r6g.large vs r5.large - qyjohn/AWS_Tutorials GitHub Wiki

r6g.large with 1024 GB root EBS volume

CPU Benchmark:

   #    #  #    #  #  #    #          #####   ######  #    #   ####   #    #
   #    #  ##   #  #   #  #           #    #  #       ##   #  #    #  #    #
   #    #  # #  #  #    ##            #####   #####   # #  #  #       ######
   #    #  #  # #  #    ##            #    #  #       #  # #  #       #    #
   #    #  #   ##  #   #  #           #    #  #       #   ##  #    #  #    #
    ####   #    #  #  #    #          #####   ######  #    #   ####   #    #

   Version 5.1.3                      Based on the Byte Magazine Unix Benchmark

   Multi-CPU version                  Version 5 revisions by Ian Smith,
                                      Sunnyvale, CA, USA
   January 13, 2011                   johantheghost at yahoo period com

------------------------------------------------------------------------------
   Use directories for:
      * File I/O tests (named fs***) = /home/ec2-user/byte-unixbench/UnixBench/tmp
      * Results                      = /home/ec2-user/byte-unixbench/UnixBench/results
------------------------------------------------------------------------------


1 x Dhrystone 2 using register variables  1 2 3 4 5 6 7 8 9 10

1 x Double-Precision Whetstone  1 2 3 4 5 6 7 8 9 10

1 x Execl Throughput  1 2 3

1 x File Copy 1024 bufsize 2000 maxblocks  1 2 3

1 x File Copy 256 bufsize 500 maxblocks  1 2 3

1 x File Copy 4096 bufsize 8000 maxblocks  1 2 3

1 x Pipe Throughput  1 2 3 4 5 6 7 8 9 10

1 x Pipe-based Context Switching  1 2 3 4 5 6 7 8 9 10

1 x Process Creation  1 2 3

1 x System Call Overhead  1 2 3 4 5 6 7 8 9 10

1 x Shell Scripts (1 concurrent)  1 2 3

1 x Shell Scripts (8 concurrent)  1 2 3

2 x Dhrystone 2 using register variables  1 2 3 4 5 6 7 8 9 10

2 x Double-Precision Whetstone  1 2 3 4 5 6 7 8 9 10

2 x Execl Throughput  1 2 3

2 x File Copy 1024 bufsize 2000 maxblocks  1 2 3

2 x File Copy 256 bufsize 500 maxblocks  1 2 3

2 x File Copy 4096 bufsize 8000 maxblocks  1 2 3

2 x Pipe Throughput  1 2 3 4 5 6 7 8 9 10

2 x Pipe-based Context Switching  1 2 3 4 5 6 7 8 9 10

2 x Process Creation  1 2 3

2 x System Call Overhead  1 2 3 4 5 6 7 8 9 10

2 x Shell Scripts (1 concurrent)  1 2 3

2 x Shell Scripts (8 concurrent)  1 2 3

========================================================================
   BYTE UNIX Benchmarks (Version 5.1.3)

   System: ip-172-31-85-115.ec2.internal: GNU/Linux
   OS: GNU/Linux -- 4.14.219-164.354.amzn2.aarch64 -- #1 SMP Mon Feb 22 21:18:49 UTC 2021
   Machine: aarch64 (aarch64)
   Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
   22:51:11 up 5 min,  1 user,  load average: 0.13, 0.16, 0.09; runlevel 2021-03-18

------------------------------------------------------------------------
Benchmark Run: Thu Mar 18 2021 22:51:11 - 23:19:08
2 CPUs in system; running 1 parallel copy of tests

