[jira] [Updated] (HADOOP-17714) ABFS: testBlobBackCompatibility, testRandomRead & WasbAbfsCompatibility tests fail when triggered with default configs
[ https://issues.apache.org/jira/browse/HADOOP-17714?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Sneha Varma updated HADOOP-17714: - Summary: ABFS: testBlobBackCompatibility, testRandomRead & WasbAbfsCompatibility tests fail when triggered with default configs (was: ABFS: testBlobBackCompatibility & WasbAbfsCompatibility tests fail when triggered with default configs) > ABFS: testBlobBackCompatibility, testRandomRead & WasbAbfsCompatibility tests > fail when triggered with default configs > -- > > Key: HADOOP-17714 > URL: https://issues.apache.org/jira/browse/HADOOP-17714 > Project: Hadoop Common > Issue Type: Sub-task > Components: test >Reporter: Sneha Varma >Priority: Minor > Labels: pull-request-available > Time Spent: 1h 20m > Remaining Estimate: 0h > > testBlobBackCompatibility & WasbAbfsCompatibility tests fail when triggered > with default configs as http is not enabled on gen2 accounts by default. > > Options to fix it: > tests' config should enforce https by default > or the tests should be modified not execute http requests > -- This message was sent by Atlassian Jira (v8.3.4#803005) - To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-issues-h...@hadoop.apache.org
[jira] [Updated] (HADOOP-17714) ABFS: testBlobBackCompatibility, testRandomRead & WasbAbfsCompatibility tests fail when triggered with default configs
[ https://issues.apache.org/jira/browse/HADOOP-17714?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Sneha Varma updated HADOOP-17714: - Description: testBlobBackCompatibility, testRandomRead & WasbAbfsCompatibility tests fail when triggered with default configs as http is not enabled on gen2 accounts by default. Options to fix it: tests' config should enforce https by default or the tests should be modified not execute http requests was: testBlobBackCompatibility & WasbAbfsCompatibility tests fail when triggered with default configs as http is not enabled on gen2 accounts by default. Options to fix it: tests' config should enforce https by default or the tests should be modified not execute http requests > ABFS: testBlobBackCompatibility, testRandomRead & WasbAbfsCompatibility tests > fail when triggered with default configs > -- > > Key: HADOOP-17714 > URL: https://issues.apache.org/jira/browse/HADOOP-17714 > Project: Hadoop Common > Issue Type: Sub-task > Components: test >Reporter: Sneha Varma >Priority: Minor > Labels: pull-request-available > Time Spent: 1h 20m > Remaining Estimate: 0h > > testBlobBackCompatibility, testRandomRead & WasbAbfsCompatibility tests fail > when triggered with default configs as http is not enabled on gen2 accounts > by default. > > Options to fix it: > tests' config should enforce https by default > or the tests should be modified not execute http requests > -- This message was sent by Atlassian Jira (v8.3.4#803005) - To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-issues-h...@hadoop.apache.org
[jira] [Updated] (HADOOP-17714) ABFS: testBlobBackCompatibility & WasbAbfsCompatibility tests fail when triggered with default configs
[ https://issues.apache.org/jira/browse/HADOOP-17714?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Sneha Varma updated HADOOP-17714: - Summary: ABFS: testBlobBackCompatibility & WasbAbfsCompatibility tests fail when triggered with default configs (was: testBlobBackCompatibility & WasbAbfsCompatibility tests fail when triggered with default configs) > ABFS: testBlobBackCompatibility & WasbAbfsCompatibility tests fail when > triggered with default configs > -- > > Key: HADOOP-17714 > URL: https://issues.apache.org/jira/browse/HADOOP-17714 > Project: Hadoop Common > Issue Type: Sub-task > Components: test >Reporter: Sneha Varma >Priority: Minor > > testBlobBackCompatibility & WasbAbfsCompatibility tests fail when triggered > with default configs as http is not enabled on gen2 accounts by default. > > Options to fix it: > tests' config should enforce https by default > or the tests should be modified not execute http requests > -- This message was sent by Atlassian Jira (v8.3.4#803005) - To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-issues-h...@hadoop.apache.org
[jira] [Updated] (HADOOP-17715) ABFS: Append blob tests with non HNS accounts fail
[ https://issues.apache.org/jira/browse/HADOOP-17715?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Sneha Varma updated HADOOP-17715: - Summary: ABFS: Append blob tests with non HNS accounts fail (was: Append blob tests with non HNS accounts fail) > ABFS: Append blob tests with non HNS accounts fail > -- > > Key: HADOOP-17715 > URL: https://issues.apache.org/jira/browse/HADOOP-17715 > Project: Hadoop Common > Issue Type: Sub-task >Reporter: Sneha Varma >Priority: Minor > > Append blob tests with non HNS accounts fail. > # The script to run the tests should ensure that append blob tests with non > HNS account don't execute > # Should have proper documentation mentioning that append blob is allowed > only for HNS accounts -- This message was sent by Atlassian Jira (v8.3.4#803005) - To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-issues-h...@hadoop.apache.org
[jira] [Updated] (HADOOP-17716) ABFS: ITestAbfsStreamStatistics TestAbfsStreamOps fail with append blob on HNS account
