfvz ycsb-0.11.0.tar.gz
mv ycsb-0.11.0 YCSB

Create Workload Spec

The default workload a-f are in ./workload_spec

You can of course generate your own spec and put it in this folder.
Modify workload_config.inp

1st arg: workload spec file name 2nd arg: key type (randint = random integer; monoint = monotonically increasing integer; email = email keys with host name reversed)
Generate
```
make generate_workload
```
The generated workload files will be in ./workloads
NOTE: To generate email-key workloads, you need an email list (list.txt)# index-microbench

Publications

This index benchmarking framework has been used as the experimental environment for the following research papers:

Ziqi Wang, Andrew Pavlo, Hyeontaek Lim, Viktor Leis, Huanchen Zhang, Michael Kaminsky, and David G. Andersen. 2018. Building a Bw-Tree Takes More Than Just Buzz Words. In Proceedings of 2018 International Conference on Management of Data (SIGMOD’18). ACM, New York, NY, USA, 16 pages. https://doi.org/10.1145/3183713.3196895

index-microbench's People

Contributors

Stargazers

Watchers

index-microbench's Issues

Script not working

I get an error when I run the script.

I put these two lines in workload_config.inp:

workloade
randint

But then when I run make generate_workload
I get the following error:

$ make generate_workload
python gen_workload.py workload_config.inp
workload = workloade
key type = randint
sh: workloads/ycsb_load_randint_workloade: No such file or directory
sh: workloads/ycsb_txn_randint_workloade: No such file or directory
Traceback (most recent call last):
  File "gen_workload.py", line 65, in <module>
    f_load = open (out_ycsb_load, 'r')
IOError: [Errno 2] No such file or directory: 'workloads/ycsb_load_randint_workloade'
make: *** [generate_workload] Error 1

How should I generate the workloads/ycsb_* files that the script is asking for?

What is btree-rtm?

Does rtm mean Intel TSX instructions?

ARTOLC segfaults for workload a

I am using a fork of the branch (https://github.com/ajitmathew/index-microbench) to benchmark ART. The modification to the fork consists of commits to fix some compile errors. For workload A, art segfaults even for one thread.

  ./workload a rand artolc 1

 Error: unsupported processor. Only Intel(R) processors are supported (Atom(R) and microarchitecture codename Nehalem/Nehalem-EP, Atom(tm), Westmere/Clarkdale, Sandy Bridge, Westmere-EP, Sandy Bridge-EP/Jaketown, Nehalem-EX, Westmere-EX, Ivy Bridge, Haswell, Broadwell, Ivy Bridge-EP/EN/EX/Ivytown, Haswell-EP/EN/EX, Broadwell-EP/EX, Broadwell-DE, Knights Landing, Skylake, Kabylake). CPU model number: 85 Brand: "Intel(R) Xeon(R) Platinum 8180 CPU @ 2.50GHz"
Number of threads: 1
  BwTree will collect statistics
Leaf delta chain threshold: 24; Inner delta chain threshold: 2
  BTree element pair count: 255
Loaded 50001 keys
Finished loading workload file (mem = 1415576)
Populating the index with 50001 keys using 1 threads
insert 3.54819
# of Txn: 10000000
Segmentation fault (core dumped)

I am using Fedora 28 and all the dependency are installed using dnf.

Changing value sizes

Hi,
I am using index-microbench for my evaluations, I wanted to generate 8-byte keys and 64-byte values.
when I changed the field length parameter (field length=1 to fieldlength=64) in the workload file still the value generated is 8 bytes. Can some help me with this? any help is appreciated.

Thanks

wangziqi2016 / index-microbench Goto Github PK

index-microbench's Introduction

index-microbench

Generate Workloads

Publications

index-microbench's People

Contributors

Stargazers

Watchers

Forkers

index-microbench's Issues

Script not working

What is btree-rtm?

ARTOLC segfaults for workload a

Changing value sizes

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent