GPU not receiving tasks when CPU computing disabled

Message boards : Questions and problems : GPU not receiving tasks when CPU computing disabled
Message board moderation

To post messages, you must log in.

Previous · 1 · 2 · 3 · 4 · 5 · Next

AuthorMessage
goben_2003

Send message
Joined: 29 Apr 21
Posts: 50
Message 104253 - Posted: 2 May 2021, 16:27:06 UTC - in response to Message 104248.  

OK, now we're sucking diesel - or diesel fumes, at any rate.

02/05/2021 16:12:11 | World Community Grid | Sending scheduler request: Project initialization.
02/05/2021 16:12:11 | World Community Grid | Requesting new tasks for CPU and Intel GPU
02/05/2021 16:12:12 | World Community Grid | Scheduler request completed: got 0 new tasks
02/05/2021 16:12:12 | World Community Grid | No tasks are available for OpenPandemics - COVID-19 - GPU
02/05/2021 16:12:12 | World Community Grid | Tasks for CPU are available, but your preferences are set to not accept them
02/05/2021 16:12:12 | World Community Grid | Tasks for NVIDIA GPU are available, but your preferences are set to not accept them
02/05/2021 16:12:12 | World Community Grid | Tasks for AMD/ATI GPU are available, but your preferences are set to not accept them
02/05/2021 16:12:12 | World Community Grid | Project requested delay of 121 seconds
02/05/2021 16:12:12 | World Community Grid | General prefs: from World Community Grid (last modified 02-May-2021 14:35:25)
02/05/2021 16:12:12 | World Community Grid | Computer location: home
02/05/2021 16:14:15 | World Community Grid | Sending scheduler request: To fetch work.
02/05/2021 16:14:15 | World Community Grid | Requesting new tasks for Intel GPU
02/05/2021 16:14:15 | World Community Grid | [sched_op] CPU work request: 0.00 seconds; 0.00 devices
02/05/2021 16:14:15 | World Community Grid | [sched_op] Intel GPU work request: 9504.00 seconds; 1.00 devices
02/05/2021 16:14:16 | World Community Grid | Scheduler request completed: got 0 new tasks
So far, so bad. I'll keep trying a few different combinations.

This is a combination I had not tried: only having intel GPU enabled, not CPU or NVIDIA or AMD/ATI.
ID: 104253 · Report as offensive
goben_2003

Send message
Joined: 29 Apr 21
Posts: 50
Message 104254 - Posted: 2 May 2021, 16:27:15 UTC - in response to Message 104251.  

And we have lift-off:

02/05/2021 16:46:08 | World Community Grid | Computer location: school
02/05/2021 16:48:10 | World Community Grid | [sched_op] Starting scheduler request
02/05/2021 16:48:12 | World Community Grid | Sending scheduler request: To fetch work.
02/05/2021 16:48:12 | World Community Grid | Requesting new tasks for CPU and Intel GPU
02/05/2021 16:48:12 | World Community Grid | [sched_op] CPU work request: 28512.00 seconds; 3.00 devices
02/05/2021 16:48:12 | World Community Grid | [sched_op] Intel GPU work request: 9504.00 seconds; 1.00 devices
02/05/2021 16:48:13 | World Community Grid | Scheduler request completed: got 4 new tasks
02/05/2021 16:48:13 | World Community Grid | [sched_op] estimated total CPU task duration: 30176 seconds
02/05/2021 16:48:13 | World Community Grid | [sched_op] estimated total Intel GPU task duration: 5119 seconds

Did you only get tasks when the CPU was enabled?

Or maybe not:

02/05/2021 16:50:16 | World Community Grid | Sending scheduler request: To fetch work.
02/05/2021 16:50:16 | World Community Grid | Requesting new tasks for CPU and Intel GPU
02/05/2021 16:50:16 | World Community Grid | [sched_op] CPU work request: 8724.32 seconds; 0.85 devices
02/05/2021 16:50:16 | World Community Grid | [sched_op] Intel GPU work request: 4439.86 seconds; 0.00 devices
02/05/2021 16:50:17 | World Community Grid | Scheduler request completed: got 0 new tasks
02/05/2021 16:50:17 | World Community Grid | No tasks are available for the applications you have selected.

