[jira] [Updated] (YARN-7292) Revisit Resource Profile Behavior
[ https://issues.apache.org/jira/browse/YARN-7292?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Wangda Tan updated YARN-7292: - Attachment: YARN-7292.007.patch > Revisit Resource Profile Behavior > - > > Key: YARN-7292 > URL: https://issues.apache.org/jira/browse/YARN-7292 > Project: Hadoop YARN > Issue Type: Sub-task > Components: nodemanager, resourcemanager >Reporter: Wangda Tan >Assignee: Wangda Tan >Priority: Blocker > Attachments: YARN-7292.002.patch, YARN-7292.003.patch, > YARN-7292.004.patch, YARN-7292.005.patch, YARN-7292.006.patch, > YARN-7292.007.patch, YARN-7292.wip.001.patch > > > Had discussions with [~templedf], [~vvasudev], [~sunilg] offline. There're a > couple of resource profile related behaviors might need to be updated: > 1) Configure resource profile in server side or client side: > Currently resource profile can be only configured centrally: > - Advantages: > A given resource profile has a the same meaning in the cluster. It won’t > change when we run different apps in different configurations. A job can run > under Amazon’s G2.8X can also run on YARN with G2.8X profile. A side benefit > is YARN scheduler can potentially do better bin packing. > - Disadvantages: > Hard for applications to add their own resource profiles. > 2) Do we really need mandatory resource profiles such as > minimum/maximum/default? > 3) Should we send resource profile name inside ResourceRequest, or should > client/AM translate it to resource and set it to the existing resource > fields? > 4) Related to above, should we allow resource overrides or client/AM should > send final resource to RM? -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: yarn-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: yarn-issues-h...@hadoop.apache.org
[jira] [Updated] (YARN-7292) Revisit Resource Profile Behavior
[ https://issues.apache.org/jira/browse/YARN-7292?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Wangda Tan updated YARN-7292: - Attachment: YARN-7292.006.patch > Revisit Resource Profile Behavior > - > > Key: YARN-7292 > URL: https://issues.apache.org/jira/browse/YARN-7292 > Project: Hadoop YARN > Issue Type: Sub-task > Components: nodemanager, resourcemanager >Reporter: Wangda Tan >Assignee: Wangda Tan >Priority: Blocker > Attachments: YARN-7292.002.patch, YARN-7292.003.patch, > YARN-7292.004.patch, YARN-7292.005.patch, YARN-7292.006.patch, > YARN-7292.wip.001.patch > > > Had discussions with [~templedf], [~vvasudev], [~sunilg] offline. There're a > couple of resource profile related behaviors might need to be updated: > 1) Configure resource profile in server side or client side: > Currently resource profile can be only configured centrally: > - Advantages: > A given resource profile has a the same meaning in the cluster. It won’t > change when we run different apps in different configurations. A job can run > under Amazon’s G2.8X can also run on YARN with G2.8X profile. A side benefit > is YARN scheduler can potentially do better bin packing. > - Disadvantages: > Hard for applications to add their own resource profiles. > 2) Do we really need mandatory resource profiles such as > minimum/maximum/default? > 3) Should we send resource profile name inside ResourceRequest, or should > client/AM translate it to resource and set it to the existing resource > fields? > 4) Related to above, should we allow resource overrides or client/AM should > send final resource to RM? -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: yarn-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: yarn-issues-h...@hadoop.apache.org
[jira] [Updated] (YARN-7292) Revisit Resource Profile Behavior
[ https://issues.apache.org/jira/browse/YARN-7292?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Wangda Tan updated YARN-7292: - Attachment: YARN-7292.005.patch > Revisit Resource Profile Behavior > - > > Key: YARN-7292 > URL: https://issues.apache.org/jira/browse/YARN-7292 > Project: Hadoop YARN > Issue Type: Sub-task > Components: nodemanager, resourcemanager >Reporter: Wangda Tan >Assignee: Wangda Tan >Priority: Blocker > Attachments: YARN-7292.002.patch, YARN-7292.003.patch, > YARN-7292.004.patch, YARN-7292.005.patch, YARN-7292.wip.001.patch > > > Had discussions with [~templedf], [~vvasudev], [~sunilg] offline. There're a > couple of resource profile related behaviors might need to be updated: > 1) Configure resource profile in server side or client side: > Currently resource profile can be only configured centrally: > - Advantages: > A given resource profile has a the same meaning in the cluster. It won’t > change when we run different apps in different configurations. A job can run > under Amazon’s G2.8X can also run on YARN with G2.8X profile. A side benefit > is YARN scheduler can potentially do better bin packing. > - Disadvantages: > Hard for applications to add their own resource profiles. > 2) Do we really need mandatory resource profiles such as > minimum/maximum/default? > 3) Should we send resource profile name inside ResourceRequest, or should > client/AM translate it to resource and set it to the existing resource > fields? > 4) Related to above, should we allow resource overrides or client/AM should > send final resource to RM? -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: yarn-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: yarn-issues-h...@hadoop.apache.org