[ https://issues.apache.org/jira/browse/HADOOP-17716?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Sneha Varma updated HADOOP-17716: - Summary: ABFS: ITestAbfsStreamStatistics TestAbfsStreamOps fail with append blob on HNS account (was: ITestAbfsStreamStatistics TestAbfsStreamOps fail with append blob on HNS account) > ABFS: ITestAbfsStreamStatistics TestAbfsStreamOps fail with append blob on > HNS account > -- > > Key: HADOOP-17716 > URL: https://issues.apache.org/jira/browse/HADOOP-17716 > Project: Hadoop Common > Issue Type: Sub-task >Reporter: Sneha Varma >Priority: Minor > > ITestAbfsStreamStatistics -TestAbfsStreamOps fail with append blob on HNS > account -- This message was sent by Atlassian Jira (v8.3.4#803005) - To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-issues-h...@hadoop.apache.org
[jira] [Created] (HADOOP-17716) ITestAbfsStreamStatistics TestAbfsStreamOps fail with append blob on HNS account
Sneha Varma created HADOOP-17716: Summary: ITestAbfsStreamStatistics TestAbfsStreamOps fail with append blob on HNS account Key: HADOOP-17716 URL: https://issues.apache.org/jira/browse/HADOOP-17716 Project: Hadoop Common Issue Type: Sub-task Reporter: Sneha Varma ITestAbfsStreamStatistics -TestAbfsStreamOps fail with append blob on HNS account -- This message was sent by Atlassian Jira (v8.3.4#803005) - To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-issues-h...@hadoop.apache.org
[jira] [Created] (HADOOP-17715) Append blob tests with non HNS accounts fail
Sneha Varma created HADOOP-17715: Summary: Append blob tests with non HNS accounts fail Key: HADOOP-17715 URL: https://issues.apache.org/jira/browse/HADOOP-17715 Project: Hadoop Common Issue Type: Sub-task Reporter: Sneha Varma Append blob tests with non HNS accounts fail. # The script to run the tests should ensure that append blob tests with non HNS account don't execute # Should have proper documentation mentioning that append blob is allowed only for HNS accounts -- This message was sent by Atlassian Jira (v8.3.4#803005) - To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-issues-h...@hadoop.apache.org
[jira] [Created] (HADOOP-17714) testBlobBackCompatibility & WasbAbfsCompatibility tests fail when triggered with default configs
Sneha Varma created HADOOP-17714: Summary: testBlobBackCompatibility & WasbAbfsCompatibility tests fail when triggered with default configs Key: HADOOP-17714 URL: https://issues.apache.org/jira/browse/HADOOP-17714 Project: Hadoop Common Issue Type: Sub-task Components: test Reporter: Sneha Varma testBlobBackCompatibility & WasbAbfsCompatibility tests fail when triggered with default configs as http is not enabled on gen2 accounts by default. Options to fix it: tests' config should enforce https by default or the tests should be modified not execute http requests -- This message was sent by Atlassian Jira (v8.3.4#803005) - To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-issues-h...@hadoop.apache.org
[jira] [Commented] (HADOOP-17628) ABFS: Distcp contract test testDistCpWithIterator is timing out consistently
[ https://issues.apache.org/jira/browse/HADOOP-17628?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17348176#comment-17348176 ] Sneha Varma commented on HADOOP-17628: -- [~bilahari.th] Would like to add that ContractSecureDistCp is also seeing the same issue would be great if we could add the same info in description of the issue for it as well > ABFS: Distcp contract test testDistCpWithIterator is timing out consistently > - > > Key: HADOOP-17628 > URL: https://issues.apache.org/jira/browse/HADOOP-17628 > Project: Hadoop Common > Issue Type: Sub-task >Affects Versions: 3.4.0 >Reporter: Bilahari T H >Priority: Minor > > The test case testDistCpWithIterator in AbstractContractDistCpTest is > consistently timing out. > -- This message was sent by Atlassian Jira (v8.3.4#803005) - To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-issues-h...@hadoop.apache.org
[jira] [Updated] (HADOOP-17590) ABFS: Introduce Lease Operations with Append to provide single writer semantics
[ https://issues.apache.org/jira/browse/HADOOP-17590?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Sneha Varma updated HADOOP-17590: - Description: The lease operations will be introduced as part of Append, Flush to ensure the single writer semantics. Details: Acquire Lease will be introduced in Create, Auto-Renew, Acquire will be added to Append & Release, Auto-Renew, Acquire in Flush. Duration the creation of the file the lease will be acquired, as part of appends the lease will be auto-renewed & the lease can be released as part of flush. By default the lease duration will be of 60 seconds. "fs.azure.write.enforcelease" & "fs.azure.write.lease.duration" two configs will be introduced. was: The lease operations will be introduced as part of Append, Flush to ensure the single writer semantics. Acquire Lease will be introduced in Create, Auto-Renew, Acquire will be added to Append & Release, Auto-Renew, Acquire in Flush. By default the lease duration will be of 60 seconds. "fs.azure.write.enforcelease" & "fs.azure.write.lease.duration" two configs will be introduced. > ABFS: Introduce Lease Operations with Append to provide single writer > semantics > --- > > Key: HADOOP-17590 > URL: https://issues.apache.org/jira/browse/HADOOP-17590 > Project: Hadoop Common > Issue Type: Sub-task >Reporter: Sneha Varma >Priority: Major > > The lease operations will be introduced as part of Append, Flush to ensure > the single writer semantics. > > Details: > Acquire Lease will be introduced in Create, Auto-Renew, Acquire will be added > to Append & Release, Auto-Renew, Acquire in Flush. > > Duration the creation of the file the lease will be acquired, as part of > appends the lease will be auto-renewed & the lease can be released as part of > flush. > > By default the lease duration will be of 60 seconds. > "fs.azure.write.enforcelease" & "fs.azure.write.lease.duration" two configs > will be introduced. -- This message was sent by Atlassian Jira (v8.3.4#803005) - To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-issues-h...@hadoop.apache.org