I would take this as the case you mentioned before. Meaning where the scheduler happens to not have work(for the CPU or intel GPU with whichever wcg projects are selected) at the precise time when you requested it.
I think that is from sched_send.cpp L1295 in the "if client asked for work and we're not sending any, explain why" section:
        if (g_wreq->no_allowed_apps_available) {
            g_reply->insert_message(
                _("No tasks are available for the applications you have selected."),
                "low"
            );
ID: 104254 · Report as offensive
Richard Haselgrove
Volunteer tester
Help desk expert

Send message
Joined: 5 Oct 06
Posts: 5077
United Kingdom
Message 104256 - Posted: 2 May 2021, 16:31:40 UTC - in response to Message 104254.  

I would take this as the case you mentioned before. Meaning where the scheduler happens to not have work(for the CPU or intel GPU with whichever wcg projects are selected) at the precise time when you requested it.
I think that is from sched_send.cpp L1295 in the "if client asked for work and we're not sending any, explain why" section:
        if (g_wreq->no_allowed_apps_available) {
            g_reply->insert_message(
                _("No tasks are available for the applications you have selected."),
                "low"
            );
The problem with that one is that it's so badly implemented (at all projects, not just WCG) that it chucks out every possible excuse. That last 17:21 reply, in full, was:

02/05/2021 17:21:45 | World Community Grid | No tasks sent
02/05/2021 17:21:45 | World Community Grid | No tasks are available for OpenPandemics - COVID 19
02/05/2021 17:21:45 | World Community Grid | No tasks are available for OpenPandemics - COVID-19 - GPU
02/05/2021 17:21:45 | World Community Grid | Tasks for NVIDIA GPU are available, but your preferences are set to not accept them
02/05/2021 17:21:45 | World Community Grid | Tasks for AMD/ATI GPU are available, but your preferences are set to not accept them
02/05/2021 17:21:45 | World Community Grid | This computer has reached a limit on tasks in progress
02/05/2021 17:21:45 | World Community Grid | Project has no tasks available
02/05/2021 17:21:45 | World Community Grid | Project requested delay of 121 seconds
Take your choice: the final one is usually the most reliable.
ID: 104256 · Report as offensive
Richard Haselgrove
Volunteer tester
Help desk expert

Send message
Joined: 5 Oct 06
Posts: 5077
United Kingdom
Message 104257 - Posted: 2 May 2021, 16:37:27 UTC

Kevin just said:

There are between 40-48 hours of work left to be run at the current pace of the stress test (so around Tuesday 12:00 UTC +/- 3-4 hours).
Good thing tomorrow is a public holiday in the UK - and forecast to be very wet. I can stay indoors and keep trying.
ID: 104257 · Report as offensive
goben_2003

Send message
Joined: 29 Apr 21
Posts: 50
Message 104258 - Posted: 2 May 2021, 16:51:26 UTC - in response to Message 104252.  

But I can't get beyond here. Computer is a quad-core plus iGPU: I wanted to run 3xCPU + iGPU, but instead I've got 2xCPU (both running) and 4xiGPU (one running). And

02/05/2021 17:21:05 | World Community Grid | Computer location: school
02/05/2021 17:21:05 | | Number of usable CPUs has changed from 3 to 4.
02/05/2021 17:21:44 | World Community Grid | [sched_op] CPU work request: 17544.75 seconds; 1.85 devices
02/05/2021 17:21:44 | World Community Grid | [sched_op] Intel GPU work request: 0.00 seconds; 0.00 devices
02/05/2021 17:21:45 | World Community Grid | No tasks sent
02/05/2021 17:21:45 | World Community Grid | This computer has reached a limit on tasks in progress
Do we know that limit?

Other than it being from Job Limits, we have observations but not an explicit declaration from WCG.
ID: 104258 · Report as offensive
goben_2003

Send message
Joined: 29 Apr 21
Posts: 50
Message 104259 - Posted: 2 May 2021, 17:03:19 UTC - in response to Message 104256.  

I would take this as the case you mentioned before. Meaning where the scheduler happens to not have work(for the CPU or intel GPU with whichever wcg projects are selected) at the precise time when you requested it.
I think that is from sched_send.cpp L1295 in the "if client asked for work and we're not sending any, explain why" section:
        if (g_wreq->no_allowed_apps_available) {
            g_reply->insert_message(
                _("No tasks are available for the applications you have selected."),
                "low"
            );
The problem with that one is that it's so badly implemented (at all projects, not just WCG) that it chucks out every possible excuse. That last 17:21 reply, in full, was:

02/05/2021 17:21:45 | World Community Grid | No tasks sent
02/05/2021 17:21:45 | World Community Grid | No tasks are available for OpenPandemics - COVID 19
02/05/2021 17:21:45 | World Community Grid | No tasks are available for OpenPandemics - COVID-19 - GPU
02/05/2021 17:21:45 | World Community Grid | Tasks for NVIDIA GPU are available, but your preferences are set to not accept them
02/05/2021 17:21:45 | World Community Grid | Tasks for AMD/ATI GPU are available, but your preferences are set to not accept them
02/05/2021 17:21:45 | World Community Grid | This computer has reached a limit on tasks in progress
02/05/2021 17:21:45 | World Community Grid | Project has no tasks available
02/05/2021 17:21:45 | World Community Grid | Project requested delay of 121 seconds
Take your choice: the final one is usually the most reliable.

