Re: chooseleaf_descend_once
Hey Jim, Running the third test with tunable chooseleaf_descend_once 0 with no devices marked out yields the following result (999.827397, 0.48667056652539997) so chi squared value is 999 with a corresponding p value of 0.487 so that the placement distribution seems to be drawn from the uniform distribution as desired. Caleb -- To unsubscribe from this list: send the line unsubscribe ceph-devel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: chooseleaf_descend_once
On 11/28/2012 09:11 AM, Caleb Miles wrote: Hey Jim, Running the third test with tunable chooseleaf_descend_once 0 with no devices marked out yields the following result (999.827397, 0.48667056652539997) so chi squared value is 999 with a corresponding p value of 0.487 so that the placement distribution seems to be drawn from the uniform distribution as desired. Great, thanks for doing that extra test. Plus, I see that Sage has merged it. Cool. Thanks -- Jim Caleb On Tue, Nov 27, 2012 at 1:28 PM, Jim Schuttjasc...@sandia.gov wrote: Hi Caleb, On 11/26/2012 07:28 PM, caleb miles wrote: Hello all, Here's what I've done to try and validate the new chooseleaf_descend_once tunable first described in commit f1a53c5e80a48557e63db9c52b83f3**9391bc69b8 in the wip-crush branch of ceph.git. First I set the new tunable to it's legacy value, disabled, tunable choose_local_tries 0 tunable choose_local_fallback_tries 0 tunable choose_total_tries 50 tunable chooseleaf_descend_once 0 The map contains one thousand osd devices contained in one hundred hosts with the following data rule rule data { ruleset 0 type replicated min_size 1 max_size 10 step take default step chooseleaf firstn 0 type host step emit } I then simulate the creation of one million placement groups using the crushtool $ crushtool -i hundred.map --test --min-x 0 --max-x 99 --num-rep 3 --output-csv --weight 120 0.0 --weight 121 0.0 --weight 122 0.0 --weight 123 0.0 --weight 124 0.0 --weight 125 0.0 --weight 125 0.0 --weight 150 0.0 --weight 151 0.0 --weight 152 0.0 --weight 153 0.0 --weight 154 0.0 --weight 155 0.0 --weight 156 0.0 --weight 180 0.0 --weight 181 0.0 --weight 182 0.0 --weight 183 0.0 --weight 184 0.0 --weight 185 0.0 --weight 186 0.0 with the majority of devices in three hosts marked out. Then in (I)Python import scipy.stats as s import matplotlib.mlab as m data = m.csv2rec(data-device_**utilization.csv) s.chisquare(data['number_of_**objects_stored'], data['number_of_objects_* *expected']) which will output (122939.76474477499, 0.0) so that the chi squared value is 122939.795 and the p value is, rounded to, 0.0 and the observed placement distribution statistically differs from a uniform distribution. Repeating with the new tunable set to tunable chooseleaf_descend_once 1 I obtain the following result (998.97643161876761, 0.32151775131589833) so that the chi squared value is 998.976 and the p value is 0.32 and the observed placement distribution is statistically identical to the uniform distribution at the five and ten percent confidence levels, higher as well of course. The p value is the probability of obtaining a chi squared value more extreme than the statistic observed. Basically, from my rudimentary understanding of probability theory, that if you obtain a p value p P then reject the null hypothesis, in our case that the observed placement distribution is drawn from the uniform distribution, at the P confidence level. Cool. Thanks for doing these tests. Is there any point to doing a third test, with tunable chooseleaf_descend_once 0 and no devices marked out, but in all other respects the same as the above two tests? I would expect the results for that case and the last case you tested to be essentially identical in the degree of uniformity, but is it worth verifying? -- Jim Caleb -- To unsubscribe from this list: send the line unsubscribe ceph-devel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/**majordomo-info.htmlhttp://vger.kernel.org/majordomo-info.html -- To unsubscribe from this list: send the line unsubscribe ceph-devel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: chooseleaf_descend_once
