Ben's notes

Linux, Unix, network, radio...

User Tools

Site Tools

Trace:
simple_sequential_baseline_test

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision		Previous revision
Next revisionBoth sides next revision
simple_sequential_baseline_test [2019/06/28 19:05] – adminsimple_sequential_baseline_test [2019/06/28 19:05] – admin
Line 2: Line 2:
  
 **Direct Write Test, simple benchmark with dd** **Direct Write Test, simple benchmark with dd**
 +
 First off remember system OS'es, and controllers, are always setup for caching and buffering, so use DirectIO, here is an example syntax that should work on most flavors of Linux/Unix, or try Cygwin on Windows to achieve the same. So to me it seems amazingly universal but you tell me, is there a more universal tool than "dd" out there that's more powerful and more standard for a fast memory to device copy test. First off remember system OS'es, and controllers, are always setup for caching and buffering, so use DirectIO, here is an example syntax that should work on most flavors of Linux/Unix, or try Cygwin on Windows to achieve the same. So to me it seems amazingly universal but you tell me, is there a more universal tool than "dd" out there that's more powerful and more standard for a fast memory to device copy test.
  
Line 13: Line 14:
 sys 0m0.217s</code> sys 0m0.217s</code>
  
-===Direct Read Test===+**Direct Read Test** 
 You can reverse things to see what the read test looks like, things should be faster on reads in all cases with respect to the SSD: You can reverse things to see what the read test looks like, things should be faster on reads in all cases with respect to the SSD:
  
Line 24: Line 26:
 user 0m0.015s</code> user 0m0.015s</code>
  
-===Read Cache Test===+**Read Cache Test**
  
 (testing the DRAM memory, and system in this case) (testing the DRAM memory, and system in this case)
Line 37: Line 39:
 sys 0m0.296s</code> sys 0m0.296s</code>
  
-===IBM P520, POWER6, PowerVM (with RHEL6), Hitachi Ultrastar 15K300 SAS, 147GB===+====IBM P520, POWER6, PowerVM (with RHEL6), Hitachi Ultrastar 15K300 SAS, 147GB====
 <code>Direct write: 1073741824 bytes (1.1 GB) copied, 14.604 s, 73.5 MB/s <code>Direct write: 1073741824 bytes (1.1 GB) copied, 14.604 s, 73.5 MB/s
 Direct read:  1073741824 bytes (1.1 GB) copied, 16.7439 s, 64.1 MB/s Direct read:  1073741824 bytes (1.1 GB) copied, 16.7439 s, 64.1 MB/s
Line 44: Line 46:
 </code> </code>
  
-===USB UAS attached Samsung 850 EVO 500GB SSD, attached to Intel NUC NUC6i7KYK===+====USB UAS attached Samsung 850 EVO 500GB SSD, attached to Intel NUC NUC6i7KYK====
 Benchmarking an encrypted filesystem, the speed drops to around 370MB/sec write, 430MB/sec read. Benchmarking an encrypted filesystem, the speed drops to around 370MB/sec write, 430MB/sec read.
 <code>Direct write: 2147483648 bytes (2,1 GB, 2,0 GiB) copied, 5,11402 s, 420 MB/s <code>Direct write: 2147483648 bytes (2,1 GB, 2,0 GiB) copied, 5,11402 s, 420 MB/s
Line 51: Line 53:
 </code> </code>
  
-===USB UAS attached Samsung 850 EVO 500GB SSD, attached to Lenovo X1 carbon (2015), LUKS encrypted fs===+====USB UAS attached Samsung 850 EVO 500GB SSD, attached to Lenovo X1 carbon (2015), LUKS encrypted fs====
 <code>Direct write: 1073741824 bytes (1,1 GB, 1,0 GiB) copied, 3,23224 s, 332 MB/s <code>Direct write: 1073741824 bytes (1,1 GB, 1,0 GiB) copied, 3,23224 s, 332 MB/s
 Direct read:  1073741824 bytes (1,1 GB, 1,0 GiB) copied, 3,14576 s, 341 MB/s Direct read:  1073741824 bytes (1,1 GB, 1,0 GiB) copied, 3,14576 s, 341 MB/s
simple_sequential_baseline_test.txt · Last modified: 2022/10/18 18:36 by admin