[jira] [Updated] (HADOOP-17590) ABFS: Introduce Lease Operations with Append to provide single writer semantics
[ https://issues.apache.org/jira/browse/HADOOP-17590?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Sneha Varma updated HADOOP-17590: - Description: The lease operations will be introduced as part of Append, Flush to ensure the single writer semantics. Acquire Lease will be introduced in Create, Auto-Renew, Acquire will be added to Append & Release, Auto-Renew, Acquire in Flush. By default the lease duration will be of 60 seconds. "fs.azure.write.enforcelease" & "fs.azure.write.lease.duration" two configs will be introduced. was: The lease operations will be introduced as part of Append, Flush to ensure the single writer semantics. Acquire Lease will be introduced in Create, Auto-Renew, Acquire will be added to Append & Release, Auto-Renew, Acquire in Flush. By default the lease duration will be of 60 seconds. > ABFS: Introduce Lease Operations with Append to provide single writer > semantics > --- > > Key: HADOOP-17590 > URL: https://issues.apache.org/jira/browse/HADOOP-17590 > Project: Hadoop Common > Issue Type: Sub-task >Reporter: Sneha Varma >Priority: Major > > The lease operations will be introduced as part of Append, Flush to ensure > the single writer semantics. > Acquire Lease will be introduced in Create, Auto-Renew, Acquire will be > added to Append & Release, Auto-Renew, Acquire in Flush. > By default the lease duration will be of 60 seconds. > "fs.azure.write.enforcelease" & "fs.azure.write.lease.duration" two configs > will be introduced. -- This message was sent by Atlassian Jira (v8.3.4#803005) - To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-issues-h...@hadoop.apache.org
[jira] [Updated] (HADOOP-17590) ABFS: Introduce Lease Operations with Append to provide single writer semantics
[ https://issues.apache.org/jira/browse/HADOOP-17590?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Sneha Varma updated HADOOP-17590: - Description: The lease operations will be introduced as part of Append, Flush to ensure the single writer semantics. Acquire Lease will be introduced in Create, Auto-Renew, Acquire will be added to Append & Release, Auto-Renew, Acquire in Flush. By default the lease duration will be of 60 seconds. was: The lease operations will be introduced as part of Append, Flush to ensure the single writer semantics. Acquire Lease will be introduced in Create, Auto-Renew, Acquire will be added to Append & Release, Auto-Renew, Acquire in Flush. > ABFS: Introduce Lease Operations with Append to provide single writer > semantics > --- > > Key: HADOOP-17590 > URL: https://issues.apache.org/jira/browse/HADOOP-17590 > Project: Hadoop Common > Issue Type: Sub-task >Reporter: Sneha Varma >Priority: Major > > The lease operations will be introduced as part of Append, Flush to ensure > the single writer semantics. > > Acquire Lease will be introduced in Create, Auto-Renew, Acquire will be added > to Append & Release, Auto-Renew, Acquire in Flush. > > By default the lease duration will be of 60 seconds. -- This message was sent by Atlassian Jira (v8.3.4#803005) - To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-issues-h...@hadoop.apache.org
[jira] [Updated] (HADOOP-17590) ABFS: Introduce Lease Operations with Append to provide single writer semantics
[ https://issues.apache.org/jira/browse/HADOOP-17590?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Sneha Varma updated HADOOP-17590: - Description: The lease operations will be introduced as part of Append, Flush to ensure the single writer semantics. Acquire Lease will be introduced in Create, Auto-Renew, Acquire will be added to Append & Release, Auto-Renew, Acquire in Flush. > ABFS: Introduce Lease Operations with Append to provide single writer > semantics > --- > > Key: HADOOP-17590 > URL: https://issues.apache.org/jira/browse/HADOOP-17590 > Project: Hadoop Common > Issue Type: Sub-task >Reporter: Sneha Varma >Priority: Major > > The lease operations will be introduced as part of Append, Flush to ensure > the single writer semantics. > > Acquire Lease will be introduced in Create, Auto-Renew, Acquire will be added > to Append & Release, Auto-Renew, Acquire in Flush. -- This message was sent by Atlassian Jira (v8.3.4#803005) - To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-issues-h...@hadoop.apache.org
[jira] [Created] (HADOOP-17590) ABFS: Introduce Lease Operations with Append to provide single writer semantics
Sneha Varma created HADOOP-17590: Summary: ABFS: Introduce Lease Operations with Append to provide single writer semantics Key: HADOOP-17590 URL: https://issues.apache.org/jira/browse/HADOOP-17590 Project: Hadoop Common Issue Type: Sub-task Reporter: Sneha Varma -- This message was sent by Atlassian Jira (v8.3.4#803005) - To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-issues-h...@hadoop.apache.org
[jira] [Assigned] (HADOOP-16402) AAD MSI flow is broken
[ https://issues.apache.org/jira/browse/HADOOP-16402?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Sneha Varma reassigned HADOOP-16402: Assignee: Sneha Varma (was: Vishwajeet Dusane) > AAD MSI flow is broken > -- > > Key: HADOOP-16402 > URL: https://issues.apache.org/jira/browse/HADOOP-16402 > Project: Hadoop Common > Issue Type: Bug > Components: fs/adl >Affects Versions: 2.9.0 >Reporter: Vishwajeet Dusane >Assignee: Sneha Varma >Priority: Major > > For AAD with MSI flow to work, ADL driver needs to initialize > MsiTokenProvider class with AAD Client id and tenant id. With the current > implementation, AAD MSI flow is broken. -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-issues-h...@hadoop.apache.org
