I have a bunch of Raspberry Pi's. As of this week they are having problems getting BRP4 work. The server status page said there are 41,000 tasks available to send. In this case it was running a single BRP4 task and the other 3 cores are idle. I have other Pis with idle cores unable to get work.
BOINC log
Einstein@Home 03-08-2019 12:28 PM see scheduler log messages on https://einsteinathome.org/host/12634175/log
Einstein@Home 03-08-2019 12:28 PM No work available for the applications you have selected. Please check your preferences on the web site.
Einstein@Home 03-08-2019 12:29 PM Sending scheduler request: To fetch work.
Einstein@Home 03-08-2019 12:29 PM Requesting new tasks for CPU
Einstein@Home 03-08-2019 12:29 PM Scheduler request completed: got 0 new tasks
Einstein@Home 03-08-2019 12:29 PM No work sent
Einstein@Home 03-08-2019 12:29 PM see scheduler log messages on https://einsteinathome.org/host/12634175/log
Einstein@Home 03-08-2019 12:29 PM No work available for the applications you have selected. Please check your preferences on the web site.
Einstein@Home 03-08-2019 12:31 PM update requested by user
Einstein@Home 03-08-2019 12:31 PM Sending scheduler request: Requested by user.
Einstein@Home 03-08-2019 12:31 PM Requesting new tasks for CPU
Einstein@Home 03-08-2019 12:31 PM Scheduler request completed: got 0 new tasks
Einstein@Home 03-08-2019 12:31 PM No work sent
Einstein@Home 03-08-2019 12:31 PM see scheduler log messages on https://einsteinathome.org/host/12634175/log
Scheduler log
2019-08-03 02:32:36.5268 [PID=12754] Request: [USER#xxxxx] [HOST#12634175] [IP xxx.xxx.xxx.69] client 7.14.2 2019-08-03 02:32:36.6542 [PID=12754] [debug] have_master:1 have_working: 1 have_db: 1 2019-08-03 02:32:36.6543 [PID=12754] [debug] using working prefs 2019-08-03 02:32:36.6543 [PID=12754] [debug] have db 1; dbmod 1461748411.000000; global mod 1492690457.000000 2019-08-03 02:32:36.6543 [PID=12754] [send] effective_ncpus 4 max_jobs_on_host_cpu 999999 max_jobs_on_host 999999 2019-08-03 02:32:36.6543 [PID=12754] [send] effective_ngpus 0 max_jobs_on_host_gpu 999999 2019-08-03 02:32:36.6543 [PID=12754] [send] Not using matchmaker scheduling; Not using EDF sim 2019-08-03 02:32:36.6543 [PID=12754] [send] CPU: req 12960.00 sec, 3.00 instances; est delay 0.00 2019-08-03 02:32:36.6543 [PID=12754] [send] work_req_seconds: 12960.00 secs 2019-08-03 02:32:36.6543 [PID=12754] [send] available disk 1.99 GB, work_buf_min 3456 2019-08-03 02:32:36.6543 [PID=12754] [send] active_frac 0.999980 on_frac 0.999882 DCF 4.833618 2019-08-03 02:32:36.6555 [PID=12754] [mixed] sending locality work first (0.3876) 2019-08-03 02:32:36.6565 [PID=12754] [mixed] sending non-locality work second 2019-08-03 02:32:36.6740 [PID=12754] [send] [HOST#12634175] will accept beta work. Scanning for beta work. 2019-08-03 02:32:36.6839 [PID=12754] [version] Checking plan class 'NEON' 2019-08-03 02:32:36.6875 [PID=12754] [version] reading plan classes from file '/BOINC/projects/EinsteinAtHome/plan_class_spec.xml' 2019-08-03 02:32:36.6876 [PID=12754] [version] plan class ok 2019-08-03 02:32:36.6876 [PID=12754] [version] Checking plan class 'NEON_Beta' 2019-08-03 02:32:36.6876 [PID=12754] [version] plan class ok 2019-08-03 02:32:36.6876 [PID=12754] [version] Best version of app einsteinbinary_BRP4 is 1.47 ID 769 NEON_Beta (2.12 GFLOPS) 2019-08-03 02:32:36.6886 [PID=12754] Only one Beta app version result per WU (#410205975, re#1) 2019-08-03 02:32:36.6887 [PID=12754] [send] [HOST#12634175] [WU#410205975 p2030.20170417.G44.77-01.19.N.b5s0g0.00000_2503] WU is infeasible: Project-specific customization 2019-08-03 02:32:36.6895 [PID=12754] Only one Beta app version result per WU (#410502230, re#2) 2019-08-03 02:32:36.6906 [PID=12754] Only one Beta app version result per WU (#410612900, re#3)
...
2019-08-03 02:32:36.7864 [PID=12754] Only one Beta app version result per WU (#410612836, re#145) 2019-08-03 02:32:36.7870 [PID=12754] Only one Beta app version result per WU (#410612841, re#146) 2019-08-03 02:32:36.7888 [PID=12754] [debug] [HOST#12634175] MSG(high) No work sent 2019-08-03 02:32:36.7888 [PID=12754] [debug] [HOST#12634175] MSG(high) see scheduler log messages on https://einsteinathome.org/host/12634175/log 2019-08-03 02:32:36.7888 [PID=12754] [debug] [HOST#12634175] MSG(high) No work available for the applications you have selected. Please check your preferences on the web site. 2019-08-03 02:32:36.7888 [PID=12754] Sending reply to [HOST#12634175]: 0 results, delay req 60.00 2019-08-03 02:32:36.7889 [PID=12754] Scheduler ran 0.267 seconds
Copyright © 2024 Einstein@Home. All rights reserved.
I am new to E@H and have 2
)
I am new to E@H and have 2 Raspberry Pi's, a 3B and a new 4B. Both of them are seeing the same problem as described above. I would like to know if anyone has any information on this problem and/or how to correct the situation.
Any help would be greatly appreciated,
Tom
Its a server-side issue so
)
Its a server-side issue so there is nothing us mere mortals can do.
Having said that the Ready to send figure on the server status page has now dropped to 16,109 so its been giving work units to somebody.
MarksRpiCluster
Thank's for the PM, I'm
)
Thank's for the PM, I'm looking into it. May take a day, though, Raspberry Pi isn't our highest priority.
BM
Thank You very much for the
)
Thank You very much for the information!
Tom
Thanks Bernd. Ready to send
)
Thanks Bernd. Ready to send is down to 8,000 but it seems to have stabilized now, work requests are getting filled again.
MarksRpiCluster