hadoop-yarn-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Jonathan Eagles (JIRA)" <j...@apache.org>
Subject [jira] [Updated] (YARN-3448) Add Rolling Time To Lives Level DB Plugin Capabilities
Date Thu, 23 Apr 2015 00:49:39 GMT

     [ https://issues.apache.org/jira/browse/YARN-3448?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]

Jonathan Eagles updated YARN-3448:
----------------------------------
    Attachment: YARN-3448.12.patch

Improved the patch further by running the code with a java profile. This patch is 25% faster
and generates roughly 20% smaller database than the previous version.
 - Removed unnecessary PREFIX since each type is in its own database and is not needed to
distinguish.
- Removed unused invisible related entities to reduce to reduce further operations.
- Changed database serialization method to more quickly generate a smaller serialized size
of the primary filter values and other info. Library introduced is verified Apache License
2.0 from fast-serialization.
- Profile show much time spent converting Strings to byte arrays. Converted the strings once
and reused for all the database keys.
- Reduced the read cache and write buffer size to take into consideration the 7 day default
retention.
- Removed insert time from start time database. This feature is used to detect changes since
last query, but is not functional since it forces a scan of all data entries. Could be added
back at a later time.


> Add Rolling Time To Lives Level DB Plugin Capabilities
> ------------------------------------------------------
>
>                 Key: YARN-3448
>                 URL: https://issues.apache.org/jira/browse/YARN-3448
>             Project: Hadoop YARN
>          Issue Type: Sub-task
>          Components: timelineserver
>            Reporter: Jonathan Eagles
>            Assignee: Jonathan Eagles
>         Attachments: YARN-3448.1.patch, YARN-3448.10.patch, YARN-3448.12.patch, YARN-3448.2.patch,
YARN-3448.3.patch, YARN-3448.4.patch, YARN-3448.5.patch, YARN-3448.7.patch, YARN-3448.8.patch,
YARN-3448.9.patch
>
>
> For large applications, the majority of the time in LeveldbTimelineStore is spent deleting
old entities record at a time. An exclusive write lock is held during the entire deletion
phase which in practice can be hours. If we are to relax some of the consistency constraints,
other performance enhancing techniques can be employed to maximize the throughput and minimize
locking time.
> Split the 5 sections of the leveldb database (domain, owner, start time, entity, index)
into 5 separate databases. This allows each database to maximize the read cache effectiveness
based on the unique usage patterns of each database. With 5 separate databases each lookup
is much faster. This can also help with I/O to have the entity and index databases on separate
disks.
> Rolling DBs for entity and index DBs. 99.9% of the data are in these two sections 4:1
ration (index to entity) at least for tez. We replace DB record removal with file system removal
if we create a rolling set of databases that age out and can be efficiently removed. To do
this we must place a constraint to always place an entity's events into it's correct rolling
db instance based on start time. This allows us to stitching the data back together while
reading and artificial paging.
> Relax the synchronous writes constraints. If we are willing to accept losing some records
that we not flushed in the operating system during a crash, we can use async writes that can
be much faster.
> Prefer Sequential writes. sequential writes can be several times faster than random writes.
Spend some small effort arranging the writes in such a way that will trend towards sequential
write performance over random write performance.



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

Mime
View raw message