I could be following the code wrong, but I think that both of those can be true.
The computer has reached a limit on tasks in progress is from either the per host or per processor type being exceeded
sched_types.h
    bool max_jobs_exceeded() {
        if (max_jobs_on_host_exceeded) return true;
        for (int i=0; i<NPROC_TYPES; i++) {
            if (max_jobs_on_host_proc_type_exceeded[i]) return true;
        }
        return false;
    }


No tasks available - Either it was not ready or it searched through wu_results and did not find any available.
shmem.cpp L328
// see if there's any work.
// If there is, reserve it for this process
// (if we don't do this, there's a race condition where lots
// of servers try to get a single work item)
//
bool SCHED_SHMEM::no_work(int pid) {
    if (!ready) return true;
    for (int i=0; i<max_wu_results; i++) {
        if (wu_results[i].state == WR_STATE_PRESENT) {
            wu_results[i].state = pid;
            return false;
        }
    }
    return true;
}
ID: 104259 · Report as offensive
Richard Haselgrove
Volunteer tester
Help desk expert

Send message
Joined: 5 Oct 06
Posts: 5077
United Kingdom
Message 104260 - Posted: 2 May 2021, 17:18:16 UTC - in response to Message 104259.  

The 'school' venue is one I usually reserve for an Android tablet to run CPU tasks. It was set to maximum 2 tasks in WCG device profiles, but by 17:21 I'd realised that and removed the restriction. The only limit I can think of after that would be 'four per (intel) GPU', which has never been mentioned, and I think I've seen exceeded on 'big' machines.
ID: 104260 · Report as offensive
goben_2003

Send message
Joined: 29 Apr 21
Posts: 50
Message 104261 - Posted: 2 May 2021, 17:29:11 UTC

By the way, I noticed something while looking in sched_send.cpp. Take a look and see if what you think.
This is from sched_send.cpp L1645
I apologize for the formatting, I chose quote so I could bold where the order of send_work_{old | locality} is in relation to the rest.
This part seems fine:
if (drand() < config.locality_scheduler_fraction) {
if (config.debug_locality) {
log_messages.printf(MSG_NORMAL,
"[mixed] sending locality work first\n"
);
}
send_work_locality();

// save 'insufficient' flags from the first scheduler
bool disk_insufficient = g_wreq->disk.insufficient;
bool speed_insufficient = g_wreq->speed.insufficient;
bool mem_insufficient = g_wreq->mem.insufficient;
bool no_allowed_apps_available = g_wreq->no_allowed_apps_available;

// reset 'insufficient' flags for the second scheduler
g_wreq->disk.insufficient = false;
g_wreq->speed.insufficient = false;
g_wreq->mem.insufficient = false;
g_wreq->no_allowed_apps_available = false;

if (config.debug_locality) {
log_messages.printf(MSG_NORMAL,
"[mixed] sending non-locality work second\n"
);
}
send_work_old();

// recombine the 'insufficient' flags from the two schedulers
g_wreq->disk.insufficient = g_wreq->disk.insufficient && disk_insufficient;
g_wreq->speed.insufficient = g_wreq->speed.insufficient && speed_insufficient;
g_wreq->mem.insufficient = g_wreq->mem.insufficient && mem_insufficient;
g_wreq->no_allowed_apps_available = g_wreq->no_allowed_apps_available && no_allowed_apps_available;

}

However this one does not:
else {
if (config.debug_locality) {
log_messages.printf(MSG_NORMAL,
"[mixed] sending non-locality work first\n"
);
}

// save 'insufficient' flags from the first scheduler
bool disk_insufficient = g_wreq->disk.insufficient;
bool speed_insufficient = g_wreq->speed.insufficient;
bool mem_insufficient = g_wreq->mem.insufficient;
bool no_allowed_apps_available = g_wreq->no_allowed_apps_available;

