[jira] [Updated] (HDFS-11535) Performance analysis of new DFSNetworkTopology#chooseRandom
[ https://issues.apache.org/jira/browse/HDFS-11535?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Arpit Agarwal updated HDFS-11535: - Resolution: Fixed Hadoop Flags: Reviewed Fix Version/s: 3.0.0-alpha3 Status: Resolved (was: Patch Available) Committed this to trunk. Thanks for the contribution [~vagarychen]. > Performance analysis of new DFSNetworkTopology#chooseRandom > --- > > Key: HDFS-11535 > URL: https://issues.apache.org/jira/browse/HDFS-11535 > Project: Hadoop HDFS > Issue Type: Sub-task > Components: namenode >Reporter: Chen Liang >Assignee: Chen Liang > Fix For: 3.0.0-alpha3 > > Attachments: HDFS-11535.001.patch, HDFS-11535.002.patch, > HDFS-11535.003.patch, HDFS-11535.004.patch, PerfTest.pdf > > > This JIRA is created to post the results of some performance experiments we > did. For those who are interested, please the attached .pdf file for more > detail. The attached patch file includes the experiment code we ran. > The key insights we got from these tests is that: although *the new method > outperforms the current one in most cases*. There is still *one case where > the current one is better*. Which is when there is only one storage type in > the cluster, and we also always look for this storage type. In this case, it > is simply a waste of time to perform storage-type-based pruning, blindly > picking up a random node (current methods) would suffice. > Therefore, based on the analysis, we propose to use a *combination of both > the old and the new methods*: > say, we search for a node of type X, since now inner node all keep storage > type info, we can *just check root node to see if X is the only type it has*. > If yes, blindly picking a random leaf will work, so we simply call the old > method, otherwise we call the new method. > There is still at least one missing piece in this performance test, which is > garbage collection. The new method does a few more object creation when doing > the search, which adds overhead to GC. I'm still thinking of any potential > optimization but this seems tricky, also I'm not sure whether this > optimization worth doing at all. Please feel free to leave any > comments/suggestions. > Thanks [~arpitagarwal] and [~szetszwo] for the offline discussion. -- This message was sent by Atlassian JIRA (v6.3.15#6346) - To unsubscribe, e-mail: hdfs-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: hdfs-issues-h...@hadoop.apache.org
[jira] [Updated] (HDFS-11535) Performance analysis of new DFSNetworkTopology#chooseRandom
[ https://issues.apache.org/jira/browse/HDFS-11535?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Chen Liang updated HDFS-11535: -- Attachment: HDFS-11535.004.patch Thanks [~arpitagarwal] for the comments! Post v004 patch with a number of style updates. > Performance analysis of new DFSNetworkTopology#chooseRandom > --- > > Key: HDFS-11535 > URL: https://issues.apache.org/jira/browse/HDFS-11535 > Project: Hadoop HDFS > Issue Type: Sub-task > Components: namenode >Reporter: Chen Liang >Assignee: Chen Liang > Attachments: HDFS-11535.001.patch, HDFS-11535.002.patch, > HDFS-11535.003.patch, HDFS-11535.004.patch, PerfTest.pdf > > > This JIRA is created to post the results of some performance experiments we > did. For those who are interested, please the attached .pdf file for more > detail. The attached patch file includes the experiment code we ran. > The key insights we got from these tests is that: although *the new method > outperforms the current one in most cases*. There is still *one case where > the current one is better*. Which is when there is only one storage type in > the cluster, and we also always look for this storage type. In this case, it > is simply a waste of time to perform storage-type-based pruning, blindly > picking up a random node (current methods) would suffice. > Therefore, based on the analysis, we propose to use a *combination of both > the old and the new methods*: > say, we search for a node of type X, since now inner node all keep storage > type info, we can *just check root node to see if X is the only type it has*. > If yes, blindly picking a random leaf will work, so we simply call the old > method, otherwise we call the new method. > There is still at least one missing piece in this performance test, which is > garbage collection. The new method does a few more object creation when doing > the search, which adds overhead to GC. I'm still thinking of any potential > optimization but this seems tricky, also I'm not sure whether this > optimization worth doing at all. Please feel free to leave any > comments/suggestions. > Thanks [~arpitagarwal] and [~szetszwo] for the offline discussion. -- This message was sent by Atlassian JIRA (v6.3.15#6346) - To unsubscribe, e-mail: hdfs-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: hdfs-issues-h...@hadoop.apache.org
[jira] [Updated] (HDFS-11535) Performance analysis of new DFSNetworkTopology#chooseRandom
