Uploaded image for project: 'IMPALA'
  1. IMPALA
  2. IMPALA-4835

HDFS scans should operate with a constrained number of I/O buffers

    XMLWordPrintableJSON

Details

    Description

      The HDFS scan nodes should be able to operate with a fixed number of I/O buffers in most cases (excluding very large rows). We should modify them to claim a reservation upfront and use this for all disk I/O.

      This probably also requires switching DiskIoMgr to allocate memory from BufferPool.

      Attachments

        Issue Links

          blocks

          Epic - Created by Jira Software - do not edit or delete. Issue type for a big user story that needs to be broken down. IMPALA-6460 More flexible memory-based admission control policies

          • Major - Major loss of function.
          • Resolved
          breaks

          Sub-task - The sub-task of the issue IMPALA-6587 Crash in DiskMgr::AllocateBuffersForRange

          • Major - Major loss of function.
          • Resolved

          Sub-task - The sub-task of the issue IMPALA-6592 Fix test gap - no test of handling for invalid/unsupported Parquet codec

          • Major - Major loss of function.
          • Resolved

          Sub-task - The sub-task of the issue IMPALA-6594 Various tests failing (some flaky) with memory limit exceeded

          • Major - Major loss of function.
          • Resolved

          Sub-task - The sub-task of the issue IMPALA-6598 Investigate memory requirement regression from scanner buffer pool change

          • Major - Major loss of function.
          • Resolved

          Bug - A problem which impairs or prevents the functions of the product. IMPALA-6588 test_compute_stats_tablesample failing with "Cancelled"

          • Blocker - Blocks development and/or testing work, production could not run
          • Resolved

          Bug - A problem which impairs or prevents the functions of the product. IMPALA-6585 test_low_mem_limit_q21 flaky under ASAN

          • Critical - Crashes, loss of data, severe memory leak.
          • Resolved
          depends upon

          Sub-task - The sub-task of the issue IMPALA-6587 Crash in DiskMgr::AllocateBuffersForRange

          • Major - Major loss of function.
          • Resolved

          Sub-task - The sub-task of the issue IMPALA-6592 Fix test gap - no test of handling for invalid/unsupported Parquet codec

          • Major - Major loss of function.
          • Resolved

          Sub-task - The sub-task of the issue IMPALA-6594 Various tests failing (some flaky) with memory limit exceeded

          • Major - Major loss of function.
          • Resolved

          Sub-task - The sub-task of the issue IMPALA-6598 Investigate memory requirement regression from scanner buffer pool change

          • Major - Major loss of function.
          • Resolved

          Improvement - An improvement or enhancement to an existing feature or task. IMPALA-5389 Clarify lifetime of DiskIoMgr::BufferDescriptor objects

          • Minor - Minor loss of function, or other problem where easy workaround is present.
          • Resolved
          is blocked by

          Bug - A problem which impairs or prevents the functions of the product. IMPALA-6564 Queries randomly fail with "CANCELLED" due to a race with IssueInitialRanges()

          • Blocker - Blocks development and/or testing work, production could not run
          • Resolved
          is depended upon by

          Improvement - An improvement or enhancement to an existing feature or task. IMPALA-6673 Be smarter about I/O patterns for Parquet scan ranges

          • Major - Major loss of function.
          • Open

          Improvement - An improvement or enhancement to an existing feature or task. IMPALA-6875 Reservations for ORC scanner

          • Major - Major loss of function.
          • Open

          Improvement - An improvement or enhancement to an existing feature or task. IMPALA-6555 Clean up relationship between DiskIoMgr::min_buffer_size_ and BufferPool::min_buffer_len_

          • Minor - Minor loss of function, or other problem where easy workaround is present.
          • Resolved
          is duplicated by

          Improvement - An improvement or enhancement to an existing feature or task. IMPALA-3209 Optimize scanner memory usage and make scan nodes adhere to a memory constraint

          • Major - Major loss of function.
          • Resolved

          Activity

            People

              tarmstrong Tim Armstrong
              tarmstrong Tim Armstrong
              Votes:
              0 Vote for this issue
              Watchers:
              6 Start watching this issue

              Dates

                Created:
                Updated:
                Resolved: