hbase-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Karthick Sankarachary (JIRA)" <j...@apache.org>
Subject [jira] Commented: (HBASE-2939) Allow Client-Side Connection Pooling
Date Wed, 01 Sep 2010 07:03:53 GMT

    [ https://issues.apache.org/jira/browse/HBASE-2939?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12904950#action_12904950
] 

Karthick Sankarachary commented on HBASE-2939:
----------------------------------------------

Ryan,  

Thanks for the feedback - it is much appreciated. Some of the concerns you raised should be
addressed by the second version of the patch which:

* Modifies the "threadlocal" pool's #values method so that it return all connections across
all threads, instead of the one local to the current thread that could potentially be null,
which should resolve the NPEs on client shutdown.
* Defaults the pool type to a bounded "roundrobin" of size 1, which would emulate pre-patch
behavior. On the other hand, the "threadlocal" pool's size is bounded only by the clients'
thread pool size. 

Additionally, it:
* Renames the SharedMap class to PoolMap, for lack of a better name.
* Adds a test case for the PoolMap, which demonstrates how pools of different types and sizes
behave under different loads.
* Constrains the value for "hbase.client.ipc.pool.type" to one of the following: "roundrobin",
and "threadlocal".

To your point about file descriptor limits, the prescribed workaround for that is described
[here|http://www.cloudera.com/blog/2009/03/configuration-parameters-what-can-you-just-ignore/].
We found out about that limit the hard way too.

The 20% speed up in "threadlocal" is good, although it may be even better if the benchmark
runs at high throughputs. The "roundrobin" pool should not be unbounded, which is no longer
the default - in general, it should be somewhere between 1 and the number of user-defined
threads.

> Allow Client-Side Connection Pooling
> ------------------------------------
>
>                 Key: HBASE-2939
>                 URL: https://issues.apache.org/jira/browse/HBASE-2939
>             Project: HBase
>          Issue Type: Improvement
>          Components: client
>    Affects Versions: 0.89.20100621
>            Reporter: Karthick Sankarachary
>         Attachments: HBASE-2939.patch, HBASE-2939.patch
>
>
> By design, the HBase RPC client multiplexes calls to a given region server (or the master
for that matter) over a single socket, access to which is managed by a connection thread defined
in the HBaseClient class. While this approach may suffice for most cases, it tends to break
down in the context of a real-time, multi-threaded server, where latencies need to be lower
and throughputs higher. 
> In brief, the problem is that we dedicate one thread to handle all client-side reads
and writes for a given server, which in turn forces them to share the same socket. As load
increases, this is bound to serialize calls on the client-side. In particular, when the rate
at which calls are submitted to the connection thread is greater than that at which the server
responds, then some of those calls will inevitably end up sitting idle, just waiting their
turn to go over the wire.
> In general, sharing sockets across multiple client threads is a good idea, but limiting
the number of such sockets to one may be overly restrictive for certain cases. Here, we propose
a way of defining multiple sockets per server endpoint, access to which may be managed through
either a load-balancing or thread-local pool. To that end, we define the notion of a SharedMap,
which maps a key to a resource pool, and supports both of those pool types. Specifically,
we will apply that map in the HBaseClient, to associate multiple connection threads with each
server endpoint (denoted by a connection id). 
>  Currently, the SharedMap supports the following types of pools:
>     * A ThreadLocalPool, which represents a pool that builds on the ThreadLocal class.
It essentially binds the resource to the thread from which it is accessed.
>     * A ReusablePool, which represents a pool that builds on the LinkedList class. It
essentially allows resources to be checked out, at which point it is (temporarily) removed
from the pool. When the resource is no longer required, it should be returned to the pool
in order to be reused.
>     * A RoundRobinPool, which represents a pool that stores its resources in an ArrayList.
It load-balances access to its resources by returning a different resource every time a given
key is looked up.
> To control the type and size of the connection pools, we give the user a couple of parameters
(viz. "hbase.client.ipc.pool.type" and "hbase.client.ipc.pool.size"). In case the size of
the pool is set to a non-zero positive number, that is used to cap the number of resources
that a pool may contain for any given key. A size of Integer#MAX_VALUE is interpreted to mean
an unbounded pool.

-- 
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.


Mime
View raw message