[jira] [Commented] (HADOOP-15778) ABFS: Fix client side throttling for read
[ https://issues.apache.org/jira/browse/HADOOP-15778?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16623033#comment-16623033 ] Sneha Varma commented on HADOOP-15778: -- Patch HADOOP-15778-HADOOP-15407-002.patch Incorporating the comment ABFS tests Results: Tests run: 36, Failures: 0, Errors: 0, Skipped: 0 Tests run: 269, Failures: 0, Errors: 0, Skipped: 182 Tests run: 165, Failures: 0, Errors: 0, Skipped: 15 > ABFS: Fix client side throttling for read > - > > Key: HADOOP-15778 > URL: https://issues.apache.org/jira/browse/HADOOP-15778 > Project: Hadoop Common > Issue Type: Sub-task >Reporter: Sneha Varma >Assignee: Sneha Varma >Priority: Minor > Attachments: HADOOP-15778-HADOOP-15407-001.patch, > HADOOP-15778-HADOOP-15407-002.patch > > > 1. The content length for ReadFile in updateMetrics of > AbfsClientThrottlingIntercept is incorrect for cases when the request fails. > It is currently equal to the number of bytes that are read whereas it should > be equal to the number of bytes requested. > 2. sendingRequest of AbfsClientThrottlingIntercept at AbfsRestOperation > should be called irrespective of whether the request has body. -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-issues-h...@hadoop.apache.org
[jira] [Updated] (HADOOP-15778) ABFS: Fix client side throttling for read
[ https://issues.apache.org/jira/browse/HADOOP-15778?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Sneha Varma updated HADOOP-15778: - Attachment: HADOOP-15778-HADOOP-15407-002.patch Status: Patch Available (was: Open) > ABFS: Fix client side throttling for read > - > > Key: HADOOP-15778 > URL: https://issues.apache.org/jira/browse/HADOOP-15778 > Project: Hadoop Common > Issue Type: Sub-task >Reporter: Sneha Varma >Assignee: Sneha Varma >Priority: Minor > Attachments: HADOOP-15778-HADOOP-15407-001.patch, > HADOOP-15778-HADOOP-15407-002.patch > > > 1. The content length for ReadFile in updateMetrics of > AbfsClientThrottlingIntercept is incorrect for cases when the request fails. > It is currently equal to the number of bytes that are read whereas it should > be equal to the number of bytes requested. > 2. sendingRequest of AbfsClientThrottlingIntercept at AbfsRestOperation > should be called irrespective of whether the request has body. -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-issues-h...@hadoop.apache.org
[jira] [Updated] (HADOOP-15778) ABFS: Fix client side throttling for read
[ https://issues.apache.org/jira/browse/HADOOP-15778?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Sneha Varma updated HADOOP-15778: - Attachment: (was: HADOOP-15778-HADOOP-15407-002.patch) > ABFS: Fix client side throttling for read > - > > Key: HADOOP-15778 > URL: https://issues.apache.org/jira/browse/HADOOP-15778 > Project: Hadoop Common > Issue Type: Sub-task >Reporter: Sneha Varma >Assignee: Sneha Varma >Priority: Minor > Attachments: HADOOP-15778-HADOOP-15407-001.patch > > > 1. The content length for ReadFile in updateMetrics of > AbfsClientThrottlingIntercept is incorrect for cases when the request fails. > It is currently equal to the number of bytes that are read whereas it should > be equal to the number of bytes requested. > 2. sendingRequest of AbfsClientThrottlingIntercept at AbfsRestOperation > should be called irrespective of whether the request has body. -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-issues-h...@hadoop.apache.org
[jira] [Updated] (HADOOP-15778) ABFS: Fix client side throttling for read
[ https://issues.apache.org/jira/browse/HADOOP-15778?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Sneha Varma updated HADOOP-15778: - Status: Open (was: Patch Available) > ABFS: Fix client side throttling for read > - > > Key: HADOOP-15778 > URL: https://issues.apache.org/jira/browse/HADOOP-15778 > Project: Hadoop Common > Issue Type: Sub-task >Reporter: Sneha Varma >Assignee: Sneha Varma >Priority: Minor > Attachments: HADOOP-15778-HADOOP-15407-001.patch, > HADOOP-15778-HADOOP-15407-002.patch > > > 1. The content length for ReadFile in updateMetrics of > AbfsClientThrottlingIntercept is incorrect for cases when the request fails. > It is currently equal to the number of bytes that are read whereas it should > be equal to the number of bytes requested. > 2. sendingRequest of AbfsClientThrottlingIntercept at AbfsRestOperation > should be called irrespective of whether the request has body. -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-issues-h...@hadoop.apache.org
[jira] [Updated] (HADOOP-15778) ABFS: Fix client side throttling for read
[ https://issues.apache.org/jira/browse/HADOOP-15778?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Sneha Varma updated HADOOP-15778: - Attachment: HADOOP-15778-HADOOP-15407-002.patch > ABFS: Fix client side throttling for read > - > > Key: HADOOP-15778 > URL: https://issues.apache.org/jira/browse/HADOOP-15778 > Project: Hadoop Common > Issue Type: Sub-task >Reporter: Sneha Varma >Assignee: Sneha Varma >Priority: Minor > Attachments: HADOOP-15778-HADOOP-15407-001.patch, > HADOOP-15778-HADOOP-15407-002.patch > > > 1. The content length for ReadFile in updateMetrics of > AbfsClientThrottlingIntercept is incorrect for cases when the request fails. > It is currently equal to the number of bytes that are read whereas it should > be equal to the number of bytes requested. > 2. sendingRequest of AbfsClientThrottlingIntercept at AbfsRestOperation > should be called irrespective of whether the request has body. -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-issues-h...@hadoop.apache.org