[jira] [Updated] (YARN-7292) Revisit Resource Profile Behavior
[ https://issues.apache.org/jira/browse/YARN-7292?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Sunil G updated YARN-7292: -- Attachment: YARN-7292.004.patch > Revisit Resource Profile Behavior > - > > Key: YARN-7292 > URL: https://issues.apache.org/jira/browse/YARN-7292 > Project: Hadoop YARN > Issue Type: Sub-task > Components: nodemanager, resourcemanager >Reporter: Wangda Tan >Assignee: Wangda Tan >Priority: Blocker > Attachments: YARN-7292.002.patch, YARN-7292.003.patch, > YARN-7292.004.patch, YARN-7292.wip.001.patch > > > Had discussions with [~templedf], [~vvasudev], [~sunilg] offline. There're a > couple of resource profile related behaviors might need to be updated: > 1) Configure resource profile in server side or client side: > Currently resource profile can be only configured centrally: > - Advantages: > A given resource profile has a the same meaning in the cluster. It won’t > change when we run different apps in different configurations. A job can run > under Amazon’s G2.8X can also run on YARN with G2.8X profile. A side benefit > is YARN scheduler can potentially do better bin packing. > - Disadvantages: > Hard for applications to add their own resource profiles. > 2) Do we really need mandatory resource profiles such as > minimum/maximum/default? > 3) Should we send resource profile name inside ResourceRequest, or should > client/AM translate it to resource and set it to the existing resource > fields? > 4) Related to above, should we allow resource overrides or client/AM should > send final resource to RM? -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: yarn-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: yarn-issues-h...@hadoop.apache.org
[jira] [Updated] (YARN-7292) Revisit Resource Profile Behavior
[ https://issues.apache.org/jira/browse/YARN-7292?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Wangda Tan updated YARN-7292: - Attachment: YARN-7292.003.patch > Revisit Resource Profile Behavior > - > > Key: YARN-7292 > URL: https://issues.apache.org/jira/browse/YARN-7292 > Project: Hadoop YARN > Issue Type: Sub-task > Components: nodemanager, resourcemanager >Reporter: Wangda Tan >Assignee: Wangda Tan >Priority: Blocker > Attachments: YARN-7292.002.patch, YARN-7292.003.patch, > YARN-7292.wip.001.patch > > > Had discussions with [~templedf], [~vvasudev], [~sunilg] offline. There're a > couple of resource profile related behaviors might need to be updated: > 1) Configure resource profile in server side or client side: > Currently resource profile can be only configured centrally: > - Advantages: > A given resource profile has a the same meaning in the cluster. It won’t > change when we run different apps in different configurations. A job can run > under Amazon’s G2.8X can also run on YARN with G2.8X profile. A side benefit > is YARN scheduler can potentially do better bin packing. > - Disadvantages: > Hard for applications to add their own resource profiles. > 2) Do we really need mandatory resource profiles such as > minimum/maximum/default? > 3) Should we send resource profile name inside ResourceRequest, or should > client/AM translate it to resource and set it to the existing resource > fields? > 4) Related to above, should we allow resource overrides or client/AM should > send final resource to RM? -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: yarn-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: yarn-issues-h...@hadoop.apache.org
[jira] [Updated] (YARN-7292) Revisit Resource Profile Behavior