// reset 'insufficient' flags for the second scheduler
g_wreq->disk.insufficient = false;
g_wreq->speed.insufficient = false;
g_wreq->mem.insufficient = false;
g_wreq->no_allowed_apps_available = false;

send_work_old();
if (config.debug_locality) {
log_messages.printf(MSG_NORMAL,
"[mixed] sending locality work second\n"
);
}
send_work_locality();

// recombine the 'insufficient' flags from the two schedulers
g_wreq->disk.insufficient = g_wreq->disk.insufficient && disk_insufficient;
g_wreq->speed.insufficient = g_wreq->speed.insufficient && speed_insufficient;
g_wreq->mem.insufficient = g_wreq->mem.insufficient && mem_insufficient;
g_wreq->no_allowed_apps_available = g_wreq->no_allowed_apps_available && no_allowed_apps_available;

}

Notice how it says it is saving the 'insufficient' flags from the first scheduler, but it calls the first scheduler after it saves the flags.
I am not saying it is affecting us in this case as I do not know how config.locality_scheduling, config.sched_old, or config.locality_scheduler_fraction are set. Also if we do get to this section, it appears that the effect would be to always have the 'insufficient' flags as false when the drand() sends it to the second part. Thus making the "No tasks are available for the applications you have selected." not show up even if it should be true.
ID: 104261 · Report as offensive
goben_2003

Send message
Joined: 29 Apr 21
Posts: 50
Message 104262 - Posted: 2 May 2021, 17:36:58 UTC - in response to Message 104258.  

But I can't get beyond here. Computer is a quad-core plus iGPU: I wanted to run 3xCPU + iGPU, but instead I've got 2xCPU (both running) and 4xiGPU (one running). And

02/05/2021 17:21:05 | World Community Grid | Computer location: school
02/05/2021 17:21:05 | | Number of usable CPUs has changed from 3 to 4.
02/05/2021 17:21:44 | World Community Grid | [sched_op] CPU work request: 17544.75 seconds; 1.85 devices
02/05/2021 17:21:44 | World Community Grid | [sched_op] Intel GPU work request: 0.00 seconds; 0.00 devices
02/05/2021 17:21:45 | World Community Grid | No tasks sent
02/05/2021 17:21:45 | World Community Grid | This computer has reached a limit on tasks in progress
Do we know that limit?

Other than it being from Job Limits, we have observations but not an explicit declaration from WCG.

I was mistaken before. This can be from the config.xml limits or the user's project preferences.
sched_types.h L492
    bool max_jobs_exceeded() {
        if (max_jobs_on_host_exceeded) return true;
        for (int i=0; i<NPROC_TYPES; i++) {
            if (max_jobs_on_host_proc_type_exceeded[i]) return true;
        }
        return false;
    }

sched_send.cpp L783
    // check user-specified project prefs limit on # of jobs in progress
    //
    int mj = g_wreq->project_prefs.max_jobs_in_progress;
    if (mj && config.max_jobs_in_progress.project_limits.total.njobs >= mj) {
        if (config.debug_send) {
            log_messages.printf(MSG_NORMAL,
                "[send] user project preferences job limit exceeded\n"
            );
        }
        g_wreq->max_jobs_on_host_exceeded = true;
        return false;
    }
<snip>
    if (!some_type_allowed) {
        if (config.debug_send) {
            log_messages.printf(MSG_NORMAL,
                "[send] config.xml max_jobs_in_progress limit exceeded\n"
            );
        }
        g_wreq->max_jobs_on_host_exceeded = true;
        return false;
    }
ID: 104262 · Report as offensive
goben_2003

Send message
Joined: 29 Apr 21
Posts: 50
Message 104263 - Posted: 2 May 2021, 17:40:15 UTC - in response to Message 104260.  

The 'school' venue is one I usually reserve for an Android tablet to run CPU tasks. It was set to maximum 2 tasks in WCG device profiles, but by 17:21 I'd realised that and removed the restriction. The only limit I can think of after that would be 'four per (intel) GPU', which has never been mentioned, and I think I've seen exceeded on 'big' machines.

Yes, I have gotten a lot more than four intel gpu units. When I set the limit to 50 and did any of the 3 things I mentioned earlier to get intel gpu tasks, it kept getting them until it got to the limit of 50 that I set in the wcg profile.
(I have seen it get much higher, but I have avoided trying to figure out why as it is harder to chase 2 potential scheduler issues at the same time).
ID: 104263 · Report as offensive
goben_2003

Send message
Joined: 29 Apr 21
Posts: 50
Message 104264 - Posted: 2 May 2021, 17:43:45 UTC - in response to Message 104257.  