[jira] [Updated] (HADOOP-15778) ABFS: Fix client side throttling for read
[ https://issues.apache.org/jira/browse/HADOOP-15778?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Sneha Varma updated HADOOP-15778: - Assignee: Sneha Varma Attachment: HADOOP-15778-HADOOP-15407-001.patch Status: Patch Available (was: Open) ABFS tests Results: Tests run: 36, Failures: 0, Errors: 0, Skipped: 0 Tests run: 269, Failures: 0, Errors: 0, Skipped: 182 Tests run: 165, Failures: 0, Errors: 0, Skipped: 15 > ABFS: Fix client side throttling for read > - > > Key: HADOOP-15778 > URL: https://issues.apache.org/jira/browse/HADOOP-15778 > Project: Hadoop Common > Issue Type: Sub-task >Reporter: Sneha Varma >Assignee: Sneha Varma >Priority: Minor > Attachments: HADOOP-15778-HADOOP-15407-001.patch > > > 1. The content length for ReadFile in updateMetrics of > AbfsClientThrottlingIntercept is incorrect for cases when the request fails. > It is currently equal to the number of bytes that are read whereas it should > be equal to the number of bytes requested. > 2. sendingRequest of AbfsClientThrottlingIntercept at AbfsRestOperation > should be called irrespective of whether the request has body. -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-issues-h...@hadoop.apache.org
[jira] [Created] (HADOOP-15778) ABFS: Fix client side throttling for read
Sneha Varma created HADOOP-15778: Summary: ABFS: Fix client side throttling for read Key: HADOOP-15778 URL: https://issues.apache.org/jira/browse/HADOOP-15778 Project: Hadoop Common Issue Type: Sub-task Reporter: Sneha Varma 1. The content length for ReadFile in updateMetrics of AbfsClientThrottlingIntercept is incorrect for cases when the request fails. It is currently equal to the number of bytes that are read whereas it should be equal to the number of bytes requested. 2. sendingRequest of AbfsClientThrottlingIntercept at AbfsRestOperation should be called irrespective of whether the request has body. -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-issues-h...@hadoop.apache.org
[jira] [Issue Comment Deleted] (HADOOP-15740) ABFS: Check variable names during initialization of AbfsClientThrottlingIntercept
[ https://issues.apache.org/jira/browse/HADOOP-15740?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Sneha Varma updated HADOOP-15740: - Comment: was deleted (was: Thanks a lot Thomas & Da Zhou, Below are the ABFS test results: *Account without namespace support* Tests run: 29, Failures: 0, Errors: 0, Skipped: 0 Tests run: 268, Failures: 0, Errors: 0, Skipped: 182 Tests run: 167, Failures: 0, Errors: 0, Skipped: 27 *Account with namespace support*: Tests run: 29, Failures: 0, Errors: 0, Skipped: 0 Tests run: 268, Failures: 0, Errors: 0, Skipped: 30 Tests run: 167, Failures: 0, Errors: 0, Skipped: 27) > ABFS: Check variable names during initialization of > AbfsClientThrottlingIntercept > -- > > Key: HADOOP-15740 > URL: https://issues.apache.org/jira/browse/HADOOP-15740 > Project: Hadoop Common > Issue Type: Sub-task >Reporter: Sneha Varma >Assignee: Sneha Varma >Priority: Minor > Attachments: HADOOP-15740-HADOOP-15407-001.patch > > > In the initializeSingleton function of the AbfsClientThrottlingIntercept the > local variable name is same as global variable isAutoThrottlingEnabled > because of which the global isAutoThrottlingEnabled is not being set to true. > -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-issues-h...@hadoop.apache.org
[jira] [Commented] (HADOOP-15740) ABFS: Check variable names during initialization of AbfsClientThrottlingIntercept
[ https://issues.apache.org/jira/browse/HADOOP-15740?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16612539#comment-16612539 ] Sneha Varma commented on HADOOP-15740: -- Thanks a lot Thomas & Da Zhou, Below are the ABFS test results: *Account without namespace support* Tests run: 29, Failures: 0, Errors: 0, Skipped: 0 Tests run: 268, Failures: 0, Errors: 0, Skipped: 182 Tests run: 167, Failures: 0, Errors: 0, Skipped: 27 *Account with namespace support*: Tests run: 29, Failures: 0, Errors: 0, Skipped: 0 Tests run: 268, Failures: 0, Errors: 0, Skipped: 30 Tests run: 167, Failures: 0, Errors: 0, Skipped: 27 > ABFS: Check variable names during initialization of > AbfsClientThrottlingIntercept > -- > > Key: HADOOP-15740 > URL: https://issues.apache.org/jira/browse/HADOOP-15740 > Project: Hadoop Common > Issue Type: Sub-task >Reporter: Sneha Varma >Assignee: Sneha Varma >Priority: Minor > Attachments: HADOOP-15740-HADOOP-15407-001.patch > > > In the initializeSingleton function of the AbfsClientThrottlingIntercept the > local variable name is same as global variable isAutoThrottlingEnabled > because of which the global isAutoThrottlingEnabled is not being set to true. > -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-issues-h...@hadoop.apache.org
[jira] [Comment Edited] (HADOOP-15740) ABFS: Check variable names during initialization of AbfsClientThrottlingIntercept
