Comment #15 on issue 10727 by [email protected]: Very heavy cache-access  
makes for serious performance degradation
http://code.google.com/p/chromium/issues/detail?id=10727

Some more data for the record.

 From aggregated anonymous stats:

DiskCache.ReadTime (1.0.154.53) [7_days/2009.03.25-2009.03.31]
Cutoff  Value   Min Avg ~Avg    Max Avg
98.00%  21.67   0.42    0.44    0.45
99.00%  42.81   0.70    0.74    0.77
99.50%  68.63   0.94    1.00    1.06
99.80%  115.5   1.18    1.26    1.33
99.90%  167.1   1.31    1.39    1.48
99.95%  241.4   1.39    1.49    1.59
99.99%  593.9   1.52    1.63    1.74
99.999% 3436    1.61    1.73    1.84

DiskCache.ReadTime (2.0.172.33) [7_days/2009.06.24-2009.06.30]
Cutoff  Value   Min Avg ~Avg    Max Avg
98.00%  23.84   0.55    0.57    0.59
99.00%  43.43   0.84    0.89    0.93
99.50%  67.70   1.08    1.15    1.21
99.80%  113.2   1.31    1.40    1.49
99.90%  164.5   1.44    1.53    1.63
99.95%  239.2   1.53    1.63    1.73
99.99%  598.8   1.65    1.77    1.88
99.999% 3518    1.74    1.87    1.99

The cutoff times are not significantly different in the last three months.  
However,
the average time using a given cutoff point is about 8%-20% bigger now than  
with the
old version (although even the highest value on the table is quite low:  
1.87 mS). The
cache size for most people was 80 MB with ver 1 vs 200 MB with version 2.

We'll have to wait for more precise measurements.

--
You received this message because you are listed in the owner
or CC fields of this issue, or because you starred this issue.
You may adjust your issue notification preferences at:
http://code.google.com/hosting/settings

--~--~---------~--~----~------------~-------~--~----~
Automated mail from issue updates at http://crbug.com/
Subscription options: http://groups.google.com/group/chromium-bugs
-~----------~----~----~----~------~----~------~--~---

Reply via email to