RE: Send Buffers overloaded in NDB kernel

[Matthew Boehm]

A benchmarking application wouldn't produce good results if it had to
"do again". Basically this shows that cluster cannot handle 256 threads
of "update non-index" style SQL.

I have this same bench running but updating an index column (int) and
it's going fine so far.

-Matthew

> -----Original Message-----
> From: Pekka.Nousiainen@stripped [mailto:Pekka.Nousiainen@stripped]
> Sent: Tuesday, November 03, 2009 9:58 AM
> To: cluster@stripped
> Subject: Re: Send Buffers overloaded in NDB kernel
> 
> On 091103, Boehm, Matthew wrote:
> > Got temporary error 1218 'Send Buffers overloaded in NDB kernel'
from
> > NDBCLUSTER
> > FATAL: database error, exiting..."
> 
> Temporary errors are not FATAL.  The application must try again,
> possibly any number of times.  In case of data transaction, all
> operations in the transaction must be submitted again.
> 
> This is by design.  Temporary errors are handled by the application.
> 
> (Sort of like interruptible syscalls in unix aka "worse is better".)
> 
> --
> Pekka Nousiainen, Software Engineer, Sun Microsystems / MySQL
> 
> --
> MySQL Cluster Mailing List
> For list archives: http://lists.mysql.com/cluster
> To unsubscribe:
> http://lists.mysql.com/cluster?unsub=1