Kevin just said:

There are between 40-48 hours of work left to be run at the current pace of the stress test (so around Tuesday 12:00 UTC +/- 3-4 hours).
Good thing tomorrow is a public holiday in the UK - and forecast to be very wet. I can stay indoors and keep trying.

Happy May Day! :)

If the end of work is that soon, is it time to post about the intel_gpu issue in the WCG forums? Or did you want to do some more testing first?
ID: 104264 · Report as offensive
Richard Haselgrove
Volunteer tester
Help desk expert

Send message
Joined: 5 Oct 06
Posts: 5077
United Kingdom
Message 104265 - Posted: 2 May 2021, 17:45:31 UTC - in response to Message 104262.  

This can be from the config.xml limits or the user's project preferences.
Indeed. I was caught out initially (I don't usually use project preferences for that), but I'd corrected it by then - and the limit is still being applied. First iGPU task still has 45 minutes to run - we'll see what happens then.
ID: 104265 · Report as offensive
Richard Haselgrove
Volunteer tester
Help desk expert

Send message
Joined: 5 Oct 06
Posts: 5077
United Kingdom
Message 104266 - Posted: 2 May 2021, 17:49:59 UTC - in response to Message 104264.  

If the end of work is that soon, is it time to post about the intel_gpu issue in the WCG forums? Or did you want to do some more testing first?
It's not the end of work, just the end of the stress test. Then back to a trickle of 2,000 every half hour, or whatever it was. I'd imagine they'd want to process the resulting server load issues first: I'd imagine it'll be better to wait until we have a constructive diagnosis to pass on.
ID: 104266 · Report as offensive
goben_2003

Send message
Joined: 29 Apr 21
Posts: 50
Message 104267 - Posted: 2 May 2021, 17:55:25 UTC - in response to Message 104266.  

If the end of work is that soon, is it time to post about the intel_gpu issue in the WCG forums? Or did you want to do some more testing first?
It's not the end of work, just the end of the stress test. Then back to a trickle of 2,000 every half hour, or whatever it was. I'd imagine they'd want to process the resulting server load issues first: I'd imagine it'll be better to wait until we have a constructive diagnosis to pass on.

Sorry, I meant the end of near constant work availability. Having work constantly available enabled me to run tests and replicate the issue on command repeatedly.
ID: 104267 · Report as offensive
Richard Haselgrove
Volunteer tester
Help desk expert

Send message
Joined: 5 Oct 06
Posts: 5077
United Kingdom
Message 104268 - Posted: 2 May 2021, 18:06:52 UTC - in response to Message 104267.  

Having work constantly available enabled me to run tests and replicate the issue on command repeatedly.
We have scripts for that now!. Also, I converted one of the early Betas to run offline at a command prompt, which removed the dependency on new work.
ID: 104268 · Report as offensive
Richard Haselgrove
Volunteer tester
Help desk expert

Send message
Joined: 5 Oct 06
Posts: 5077
United Kingdom
Message 104269 - Posted: 2 May 2021, 18:18:37 UTC
Last modified: 2 May 2021, 18:29:14 UTC

Now I'm up to five iGPU tasks:

02/05/2021 19:06:44 | World Community Grid | Sending scheduler request: To fetch work.
02/05/2021 19:06:44 | World Community Grid | Requesting new tasks for CPU and Intel GPU
02/05/2021 19:06:44 | World Community Grid | [sched_op] CPU work request: 11778.07 seconds; 0.85 devices
02/05/2021 19:06:44 | World Community Grid | [sched_op] Intel GPU work request: 1093.86 seconds; 0.00 devices
02/05/2021 19:06:45 | World Community Grid | Scheduler request completed: got 1 new tasks
02/05/2021 19:06:45 | World Community Grid | [sched_op] estimated total CPU task duration: 0 seconds
02/05/2021 19:06:45 | World Community Grid | [sched_op] estimated total Intel GPU task duration: 2559 seconds
Though the first is due to finish in about five minutes.

Edit - iGPU completed and reported, and I got my third CPU task in return. No configuration changes in the last two hours.

