hdparam
$ hdparm -tT /dev/mapper/vg_00-lv_root /dev/mapper/vg_00-lv_root: Timing cached reads: 15752 MB in 1.99 seconds = 7920.19 MB/sec Timing buffered disk reads: 602 MB in 3.01 seconds = 200.17 MB/sec
fio
[global]
ioengine=libaio
iodepth=1
size=1g
direct=1
runtime=60
directory=${TARGET}
stonewall
[Seq-Read]
bs=128k
rw=read
[Seq-Write]
bs=128k
rw=write
[Rand-Read-512K]
bs=512k
rw=randread
[Rand-Write-512K]
bs=512k
rw=randwrite
[Rand-Read-4K]
bs=4k
rw=randread
[Rand-Write-4K]
bs=4k
rw=randwrite
みたいな設定ファイルを作って
# mkdir fio_target
# TARGET_DIR="$(pwd)/fio_target"
# ls -l
-rw-rw-r-- 1 yumetodo yumetodo 329 8月 14 16:24 fio.txt
drwxr-xr-x 2 root root 6 8月 14 16:30 fio_target
# TARGET=${TARGET_DIR} fio -f fio.txt --output-format=json | tee /tmp/fioresult_hostname.json
すると計測できる。あとはjqでjq '.jobs[]|select(.jobname == "Seq-Read")|{"128kread_bw_bytes": .read.bw_bytes}'とかして必要なやつだけ取り出す
UnixBench
Dhrystone 2 using register variables 39643828.0 lps (10.0 s, 7 samples)
Double-Precision Whetstone 6746.9 MWIPS (8.9 s, 7 samples)
Execl Throughput 3371.3 lps (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 533058.1 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 140689.9 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 1581604.7 KBps (30.0 s, 2 samples)
Pipe Throughput 669822.4 lps (10.0 s, 7 samples)
Pipe-based Context Switching 80602.7 lps (10.0 s, 7 samples)
Process Creation 7833.5 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 5743.2 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 1241.8 lpm (60.0 s, 2 samples)
System Call Overhead 415196.9 lps (10.0 s, 7 samples)
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 39643828.0 3397.1
Double-Precision Whetstone 55.0 6746.9 1226.7
Execl Throughput 43.0 3371.3 784.0
File Copy 1024 bufsize 2000 maxblocks 3960.0 533058.1 1346.1
File Copy 256 bufsize 500 maxblocks 1655.0 140689.9 850.1
File Copy 4096 bufsize 8000 maxblocks 5800.0 1581604.7 2726.9
Pipe Throughput 12440.0 669822.4 538.4
Pipe-based Context Switching 4000.0 80602.7 201.5
Process Creation 126.0 7833.5 621.7
Shell Scripts (1 concurrent) 42.4 5743.2 1354.5
Shell Scripts (8 concurrent) 6.0 1241.8 2069.6
System Call Overhead 15000.0 415196.9 276.8
========
System Benchmarks Index Score 949.0
みたいな結果が得られる