Dhrystone 2 using register variables       41235962.4 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     5929.6 MWIPS (9.6 s, 7 samples)
Execl Throughput                               6683.2 lps   (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks       1016665.9 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          283785.5 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks       2763329.3 KBps  (30.0 s, 2 samples)
Pipe Throughput                             1784320.9 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                 134137.4 lps   (10.0 s, 7 samples)
Process Creation                              11122.4 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   8529.7 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                   1659.5 lpm   (60.0 s, 2 samples)
System Call Overhead                        1732020.5 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   41235962.4   3533.5
Double-Precision Whetstone                       55.0       5929.6   1078.1
Execl Throughput                                 43.0       6683.2   1554.2
File Copy 1024 bufsize 2000 maxblocks          3960.0    1016665.9   2567.3
File Copy 256 bufsize 500 maxblocks            1655.0     283785.5   1714.7
File Copy 4096 bufsize 8000 maxblocks          5800.0    2763329.3   4764.4
Pipe Throughput                               12440.0    1784320.9   1434.3
Pipe-based Context Switching                   4000.0     134137.4    335.3
Process Creation                                126.0      11122.4    882.7
Shell Scripts (1 concurrent)                     42.4       8529.7   2011.7
Shell Scripts (8 concurrent)                      6.0       1659.5   2765.8
System Call Overhead                          15000.0    1732020.5   1154.7
                                                                   ========
System Benchmarks Index Score                                        1624.9

------------------------------------------------------------------------
Benchmark Run: Thu Mar 18 2021 23:19:08 - 23:47:04
2 CPUs in system; running 2 parallel copies of tests

Dhrystone 2 using register variables       82503647.0 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                    11852.7 MWIPS (9.6 s, 7 samples)
Execl Throughput                              10944.5 lps   (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks       1320739.9 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          426491.8 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks       3243166.5 KBps  (30.0 s, 2 samples)
Pipe Throughput                             3568775.4 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                 665209.8 lps   (10.0 s, 7 samples)
Process Creation                              21656.7 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                  12544.4 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                   1708.5 lpm   (60.0 s, 2 samples)
System Call Overhead                        2720605.2 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   82503647.0   7069.7
Double-Precision Whetstone                       55.0      11852.7   2155.0
Execl Throughput                                 43.0      10944.5   2545.2
File Copy 1024 bufsize 2000 maxblocks          3960.0    1320739.9   3335.2
File Copy 256 bufsize 500 maxblocks            1655.0     426491.8   2577.0
File Copy 4096 bufsize 8000 maxblocks          5800.0    3243166.5   5591.7
Pipe Throughput                               12440.0    3568775.4   2868.8
Pipe-based Context Switching                   4000.0     665209.8   1663.0
Process Creation                                126.0      21656.7   1718.8
Shell Scripts (1 concurrent)                     42.4      12544.4   2958.6
Shell Scripts (8 concurrent)                      6.0       1708.5   2847.5
System Call Overhead                          15000.0    2720605.2   1813.7
                                                                   ========
System Benchmarks Index Score                                        2801.3

Memory Benchmark:

[ec2-user@ip-172-31-85-115 mbw]$ ./mbw 4096
Long uses 8 bytes. Allocating 2*536870912 elements = 8589934592 bytes of memory.
Using 262144 bytes as blocks for memcpy block copy test.
Getting down to business... Doing 10 runs per test.
0	Method: MEMCPY	Elapsed: 0.26169	MiB: 4096.00000	Copy: 15652.227 MiB/s
1	Method: MEMCPY	Elapsed: 0.26057	MiB: 4096.00000	Copy: 15719.565 MiB/s
2	Method: MEMCPY	Elapsed: 0.26073	MiB: 4096.00000	Copy: 15709.678 MiB/s
3	Method: MEMCPY	Elapsed: 0.26135	MiB: 4096.00000	Copy: 15672.410 MiB/s
4	Method: MEMCPY	Elapsed: 0.26108	MiB: 4096.00000	Copy: 15688.437 MiB/s
5	Method: MEMCPY	Elapsed: 0.26042	MiB: 4096.00000	Copy: 15728.439 MiB/s
6	Method: MEMCPY	Elapsed: 0.26146	MiB: 4096.00000	Copy: 15665.637 MiB/s
7	Method: MEMCPY	Elapsed: 0.26136	MiB: 4096.00000	Copy: 15672.170 MiB/s
8	Method: MEMCPY	Elapsed: 0.26078	MiB: 4096.00000	Copy: 15706.485 MiB/s
9	Method: MEMCPY	Elapsed: 0.26085	MiB: 4096.00000	Copy: 15702.330 MiB/s
AVG	Method: MEMCPY	Elapsed: 0.26103	MiB: 4096.00000	Copy: 15691.701 MiB/s
0	Method: DUMB	Elapsed: 2.89253	MiB: 4096.00000	Copy: 1416.062 MiB/s
1	Method: DUMB	Elapsed: 2.89114	MiB: 4096.00000	Copy: 1416.742 MiB/s
2	Method: DUMB	Elapsed: 2.89177	MiB: 4096.00000	Copy: 1416.432 MiB/s
3	Method: DUMB	Elapsed: 2.89048	MiB: 4096.00000	Copy: 1417.065 MiB/s
4	Method: DUMB	Elapsed: 2.89254	MiB: 4096.00000	Copy: 1416.057 MiB/s
5	Method: DUMB	Elapsed: 2.89032	MiB: 4096.00000	Copy: 1417.142 MiB/s
6	Method: DUMB	Elapsed: 2.89157	MiB: 4096.00000	Copy: 1416.533 MiB/s
7	Method: DUMB	Elapsed: 2.89173	MiB: 4096.00000	Copy: 1416.453 MiB/s
8	Method: DUMB	Elapsed: 2.89212	MiB: 4096.00000	Copy: 1416.262 MiB/s
9	Method: DUMB	Elapsed: 2.89066	MiB: 4096.00000	Copy: 1416.976 MiB/s
AVG	Method: DUMB	Elapsed: 2.89149	MiB: 4096.00000	Copy: 1416.572 MiB/s
0	Method: MCBLOCK	Elapsed: 0.26532	MiB: 4096.00000	Copy: 15437.671 MiB/s
1	Method: MCBLOCK	Elapsed: 0.26577	MiB: 4096.00000	Copy: 15412.054 MiB/s
2	Method: MCBLOCK	Elapsed: 0.26510	MiB: 4096.00000	Copy: 15450.890 MiB/s
3	Method: MCBLOCK	Elapsed: 0.26570	MiB: 4096.00000	Copy: 15416.115 MiB/s
4	Method: MCBLOCK	Elapsed: 0.26463	MiB: 4096.00000	Copy: 15478.332 MiB/s
5	Method: MCBLOCK	Elapsed: 0.26534	MiB: 4096.00000	Copy: 15436.624 MiB/s
6	Method: MCBLOCK	Elapsed: 0.26497	MiB: 4096.00000	Copy: 15458.645 MiB/s
7	Method: MCBLOCK	Elapsed: 0.26470	MiB: 4096.00000	Copy: 15473.946 MiB/s
8	Method: MCBLOCK	Elapsed: 0.26486	MiB: 4096.00000	Copy: 15465.066 MiB/s
9	Method: MCBLOCK	Elapsed: 0.26508	MiB: 4096.00000	Copy: 15451.997 MiB/s
AVG	Method: MCBLOCK	Elapsed: 0.26515	MiB: 4096.00000	Copy: 15448.104 MiB/s

[ec2-user@ip-172-31-85-115 mbw]$  lstopo
Machine (16GB)
  Package L#0 + L3 L#0 (32MB)
    L2 L#0 (1024KB) + L1d L#0 (64KB) + L1i L#0 (64KB) + Core L#0 + PU L#0 (P#0)
    L2 L#1 (1024KB) + L1d L#1 (64KB) + L1i L#1 (64KB) + Core L#1 + PU L#1 (P#1)
  HostBridge L#0
    PCI 1d0f:8061
    PCI 1d0f:ec20
      Net L#0 "eth0"

r5.large with 1024 GB root EBS volume

CPU Benchmark:

   #    #  #    #  #  #    #          #####   ######  #    #   ####   #    #
   #    #  ##   #  #   #  #           #    #  #       ##   #  #    #  #    #
   #    #  # #  #  #    ##            #####   #####   # #  #  #       ######
   #    #  #  # #  #    ##            #    #  #       #  # #  #       #    #
   #    #  #   ##  #   #  #           #    #  #       #   ##  #    #  #    #
    ####   #    #  #  #    #          #####   ######  #    #   ####   #    #

   Version 5.1.3                      Based on the Byte Magazine Unix Benchmark

   Multi-CPU version                  Version 5 revisions by Ian Smith,
                                      Sunnyvale, CA, USA
   January 13, 2011                   johantheghost at yahoo period com

------------------------------------------------------------------------------
   Use directories for:
      * File I/O tests (named fs***) = /home/ec2-user/byte-unixbench/UnixBench/tmp
      * Results                      = /home/ec2-user/byte-unixbench/UnixBench/results
------------------------------------------------------------------------------


1 x Dhrystone 2 using register variables  1 2 3 4 5 6 7 8 9 10

1 x Double-Precision Whetstone  1 2 3 4 5 6 7 8 9 10

1 x Execl Throughput  1 2 3

1 x File Copy 1024 bufsize 2000 maxblocks  1 2 3

1 x File Copy 256 bufsize 500 maxblocks  1 2 3

1 x File Copy 4096 bufsize 8000 maxblocks  1 2 3

1 x Pipe Throughput  1 2 3 4 5 6 7 8 9 10

1 x Pipe-based Context Switching  1 2 3 4 5 6 7 8 9 10

1 x Process Creation  1 2 3

1 x System Call Overhead  1 2 3 4 5 6 7 8 9 10

1 x Shell Scripts (1 concurrent)  1 2 3

1 x Shell Scripts (8 concurrent)  1 2 3

2 x Dhrystone 2 using register variables  1 2 3 4 5 6 7 8 9 10

2 x Double-Precision Whetstone  1 2 3 4 5 6 7 8 9 10

2 x Execl Throughput  1 2 3

2 x File Copy 1024 bufsize 2000 maxblocks  1 2 3

2 x File Copy 256 bufsize 500 maxblocks  1 2 3

2 x File Copy 4096 bufsize 8000 maxblocks  1 2 3

2 x Pipe Throughput  1 2 3 4 5 6 7 8 9 10

2 x Pipe-based Context Switching  1 2 3 4 5 6 7 8 9 10

2 x Process Creation  1 2 3

2 x System Call Overhead  1 2 3 4 5 6 7 8 9 10

2 x Shell Scripts (1 concurrent)  1 2 3

2 x Shell Scripts (8 concurrent)  1 2 3

========================================================================
   BYTE UNIX Benchmarks (Version 5.1.3)

   System: ip-172-31-89-96.ec2.internal: GNU/Linux
   OS: GNU/Linux -- 4.14.219-164.354.amzn2.x86_64 -- #1 SMP Mon Feb 22 21:18:39 UTC 2021
   Machine: x86_64 (x86_64)
   Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
   CPU 0: Intel(R) Xeon(R) Platinum 8175M CPU @ 2.50GHz (5000.0 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
   CPU 1: Intel(R) Xeon(R) Platinum 8175M CPU @ 2.50GHz (5000.0 bogomips)
          Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
   22:51:03 up 6 min,  1 user,  load average: 0.17, 0.07, 0.01; runlevel 2021-03-18

------------------------------------------------------------------------
Benchmark Run: Thu Mar 18 2021 22:51:03 - 23:19:02
2 CPUs in system; running 1 parallel copy of tests

