[
https://issues.apache.org/jira/browse/HADOOP-17461?focusedWorklogId=790033&page=com.atlassian.jira.plugin.system.issuetabpanels:worklog-tabpanel#worklog-790033
]
ASF GitHub Bot logged work on HADOOP-17461:
-------------------------------------------
Author: ASF GitHub Bot
Created on: 12/Jul/22 13:26
Start Date: 12/Jul/22 13:26
Worklog Time Spent: 10m
Work Description: mehakmeet commented on PR #4352:
URL: https://github.com/apache/hadoop/pull/4352#issuecomment-1181759094
Changed the way streams are accessing the thread IOStatistics, now we would
directly get them from the current active context in the stream's constructor
rather than pass them around through the builders, as it didn't seem to add
anything if we can directly get it due to static nature of the context. Also,
made the weakRef as IOstatisticsSnapshot rather than an aggregator and then
cast as discussed above.
Issue Time Tracking
-------------------
Worklog Id: (was: 790033)
Time Spent: 3h 10m (was: 3h)
> Add thread-level IOStatistics Context
> -------------------------------------
>
> Key: HADOOP-17461
> URL: https://issues.apache.org/jira/browse/HADOOP-17461
> Project: Hadoop Common
> Issue Type: Sub-task
> Components: fs, fs/azure, fs/s3
> Affects Versions: 3.3.1
> Reporter: Steve Loughran
> Assignee: Mehakmeet Singh
> Priority: Major
> Labels: pull-request-available
> Time Spent: 3h 10m
> Remaining Estimate: 0h
>
> For effective reporting of the iostatistics of individual worker threads, we
> need a thread-level context which IO components update.
> * this contact needs to be passed in two background thread forming work on
> behalf of a task.
> * IO Components (streams, iterators, filesystems) need to update this context
> statistics as they perform work
> * Without double counting anything.
> I imagine a ThreadLocal IOStatisticContext which will be updated in the
> FileSystem API Calls. This context MUST be passed into the background threads
> used by a task, so that IO is correctly aggregated.
> I don't want streams, listIterators &c to do the updating as there is more
> risk of double counting. However, we need to see their statistics if we want
> to know things like "bytes discarded in backwards seeks". And I don't want to
> be updating a shared context object on every read() call.
> If all we want is store IO (HEAD, GET, DELETE, list performance etc) then the
> FS is sufficient.
> If we do want the stream-specific detail, then I propose
> * caching the context in the constructor
> * updating it only in close() or unbuffer() (as we do from S3AInputStream to
> S3AInstrumenation)
> * excluding those we know the FS already collects.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org
For additional commands, e-mail: common-issues-h...@hadoop.apache.org
