did you consider using oprofile?
On 07/25/2012 03:44 PM, Nadav Har'El wrote:
On Wed, Jul 25, 2012, Oleg Goldshmidt wrote about "Re: High-resolution user/system
times?":
Actually, there is the default HZ and inside the kernel HZ there is HZ that
you can configure at compile time (with CONFIG_H
On Wed, Jul 25, 2012 at 3:44 PM, Nadav Har'El wrote:
>
> USER_HZ is just used to fake the reports to user-space, pretending the
> resolution is of USER_HZ. The actual measured resolution is of
> CONFIG_HZ.
>
Yes, but all this means is that the last digit of the result you get from
times(2) or get
Reminder from years back: we would love to have a Haifux talk about timers,
time, tickless kernel, Jiffies, etc.
So if you (that's you) are reading this, and are interested in the topic,
what is a better time to learn it to depth and talk about it?
Thanks
Orna
On Wed, Jul 25, 2012 at 3:28 PM, Ole
On Wed, Jul 25, 2012, Oleg Goldshmidt wrote about "Re: High-resolution
user/system times?":
> Actually, there is the default HZ and inside the kernel HZ there is HZ that
> you can configure at compile time (with CONFIG_HZ) and USER_HZ, which, I
> think, is still 100 whether or not the kernel's HZ
On Wed, Jul 25, 2012 at 2:29 PM, Nadav Har'El wrote:
>
> HZ used to default to 100 in the Linux kernel, but now it actually
> defaults (unless I'm mis-remembering) to 250, and this is where the 4-ms
> resolution came from.
Actually, there is the default HZ and inside the kernel HZ there is HZ th
On Wed, Jul 25, 2012, Oleg Goldshmidt wrote about "Re: High-resolution
user/system times?":
> > It appears that while times(2) has a 4-ms resolution,
>
>
> Sanity check: I assume you measured it, right? Out of curiosity I did
>
> #include
> #include
> #include
>
> int main(void) {
> ret
On Wed, Jul 25, 2012, Valery Reznic wrote about "Re: High-resolution
user/system times?":
> If the process that quick why it is of such interest what time it spent in
> user space and in kernel space?
This is a CGI script, i.e., a tiny program run by a Web server to
generate a page's output. Yes
Does anyone have or know about the Chromebooks?
Does the 3G model work in Israel? The ones Amazon sells include a
contract with Verizon, which is CDMA and not GSM, so it looks like they
don't. Anyone know for sure?
Does the operating system support a netstick? (USB cellular modem).
Ubuntu doe
On Wed, Jul 25, 2012 at 11:07 AM, Nadav Har'El wrote:
> On Wed, Jul 25, 2012, Nadav Har'El wrote about "High-resolution
> user/system times?":
> > I'm now trying to measure a process running around 3 milliseconds, less
> > than one jiffy, and I still want to understand how much of it is spent in
>
Hi Ohad,
I switched to Chef because I moved to a new company (Wix) which already uses
Chef :-)
Both Chef and Puppet have different advantages and disadvantages, but they are
both improving rapidly.
I'd be interested in a devops event and Wix is usually up for hosting tech
talks, if you need a
Not really suggestion, but anyway...
If the process that quick why it is of such interest what time it spent in user
space and in kernel space?
Valery
>
> From: Oleg Goldshmidt
>To: Nadav Har'El
>Cc: linux-il@cs.huji.ac.il
>Sent: Wednesday, July 25, 2012 1
On Wed, Jul 25, 2012 at 11:15 AM, Nadav Har'El wrote:
> On Wed, Jul 25, 2012, Oleg Goldshmidt wrote about "Re: High-resolution
> user/system times?":
> > > Hi, as you know the time(1) command, and the times(2) system call is
> > > able to separate a process's running time into "user" and "system"
On Wed, Jul 25, 2012, Oleg Goldshmidt wrote about "Re: High-resolution
user/system times?":
> > Hi, as you know the time(1) command, and the times(2) system call is
> > able to separate a process's running time into "user" and "system" time,
> > measuring the CPU time in user space and kernel spac
On Wed, Jul 25, 2012, Nadav Har'El wrote about "High-resolution user/system
times?":
> I'm now trying to measure a process running around 3 milliseconds, less
> than one jiffy, and I still want to understand how much of it is spent in
> user space, and how much of it is spent in kernel space (e.g.
On Wed, Jul 25, 2012 at 10:09 AM, Nadav Har'El wrote:
> Hi, as you know the time(1) command, and the times(2) system call is
> able to separate a process's running time into "user" and "system" time,
> measuring the CPU time in user space and kernel space respectively.
>
> However, these only have
On Wed, Jul 25, 2012 at 10:09 AM, Nadav Har'El wrote:
> Hi, as you know the time(1) command, and the times(2) system call is
> able to separate a process's running time into "user" and "system" time,
> measuring the CPU time in user space and kernel space respectively.
>
> However, these only have
I remember doing this some ~15 years ago, simply by emitting RDTSC
instructions into my C code (RDTSC == Read Time Stamp Counter).
This was done with Watcom C under DOS though.
http://en.wikipedia.org/wiki/Time_Stamp_Counter
On Wed, Jul 25, 2012 at 10:09 AM, Nadav Har'El wrote:
> Hi, as you kno
A quick Google search ended with this -
http://serverfault.com/questions/151109/bash-how-do-i-get-current-unix-time-in-milliseconds
,
so maybe running 'date +%s%N | cut -b1-13' before starting the process and
after it's finished will help...
Ori
On Wed, Jul 25, 2012 at 10:09 AM, Nadav Har'El wrot
Hi, as you know the time(1) command, and the times(2) system call is
able to separate a process's running time into "user" and "system" time,
measuring the CPU time in user space and kernel space respectively.
However, these only have a jiffy (often 1/250 seconds) resultion.
I'm now trying to mea
19 matches
Mail list logo