02/05/2021 19:26:05 | World Community Grid | Reporting 1 completed tasks
02/05/2021 19:26:05 | World Community Grid | Requesting new tasks for CPU
02/05/2021 19:26:05 | World Community Grid | [sched_op] CPU work request: 13271.04 seconds; 0.85 devices
02/05/2021 19:26:05 | World Community Grid | [sched_op] Intel GPU work request: 0.00 seconds; 0.00 devices
02/05/2021 19:26:06 | World Community Grid | Scheduler request completed: got 1 new tasks
02/05/2021 19:26:06 | World Community Grid | [sched_op] estimated total CPU task duration: 15263 seconds
02/05/2021 19:26:06 | World Community Grid | [sched_op] estimated total Intel GPU task duration: 0 seconds
ID: 104269 · Report as offensive
goben_2003

Send message
Joined: 29 Apr 21
Posts: 50
Message 104270 - Posted: 2 May 2021, 18:36:59 UTC - in response to Message 104269.  

Now I'm up to five iGPU tasks:

02/05/2021 19:06:44 | World Community Grid | Sending scheduler request: To fetch work.
02/05/2021 19:06:44 | World Community Grid | Requesting new tasks for CPU and Intel GPU
02/05/2021 19:06:44 | World Community Grid | [sched_op] CPU work request: 11778.07 seconds; 0.85 devices
02/05/2021 19:06:44 | World Community Grid | [sched_op] Intel GPU work request: 1093.86 seconds; 0.00 devices
02/05/2021 19:06:45 | World Community Grid | Scheduler request completed: got 1 new tasks
02/05/2021 19:06:45 | World Community Grid | [sched_op] estimated total CPU task duration: 0 seconds
02/05/2021 19:06:45 | World Community Grid | [sched_op] estimated total Intel GPU task duration: 2559 seconds
Though the first is due to finish in about five minutes.

Edit - iGPU completed and reported, and I got my third CPU task in return. No configuration changes in the last two hours.

02/05/2021 19:26:05 | World Community Grid | Reporting 1 completed tasks
02/05/2021 19:26:05 | World Community Grid | Requesting new tasks for CPU
02/05/2021 19:26:05 | World Community Grid | [sched_op] CPU work request: 13271.04 seconds; 0.85 devices
02/05/2021 19:26:05 | World Community Grid | [sched_op] Intel GPU work request: 0.00 seconds; 0.00 devices
02/05/2021 19:26:06 | World Community Grid | Scheduler request completed: got 1 new tasks
02/05/2021 19:26:06 | World Community Grid | [sched_op] estimated total CPU task duration: 15263 seconds
02/05/2021 19:26:06 | World Community Grid | [sched_op] estimated total Intel GPU task duration: 0 seconds

This seems to be behaving as expected - CPU and Intel GPU computing is enabled and you get both CPU and Intel GPU. Since I set my test machine back to stock boinc this morning(almost 13 hours ago) it has not gotten Intel GPU tasks.
ID: 104270 · Report as offensive
Richard Haselgrove
Volunteer tester
Help desk expert

Send message
Joined: 5 Oct 06
Posts: 5077
United Kingdom
Message 104271 - Posted: 2 May 2021, 18:43:22 UTC - in response to Message 104270.  

This seems to be behaving as expected - CPU and Intel GPU computing is enabled and you get both CPU and Intel GPU. Since I set my test machine back to stock boinc this morning(almost 13 hours ago) it has not gotten Intel GPU tasks.
Are you running any sort of 'retry' automation? Otherwise, the backoffs will cut you down to very few requests.
ID: 104271 · Report as offensive
goben_2003

Send message
Joined: 29 Apr 21
Posts: 50
Message 104272 - Posted: 2 May 2021, 18:51:18 UTC - in response to Message 104271.  

This seems to be behaving as expected - CPU and Intel GPU computing is enabled and you get both CPU and Intel GPU. Since I set my test machine back to stock boinc this morning(almost 13 hours ago) it has not gotten Intel GPU tasks.
Are you running any sort of 'retry' automation? Otherwise, the backoffs will cut you down to very few requests.

Affirmative, otherwise the backoffs would be even worse with the extra under sea cables I have to go through.
ID: 104272 · Report as offensive
goben_2003

Send message
Joined: 29 Apr 21
Posts: 50
Message 104273 - Posted: 2 May 2021, 18:56:56 UTC

