< Previous by Date Date Index Next by Date >
< Previous in Thread Thread Index Next in Thread >

Re: [reSIProcate] Random.cxx and MultiCore systems


Now that I've slept on it - I suppose that some level of parallelism would hurt this problem. Is there any chance that your application is calling the Helper functions that generate the CallIDs from more than one thread? Your results below are exactly inline with what I see on my system. I'm not convinced this is a problem.. (specifically that these results illustrate the problem). More consideration is required.

Can you rule out that you call random (via a routine that makes a callid) from more than one thread?

Thanks
Alan

On 20-Mar-08, at 10:44 , Aron Rosenberg wrote:
First run – Count was around 70
 
mp-test ~ # ./a.out
tot: 778262873
l1: 2060261465
l2: 2060261465
Aborted
 
Second Run – Count was at 400
mp-test ~ # ./a.out
tot: 4033371507
l1: 1314891622
l2: 1314891622
Aborted
 
Third Run – Count was at 130
mp-test ~ # ./a.out
tot: 1427405301
l1: 475005228
l2: 475005228
Aborted
 
mp-test ~ # ./a.out
tot: 1309167503
l1: 71029242
l2: 71029242
Aborted
 
-Aron
 
From: Alan Hawrylyshen [mailto:alan@xxxxxxxxxxxx] 
Sent: Thursday, March 20, 2008 11:39 AM
To: Aron Rosenberg
Cc: Byron Campen; resiprocate-devel
Subject: Re: [reSIProcate] Random.cxx and MultiCore systems
 
I am still quite tempted to prove what the failure is with a minimal test driver. I fear that it might be something slightly more insidious. So, once we can cause this to happen at-will, we can address the appropriate root cause. Is this something that can be checked easily? Anyone?
 
I have a test driver that fails on a dual core intel platform, gcc 4.0.1, Mac OS X 10.5.2
This will fail around the 100 mark in the progress output (but I have waited much longer).
Let it run for a while and see.
This will abort when two successive calls to random() match.
 
I would expect this to be unlikely, but should we check this on a single processor / single core system?
Does it happen more often on dual core or SMP systems?
Aron - can you try this on your platform?
Please run it a LOT and see if the time-to-run varies greatly or if it fails reliably.
 
Thanks
Alan
 
--
 
#include <stdio.h>
#include <time.h>
#include <unistd.h>
#include <stdlib.h>
#include <string.h>
 
int
main()
{
    unsigned long long t = 0;
    unsigned long l1 = (unsigned long)random();
 
    srandom(time(0));
 
    unsigned long l2 = 0UL;
    while (3)
        {
 
            l2 = (unsigned long)random();
 
            if ( l1 == l2 ){
                printf("tot: %llu\nl1: %lu\nl2: %lu\n",t,l1,l2);
                abort();
            }
            l1 = l2;
            t++;
            const int modulator = 10000000L;
            if (!(t % modulator)) {
                printf("%llu...\r",(t/modulator));
                fflush(stdout);
            }
        }
 
    return 0;
}
 
 
Alan
 
On 19-Mar-08, at 15:56 , Aron Rosenberg wrote:


The only thing that I could think of is to use the new random_r and srand_r functions instead of random and srand. The glibc _r ones force the application to keep the “seed” value which might make it immune to the caching problem.
 
The issue with this approach was that the entire Random() class is static although you could just add a class wide static variable to hold the new userland data.