Re: [ PATCH 0/8] sched: remove cpu_load array
On 03/17/2014 11:24 AM, Alex Shi wrote: > On 03/13/2014 01:57 PM, Alex Shi wrote: >> In the cpu_load decay usage, we mixed the long term, short term load with >> balance bias, randomly pick a big/small value from them according to balance >> destination or source. This mix is wrong, the balance bias should be based >> on task moving cost between cpu groups, not on random history or instant >> load. >> History load maybe diverage a lot from real load, that lead to incorrect >> bias. >> >> In fact, the cpu_load decays can be replaced by the sched_avg decay, that >> also decays load on time. The balance bias part can fully use fixed bias -- >> imbalance_pct, which is already used in newly idle, wake, forkexec balancing >> and numa balancing scenarios. >> >> Currently the only working idx is busy_idx and idle_idx. >> As to busy_idx: >> We mix history load decay and bias together. The ridiculous thing is, when >> all cpu load are continuous stable, long/short term load is same. then we >> lose the bias meaning, so any minimum imbalance may cause unnecessary task >> moving. To prevent this funny thing happen, we have to reuse the >> imbalance_pct again in find_busiest_group(). But that clearly causes over >> bias in normal time. If there are some burst load in system, it is more >> worse. >> > > Any comments? IMHO, task moving resistance, bias, is only related with task migration cost. no relationship with history load. Another issue of history load mix with bias is that we want to care the history load impact, but it is often ignored when instant load is fit bias required more -- bigger in destination or smaller in source. Any comments on this? :) > >> As to idle_idx: >> Though I have some concern of usage correction, >> https://lkml.org/lkml/2014/3/12/247, but since we are working on cpu >> idle migration into scheduler. The problem will be reconsidered. We don't >> need to care it now. >> >> This patch removed the cpu_load idx decay, since it can be replaced by >> sched_avg feature. and left the imbalance_pct bias untouched, since only >> idle_idx missed it, but it is fine. and will be reconsidered soon. >> >> >> V5, >> 1, remove unify bias patch and biased_load function. Thanks for PeterZ's >> comments! >> 2, remove get_sd_load_idx() in the 1st patch as SrikarD's suggestion. >> 3, remove LB_BIAS feature, it is not needed now. > > -- Thanks Alex -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [ PATCH 0/8] sched: remove cpu_load array
On 03/17/2014 11:24 AM, Alex Shi wrote: On 03/13/2014 01:57 PM, Alex Shi wrote: In the cpu_load decay usage, we mixed the long term, short term load with balance bias, randomly pick a big/small value from them according to balance destination or source. This mix is wrong, the balance bias should be based on task moving cost between cpu groups, not on random history or instant load. History load maybe diverage a lot from real load, that lead to incorrect bias. In fact, the cpu_load decays can be replaced by the sched_avg decay, that also decays load on time. The balance bias part can fully use fixed bias -- imbalance_pct, which is already used in newly idle, wake, forkexec balancing and numa balancing scenarios. Currently the only working idx is busy_idx and idle_idx. As to busy_idx: We mix history load decay and bias together. The ridiculous thing is, when all cpu load are continuous stable, long/short term load is same. then we lose the bias meaning, so any minimum imbalance may cause unnecessary task moving. To prevent this funny thing happen, we have to reuse the imbalance_pct again in find_busiest_group(). But that clearly causes over bias in normal time. If there are some burst load in system, it is more worse. Any comments? IMHO, task moving resistance, bias, is only related with task migration cost. no relationship with history load. Another issue of history load mix with bias is that we want to care the history load impact, but it is often ignored when instant load is fit bias required more -- bigger in destination or smaller in source. Any comments on this? :) As to idle_idx: Though I have some concern of usage correction, https://lkml.org/lkml/2014/3/12/247, but since we are working on cpu idle migration into scheduler. The problem will be reconsidered. We don't need to care it now. This patch removed the cpu_load idx decay, since it can be replaced by sched_avg feature. and left the imbalance_pct bias untouched, since only idle_idx missed it, but it is fine. and will be reconsidered soon. V5, 1, remove unify bias patch and biased_load function. Thanks for PeterZ's comments! 2, remove get_sd_load_idx() in the 1st patch as SrikarD's suggestion. 3, remove LB_BIAS feature, it is not needed now. -- Thanks Alex -- To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [ PATCH 0/8] sched: remove cpu_load array
