[HBASE-6974] Metric for blocked updates - ASF JIRA

XML

Word

Printable

JSON

Details

Type: Bug
Status: Closed
Priority: Critical
Resolution: Fixed
Affects Version/s: None
Fix Version/s: 0.94.3, 0.95.0
Component/s: None
Labels:
None

Hadoop Flags:

Reviewed

Description

When the disc subsystem cannot keep up with a sustained high write load, a region will eventually block updates to throttle clients.
(HRegion.checkResources).

It would be nice to have a metric for this, so that these occurrences can be tracked.

Attachments

- Sort By Name
- Sort By Date
- Ascending
- Descending

6974-v5.txt
18/Oct/12 20:55
8 kB
Lars Hofhansl
HBASE-6974.patch
16/Oct/12 21:32
5 kB
Michael Drzal
HBASE-6974-v2.patch
17/Oct/12 15:36
8 kB
Michael Drzal
HBASE-6974-v3.patch
17/Oct/12 19:09
8 kB
Michael Drzal
HBASE-6974-v4.patch
17/Oct/12 21:44
9 kB
Michael Drzal

Issue Links

relates to

HBASE-9731 updatesBlockedSeconds RegionServer metric should not be a histogram

Closed

Sub-Tasks

HRegion.mutateRowsWithLocks should call checkResources/checkReadOnly

Closed

Lars Hofhansl

Activity

People

Assignee:: Michael Drzal

Reporter:: Lars Hofhansl

Votes:: 0 Vote for this issue

Watchers:: 6 Start watching this issue

Dates

Created:: 11/Oct/12 00:34

Updated:: 23/Nov/14 01:37

Resolved:: 18/Oct/12 21:59