dtrace discuss - Oct 2010 - save and recall more than one value of the same thread

Hi,

I''d like to know if D enables to save and recall values of the same
thread in a way like self->... does.

Let''s say a thread fires syscall::open:entry two times and gets 2
filedescriptors. How could I save those in syscall::open:return for later reuse?
The use of just 1 variable (e.g.self->fd) only would overwrite the value at
the 2nd call. Maybe an associative array would tend to a solution, like
self->fd[port] = ...  ?
And how could I evaluate them in a predicate of another probe?


thank you,

goinsane
-- 
This message posted from opensolaris.org

On 26.10.10 15:32, goinsane wrote:
> Hi,
>
> I''d like to know if D enables to save and recall values of the
same thread in a way like self->... does.
>
> Let''s say a thread fires syscall::open:entry two times and gets 2
filedescriptors. How could I save those in syscall::open:return for later reuse?
> The use of just 1 variable (e.g.self->fd) only would overwrite the value
at the 2nd call. Maybe an associative array would tend to a solution, like
self->fd[port] = ...  ?
> And how could I evaluate them in a predicate of another probe?
how about storing what interests you about this fd in
self->stuff[self->fd]
(where I assume self->fd is the "current" fd being opened)? would
that work
for your app?

Michael
-- 
michael.schuster at oracle.com	http://blogs.sun.com/recursion
Recursion, n.: see ''Recursion''

goinsane wrote:
> Hi,
> 
> I''d like to know if D enables to save and recall values of the
same thread in a way like self->... does.
> 
> Let''s say a thread fires syscall::open:entry two times and gets 2
filedescriptors. How could I save those in syscall::open:return for later reuse?
> The use of just 1 variable (e.g.self->fd) only would overwrite the value
at the 2nd call. Maybe an associative array would tend to a solution, like
self->fd[port] = ...  ?
Yep; that''s how you''d do it.

Note that this might not work quite the way you want for multi-threaded
programs that use the same fd in more than one thread.  To handle that
case (which is a superset of the case you''re looking at), I think
you''d
need a global array indexed on pid and fd, because fds are allocated to
a process, not a thread, and D doesn''t seem to have a per-process
storage mechanism.
> And how could I evaluate them in a predicate of another probe?
self->fd[port] -- where "port" needs to be the fd.  Depending on
the
definition of the probe and the way you write your code, "port" might
be
argv0, or it might be self->port, or perhaps something else.

-- 
James Carlson         42.703N 71.076W         <carlsonj at
workingcode.com>

yes, it does. thank you!
-- 
This message posted from opensolaris.org

Thank you again for assistance, James. Actually, there was another thread
accessing the fd too, so the global array did work for me.
-- 
This message posted from opensolaris.org