[ https://issues.apache.org/jira/browse/HADOOP-15740?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16612534#comment-16612534 ] Sneha Varma edited comment on HADOOP-15740 at 9/12/18 6:01 PM: --- Thanks a lot Thomas & Da Zhou, Below are the ABFS test results: *Account without namespace support* Tests run: 29, Failures: 0, Errors: 0, Skipped: 0 Tests run: 268, Failures: 0, Errors: 0, Skipped: 182 Tests run: 167, Failures: 0, Errors: 0, Skipped: 27 *Account with namespace support*: Tests run: 29, Failures: 0, Errors: 0, Skipped: 0 Tests run: 268, Failures: 0, Errors: 0, Skipped: 30 Tests run: 167, Failures: 0, Errors: 0, Skipped: 27 was (Author: sneha_varma): Thanks a lot Thomas & Da Zhou, Below are the ABFS tests result: ** *Account without namespace support* Tests run: 29, Failures: 0, Errors: 0, Skipped: 0 Tests run: 268, Failures: 0, Errors: 0, Skipped: 182 Tests run: 167, Failures: 0, Errors: 0, Skipped: 27 *Account with namespace support*: Tests run: 29, Failures: 0, Errors: 0, Skipped: 0 Tests run: 268, Failures: 0, Errors: 0, Skipped: 30 Tests run: 167, Failures: 0, Errors: 0, Skipped: 27 > ABFS: Check variable names during initialization of > AbfsClientThrottlingIntercept > -- > > Key: HADOOP-15740 > URL: https://issues.apache.org/jira/browse/HADOOP-15740 > Project: Hadoop Common > Issue Type: Sub-task >Reporter: Sneha Varma >Assignee: Sneha Varma >Priority: Minor > Attachments: HADOOP-15740-HADOOP-15407-001.patch > > > In the initializeSingleton function of the AbfsClientThrottlingIntercept the > local variable name is same as global variable isAutoThrottlingEnabled > because of which the global isAutoThrottlingEnabled is not being set to true. > -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-issues-h...@hadoop.apache.org
[jira] [Commented] (HADOOP-15740) ABFS: Check variable names during initialization of AbfsClientThrottlingIntercept
[ https://issues.apache.org/jira/browse/HADOOP-15740?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16612534#comment-16612534 ] Sneha Varma commented on HADOOP-15740: -- Thanks a lot Thomas & Da Zhou, Below are the ABFS tests result: ** *Account without namespace support* Tests run: 29, Failures: 0, Errors: 0, Skipped: 0 Tests run: 268, Failures: 0, Errors: 0, Skipped: 182 Tests run: 167, Failures: 0, Errors: 0, Skipped: 27 *Account with namespace support*: Tests run: 29, Failures: 0, Errors: 0, Skipped: 0 Tests run: 268, Failures: 0, Errors: 0, Skipped: 30 Tests run: 167, Failures: 0, Errors: 0, Skipped: 27 > ABFS: Check variable names during initialization of > AbfsClientThrottlingIntercept > -- > > Key: HADOOP-15740 > URL: https://issues.apache.org/jira/browse/HADOOP-15740 > Project: Hadoop Common > Issue Type: Sub-task >Reporter: Sneha Varma >Assignee: Sneha Varma >Priority: Minor > Attachments: HADOOP-15740-HADOOP-15407-001.patch > > > In the initializeSingleton function of the AbfsClientThrottlingIntercept the > local variable name is same as global variable isAutoThrottlingEnabled > because of which the global isAutoThrottlingEnabled is not being set to true. > -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-issues-h...@hadoop.apache.org
[jira] [Updated] (HADOOP-15740) ABFS: Check variable names during initialization of AbfsClientThrottlingIntercept
[ https://issues.apache.org/jira/browse/HADOOP-15740?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Sneha Varma updated HADOOP-15740: - Description: In the initializeSingleton function of the AbfsClientThrottlingIntercept the local variable name is same as global variable isAutoThrottlingEnabled because of which the global isAutoThrottlingEnabled is not being set to true. > ABFS: Check variable names during initialization of > AbfsClientThrottlingIntercept > -- > > Key: HADOOP-15740 > URL: https://issues.apache.org/jira/browse/HADOOP-15740 > Project: Hadoop Common > Issue Type: Sub-task >Reporter: Sneha Varma >Assignee: Sneha Varma >Priority: Minor > Attachments: HADOOP-15740-HADOOP-15407-001.patch > > > In the initializeSingleton function of the AbfsClientThrottlingIntercept the > local variable name is same as global variable isAutoThrottlingEnabled > because of which the global isAutoThrottlingEnabled is not being set to true. > -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-issues-h...@hadoop.apache.org
[jira] [Updated] (HADOOP-15740) ABFS: Check variable names during initialization of AbfsClientThrottlingIntercept
[ https://issues.apache.org/jira/browse/HADOOP-15740?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Sneha Varma updated HADOOP-15740: - Attachment: HADOOP-15740-HADOOP-15407-001.patch Status: Patch Available (was: Open) > ABFS: Check variable names during initialization of > AbfsClientThrottlingIntercept > -- > > Key: HADOOP-15740 > URL: https://issues.apache.org/jira/browse/HADOOP-15740 > Project: Hadoop Common > Issue Type: Sub-task >Reporter: Sneha Varma >Assignee: Sneha Varma >Priority: Minor > Attachments: HADOOP-15740-HADOOP-15407-001.patch > > -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-issues-h...@hadoop.apache.org
[jira] [Created] (HADOOP-15740) ABFS: Check variable names during initialization of AbfsClientThrottlingIntercept
Sneha Varma created HADOOP-15740: Summary: ABFS: Check variable names during initialization of AbfsClientThrottlingIntercept Key: HADOOP-15740 URL: https://issues.apache.org/jira/browse/HADOOP-15740 Project: Hadoop Common Issue Type: Sub-task Reporter: Sneha Varma Assignee: Sneha Varma -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-issues-h...@hadoop.apache.org
[jira] [Updated] (HADOOP-15703) ABFS - Implement client-side throttling
[ https://issues.apache.org/jira/browse/HADOOP-15703?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Sneha Varma updated HADOOP-15703: - Status: Open (was: Patch Available) > ABFS - Implement client-side throttling > > > Key: HADOOP-15703 > URL: https://issues.apache.org/jira/browse/HADOOP-15703 > Project: Hadoop Common > Issue Type: Sub-task >Reporter: Sneha Varma >Priority: Major > Attachments: HADOOP-15703-HADOOP-15407-001.patch > > > Big data workloads frequently exceed the AzureBlobFS max ingress and egress > limits > (https://docs.microsoft.com/en-us/azure/storage/common/storage-scalability-targets). > For example, the max ingress limit for a GRS account in the United States is > currently 10 Gbps. When the limit is exceeded, the AzureBlobFS service fails > a percentage of incoming requests, and this causes the client to initiate the > retry policy. The retry policy delays requests by sleeping, but the sleep > duration is independent of the client throughput and account limit. This > results in low throughput, due to the high number of failed requests and > thrashing causes by the retry policy. > To fix this, we introduce a client-side throttle which minimizes failed > requests and maximizes throughput. -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-issues-h...@hadoop.apache.org
