Possible evidence of performance regression for 8.1-S (vs. 7.1)
Mike Tancsa
mike at sentex.net
Wed Oct 27 19:36:46 UTC 2010
At 01:05 PM 10/27/2010, Mike Tancsa wrote:
>At 12:34 PM 10/27/2010, David Wolfskill wrote:
>
>>* release/7.1.0, with the following merged in:
>> r186860 from stable/7
>> r190970 from stable/7
>> r203072 from head
>> r209964 from stable/7
>> and using the MAC kernel config
>>
>>* stable/8 @r214029 using the GENERIC kernel config
>
>OK.
>I was using GENERIC vs GENERIC from RELENG7 and RELENG8 from
>today. MAC is in by default in RELENG_8
I ran the file io tests again 5 times
RELENG7,
Operations performed: 6000 Read, 4000 Write, 12672 Other = 22672 Total
Read 93.75Mb Written 62.5Mb Total transferred 156.25Mb (6.1136Mb/sec)
391.27 Requests/sec executed
Test execution summary:
total time: 25.5578s
total number of events: 10000
total time taken by event execution: 12.0346
per-request statistics:
min: 0.01ms
avg: 1.20ms
max: 101.39ms
approx. 95 percentile: 4.77ms
Threads fairness:
events (avg/stddev): 625.0000/97.89
execution time (avg/stddev): 0.7522/0.15
RELENG7
times for 5 runs
25.5578
26.5351
25.5734
27.0934
26.6094
RELENG8, ATA driver
times for 5 runs
28.9372
27.3766
29.3507
28.3406
28.0904
RELENG7 throughput (MB/s)
6.1136
5.8884
6.1099
5.7671
5.8720
RELENG_8 ATA throughput (MB/s)
5.3996
5.7074
5.3236
5.5133
5.5624
ministat -s -w 60 7 8
x 7
+ 8
+------------------------------------------------------------+
|+ + + + + x xx x|
| |______M____A__________| |
| |__________AM_________| |
+------------------------------------------------------------+
N Min Max Median Avg Stddev
x 5 5.7671 6.1136 5.8884 5.9502 0.15464778
+ 5 5.3236 5.7074 5.5133 5.50126 0.1485552
Difference at 95.0% confidence
-0.44894 +/- 0.221147
-7.54496% +/- 3.71663%
(Student's t, pooled s = 0.151632)
--------------------------------------------------------------------
Mike Tancsa, tel +1 519 651 3400
Sentex Communications, mike at sentex.net
Providing Internet since 1994 www.sentex.net
Cambridge, Ontario Canada www.sentex.net/mike
More information about the freebsd-performance
mailing list