[ https://issues.apache.org/jira/browse/YARN-7292?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Wangda Tan updated YARN-7292: - Attachment: YARN-7292.002.patch > Revisit Resource Profile Behavior > - > > Key: YARN-7292 > URL: https://issues.apache.org/jira/browse/YARN-7292 > Project: Hadoop YARN > Issue Type: Sub-task > Components: nodemanager, resourcemanager >Reporter: Wangda Tan >Assignee: Wangda Tan >Priority: Blocker > Attachments: YARN-7292.002.patch, YARN-7292.wip.001.patch > > > Had discussions with [~templedf], [~vvasudev], [~sunilg] offline. There're a > couple of resource profile related behaviors might need to be updated: > 1) Configure resource profile in server side or client side: > Currently resource profile can be only configured centrally: > - Advantages: > A given resource profile has a the same meaning in the cluster. It won’t > change when we run different apps in different configurations. A job can run > under Amazon’s G2.8X can also run on YARN with G2.8X profile. A side benefit > is YARN scheduler can potentially do better bin packing. > - Disadvantages: > Hard for applications to add their own resource profiles. > 2) Do we really need mandatory resource profiles such as > minimum/maximum/default? > 3) Should we send resource profile name inside ResourceRequest, or should > client/AM translate it to resource and set it to the existing resource > fields? > 4) Related to above, should we allow resource overrides or client/AM should > send final resource to RM? -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: yarn-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: yarn-issues-h...@hadoop.apache.org
[jira] [Updated] (YARN-7292) Revisit Resource Profile Behavior
[ https://issues.apache.org/jira/browse/YARN-7292?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Wangda Tan updated YARN-7292: - Attachment: YARN-7292.wip.001.patch > Revisit Resource Profile Behavior > - > > Key: YARN-7292 > URL: https://issues.apache.org/jira/browse/YARN-7292 > Project: Hadoop YARN > Issue Type: Sub-task > Components: nodemanager, resourcemanager >Reporter: Wangda Tan >Assignee: Wangda Tan >Priority: Blocker > Attachments: YARN-7292.wip.001.patch > > > Had discussions with [~templedf], [~vvasudev], [~sunilg] offline. There're a > couple of resource profile related behaviors might need to be updated: > 1) Configure resource profile in server side or client side: > Currently resource profile can be only configured centrally: > - Advantages: > A given resource profile has a the same meaning in the cluster. It won’t > change when we run different apps in different configurations. A job can run > under Amazon’s G2.8X can also run on YARN with G2.8X profile. A side benefit > is YARN scheduler can potentially do better bin packing. > - Disadvantages: > Hard for applications to add their own resource profiles. > 2) Do we really need mandatory resource profiles such as > minimum/maximum/default? > 3) Should we send resource profile name inside ResourceRequest, or should > client/AM translate it to resource and set it to the existing resource > fields? > 4) Related to above, should we allow resource overrides or client/AM should > send final resource to RM? -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: yarn-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: yarn-issues-h...@hadoop.apache.org
[jira] [Updated] (YARN-7292) Revisit Resource Profile Behavior
[ https://issues.apache.org/jira/browse/YARN-7292?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Wangda Tan updated YARN-7292: - Description: Had discussions with [~templedf], [~vvasudev], [~sunilg] offline. There're a couple of resource profile related behaviors might need to be updated: 1) Configure resource profile in server side or client side: Currently resource profile can be only configured centrally: - Advantages: A given resource profile has a the same meaning in the cluster. It won’t change when we run different apps in different configurations. A job can run under Amazon’s G2.8X can also run on YARN with G2.8X profile. A side benefit is YARN scheduler can potentially do better bin packing. - Disadvantages: Hard for applications to add their own resource profiles. 2) Do we really need mandatory resource profiles such as minimum/maximum/default? 3) Should we send resource profile name inside ResourceRequest, or should client/AM translate it to resource and set it to the existing resource fields? 4) Related to above, should we allow resource overrides or client/AM should send final resource to RM? was: Had discussions with [~templedf], [~vvasudev], [~sunilg] offline. There're a couple of resource profile related behaviors might need to be updated: 1) Configure resource profile in server side or client side: Currently resource profile can be only configured centrally: - Advantages: A given resource profile has a the same meaning in the cluster. It won’t change when we run different apps in different configurations. A job can run under Amazon’s G2.8X can also run on YARN with G2.8X profile. A side benefit is YARN scheduler can potentially do better bin packing. - Disadvantages: Hard for applications to add their own resource profiles. 2) Do we really need mandatory resource profiles such as minimum/maximum/default? 3) Existing feature requires every client has a resource-types.xml in order to use multiple resource types, should we allow client/AM update supported resource types via Yarn APIs? 4) Should we send resource profile name inside ResourceRequest, or should client/AM translate it to resource and set it to the existing resource fields? 