Hi Caleb, On 11/26/2012 07:28 PM, caleb miles wrote: Hello all, Here's what I've done to try and validate the new chooseleaf_descend_once tunable first described in commit f1a53c5e80a48557e63db9c52b83f39391bc69b8 in the wip-crush branch of ceph.git. First I set the new tunable to it's legacy value, disabled, tunable choose_local_tries 0 tunable choose_local_fallback_tries 0 tunable choose_total_tries 50 tunable chooseleaf_descend_once 0 The map contains one thousand osd devices contained in one hundred hosts with the following data rule rule data { ruleset 0 type replicated min_size 1 max_size 10 step take default step chooseleaf firstn 0 type host step emit } I then simulate the creation of one million placement groups using the crushtool $ crushtool -i hundred.map --test --min-x 0 --max-x 99 --num-rep 3 --output-csv --weight 120 0.0 --weight 121 0.0 --weight 122 0.0 --weight 123 0.0 --weight 124 0.0 --weight 125 0.0 --weight 125 0.0 --weight 150 0.0 --weight 151 0.0 --weight 152 0.0 --weight 153 0.0 --weight 154 0.0 --weight 155 0.0 --weight 156 0.0 --weight 180 0.0 --weight 181 0.0 --weight 182 0.0 --weight 183 0.0 --weight 184 0.0 --weight 185 0.0 --weight 186 0.0 with the majority of devices in three hosts marked out. Then in (I)Python import scipy.stats as s import matplotlib.mlab as m data = m.csv2rec(data-device_utilization.csv) s.chisquare(data['number_of_objects_stored'], data['number_of_objects_expected']) which will output (122939.76474477499, 0.0) so that the chi squared value is 122939.795 and the p value is, rounded to, 0.0 and the observed placement distribution statistically differs from a uniform distribution. Repeating with the new tunable set to tunable chooseleaf_descend_once 1 I obtain the following result (998.97643161876761, 0.32151775131589833) so that the chi squared value is 998.976 and the p value is 0.32 and the observed placement distribution is statistically identical to the uniform distribution at the five and ten percent confidence levels, higher as well of course. The p value is the probability of obtaining a chi squared value more extreme than the statistic observed. Basically, from my rudimentary understanding of probability theory, that if you obtain a p value p P then reject the null hypothesis, in our case that the observed placement distribution is drawn from the uniform distribution, at the P confidence level. Cool. Thanks for doing these tests. Is there any point to doing a third test, with tunable chooseleaf_descend_once 0 and no devices marked out, but in all other respects the same as the above two tests? I would expect the results for that case and the last case you tested to be essentially identical in the degree of uniformity, but is it worth verifying? -- Jim Caleb -- To unsubscribe from this list: send the line unsubscribe ceph-devel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html -- To unsubscribe from this list: send the line unsubscribe ceph-devel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
chooseleaf_descend_once
Hello all, Here's what I've done to try and validate the new chooseleaf_descend_once tunable first described in commit f1a53c5e80a48557e63db9c52b83f39391bc69b8 in the wip-crush branch of ceph.git. First I set the new tunable to it's legacy value, disabled, tunable choose_local_tries 0 tunable choose_local_fallback_tries 0 tunable choose_total_tries 50 tunable chooseleaf_descend_once 0 The map contains one thousand osd devices contained in one hundred hosts with the following data rule rule data { ruleset 0 type replicated min_size 1 max_size 10 step take default step chooseleaf firstn 0 type host step emit } I then simulate the creation of one million placement groups using the crushtool $ crushtool -i hundred.map --test --min-x 0 --max-x 99 --num-rep 3 --output-csv --weight 120 0.0 --weight 121 0.0 --weight 122 0.0 --weight 123 0.0 --weight 124 0.0 --weight 125 0.0 --weight 125 0.0 --weight 150 0.0 --weight 151 0.0 --weight 152 0.0 --weight 153 0.0 --weight 154 0.0 --weight 155 0.0 --weight 156 0.0 --weight 180 0.0 --weight 181 0.0 --weight 182 0.0 --weight 183 0.0 --weight 184 0.0 --weight 185 0.0 --weight 186 0.0 with the majority of devices in three hosts marked out. Then in (I)Python import scipy.stats as s import matplotlib.mlab as m data = m.csv2rec(data-device_utilization.csv) s.chisquare(data['number_of_objects_stored'], data['number_of_objects_expected']) which will output (122939.76474477499, 0.0) so that the chi squared value is 122939.795 and the p value is, rounded to, 0.0 and the observed placement distribution statistically differs from a uniform distribution. Repeating with the new tunable set to tunable chooseleaf_descend_once 1 I obtain the following result (998.97643161876761, 0.32151775131589833) so that the chi squared value is 998.976 and the p value is 0.32 and the observed placement distribution is statistically identical to the uniform distribution at the five and ten percent confidence levels, higher as well of course. The p value is the probability of obtaining a chi squared value more extreme than the statistic observed. Basically, from my rudimentary understanding of probability theory, that if you obtain a p value p P then reject the null hypothesis, in our case that the observed placement distribution is drawn from the uniform distribution, at the P confidence level. Caleb -- To unsubscribe from this list: send the line unsubscribe ceph-devel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html