[jira] [Commented] (HBASE-5162) Basic client pushback mechanism

["Lars Hofhansl (Commented) (JIRA)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/HBASE-5162?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13207068#comment-13207068 ] 

Lars Hofhansl commented on HBASE-5162:
--------------------------------------

The exception part is nice, because it works without touching RPC.

I wonder if that should be a phased approach?
I.e. if there is light pressure, just delay the operations in the server threads (uses up server threads and memory, but will be transparent to the client, who will just see a slightly less performant server).
When the pressure gets higher despite the server delays, we'd throw exceptions back to the client, and if that is not enough we block as we do now.

The interesting part is: How exactly would we measure the pressure? Based on the number of a storefiles and the current rate of updates?
                
> Basic client pushback mechanism
> -------------------------------
>
>                 Key: HBASE-5162
>                 URL: https://issues.apache.org/jira/browse/HBASE-5162
>             Project: HBase
>          Issue Type: New Feature
>    Affects Versions: 0.92.0
>            Reporter: Jean-Daniel Cryans
>             Fix For: 0.94.0
>
>
> The current blocking we do when we are close to some limits (memstores over the multiplier factor, too many store files, global memstore memory) is bad, too coarse and confusing. After hitting HBASE-5161, it really becomes obvious that we need something better.
> I did a little brainstorm with Stack, we came up quickly with two solutions:
>  - Send some exception to the client, like OverloadedException, that's thrown when some situation happens like getting past the low memory barrier. It would be thrown when the client gets a handler and does some check while putting or deleting. The client would treat this a retryable exception but ideally wouldn't check .META. for a new location. It could be fancy and have multiple levels of pushback, like send the exception to 25% of the clients, and then go up if the situation persists. Should be "easy" to implement but we'll be using a lot more IO to send the payload over and over again (but at least it wouldn't sit in the RS's memory).
>  - Send a message alongside a successful put or delete to tell the client to slow down a little, this way we don't have to do back and forth with the payload between the client and the server. It's a cleaner (I think) but more involved solution.
> In every case the RS should do very obvious things to notify the operators of this situation, through logs, web UI, metrics, etc.
> Other ideas?

--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa
For more information on JIRA, see: http://www.atlassian.com/software/jira