Dhrystone 2 using register variables       38856036.5 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     4362.4 MWIPS (9.1 s, 7 samples)
Execl Throughput                               4827.9 lps   (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        641513.2 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          168673.9 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks       2010234.0 KBps  (30.0 s, 2 samples)
Pipe Throughput                              822556.6 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                  64993.7 lps   (10.0 s, 7 samples)
Process Creation                              12208.1 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   7847.1 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                   1239.3 lpm   (60.0 s, 2 samples)
System Call Overhead                         455151.8 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   38856036.5   3329.6
Double-Precision Whetstone                       55.0       4362.4    793.2
Execl Throughput                                 43.0       4827.9   1122.8
File Copy 1024 bufsize 2000 maxblocks          3960.0     641513.2   1620.0
File Copy 256 bufsize 500 maxblocks            1655.0     168673.9   1019.2
File Copy 4096 bufsize 8000 maxblocks          5800.0    2010234.0   3465.9
Pipe Throughput                               12440.0     822556.6    661.2
Pipe-based Context Switching                   4000.0      64993.7    162.5
Process Creation                                126.0      12208.1    968.9
Shell Scripts (1 concurrent)                     42.4       7847.1   1850.7
Shell Scripts (8 concurrent)                      6.0       1239.3   2065.5
System Call Overhead                          15000.0     455151.8    303.4
                                                                   ========
System Benchmarks Index Score                                        1061.6

------------------------------------------------------------------------
Benchmark Run: Thu Mar 18 2021 23:19:02 - 23:47:05
2 CPUs in system; running 2 parallel copies of tests

Dhrystone 2 using register variables       51138934.8 lps   (10.0 s, 7 samples)
Double-Precision Whetstone                     7330.5 MWIPS (9.3 s, 7 samples)
Execl Throughput                               6627.6 lps   (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks        837828.9 KBps  (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks          216670.0 KBps  (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks       2720468.0 KBps  (30.0 s, 2 samples)
Pipe Throughput                             1086648.8 lps   (10.0 s, 7 samples)
Pipe-based Context Switching                 288787.8 lps   (10.0 s, 7 samples)
Process Creation                              18838.0 lps   (30.0 s, 2 samples)
Shell Scripts (1 concurrent)                   9047.9 lpm   (60.0 s, 2 samples)
Shell Scripts (8 concurrent)                   1245.6 lpm   (60.1 s, 2 samples)
System Call Overhead                         587301.4 lps   (10.0 s, 7 samples)

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0   51138934.8   4382.1
Double-Precision Whetstone                       55.0       7330.5   1332.8
Execl Throughput                                 43.0       6627.6   1541.3
File Copy 1024 bufsize 2000 maxblocks          3960.0     837828.9   2115.7
File Copy 256 bufsize 500 maxblocks            1655.0     216670.0   1309.2
File Copy 4096 bufsize 8000 maxblocks          5800.0    2720468.0   4690.5
Pipe Throughput                               12440.0    1086648.8    873.5
Pipe-based Context Switching                   4000.0     288787.8    722.0
Process Creation                                126.0      18838.0   1495.1
Shell Scripts (1 concurrent)                     42.4       9047.9   2133.9
Shell Scripts (8 concurrent)                      6.0       1245.6   2076.0
System Call Overhead                          15000.0     587301.4    391.5
                                                                   ========
System Benchmarks Index Score                                        1549.3

Memory Benchmark:

[ec2-user@ip-172-31-89-96 mbw]$ ./mbw 4096
Long uses 8 bytes. Allocating 2*536870912 elements = 8589934592 bytes of memory.
Using 262144 bytes as blocks for memcpy block copy test.
Getting down to business... Doing 10 runs per test.
0	Method: MEMCPY	Elapsed: 0.86192	MiB: 4096.00000	Copy: 4752.203 MiB/s
1	Method: MEMCPY	Elapsed: 0.86208	MiB: 4096.00000	Copy: 4751.272 MiB/s
2	Method: MEMCPY	Elapsed: 0.86214	MiB: 4096.00000	Copy: 4750.957 MiB/s
3	Method: MEMCPY	Elapsed: 0.86234	MiB: 4096.00000	Copy: 4749.889 MiB/s
4	Method: MEMCPY	Elapsed: 0.86283	MiB: 4096.00000	Copy: 4747.175 MiB/s
5	Method: MEMCPY	Elapsed: 0.86273	MiB: 4096.00000	Copy: 4747.736 MiB/s
6	Method: MEMCPY	Elapsed: 0.86223	MiB: 4096.00000	Copy: 4750.445 MiB/s
7	Method: MEMCPY	Elapsed: 0.86198	MiB: 4096.00000	Copy: 4751.872 MiB/s
8	Method: MEMCPY	Elapsed: 0.86192	MiB: 4096.00000	Copy: 4752.170 MiB/s
9	Method: MEMCPY	Elapsed: 0.86223	MiB: 4096.00000	Copy: 4750.456 MiB/s
AVG	Method: MEMCPY	Elapsed: 0.86224	MiB: 4096.00000	Copy: 4750.417 MiB/s
0	Method: DUMB	Elapsed: 1.19139	MiB: 4096.00000	Copy: 3438.013 MiB/s
1	Method: DUMB	Elapsed: 1.19136	MiB: 4096.00000	Copy: 3438.076 MiB/s
2	Method: DUMB	Elapsed: 1.19066	MiB: 4096.00000	Copy: 3440.123 MiB/s
3	Method: DUMB	Elapsed: 1.19241	MiB: 4096.00000	Copy: 3435.057 MiB/s
4	Method: DUMB	Elapsed: 1.19233	MiB: 4096.00000	Copy: 3435.305 MiB/s
5	Method: DUMB	Elapsed: 1.18928	MiB: 4096.00000	Copy: 3444.086 MiB/s
6	Method: DUMB	Elapsed: 1.18906	MiB: 4096.00000	Copy: 3444.749 MiB/s
7	Method: DUMB	Elapsed: 1.18817	MiB: 4096.00000	Copy: 3447.330 MiB/s
8	Method: DUMB	Elapsed: 1.18926	MiB: 4096.00000	Copy: 3444.150 MiB/s
9	Method: DUMB	Elapsed: 1.18960	MiB: 4096.00000	Copy: 3443.168 MiB/s
AVG	Method: DUMB	Elapsed: 1.19035	MiB: 4096.00000	Copy: 3441.001 MiB/s
0	Method: MCBLOCK	Elapsed: 0.86259	MiB: 4096.00000	Copy: 4748.512 MiB/s
1	Method: MCBLOCK	Elapsed: 0.86124	MiB: 4096.00000	Copy: 4755.939 MiB/s
2	Method: MCBLOCK	Elapsed: 0.86310	MiB: 4096.00000	Copy: 4745.684 MiB/s
3	Method: MCBLOCK	Elapsed: 0.86182	MiB: 4096.00000	Copy: 4752.749 MiB/s
4	Method: MCBLOCK	Elapsed: 0.86306	MiB: 4096.00000	Copy: 4745.926 MiB/s
5	Method: MCBLOCK	Elapsed: 0.86225	MiB: 4096.00000	Copy: 4750.384 MiB/s
6	Method: MCBLOCK	Elapsed: 0.86194	MiB: 4096.00000	Copy: 4752.093 MiB/s
7	Method: MCBLOCK	Elapsed: 0.86254	MiB: 4096.00000	Copy: 4748.782 MiB/s
8	Method: MCBLOCK	Elapsed: 0.86282	MiB: 4096.00000	Copy: 4747.224 MiB/s
9	Method: MCBLOCK	Elapsed: 0.86362	MiB: 4096.00000	Copy: 4742.838 MiB/s
AVG	Method: MCBLOCK	Elapsed: 0.86250	MiB: 4096.00000	Copy: 4749.010 MiB/s

[ec2-user@ip-172-31-89-96 mbw]$ /usr/bin/lstopo-no-graphics
Machine (15GB)
  Package L#0 + L3 L#0 (33MB) + L2 L#0 (1024KB) + L1d L#0 (32KB) + L1i L#0 (32KB) + Core L#0
    PU L#0 (P#0)
    PU L#1 (P#1)
  HostBridge L#0
    PCI 1d0f:1111
    PCI 1d0f:8061
    PCI 1d0f:ec20
      Net L#0 "eth0"