[jira] [Updated] (HADOOP-15703) ABFS - Implement client-side throttling
[ https://issues.apache.org/jira/browse/HADOOP-15703?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Sneha Varma updated HADOOP-15703: - Attachment: (was: HADOOP-15703-HADOOP-15407-001.patch) > ABFS - Implement client-side throttling > > > Key: HADOOP-15703 > URL: https://issues.apache.org/jira/browse/HADOOP-15703 > Project: Hadoop Common > Issue Type: Sub-task >Reporter: Sneha Varma >Priority: Major > Attachments: HADOOP-15703-HADOOP-15407-001.patch > > > Big data workloads frequently exceed the AzureBlobFS max ingress and egress > limits > (https://docs.microsoft.com/en-us/azure/storage/common/storage-scalability-targets). > For example, the max ingress limit for a GRS account in the United States is > currently 10 Gbps. When the limit is exceeded, the AzureBlobFS service fails > a percentage of incoming requests, and this causes the client to initiate the > retry policy. The retry policy delays requests by sleeping, but the sleep > duration is independent of the client throughput and account limit. This > results in low throughput, due to the high number of failed requests and > thrashing causes by the retry policy. > To fix this, we introduce a client-side throttle which minimizes failed > requests and maximizes throughput. -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-issues-h...@hadoop.apache.org
[jira] [Updated] (HADOOP-15703) ABFS - Implement client-side throttling
[ https://issues.apache.org/jira/browse/HADOOP-15703?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Sneha Varma updated HADOOP-15703: - Attachment: HADOOP-15703-HADOOP-15407-001.patch > ABFS - Implement client-side throttling > > > Key: HADOOP-15703 > URL: https://issues.apache.org/jira/browse/HADOOP-15703 > Project: Hadoop Common > Issue Type: Sub-task >Reporter: Sneha Varma >Priority: Major > Attachments: HADOOP-15703-HADOOP-15407-001.patch > > > Big data workloads frequently exceed the AzureBlobFS max ingress and egress > limits > (https://docs.microsoft.com/en-us/azure/storage/common/storage-scalability-targets). > For example, the max ingress limit for a GRS account in the United States is > currently 10 Gbps. When the limit is exceeded, the AzureBlobFS service fails > a percentage of incoming requests, and this causes the client to initiate the > retry policy. The retry policy delays requests by sleeping, but the sleep > duration is independent of the client throughput and account limit. This > results in low throughput, due to the high number of failed requests and > thrashing causes by the retry policy. > To fix this, we introduce a client-side throttle which minimizes failed > requests and maximizes throughput. -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-issues-h...@hadoop.apache.org
[jira] [Updated] (HADOOP-15703) ABFS - Implement client-side throttling
[ https://issues.apache.org/jira/browse/HADOOP-15703?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Sneha Varma updated HADOOP-15703: - Attachment: HADOOP-15703-HADOOP-15407-001.patch > ABFS - Implement client-side throttling > > > Key: HADOOP-15703 > URL: https://issues.apache.org/jira/browse/HADOOP-15703 > Project: Hadoop Common > Issue Type: Sub-task >Reporter: Sneha Varma >Priority: Major > Attachments: HADOOP-15703-HADOOP-15407-001.patch > > > Big data workloads frequently exceed the AzureBlobFS max ingress and egress > limits > (https://docs.microsoft.com/en-us/azure/storage/common/storage-scalability-targets). > For example, the max ingress limit for a GRS account in the United States is > currently 10 Gbps. When the limit is exceeded, the AzureBlobFS service fails > a percentage of incoming requests, and this causes the client to initiate the > retry policy. The retry policy delays requests by sleeping, but the sleep > duration is independent of the client throughput and account limit. This > results in low throughput, due to the high number of failed requests and > thrashing causes by the retry policy. > To fix this, we introduce a client-side throttle which minimizes failed > requests and maximizes throughput. -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-issues-h...@hadoop.apache.org
[jira] [Updated] (HADOOP-15703) ABFS - Implement client-side throttling
[ https://issues.apache.org/jira/browse/HADOOP-15703?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Sneha Varma updated HADOOP-15703: - Attachment: (was: HADOOP-15703-001.patch) > ABFS - Implement client-side throttling > > > Key: HADOOP-15703 > URL: https://issues.apache.org/jira/browse/HADOOP-15703 > Project: Hadoop Common > Issue Type: Sub-task >Reporter: Sneha Varma >Priority: Major > > Big data workloads frequently exceed the AzureBlobFS max ingress and egress > limits > (https://docs.microsoft.com/en-us/azure/storage/common/storage-scalability-targets). > For example, the max ingress limit for a GRS account in the United States is > currently 10 Gbps. When the limit is exceeded, the AzureBlobFS service fails > a percentage of incoming requests, and this causes the client to initiate the > retry policy. The retry policy delays requests by sleeping, but the sleep > duration is independent of the client throughput and account limit. This > results in low throughput, due to the high number of failed requests and > thrashing causes by the retry policy. > To fix this, we introduce a client-side throttle which minimizes failed > requests and maximizes throughput. -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-issues-h...@hadoop.apache.org