[ https://issues.apache.org/jira/browse/HDFS-11535?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Chen Liang updated HDFS-11535: -- Attachment: HDFS-11535.003.patch Post v003 patch with the tests ignored. Also removed writing numbers to files. > Performance analysis of new DFSNetworkTopology#chooseRandom > --- > > Key: HDFS-11535 > URL: https://issues.apache.org/jira/browse/HDFS-11535 > Project: Hadoop HDFS > Issue Type: Sub-task > Components: namenode >Reporter: Chen Liang >Assignee: Chen Liang > Attachments: HDFS-11535.001.patch, HDFS-11535.002.patch, > HDFS-11535.003.patch, PerfTest.pdf > > > This JIRA is created to post the results of some performance experiments we > did. For those who are interested, please the attached .pdf file for more > detail. The attached patch file includes the experiment code we ran. > The key insights we got from these tests is that: although *the new method > outperforms the current one in most cases*. There is still *one case where > the current one is better*. Which is when there is only one storage type in > the cluster, and we also always look for this storage type. In this case, it > is simply a waste of time to perform storage-type-based pruning, blindly > picking up a random node (current methods) would suffice. > Therefore, based on the analysis, we propose to use a *combination of both > the old and the new methods*: > say, we search for a node of type X, since now inner node all keep storage > type info, we can *just check root node to see if X is the only type it has*. > If yes, blindly picking a random leaf will work, so we simply call the old > method, otherwise we call the new method. > There is still at least one missing piece in this performance test, which is > garbage collection. The new method does a few more object creation when doing > the search, which adds overhead to GC. I'm still thinking of any potential > optimization but this seems tricky, also I'm not sure whether this > optimization worth doing at all. Please feel free to leave any > comments/suggestions. > Thanks [~arpitagarwal] and [~szetszwo] for the offline discussion. -- This message was sent by Atlassian JIRA (v6.3.15#6346) - To unsubscribe, e-mail: hdfs-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: hdfs-issues-h...@hadoop.apache.org
[jira] [Updated] (HDFS-11535) Performance analysis of new DFSNetworkTopology#chooseRandom
[ https://issues.apache.org/jira/browse/HDFS-11535?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Chen Liang updated HDFS-11535: -- Status: Patch Available (was: Reopened) > Performance analysis of new DFSNetworkTopology#chooseRandom > --- > > Key: HDFS-11535 > URL: https://issues.apache.org/jira/browse/HDFS-11535 > Project: Hadoop HDFS > Issue Type: Sub-task > Components: namenode >Reporter: Chen Liang >Assignee: Chen Liang > Attachments: HDFS-11535.001.patch, HDFS-11535.002.patch, > HDFS-11535.003.patch, PerfTest.pdf > > > This JIRA is created to post the results of some performance experiments we > did. For those who are interested, please the attached .pdf file for more > detail. The attached patch file includes the experiment code we ran. > The key insights we got from these tests is that: although *the new method > outperforms the current one in most cases*. There is still *one case where > the current one is better*. Which is when there is only one storage type in > the cluster, and we also always look for this storage type. In this case, it > is simply a waste of time to perform storage-type-based pruning, blindly > picking up a random node (current methods) would suffice. > Therefore, based on the analysis, we propose to use a *combination of both > the old and the new methods*: > say, we search for a node of type X, since now inner node all keep storage > type info, we can *just check root node to see if X is the only type it has*. > If yes, blindly picking a random leaf will work, so we simply call the old > method, otherwise we call the new method. > There is still at least one missing piece in this performance test, which is > garbage collection. The new method does a few more object creation when doing > the search, which adds overhead to GC. I'm still thinking of any potential > optimization but this seems tricky, also I'm not sure whether this > optimization worth doing at all. Please feel free to leave any > comments/suggestions. > Thanks [~arpitagarwal] and [~szetszwo] for the offline discussion. -- This message was sent by Atlassian JIRA (v6.3.15#6346) - To unsubscribe, e-mail: hdfs-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: hdfs-issues-h...@hadoop.apache.org
[jira] [Updated] (HDFS-11535) Performance analysis of new DFSNetworkTopology#chooseRandom
[ https://issues.apache.org/jira/browse/HDFS-11535?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Yiqun Lin updated HDFS-11535: - Attachment: HDFS-11535.002.patch Thanks [~szetszwo] for sharing your thought! I agree on that the threshold-based approach may seems a little complicated for users to use. So I also agree on the two-trial approach. In general, the total trials of the two-trial way will be never big than 2. I suppose this is acceptable for us. I have taken some time to add the unit test using two-trial way. The following are my local test results: {code} Percentage: 0.9 avg time: 0.005580342 avg trials: 1.1042 Percentage: 0.8 avg time: 0.00815461 avg trials: 1.1996 Percentage: 0.7 avg time: 0.008995014 avg trials: 1.30315 Percentage: 0.6 avg time: 0.010933414 avg trials: 1.3927 Percentage: 0.5 avg time: 0.009327865 avg trials: 1.50345 Percentage: 0.4 avg time: 0.015638033 avg trials: 1.59705 Percentage: 0.3 avg time: 0.014731338 avg trials: 1.7 Percentage: 0.2 avg time: 0.013827324 avg trials: 1.8023 Percentage: 0.1 avg time: 0.017193155 avg trials: 1.89965 {code} I think we can add my test in your if we are sure to use two-trial way. Finally attach the new patch with two-trial way test added. > Performance analysis of new DFSNetworkTopology#chooseRandom > --- > > Key: HDFS-11535 > URL: https://issues.apache.org/jira/browse/HDFS-11535 > Project: Hadoop HDFS > Issue Type: Sub-task > Components: namenode >Reporter: Chen Liang >Assignee: Chen Liang > Attachments: HDFS-11535.001.patch, HDFS-11535.002.patch, PerfTest.pdf > > > This JIRA is created to post the results of some performance experiments we > did. For those who are interested, please the attached .pdf file for more > detail. The attached patch file includes the experiment code we ran. > The key insights we got from these tests is that: although *the new method > outperforms the current one in most cases*. There is still *one case where > the current one is better*. Which is when there is only one storage type in > the cluster, and we also always look for this storage type. In this case, it > is simply a waste of time to perform storage-type-based pruning, blindly > picking up a random node (current methods) would suffice. > Therefore, based on the analysis, we propose to use a *combination of both > the old and the new methods*: > say, we search for a node of type X, since now inner node all keep storage > type info, we can *just check root node to see if X is the only type it has*. > If yes, blindly picking a random leaf will work, so we simply call the old > method, otherwise we call the new method. > There is still at least one missing piece in this performance test, which is > garbage collection. The new method does a few more object creation when doing > the search, which adds overhead to GC. I'm still thinking of any potential > optimization but this seems tricky, also I'm not sure whether this > optimization worth doing at all. Please feel free to leave any > comments/suggestions. > Thanks [~arpitagarwal] and [~szetszwo] for the offline discussion. -- This message was sent by Atlassian JIRA (v6.3.15#6346) - To unsubscribe, e-mail: hdfs-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: hdfs-issues-h...@hadoop.apache.org
[jira] [Updated] (HDFS-11535) Performance analysis of new DFSNetworkTopology#chooseRandom
[ https://issues.apache.org/jira/browse/HDFS-11535?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Chen Liang updated HDFS-11535: -- Description: This JIRA is created to post the results of some performance experiments we did. For those who are interested, please the attached .pdf file for more detail. The attached patch file includes the experiment code we ran. The key insights we got from these tests is that: although *the new method outperforms the current one in most cases*. There is still *one case where the current one is better*. Which is when there is only one storage type in the cluster, and we also always look for this storage type. In this case, it is simply a waste of time to perform storage-type-based pruning, blindly picking up a random node (current methods) would suffice. Therefore, based on the analysis, we propose to use a *combination of both the old and the new methods*: say, we search for a node of type X, since now inner node all keep storage type info, we can *just check root node to see if X is the only type it has*. If yes, blindly picking a random leaf will work, so we simply call the old method, otherwise we call the new method. There is still at least one missing piece in this performance test, which is garbage collection. The new method does a few more object creation when doing the search, which adds overhead to GC. I'm still thinking of any potential optimization but this seems tricky, also I'm not sure whether this optimization worth doing at all. Please feel free to leave any comments/suggestions. Thanks [~arpitagarwal] and [~szetszwo] for the offline discussion. was: This JIRA is created to post the results of some performance experiments we did. For those who are interested, please the attached .pdf file for more detail. The attached patch file includes the experiment code we ran. The key insights we got from these tests is that: although *the new method outperforms the current one in most cases*. There is still *one case where the current one is better*. Which is when there is only one storage type in the cluster, and we also always look for this storage type. In this case, it is simply a waste of time to perform storage-type-based pruning, blindly picking up a random node (current methods) would suffice. Therefore, based on the analysis, we propose to use a *combination of both the old and the new methods*: say, we search for a node of type X, since now inner node all keep storage type info, we can *just check root node to see if X is the only type it has*. If yes, blindly picking a random leaf will work, so we simply call the old method, otherwise we call the new method. There is still at least one missing piece in this performance test, which is garbage collection. The new method does a few more object creation when doing the search, which adds overhead to GC. I'm still thinking of any potential optimization but this seems tricky, also I'm not sure whether this optimization worth doing at all. Please feel free to leave any comments/suggestions. > Performance analysis of new DFSNetworkTopology#chooseRandom > --- > > Key: HDFS-11535 > URL: https://issues.apache.org/jira/browse/HDFS-11535 > Project: Hadoop HDFS > Issue Type: Sub-task > Components: namenode >Reporter: Chen Liang >Assignee: Chen Liang > Attachments: HDFS-11535.001.patch, PerfTest.pdf > > > This JIRA is created to post the results of some performance experiments we > did. For those who are interested, please the attached .pdf file for more > detail. The attached patch file includes