cgroup task groups appears sensitive to absolute magnitude of shares
When using cgroups-based task groups, the amount of cpu time for each class should be based on the relative shares of the different groups.
However, my testing shows that the absolute value of the shares matters as well, with larger shares values giving more accurate results (to a point). Consider the two testcases below, where the only difference is that in the second case all the shares are increased by a factor of 10.
Notice that the accuracy in group 4 is significantly improved.
[root@localhost schedtest]# ./fairtest test5.dat using settling delay of 1 sec, runtime of 2 sec group hierarchy (name, weight, hogs, expected usage):
1, 40, 2, 55.555553
2, 20, 2, 27.777777
3, 10, 2, 13.888888
4, 2, 2, 2.777778
group actual(%) expected(%) avg latency(ms) max_latency(ms)
1 54.90 55.56 5/5 6/57
2 27.43 27.78 8/7 63/8
3 13.71 13.89 12/13 18/379
4 3.96 2.78 7/7 57/57[root@localhost schedtest]# ./fairtest test3.dat using settling delay of 1 sec, runtime of 10 sec group hierarchy (name, weight, hogs, expected usage):
1, 400, 2, 55.555557
2, 200, 2, 27.777779
3, 100, 2, 13.888889
4, 20, 2, 2.777778
group actual(%) expected(%) avg latency(ms) max_latency(ms)
1 55.20 55.56 5/5 22/31
2 28.02 27.78 7/8 23/21
3 14.00 13.89 12/11 20/33
4 2.78 2.78 9/9 24/20I suspect that this is due to the following calculation in __update_group_shares_cpu():
shares = (sd_shares * rq_weight) / (sd_rq_weight + 1);
Because these are integers, the result will give greater rounding error when sd_shares is small.
Going to 4000/2000/1000/200 doesn't seem to give noticeable improvements, and going to 40000/20000/10000/2000 causes the test to behave unpredictably, either taking abnormally long to complete or else not completing at all.
Is it worth doing anything about this (automatic normalization of group shares?), or should we just document this behaviour somewhere and live with it?
Chris
Quoted 47 lines · Chris Friesen
When using cgroups-based task groups, the amount of cpu time for each class should be based on the relative shares of the different groups.
However, my testing shows that the absolute value of the shares matters as well, with larger shares values giving more accurate results (to a point). Consider the two testcases below, where the only difference is that in the second case all the shares are increased by a factor of 10.
Notice that the accuracy in group 4 is significantly improved.[root@localhost schedtest]# ./fairtest test5.dat using settling delay of 1 sec, runtime of 2 sec group hierarchy (name, weight, hogs, expected usage):
1, 40, 2, 55.555553 2, 20, 2, 27.777777 3, 10, 2, 13.888888 4, 2, 2, 2.777778 group actual(%) expected(%) avg latency(ms) max_latency(ms) 1 54.90 55.56 5/5 6/57 2 27.43 27.78 8/7 63/8 3 13.71 13.89 12/13 18/379 4 3.96 2.78 7/7 57/57[root@localhost schedtest]# ./fairtest test3.dat using settling delay of 1 sec, runtime of 10 sec group hierarchy (name, weight, hogs, expected usage):
1, 400, 2, 55.555557 2, 200, 2, 27.777779 3, 100, 2, 13.888889 4, 20, 2, 2.777778 group actual(%) expected(%) avg latency(ms) max_latency(ms) 1 55.20 55.56 5/5 22/31 2 28.02 27.78 7/8 23/21 3 14.00 13.89 12/11 20/33 4 2.78 2.78 9/9 24/20I suspect that this is due to the following calculation in
__update_group_shares_cpu():shares = (
sd_shares*rq_weight) / (sd_rq_weight+ 1);Because these are integers, the result will give greater rounding error when
sd_sharesis small.
Quoted 8 lines
Going to 4000/2000/1000/200 doesn't seem to give noticeable improvements, and going to 40000/20000/10000/2000 causes the test to behave unpredictably, either taking abnormally long to complete or else not completing at all.
Is it worth doing anything about this (automatic normalization of group shares?), or should we just document this behaviour somewhere and live with it?
I'm afraid this is one of the things we'll have to live with. Esp. the group scheduler runs into the limits of fixed point math, and I'm afraid I've not yet found a way around that :/
Quoted 4 lines · Chris Friesen
Going to 4000/2000/1000/200 doesn't seem to give noticeable improvements, and going to 40000/20000/10000/2000 causes the test to behave unpredictably, either taking abnormally long to complete or else not completing at all.
Hmm, I would have expected it to work for at least the normal nice range of weight values..
Will have to look into that I suppose..
Quoted 11 lines · Peter Zijlstra
Quoted 4 lines · Chris Friesen
Going to 4000/2000/1000/200 doesn't seem to give noticeable improvements, and going to 40000/20000/10000/2000 causes the test to behave unpredictably, either taking abnormally long to complete or else not completing at all.
Hmm, I would have expected it to work for at least the normal nice range of weight values..
Will have to look into that I suppose..
One thought, are you running 32 or 64 bit? If you're on 32, could you try 64? If that fixes it its probably an easy fix, otherwise I fear it might take a bit more..
Quoted 5 lines · Peter Zijlstra
Quoted 4 lines · Peter Zijlstra
Quoted 1 line · Chris Friesen
Going to 4000/2000/1000/200 doesn't seem to give noticeable improvements, and going to 40000/20000/10000/2000 causes the test to behave unpredictably, either taking abnormally long to complete or else not completing at all.
Quoted 8 lines
Quoted 4 lines
Hmm, I would have expected it to work for at least the normal nice range of weight values..
Will have to look into that I suppose..
One thought, are you running 32 or 64 bit? If you're on 32, could you try 64? If that fixes it its probably an easy fix, otherwise I fear it might take a bit more..
No such luck, this is 64-bit (powerpc though, not x86). I tried reproducing it again today and was unable to reproduce the hang, but saw
delays of up to 7 seconds (where the expected delay is 10 sec).
Chris