On 10/10/11 05:53, Brian Bockelman wrote:
>
> On Oct 10, 2011, at 5:41 AM, Andrew Hanushevsky wrote:
>
>>
>>
>> On Sun, 9 Oct 2011, Matevz Tadel wrote:
>>>>> In our experience, without the very detailed I/O monitoring, we:
>>>>> 1) Don't get any monitoring for a client that crashes (disconnects without a
>>>>> close).
>>>> That information can be put in the summary record, if need be. I say need be
>>>> because it's a relatively rare event (yes, it does happen in spurts).
>>>
>>> There could be a separate "close on disconnect" trace type that is sent in this case and includes all the information usually associated with close.
>> Sorry, I didn't make myself clear. In the summary record we could supply how many forced close events there were. What you say is along the lines of what I was talking about, indicating whether the close was real or forced. The "manual close" on disconnect is the appropriate action in the collector in any case.
>>
>
> Matevz - you now have statistics on this, yes? Can we count the percentage of file accesses in the last week that resulted in a force close?
It's about 4.5% ... some part of that could be me running xrdcp and then
Ctrl-C-ing it :)
Matevz
|