On 03/13/2014 01:57 PM, Alex Shi wrote: > In the cpu_load decay usage, we mixed the long term, short term load with > balance bias, randomly pick a big/small value from them according to balance > destination or source. This mix is wrong, the balance bias should be based > on task moving cost between cpu groups, not on random history or instant load. > History load maybe diverage a lot from real load, that lead to incorrect bias. > > In fact, the cpu_load decays can be replaced by the sched_avg decay, that > also decays load on time. The balance bias part can fullly use fixed bias -- > imbalance_pct, which is already used in newly idle, wake, forkexec balancing > and numa balancing scenarios. > > Currently the only working idx is busy_idx and idle_idx. > As to busy_idx: > We mix history load decay and bias together. The ridiculous thing is, when > all cpu load are continuous stable, long/short term load is same. then we > lose the bias meaning, so any minimum imbalance may cause unnecessary task > moving. To prevent this funny thing happen, we have to reuse the > imbalance_pct again in find_busiest_group(). But that clearly causes over > bias in normal time. If there are some burst load in system, it is more worse. > Any comments? > As to idle_idx: > Though I have some cencern of usage corretion, > https://lkml.org/lkml/2014/3/12/247, but since we are working on cpu > idle migration into scheduler. The problem will be reconsidered. We don't > need to care it now. > > This patch removed the cpu_load idx decay, since it can be replaced by > sched_avg feature. and left the imbalance_pct bias untouched, since only > idle_idx missed it, but it is fine. and will be reconsidered soon. > > > V5, > 1, remove unify bias patch and biased_load function. Thanks for PeterZ's > comments! > 2, remove get_sd_load_idx() in the 1st patch as SrikarD's suggestion. > 3, remove LB_BIAS feature, it is not needed now. -- Thanks Alex -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [ PATCH 0/8] sched: remove cpu_load array
On 03/13/2014 01:57 PM, Alex Shi wrote: In the cpu_load decay usage, we mixed the long term, short term load with balance bias, randomly pick a big/small value from them according to balance destination or source. This mix is wrong, the balance bias should be based on task moving cost between cpu groups, not on random history or instant load. History load maybe diverage a lot from real load, that lead to incorrect bias. In fact, the cpu_load decays can be replaced by the sched_avg decay, that also decays load on time. The balance bias part can fullly use fixed bias -- imbalance_pct, which is already used in newly idle, wake, forkexec balancing and numa balancing scenarios. Currently the only working idx is busy_idx and idle_idx. As to busy_idx: We mix history load decay and bias together. The ridiculous thing is, when all cpu load are continuous stable, long/short term load is same. then we lose the bias meaning, so any minimum imbalance may cause unnecessary task moving. To prevent this funny thing happen, we have to reuse the imbalance_pct again in find_busiest_group(). But that clearly causes over bias in normal time. If there are some burst load in system, it is more worse. Any comments? As to idle_idx: Though I have some cencern of usage corretion, https://lkml.org/lkml/2014/3/12/247, but since we are working on cpu idle migration into scheduler. The problem will be reconsidered. We don't need to care it now. This patch removed the cpu_load idx decay, since it can be replaced by sched_avg feature. and left the imbalance_pct bias untouched, since only idle_idx missed it, but it is fine. and will be reconsidered soon. V5, 1, remove unify bias patch and biased_load function. Thanks for PeterZ's comments! 2, remove get_sd_load_idx() in the 1st patch as SrikarD's suggestion. 3, remove LB_BIAS feature, it is not needed now. -- Thanks Alex -- To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
[ PATCH 0/8] sched: remove cpu_load array
In the cpu_load decay usage, we mixed the long term, short term load with balance bias, randomly pick a big/small value from them according to balance destination or source. This mix is wrong, the balance bias should be based on task moving cost between cpu groups, not on random history or instant load. History load maybe diverage a lot from real load, that lead to incorrect bias. In fact, the cpu_load decays can be replaced by the sched_avg decay, that also decays load on time. The balance bias part can fullly use fixed bias -- imbalance_pct, which is already used in newly idle, wake, forkexec balancing and numa balancing scenarios. Currently the only working idx is busy_idx and idle_idx. As to busy_idx: We mix history load decay and bias together. The ridiculous thing is, when all cpu load are continuous stable, long/short term load is