Thanks Andreas,
The C-app benchmark failed, I mean it never completed and there was no score at the end,
I waited for 8 hours before I did ctrl-c . It only has 4 results vs 12 results in the
first section. Are there special logs to see for the C version of the benchmark.
The below is a very small development cluster I am using until I figure out how to run
IO500 correctly.
[Leaving] datafiles in ./out//2020.05.29-17.31.34-scr
[Summary] Results files in ./results//2020.05.29-17.31.34-scr
[Summary] Data files in ./out//2020.05.29-17.31.34-scr
[RESULT] BW phase 1 ior_easy_write 6.188 GiB/s : time 357.44
seconds
[RESULT] BW phase 2 ior_hard_write 1.132 GiB/s : time 367.41
seconds
[RESULT] BW phase 3 ior_easy_read 8.090 GiB/s : time 273.37
seconds
[RESULT] BW phase 4 ior_hard_read 3.726 GiB/s : time 111.69
seconds
[RESULT] IOPS phase 1 mdtest_easy_write 4.263 kiops : time 3518.34
seconds
[RESULT] IOPS phase 2 mdtest_hard_write 2.953 kiops : time 303.52
seconds
[RESULT] IOPS phase 3 find 91.550 kiops : time 173.64
seconds
[RESULT] IOPS phase 4 mdtest_easy_stat 137.243 kiops : time 109.30
seconds
[RESULT] IOPS phase 5 mdtest_hard_stat 84.140 kiops : time 10.65
seconds
[RESULT] IOPS phase 6 mdtest_easy_delete 55.311 kiops : time 271.19
seconds
[RESULT] IOPS phase 7 mdtest_hard_read 21.778 kiops : time 41.16
seconds
[RESULT] IOPS phase 8 mdtest_hard_delete 7.133 kiops : time 129.24
seconds
[SCORE] Bandwidth 3.81212 GiB/s : IOPS 24.1149 kiops : TOTAL 9.58796
The io500.sh was run
Running the C version of the benchmark now
IO500 version io500-isc20
[RESULT] ior-easy-write 6.233210 GiB/s : time 359.216 seconds
[RESULT] mdtest-easy-write 3.750549 kIOPS : time 3999.448 seconds
[RESULT] ior-hard-write 1.415903 GiB/s : time 349.737 seconds
[RESULT] mdtest-hard-write 3.006432 kIOPS : time 305.006 seconds
^C
[root@inst-q7cdd-good-crow io500-app]#
From: Andreas Dilger <adilger(a)dilger.ca>
Date: Saturday, May 30, 2020 at 2:33 AM
To: Pinkesh Valdria <pinkesh.valdria(a)oracle.com>
Cc: <io-500(a)vi4io.org>
Subject: Re: [IO-500] Io500 runs twice - is that expected starting 2020 ?
Hi Pinkesh,
The dual runs of the IO500 benchmark for this list are intentional,
and documented in the README-ISC20.txt file in the source tree.
This is to allow comparison between the historical io500.sh script and the
new C application that runs the same IOR, mdtest, and find commands.
Please submit both results for ISC'20.
We wanted to be sure that the transition to the new C-app didn't
introduce any errors in the results. The need to run the benchmark
twice will hopefully be gone for the SC'20 list.
Cheers, Andreas(*)
* speaking on my own behalf and not on behalf of the IO500 board
On May 29, 2020, at 16:02, Pinkesh Valdria via IO-500 <io-500(a)vi4io.org> wrote:
Hello IO-500 experts,
I am trying to configure io500 . When I run it, it runs twice, first one is regular and
2nd one is called “Running the C version of the benchmark now”. Is it because I
misconfigured it or is it required to run both, starting 2020 ? My config*.ini file is
below.
[root@inst-q7cdd-good-crow io500-app]# ./io500.sh config-test1.ini
System: inst-q7cdd-good-crow
…..
Running the IO500 Benchmark now
[Creating] directories
…..
[Summary] Results files in ./results//2020.05.29-17.31.34-scr
[Summary] Data files in ./out//2020.05.29-17.31.34-scr
[RESULT] BW phase 1 ior_easy_write 6.188 GiB/s : time 357.44
seconds
[RESULT] BW phase 2 ior_hard_write 1.132 GiB/s : time 367.41
seconds
[RESULT] BW phase 3 ior_easy_read 8.090 GiB/s : time 273.37
seconds
[RESULT] BW phase 4 ior_hard_read 3.726 GiB/s : time 111.69
seconds
[RESULT] IOPS phase 1 mdtest_easy_write 4.263 kiops : time 3518.34
seconds
[RESULT] IOPS phase 2 mdtest_hard_write 2.953 kiops : time 303.52
seconds
[RESULT] IOPS phase 3 find 91.550 kiops : time 173.64
seconds
[RESULT] IOPS phase 4 mdtest_easy_stat 137.243 kiops : time 109.30
seconds
[RESULT] IOPS phase 5 mdtest_hard_stat 84.140 kiops : time 10.65
seconds
[RESULT] IOPS phase 6 mdtest_easy_delete 55.311 kiops : time 271.19
seconds
[RESULT] IOPS phase 7 mdtest_hard_read 21.778 kiops : time 41.16
seconds
[RESULT] IOPS phase 8 mdtest_hard_delete 7.133 kiops : time 129.24
seconds
[SCORE] Bandwidth 3.81212 GiB/s : IOPS 24.1149 kiops : TOTAL 9.58796
The io500.sh was run
Running the C version of the benchmark now
IO500 version io500-isc20
<currently running …when I posted this question ….
***************************************************
config-test1.ini (END)
***************************************************
[global]
datadir = ./out/
resultdir = ./results/
timestamp-resultdir = TRUE
# Chose parameters that are very small for all benchmarks
[debug]
stonewall-time = 300 # for testing
[ior-easy]
transferSize = 2m
blockSize = 102400m
[mdtest-easy]
API = POSIX
# Files per proc
n = 500000
[ior-hard]
API = POSIX
# Number of segments 10000000
segmentCount = 400000
[mdtest-hard]
API = POSIX
# Files per proc 1000000
n = 40000
[find]
external-script = /mnt/beeond/io500-app/bin/pfind
pfind-parallelize-single-dir-access-using-hashing = FALSE
***************************************************
_______________________________________________
IO-500 mailing list
IO-500(a)vi4io.org
https://www.vi4io.org/mailman/listinfo/io-500