On Thu, Apr 16, 2009 at 4:07 PM, Peter Tribble wrote:
> On Tue, Apr 7, 2009 at 8:25 PM, Jason King wrote:
>> To get around the hurdle of all kstats being effectively private,
>> which in turn makes it difficult to effectively build any sort of
>> tools that use them,
>
> That hasn't stopped plent
Ted,
The thisrun.f file looks fine. It is not ignoring runtime, as it is
putting in a "sleep 60", which does causes it to run for 60 seconds. It
sounds like go_filebench isn't running at all. You might try running
thisrun.f directly from the shell:
$thisrun.f
See what happens. You do have
Same here. Trained to reply and not reply-all.
Begin forwarded message:
From: Erik O'Shaughnessy
Date: 16 April, 2009 4:43:26 PM CDT
To: Jason King
Subject: Re: [perf-discuss] kstat stability tags
On 16 Apr, at 4:21 PM, Jason King wrote:
On Thu, Apr 16, 2009 at 4:07 PM, Peter Tribble > wr
Forgot to send this to the list as well. Whoops
Begin forwarded message:
From: Erik O'Shaughnessy
Date: 16 April, 2009 11:44:24 AM CDT
To: Jason King
Subject: Re: [perf-discuss] kstat stability tags
On 16 Apr, at 12:04 AM, Jason King wrote:
On Wed, Apr 15, 2009 at 11:22 PM, Erik O'Shaughn
I have filebench 1.4.4 compiled (32-bit with gcc 4.3.3) on Solaris 10, and
go_filebench seems to be working fine. However, the batch mode runs and
immediately returns without runnning anything. It seems as if the runtime
variable is ignored, but I'm not seeing any error messages.
bash-3.00$ fil
On Thu, Apr 16, 2009 at 4:07 PM, Peter Tribble wrote:
> On Tue, Apr 7, 2009 at 8:25 PM, Jason King wrote:
>> To get around the hurdle of all kstats being effectively private,
>> which in turn makes it difficult to effectively build any sort of
>> tools that use them,
>
> That hasn't stopped plent
On Thu, Apr 16, 2009 at 6:04 AM, Jason King wrote:
> Well one thing I wasn't sure about -- that means each instance could
> potentially have it's own stability. I'm not a kstat expert, but for
> foo:0:stat to have one stability level and foo:1:stat to have a
> different stability seems odd to me.
On Tue, Apr 7, 2009 at 8:25 PM, Jason King wrote:
> To get around the hurdle of all kstats being effectively private,
> which in turn makes it difficult to effectively build any sort of
> tools that use them,
That hasn't stopped plenty of tools being developed, though.
> I'm proposing adding sta