5) Related to above, should we allow resource overrides or client/AM should send final resource to RM? > Revisit Resource Profile Behavior > - > > Key: YARN-7292 > URL: https://issues.apache.org/jira/browse/YARN-7292 > Project: Hadoop YARN > Issue Type: Sub-task > Components: nodemanager, resourcemanager >Reporter: Wangda Tan >Assignee: Wangda Tan >Priority: Blocker > > Had discussions with [~templedf], [~vvasudev], [~sunilg] offline. There're a > couple of resource profile related behaviors might need to be updated: > 1) Configure resource profile in server side or client side: > Currently resource profile can be only configured centrally: > - Advantages: > A given resource profile has a the same meaning in the cluster. It won’t > change when we run different apps in different configurations. A job can run > under Amazon’s G2.8X can also run on YARN with G2.8X profile. A side benefit > is YARN scheduler can potentially do better bin packing. > - Disadvantages: > Hard for applications to add their own resource profiles. > 2) Do we really need mandatory resource profiles such as > minimum/maximum/default? > 3) Should we send resource profile name inside ResourceRequest, or should > client/AM translate it to resource and set it to the existing resource > fields? > 4) Related to above, should we allow resource overrides or client/AM should > send final resource to RM? -- This message was sent by Atlassian JIRA (v6.4.14#64029) - To unsubscribe, e-mail: yarn-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: yarn-issues-h...@hadoop.apache.org
[jira] [Updated] (YARN-7292) Revisit Resource Profile Behavior
[ https://issues.apache.org/jira/browse/YARN-7292?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Wangda Tan updated YARN-7292: - Description: Had discussions with [~templedf], [~vvasudev], [~sunilg] offline. There're a couple of resource profile related behaviors might need to be updated: 1) Configure resource profile in server side or client side: Currently resource profile can be only configured centrally: - Advantages: A given resource profile has a the same meaning in the cluster. It won’t change when we run different apps in different configurations. A job can run under Amazon’s G2.8X can also run on YARN with G2.8X profile. A side benefit is YARN scheduler can potentially do better bin packing. - Disadvantages: Hard for applications to add their own resource profiles. 2) Do we really need mandatory resource profiles such as minimum/maximum/default? 3) Existing feature requires every client has a resource-types.xml in order to use multiple resource types, should we allow client/AM update supported resource types via Yarn APIs? 4) Should we send resource profile name inside ResourceRequest, or should client/AM translate it to resource and set it to the existing resource fields? 5) Related to above, should we allow resource overrides or client/AM should send final resource to RM? was:Had discussions with [~templedf], [~vvasudev], [~sunilg] offline. There're a couple of resource profile related behavior > Revisit Resource Profile Behavior > - > > Key: YARN-7292 > URL: https://issues.apache.org/jira/browse/YARN-7292 > Project: Hadoop YARN > Issue Type: Sub-task > Components: nodemanager, resourcemanager >Reporter: Wangda Tan >Assignee: Wangda Tan >Priority: Blocker > > Had discussions with [~templedf], [~vvasudev], [~sunilg] offline. There're a > couple of resource profile related behaviors might need to be updated: > 1) Configure resource profile in server side or client side: > Currently resource profile can be only configured centrally: > - Advantages: > A given resource profile has a the same meaning in the cluster. It won’t > change when we run different apps in different configurations. A job can run > under Amazon’s G2.8X can also run on YARN with G2.8X profile. A side benefit > is YARN scheduler can potentially do better bin packing. > - Disadvantages: > Hard for applications to add their own resource profiles. > 2) Do we really need mandatory resource profiles such as > minimum/maximum/default? > 3) Existing feature requires every client has a resource-types.xml in order > to use multiple resource types, should we allow client/AM update supported > resource types via Yarn APIs? > 4) Should we send resource profile name inside ResourceRequest, or should > client/AM translate it to resource and set it to the existing resource > fields? > 5) Related to above, should we allow resource overrides or client/AM should > send final resource to RM? -- This message was sent by Atlassian JIRA (v6.4.14#64029) - To unsubscribe, e-mail: yarn-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: yarn-issues-h...@hadoop.apache.org
