Parfor loop just hangs, CPU usage goes to zero

15 ビュー (過去 30 日間)
JohnDapper
JohnDapper 2016 年 3 月 14 日
回答済み: Tianzong Wang 2022 年 10 月 27 日
Hi all. Here is a sample code of what I am attempting to run.
parfor i = 1:num
answer(:,i) = someFunction(someData(:,i));
end
Key information: "someFunction" is a C++ mex file. "someData" is a memmapfile (memmapfilename.data) because it is too large to be loaded onto each worker
Oddly, the parfor loop just hangs, the CPU usage goes to zero, and when I CTRL+C, here is what I get:
Operation terminated by user during distcomp.remoteparfor/getCompleteIntervals (line
127)
In parallel_function>distributed_execution (line 820)
[tags, out] = P.getCompleteIntervals(chunkSize);
In parallel_function (line 587)
R = distributed_execution(...
This isn't an issue if I replace the "parfor" with a simple "for" - everything works fine. What seems to happen is that some of the workers become unresponsive. After the above issue is encountered, even running a simple command such as
pctRunOnAll 1+1
will return "2" on only some, but not all, workers.
Any help would be great. A fresh re-installation did not help. Validation for "parpool" passed.
  5 件のコメント
John Tencer
John Tencer 2018 年 4 月 3 日
I'm observing this behavior with 2017b.
David Saidman
David Saidman 2020 年 1 月 14 日
Did anybody get any success with this? I'm having exact same 2017b, definitely no keyboard statement.
If I wait a bit, it ends up running but on a single CPU (event tho I have 18 in my pool on a cpu with 20 physical and 40 logical cores, about 10gb spare memory in performance monitor).

サインインしてコメントする。

回答 (7 件)

Dave Behera
Dave Behera 2016 年 3 月 24 日
It seems that there is a deadlock when the workers are trying to the access the file using the same object (that you got from memmapfile). Due to that, the progress is getting stalled with zero CPU usage and no abort message.
Can you try creating a separate memmapfile object within each parfor iteration and passing it to the someFunction function? This may make the file access thread-safe.
Also, could you try the same workflow with spmd?
  8 件のコメント
Hakon Haugnes
Hakon Haugnes 2019 年 9 月 16 日
I have the same problem on R2018a
Arabarra
Arabarra 2021 年 1 月 11 日
Same problem here. In my case it is not reproductible, sometimes it will work, sometimes not. No deadlocks or anything suspicious in the code.

サインインしてコメントする。


arvid Martens
arvid Martens 2018 年 1 月 9 日
I noticed that the problem started to occur after I updated the drivers of the GPUs that are being used during the calculations. Rolling back the drivers resolved the problem. However, new GPU hardware is on its way, as the current ones are pretty old. So I hope the problem is resolved by then.
Is there a way to throw an error when this stalling occurs? I could write an error handling to reduce the time lost by this stalling.

Andrea Stevanato
Andrea Stevanato 2018 年 7 月 13 日
I have the same error with matlab 2018a.

Sanjay Manohar
Sanjay Manohar 2019 年 6 月 3 日
編集済み: Sanjay Manohar 2019 年 6 月 3 日
I was having the same parfor problem, until I noticed I had a "keyboard" instruction in my code.

DeepSea
DeepSea 2021 年 8 月 15 日
I've been stucked in this problem for couples of weeks, and fixed it by removing "continue" in an if-judgement and a for-loop.
for CondA
...
if CondB
continue; % Avoid using "continue"
end
...
end

Aditya Shukla
Aditya Shukla 2021 年 10 月 23 日
I suddenly got this problem since yesterday, before which all the code ran nicely. I really do not know why this happened. it is so annoying. Any one found a solution?

Tianzong Wang
Tianzong Wang 2022 年 10 月 27 日
Same here, most cores are not working. Any suggestions? And what is the JCEF?

カテゴリ

Help Center および File ExchangeParallel for-Loops (parfor) についてさらに検索

タグ

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by