pagg
[Top] [All Lists]

Re: Possible reduced Job functionality coming - comments requested

To: Erik Jacobson <erikj@xxxxxxx>
Subject: Re: Possible reduced Job functionality coming - comments requested
From: Don Hankins <deh@xxxxxxxx>
Date: Fri, 13 Jan 2006 11:13:00 -0600
Cc: pagg@xxxxxxxxxxx
In-reply-to: <20051205195039.GA18974@xxxxxxx>
References: <20051205195039.GA18974@xxxxxxx>
Sender: pagg-bounce@xxxxxxxxxxx
User-agent: Mozilla/5.0 (X11; U; SunOS sun4u; en-US; rv:1.7.8) Gecko/20050512
Hi Erik-

Sorry for the delay in responding to this posting.  At Cray, our current
new product development plans depend on the SGI paggs open source code,
as well as CSA accounting and jobs.  We are currently basing our
operating system for future product release on SuSE SLES9 which has
already included the paggs code.   We are using the paggs code that SuSE
has included in their release, and we have added the corresponding CSA
and jobs packages to our development source tree. We fully support
having the paggs code incorporated into the kernel.org source.

As far as the specific functionality of the library calls mentioned
below, we do not have code that depends upon them.  We are depending on
having the job_getjid functionality, but performance is not a
significant issue when we are using it, since our use is merely at the
time of applications launch.

-Don Hankins


Erik Jacobson wrote:

>Some functionality in Linux Job may go away in order to make use of a 
>possible replacement for PAGG/pnotify in the kernel (task notifiers from Jack 
>Steiner if you follow lse-tech).
>
>There is opposition (not from me) to having locks in similar places that 
>PAGG/pnotify had, so operations that allow a random process to operate on the 
>Job data of another random process will no longer be available.
>
>This means these library calls may go away:
>job_detachjid
>job_detachpid
>job_attachpid
>
>These two job commands make use of the above functions and would also be
>purged:
>jattach
>jdetach
>
>Further, due to the same locking issues, looking up a JID given a PID will 
>not be as efficient.  If these operations are in any 'hot paths', performance 
>will be reduced.  I believe job_getjid calls will be the main issue here.
>
>It appears I may need to add two new library calls - a job_detach call
>that detaches the current process from a job, and a job_attach function
>that attaches the 'current' process to a supplied job.  But these
>functions would only operateon the current running process, not
>other processes on the system.
>
>I need to be aware, ASAP, if we know of any customers, companies, or
>community people  making use of functionality that may be purged or less 
>efficient.  If the functionality proposed for removal is known to be used by 
>customers or the community, it would be justification for us to push for 
>locking similar to PAGG/pnotify.  Please let me know.
>
>--
>Erik Jacobson - Linux System Software - Silicon Graphics - Eagan, Minnesota
>
>  
>


-- 
-~-~-~-~-~-~-~--~-~-~-~-~-~-~-~-~-~-~-~-~-~-~-~-~-~-
  Don Hankins   Cray Inc.,     Mendota Heights, MN
  deh@xxxxxxxx  651-605-9064   Cell: 651-428-1342
-~-~-~-~-~-~-~--~-~-~-~-~-~-~-~-~-~-~-~-~-~-~-~-~-~-
Eagles may soar, but weasels don't get sucked into
jet engines.  - Steven Wright


<Prev in Thread] Current Thread [Next in Thread>
  • Re: Possible reduced Job functionality coming - comments requested, Don Hankins <=