| Issue 2686: | problem with the sequential RW in the CTS | |
| 1 person starred this issue and may be notified of changes. | Back to list |
************************************************************
***** NOTE: THIS BUG TRACKER IS FOR GERRIT CODE REVIEW *****
***** DO NOT SUBMIT BUGS FOR CHROME, ANDROID, INTERNAL *****
***** ISSUES WITH YOUR COMPANY'S GERRIT SETUP, ETC. *****
***** THOSE ISSUE BELONG IN DIFFERENT ISSUE TRACKERS! *****
************************************************************
Affected Version:android-cts-4.4_r1
What is the expected output? What do you see instead?
Please provide any additional information below.
Problem : There is a problem about the item to measure
storage performance which is included in
android-cts-4.4_r1, especially the "test single
sequential update" part in sequential RW test.
In the test scenario, overwrite 6 times repeatedly
file which size is a double size of DRAM.
I think it is unfair what the file size to write &
execution time standard to pass the test is
controlled by the DRAM size.
Issue : To set the size of the file to write, standard to
figure it is unfair.
1) The sequential writing is processing directly to
underlying storage as we analyze the JAVA script
of the sequential RW test part.
The function 'rwd' actually does "write" for the
sequential RW. It acts like o_direct. DRAM is
just only the by pass while the sequential write.
2) The fuctionality or performance of the DRAM is
not used while the test is doing. It means the
test avoid the effects of the DRAM size to don't
make false good performance by the DRAM buffer.
The test scenario is focused on the storage only,
not the DRAM.
3) However, the parameter of the test is focused on
the DRAM. Thus, It is unfair things.
Request : Thus, I would like you reconsiderate the
parameters of the test and the creteria fairly to
be focused on the storage only.
May 28, 2014
Project Member
#1
edwin.ke...@gmail.com
Status:
Invalid
|
|
| ► Sign in to add a comment |