I restarted it into the mode where is sets the work_req to the highest req_secs (without it being anonymous platform)
Here are the last 2 requests before restarting it:
02-May-2021 21:36:47 [World Community Grid] update requested by user
02-May-2021 21:36:50 [World Community Grid] [sched_op] sched RPC pending: Requested by user
02-May-2021 21:36:50 [World Community Grid] [sched_op] Starting scheduler request
02-May-2021 21:36:50 [World Community Grid] Sending scheduler request: Requested by user.
02-May-2021 21:36:50 [World Community Grid] Requesting new tasks for Intel GPU
02-May-2021 21:36:50 [World Community Grid] [sched_op] CPU work request: 0.00 seconds; 0.00 devices
02-May-2021 21:36:50 [World Community Grid] [sched_op] Intel GPU work request: 28209.89 seconds; 0.00 devices
02-May-2021 21:36:53 [World Community Grid] Scheduler request completed: got 0 new tasks
02-May-2021 21:36:53 [World Community Grid] [sched_op] Server version 701
02-May-2021 21:36:53 [World Community Grid] Project requested delay of 121 seconds
02-May-2021 21:36:54 [World Community Grid] [sched_op] Deferring communication for 00:02:01
02-May-2021 21:36:54 [World Community Grid] [sched_op] Reason: requested by project
02-May-2021 21:37:00 [World Community Grid] Started upload of OPNG_0032778_00146_1_r1271073597_0
02-May-2021 21:37:07 [World Community Grid] Finished upload of OPNG_0032778_00146_1_r1271073597_0
02-May-2021 21:38:55 [World Community Grid] update requested by user
02-May-2021 21:38:59 [World Community Grid] [sched_op] sched RPC pending: Requested by user
02-May-2021 21:38:59 [World Community Grid] [sched_op] Starting scheduler request
02-May-2021 21:38:59 [World Community Grid] Sending scheduler request: Requested by user.
02-May-2021 21:38:59 [World Community Grid] Reporting 1 completed tasks
02-May-2021 21:38:59 [World Community Grid] Requesting new tasks for Intel GPU
02-May-2021 21:38:59 [World Community Grid] [sched_op] CPU work request: 0.00 seconds; 0.00 devices
02-May-2021 21:38:59 [World Community Grid] [sched_op] Intel GPU work request: 28190.47 seconds; 0.00 devices
02-May-2021 21:39:02 [World Community Grid] Scheduler request completed: got 0 new tasks
02-May-2021 21:39:02 [World Community Grid] [sched_op] Server version 701
02-May-2021 21:39:02 [World Community Grid] Project requested delay of 121 seconds
02-May-2021 21:39:02 [World Community Grid] [sched_op] handle_scheduler_reply(): got ack for task OPNG_0032778_00146_1
02-May-2021 21:39:02 [World Community Grid] [sched_op] Deferring communication for 00:02:01
02-May-2021 21:39:02 [World Community Grid] [sched_op] Reason: requested by project


Here are the first 2 from after(technically 3, the first failed contact though):