same. then we lose the bias meaning, so any minimum imbalance may cause unnecessary task moving. To prevent this funny thing happen, we have to reuse the imbalance_pct again in find_busiest_group(). But that clearly causes over bias in normal time. If there are some burst load in system, it is more worse. As to idle_idx: Though I have some cencern of usage corretion, https://lkml.org/lkml/2014/3/12/247, but since we are working on cpu idle migration into scheduler. The problem will be reconsidered. We don't need to care it now. This patch removed the cpu_load idx decay, since it can be replaced by sched_avg feature. and left the imbalance_pct bias untouched, since only idle_idx missed it, but it is fine. and will be reconsidered soon. V5, 1, remove unify bias patch and biased_load function. Thanks for PeterZ's comments! 2, remove get_sd_load_idx() in the 1st patch as SrikarD's suggestion. 3, remove LB_BIAS feature, it is not needed now. V4, 1, rebase on latest tip/master 2, replace target_load by biased_load as Morten's suggestion V3, 1, correct the wake_affine bias. Thanks for Morten's reminder! 2, replace source_load by weighted_cpuload for better function name meaning. V2, 1, This version do some tuning on load bias of target load. 2, Got further to remove the cpu_load in rq. 3, Revert the patch 'Limit sd->*_idx range on sysctl' since no needs Any testing/comments are appreciated. This patch rebase on latest tip/master. The git tree for this patchset at: g...@github.com:alexshi/power-scheduling.git noload Thanks Alex [PATCH 1/8] sched: shortcut to remove load_idx [PATCH 2/8] sched: remove rq->cpu_load[load_idx] array [PATCH 3/8] sched: remove source_load and target_load [PATCH 4/8] sched: remove LB_BIAS [PATCH 5/8] sched: clean up cpu_load update [PATCH 6/8] sched: rewrite update_cpu_load_nohz [PATCH 7/8] sched: remove rq->cpu_load and rq->nr_load_updates [PATCH 8/8] sched: rename update_*_cpu_load -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
[ PATCH 0/8] sched: remove cpu_load array
In the cpu_load decay usage, we mixed the long term, short term load with balance bias, randomly pick a big/small value from them according to balance destination or source. This mix is wrong, the balance bias should be based on task moving cost between cpu groups, not on random history or instant load. History load maybe diverage a lot from real load, that lead to incorrect bias. In fact, the cpu_load decays can be replaced by the sched_avg decay, that also decays load on time. The balance bias part can fullly use fixed bias -- imbalance_pct, which is already used in newly idle, wake, forkexec balancing and numa balancing scenarios. Currently the only working idx is busy_idx and idle_idx. As to busy_idx: We mix history load decay and bias together. The ridiculous thing is, when all cpu load are continuous stable, long/short term load is same. then we lose the bias meaning, so any minimum imbalance may cause unnecessary task moving. To prevent this funny thing happen, we have to reuse the imbalance_pct again in find_busiest_group(). But that clearly causes over bias in normal time. If there are some burst load in system, it is more worse. As to idle_idx: Though I have some cencern of usage corretion, https://lkml.org/lkml/2014/3/12/247, but since we are working on cpu idle migration into scheduler. The problem will be reconsidered. We don't need to care it now. This patch removed the cpu_load idx decay, since it can be replaced by sched_avg feature. and left the imbalance_pct bias untouched, since only idle_idx missed it, but it is fine. and will be reconsidered soon. V5, 1, remove unify bias patch and biased_load function. Thanks for PeterZ's comments! 2, remove get_sd_load_idx() in the 1st patch as SrikarD's suggestion. 3, remove LB_BIAS feature, it is not needed now. V4, 1, rebase on latest tip/master 2, replace target_load by biased_load as Morten's suggestion V3, 1, correct the wake_affine bias. Thanks for Morten's reminder! 2, replace source_load by weighted_cpuload for better function name meaning. V2, 1, This version do some tuning on load bias of target load. 2, Got further to remove the cpu_load in rq. 3, Revert the patch 'Limit sd-*_idx range on sysctl' since no needs Any testing/comments are appreciated. This patch rebase on latest tip/master. The git tree for this patchset at: g...@github.com:alexshi/power-scheduling.git noload Thanks Alex [PATCH 1/8] sched: shortcut to remove load_idx [PATCH 2/8] sched: remove rq-cpu_load[load_idx] array [PATCH 3/8] sched: remove source_load and target_load [PATCH 4/8] sched: remove LB_BIAS [PATCH 5/8] sched: clean up cpu_load update [PATCH 6/8] sched: rewrite update_cpu_load_nohz [PATCH 7/8] sched: remove rq-cpu_load and rq-nr_load_updates [PATCH 8/8] sched: rename update_*_cpu_load -- To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
