[ https://issues.apache.org/jira/browse/HDFS-15025?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17202755#comment-17202755 ]
YaYun Wang edited comment on HDFS-15025 at 9/27/20, 7:19 AM: ------------------------------------------------------------- [~ayushtkn],[~liuml07],Sorry didn't notice that before, I have checked the relevant code, the failure with the test case of HDFS-15600 is indeed due to NVDIMM newly added, which changes the ordinal of enum of "StorageType". Now, i have two solutions: the first one is to put NVDIMM at the end of all storage types and modify the comment In "StorageType", the other one is to keep the storage type sorted by speed. of course, both of the above solutions must modify "TestRouterQuota" because of "TestRouterQuota.testStorageTypeQuota" just set five quotas for StorageType(RAM_DISK, SSD, DISK, ARCHIVE and PROVIDED) without NVDIMM. I prefer the second solution, that is, StorageType is still "sorted by the speed of the storage types, from fast to slow", and add parameter of quota for NVDIMM, such as {code:java} verifyTypeQuotaAndConsume(new long[] {-1, -1, -1, ssQuota * 2, -1, -1}, null, usage);{code} So, which solution do you think is better? was (Author: wangyayun): [~ayushtkn],[~liuml07],Sorry didn't notice that before, I have checked the relevant code, the failure with the test case of HDFS-15600 is indeed due to NVDIMM newly added, which changes the ordinal of enum of "StorageType". Now, i have two solutions: the first one is to put NVDIMM at the end of all storage types and modify the comment In "StorageType", the other one is to keep the storage type sorted by speed. of course, both of the above solutions must modify "TestRouterQuota" because of "TestRouterQuota.testStorageTypeQuota" just set five quotas for StorageType(RAM_DISK, SSD, DISK, ARCHIVE and PROVIDED) without NVDIMM. I prefer the second solution, that is, StorageType is still "sorted by the speed of the storage types, from fast to slow", and add parameter of quota for NVDIMM, such as verifyTypeQuotaAndConsume(new long[] \{-1, -1, -1, ssQuota * 2, -1, -1}, null, usage); verifyTypeQuotaAndConsume(new long[] \{-1, -1, -1, ssQuota * 2, -1, -1}, null, usage); So, which solution do you think is better? > Applying NVDIMM storage media to HDFS > ------------------------------------- > > Key: HDFS-15025 > URL: https://issues.apache.org/jira/browse/HDFS-15025 > Project: Hadoop HDFS > Issue Type: New Feature > Components: datanode, hdfs > Reporter: YaYun Wang > Assignee: YaYun Wang > Priority: Major > Labels: pull-request-available > Fix For: 3.4.0 > > Attachments: Applying NVDIMM to HDFS.pdf, HDFS-15025.001.patch, > HDFS-15025.002.patch, HDFS-15025.003.patch, HDFS-15025.004.patch, > HDFS-15025.005.patch, HDFS-15025.006.patch, NVDIMM_patch(WIP).patch > > Time Spent: 12h 10m > Remaining Estimate: 0h > > The non-volatile memory NVDIMM is faster than SSD, it can be used > simultaneously with RAM, DISK, SSD. The data of HDFS stored directly on > NVDIMM can not only improves the response rate of HDFS, but also ensure the > reliability of the data. -- This message was sent by Atlassian Jira (v8.3.4#803005) --------------------------------------------------------------------- To unsubscribe, e-mail: hdfs-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: hdfs-issues-h...@hadoop.apache.org