02-May-2021 21:42:51 [World Community Grid] update requested by user
02-May-2021 21:42:53 [World Community Grid] [sched_op] sched RPC pending: Requested by user
02-May-2021 21:42:53 [World Community Grid] [sched_op] Starting scheduler request
02-May-2021 21:42:53 [World Community Grid] Sending scheduler request: Requested by user.
02-May-2021 21:42:53 [World Community Grid] Requesting new tasks for Intel GPU
02-May-2021 21:42:53 [World Community Grid] [sched_op] CPU work request: 0.00 seconds; 0.00 devices
02-May-2021 21:42:53 [World Community Grid] [sched_op] Intel GPU work request: 28339.31 seconds; 0.00 devices
02-May-2021 21:43:15 [World Community Grid] Scheduler request failed: Timeout was reached
02-May-2021 21:43:15 [World Community Grid] [sched_op] Deferring communication for 00:01:44
02-May-2021 21:43:15 [World Community Grid] [sched_op] Reason: Scheduler request failed
02-May-2021 21:43:17 [---] Project communication failed: attempting access to reference site
02-May-2021 21:43:18 [---] Internet access OK - project servers may be temporarily down.
02-May-2021 21:43:48 [World Community Grid] update requested by user
02-May-2021 21:43:51 [World Community Grid] [sched_op] sched RPC pending: Requested by user
02-May-2021 21:43:51 [World Community Grid] [sched_op] Starting scheduler request
02-May-2021 21:43:51 [World Community Grid] Sending scheduler request: Requested by user.
02-May-2021 21:43:51 [World Community Grid] Requesting new tasks for Intel GPU
02-May-2021 21:43:51 [World Community Grid] [sched_op] CPU work request: 0.00 seconds; 0.00 devices
02-May-2021 21:43:51 [World Community Grid] [sched_op] Intel GPU work request: 28369.33 seconds; 0.00 devices
02-May-2021 21:43:53 [World Community Grid] Scheduler request completed: got 2 new tasks
02-May-2021 21:43:53 [World Community Grid] [sched_op] Server version 701
02-May-2021 21:43:53 [World Community Grid] Project requested delay of 121 seconds
02-May-2021 21:43:53 [World Community Grid] [sched_op] estimated total CPU task duration: 0 seconds
02-May-2021 21:43:53 [World Community Grid] [sched_op] estimated total Intel GPU task duration: 2099 seconds
02-May-2021 21:43:53 [World Community Grid] [sched_op] Deferring communication for 00:02:01
02-May-2021 21:43:53 [World Community Grid] [sched_op] Reason: requested by project
02-May-2021 21:43:55 [World Community Grid] Started download of 02d83d4ada272aed6648cee61dab1e14.pdbqt
02-May-2021 21:43:55 [World Community Grid] Started download of 638aef65a57713ded99a450194f0a126.gpf
02-May-2021 21:44:08 [World Community Grid] Finished download of 638aef65a57713ded99a450194f0a126.gpf
02-May-2021 21:44:08 [World Community Grid] Started download of 33a196b92894c8647e3a400b61cef5e5.job
02-May-2021 21:44:15 [World Community Grid] Finished download of 02d83d4ada272aed6648cee61dab1e14.pdbqt
02-May-2021 21:44:15 [World Community Grid] Started download of c45f4ac109e6ef772fbe9064cf7108a7.zip
02-May-2021 21:44:20 [World Community Grid] Finished download of 33a196b92894c8647e3a400b61cef5e5.job
02-May-2021 21:44:20 [World Community Grid] Started download of fe02357443356d28b66b322244c5e850.pdbqt
02-May-2021 21:44:27 [World Community Grid] Finished download of c45f4ac109e6ef772fbe9064cf7108a7.zip
02-May-2021 21:44:27 [World Community Grid] Started download of 29ac650391f41cfe48a0f7c716aec40c.gpf
02-May-2021 21:44:39 [World Community Grid] Finished download of fe02357443356d28b66b322244c5e850.pdbqt
02-May-2021 21:44:39 [World Community Grid] Started download of 41c9297f892eb65b40b2975daf245f30.job
02-May-2021 21:44:40 [World Community Grid] Finished download of 29ac650391f41cfe48a0f7c716aec40c.gpf
02-May-2021 21:44:40 [World Community Grid] Started download of 501697aa6533d2ab5566263f5a2258b5.zip
02-May-2021 21:44:51 [World Community Grid] Finished download of 41c9297f892eb65b40b2975daf245f30.job
02-May-2021 21:44:52 [World Community Grid] Temporarily failed download of 501697aa6533d2ab5566263f5a2258b5.zip: transient HTTP error
02-May-2021 21:44:52 [World Community Grid] Backing off 00:03:12 on download of 501697aa6533d2ab5566263f5a2258b5.zip
02-May-2021 21:44:59 [World Community Grid] Started download of 501697aa6533d2ab5566263f5a2258b5.zip
02-May-2021 21:45:11 [World Community Grid] Finished download of 501697aa6533d2ab5566263f5a2258b5.zip
02-May-2021 21:45:54 [World Community Grid] [sched_op] Starting scheduler request
02-May-2021 21:45:54 [World Community Grid] Sending scheduler request: To fetch work.
02-May-2021 21:45:54 [World Community Grid] Requesting new tasks for Intel GPU
02-May-2021 21:45:54 [World Community Grid] [sched_op] CPU work request: 0.00 seconds; 0.00 devices
02-May-2021 21:45:54 [World Community Grid] [sched_op] Intel GPU work request: 133032.53 seconds; 0.00 devices
02-May-2021 21:45:57 [World Community Grid] Scheduler request completed: got 2 new tasks
02-May-2021 21:45:57 [World Community Grid] [sched_op] Server version 701
02-May-2021 21:45:57 [World Community Grid] Project requested delay of 121 seconds
02-May-2021 21:45:57 [World Community Grid] [sched_op] estimated total CPU task duration: 0 seconds
02-May-2021 21:45:57 [World Community Grid] [sched_op] estimated total Intel GPU task duration: 2099 seconds
02-May-2021 21:45:57 [World Community Grid] [sched_op] Deferring communication for 00:02:01
02-May-2021 21:45:57 [World Community Grid] [sched_op] Reason: requested by project
ID: 104273 · Report as offensive
Previous · 1 · 2 · 3 · 4 · 5 · Next

Message boards : Questions and problems : GPU not receiving tasks when CPU computing disabled

Copyright © 2024 University of California.
Permission is granted to copy, distribute and/or modify this document under the terms of the GNU Free Documentation License, Version 1.2 or any later version published by the Free Software Foundation.