the experiment code we ran. > The key insights we got from these tests is that: although *the new method > outperforms the current one in most cases*. There is still *one case where > the current one is better*. Which is when there is only one storage type in > the cluster, and we also always look for this storage type. In this case, it > is simply a waste of time to perform storage-type-based pruning, blindly > picking up a random node (current methods) would suffice. > Therefore, based on the analysis, we propose to use a *combination of both > the old and the new methods*: > say, we search for a node of type X, since now inner node all keep storage > type info, we can *just check root node to see if X is the only type it has*. > If yes, blindly picking a random leaf will work, so we simply call the old > method, otherwise we call the new method. > There is still at least one missing piece in this performance test, which is > garbage collection. The new method does a few more object creation when doing > the search, which adds overhead to GC. I'm still thinking of any potential > optimization but this seems tricky, also I'm not sure whether this > optimiza
[jira] [Updated] (HDFS-11535) Performance analysis of new DFSNetworkTopology#chooseRandom
[ https://issues.apache.org/jira/browse/HDFS-11535?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Chen Liang updated HDFS-11535: -- Attachment: HDFS-11535.001.patch > Performance analysis of new DFSNetworkTopology#chooseRandom > --- > > Key: HDFS-11535 > URL: https://issues.apache.org/jira/browse/HDFS-11535 > Project: Hadoop HDFS > Issue Type: Sub-task > Components: namenode >Reporter: Chen Liang >Assignee: Chen Liang > Attachments: HDFS-11535.001.patch, PerfTest.pdf > > > This JIRA is created to post the results of some performance experiments we > did. For those who are interested, please the attached .pdf file for more > detail. The attached patch file includes the experiment code we ran. > The key insights we got from these tests is that: although *the new method > outperforms the current one in most cases*. There is still *one case where > the current one is better*. Which is when there is only one storage type in > the cluster, and we also always look for this storage type. In this case, it > is simply a waste of time to perform storage-type-based pruning, blindly > picking up a random node (current methods) would suffice. > Therefore, based on the analysis, we propose to use a *combination of both > the old and the new methods*: > say, we search for a node of type X, since now inner node all keep storage > type info, we can *just check root node to see if X is the only type it has*. > If yes, blindly picking a random leaf will work, so we simply call the old > method, otherwise we call the new method. > There is still at least one missing piece in this performance test, which is > garbage collection. The new method does a few more object creation when doing > the search, which adds overhead to GC. I'm still thinking of any potential > optimization but this seems tricky, also I'm not sure whether this > optimization worth doing at all. Please feel free to leave any > comments/suggestions. -- This message was sent by Atlassian JIRA (v6.3.15#6346) - To unsubscribe, e-mail: hdfs-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: hdfs-issues-h...@hadoop.apache.org
[jira] [Updated] (HDFS-11535) Performance analysis of new DFSNetworkTopology#chooseRandom
[ https://issues.apache.org/jira/browse/HDFS-11535?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Chen Liang updated HDFS-11535: -- Attachment: PerfTest.pdf > Performance analysis of new DFSNetworkTopology#chooseRandom > --- > > Key: HDFS-11535 > URL: https://issues.apache.org/jira/browse/HDFS-11535 > Project: Hadoop HDFS > Issue Type: Sub-task > Components: namenode >Reporter: Chen Liang >Assignee: Chen Liang > Attachments: PerfTest.pdf > > > This JIRA is created to post the results of some performance experiments we > did. For those who are interested, please the attached .pdf file for more > detail. The attached patch file includes the experiment code we ran. > The key insights we got from these tests is that: although *the new method > outperforms the current one in most cases*. There is still *one case where > the current one is better*. Which is when there is only one storage type in > the cluster, and we also always look for this storage type. In this case, it > is simply a waste of time to perform storage-type-based pruning, blindly > picking up a random node (current methods) would suffice. > Therefore, based on the analysis, we propose to use a *combination of both > the old and the new methods*: > say, we search for a node of type X, since now inner node all keep storage > type info, we can *just check root node to see if X is the only type it has*. > If yes, blindly picking a random leaf will work, so we simply call the old > method, otherwise we call the new method. > There is still at least one missing piece in this performance test, which is > garbage collection. The new method does a few more object creation when doing > the search, which adds overhead to GC. I'm still thinking of any potential > optimization but this seems tricky, also I'm not sure whether this > optimization worth doing at all. Please feel free to leave any > comments/suggestions. -- This message was sent by Atlassian JIRA (v6.3.15#6346) - To unsubscribe, e-mail: hdfs-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: hdfs-issues-h...@hadoop.apache.org