[jira] [Updated] (HADOOP-15703) ABFS - Implement client-side throttling
[ https://issues.apache.org/jira/browse/HADOOP-15703?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Sneha Varma updated HADOOP-15703: - Summary: ABFS - Implement client-side throttling (was: AzureBlobFS - Implement client-side throttling ) > ABFS - Implement client-side throttling > > > Key: HADOOP-15703 > URL: https://issues.apache.org/jira/browse/HADOOP-15703 > Project: Hadoop Common > Issue Type: Sub-task >Reporter: Sneha Varma >Priority: Major > Attachments: HADOOP-15703-001.patch > > > Big data workloads frequently exceed the AzureBlobFS max ingress and egress > limits > (https://docs.microsoft.com/en-us/azure/storage/common/storage-scalability-targets). > For example, the max ingress limit for a GRS account in the United States is > currently 10 Gbps. When the limit is exceeded, the AzureBlobFS service fails > a percentage of incoming requests, and this causes the client to initiate the > retry policy. The retry policy delays requests by sleeping, but the sleep > duration is independent of the client throughput and account limit. This > results in low throughput, due to the high number of failed requests and > thrashing causes by the retry policy. > To fix this, we introduce a client-side throttle which minimizes failed > requests and maximizes throughput. -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-issues-h...@hadoop.apache.org
[jira] [Updated] (HADOOP-15703) AzureBlobFS - Implement client-side throttling
[ https://issues.apache.org/jira/browse/HADOOP-15703?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Sneha Varma updated HADOOP-15703: - Attachment: HADOOP-15703-001.patch Status: Patch Available (was: Open) > AzureBlobFS - Implement client-side throttling > --- > > Key: HADOOP-15703 > URL: https://issues.apache.org/jira/browse/HADOOP-15703 > Project: Hadoop Common > Issue Type: Sub-task >Reporter: Sneha Varma >Priority: Major > Attachments: HADOOP-15703-001.patch > > > Big data workloads frequently exceed the AzureBlobFS max ingress and egress > limits > (https://docs.microsoft.com/en-us/azure/storage/common/storage-scalability-targets). > For example, the max ingress limit for a GRS account in the United States is > currently 10 Gbps. When the limit is exceeded, the AzureBlobFS service fails > a percentage of incoming requests, and this causes the client to initiate the > retry policy. The retry policy delays requests by sleeping, but the sleep > duration is independent of the client throughput and account limit. This > results in low throughput, due to the high number of failed requests and > thrashing causes by the retry policy. > To fix this, we introduce a client-side throttle which minimizes failed > requests and maximizes throughput. -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-issues-h...@hadoop.apache.org
[jira] [Updated] (HADOOP-15703) AzureBlobFS - Implement client-side throttling
[ https://issues.apache.org/jira/browse/HADOOP-15703?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Sneha Varma updated HADOOP-15703: - Summary: AzureBlobFS - Implement client-side throttling (was: AzureBlobFS - implement client-side throttling ) > AzureBlobFS - Implement client-side throttling > --- > > Key: HADOOP-15703 > URL: https://issues.apache.org/jira/browse/HADOOP-15703 > Project: Hadoop Common > Issue Type: Sub-task >Reporter: Sneha Varma >Priority: Major > > Big data workloads frequently exceed the AzureBlobFS max ingress and egress > limits > (https://docs.microsoft.com/en-us/azure/storage/common/storage-scalability-targets). > For example, the max ingress limit for a GRS account in the United States is > currently 10 Gbps. When the limit is exceeded, the AzureBlobFS service fails > a percentage of incoming requests, and this causes the client to initiate the > retry policy. The retry policy delays requests by sleeping, but the sleep > duration is independent of the client throughput and account limit. This > results in low throughput, due to the high number of failed requests and > thrashing causes by the retry policy. > To fix this, we introduce a client-side throttle which minimizes failed > requests and maximizes throughput. -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-issues-h...@hadoop.apache.org
[jira] [Created] (HADOOP-15703) AzureBlobFS - implement client-side throttling
Sneha Varma created HADOOP-15703: Summary: AzureBlobFS - implement client-side throttling Key: HADOOP-15703 URL: https://issues.apache.org/jira/browse/HADOOP-15703 Project: Hadoop Common Issue Type: Sub-task Reporter: Sneha Varma Big data workloads frequently exceed the AzureBlobFS max ingress and egress limits (https://docs.microsoft.com/en-us/azure/storage/common/storage-scalability-targets). For example, the max ingress limit for a GRS account in the United States is currently 10 Gbps. When the limit is exceeded, the AzureBlobFS service fails a percentage of incoming requests, and this causes the client to initiate the retry policy. The retry policy delays requests by sleeping, but the sleep duration is independent of the client throughput and account limit. This results in low throughput, due to the high number of failed requests and thrashing causes by the retry policy. To fix this, we introduce a client-side throttle which minimizes failed requests and maximizes throughput. -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-issues-h...@hadoop.apache.org