You are viewing a plain text version of this content. The canonical link for it is here.
Posted to user@cassandra.apache.org by Roland Gude <ro...@yoochoose.com> on 2011/08/29 10:39:17 UTC
flushwriter all time blocked
Hi all,
On a 0.7.8 cluster In tpstats i can see flushwriter stage having several tasks in state all-time-blocked (immendiatly after node restart its 8 but grows over time to around 300). What does it mean (or how can I find out) and what can I do about it?
--
YOOCHOOSE GmbH
Roland Gude
Software Engineer
Im Mediapark 8, 50670 Köln
+49 221 4544151 (Tel)
+49 221 4544159 (Fax)
+49 171 7894057 (Mobil)
Email: roland.gude@yoochoose.com
WWW: www.yoochoose.com<http://www.yoochoose.com/>
YOOCHOOSE GmbH
Geschäftsführer: Dr. Uwe Alkemper, Michael Friedmann
Handelsregister: Amtsgericht Köln HRB 65275
Ust-Ident-Nr: DE 264 773 520
Sitz der Gesellschaft: Köln
AW: flushwriter all time blocked
Posted by Roland Gude <ro...@yoochoose.com>.
Hi,
This still leaves me puzzled.
Is it a bad thing?
Why is it happening?
And what does "blocked before being accepted" mean? Does it mean Cassandra did not even try to put the task into a queue?
Thanks for enlightening me,
roland
-----Ursprüngliche Nachricht-----
Von: Jonathan Ellis [mailto:jbellis@gmail.com]
Gesendet: Montag, 29. August 2011 15:10
An: user@cassandra.apache.org
Betreff: Re: flushwriter all time blocked
the javadoc for the mbeans explains:
/**
* Get the number of tasks that had blocked before being accepted (or
* rejected).
*/
public int getTotalBlockedTasks();
/**
* Get the number of tasks currently blocked, waiting to be accepted by
* the executor (because all threads are busy and the backing
queue is full).
*/
public int getCurrentlyBlockedTasks();
On Mon, Aug 29, 2011 at 3:39 AM, Roland Gude <ro...@yoochoose.com> wrote:
> Hi all,
>
>
>
> On a 0.7.8 cluster In tpstats i can see flushwriter stage having several
> tasks in state all-time-blocked (immendiatly after node restart its 8 but
> grows over time to around 300). What does it mean (or how can I find out)
> and what can I do about it?
>
>
>
> --
>
> YOOCHOOSE GmbH
>
>
>
> Roland Gude
>
> Software Engineer
>
>
>
> Im Mediapark 8, 50670 Köln
>
>
>
> +49 221 4544151 (Tel)
>
> +49 221 4544159 (Fax)
>
> +49 171 7894057 (Mobil)
>
>
>
>
>
> Email: roland.gude@yoochoose.com
>
> WWW: www.yoochoose.com
>
>
>
> YOOCHOOSE GmbH
>
> Geschäftsführer: Dr. Uwe Alkemper, Michael Friedmann
>
> Handelsregister: Amtsgericht Köln HRB 65275
>
> Ust-Ident-Nr: DE 264 773 520
>
> Sitz der Gesellschaft: Köln
>
>
--
Jonathan Ellis
Project Chair, Apache Cassandra
co-founder of DataStax, the source for professional Cassandra support
http://www.datastax.com
Re: flushwriter all time blocked
Posted by Jonathan Ellis <jb...@gmail.com>.
the javadoc for the mbeans explains:
/**
* Get the number of tasks that had blocked before being accepted (or
* rejected).
*/
public int getTotalBlockedTasks();
/**
* Get the number of tasks currently blocked, waiting to be accepted by
* the executor (because all threads are busy and the backing
queue is full).
*/
public int getCurrentlyBlockedTasks();
On Mon, Aug 29, 2011 at 3:39 AM, Roland Gude <ro...@yoochoose.com> wrote:
> Hi all,
>
>
>
> On a 0.7.8 cluster In tpstats i can see flushwriter stage having several
> tasks in state all-time-blocked (immendiatly after node restart its 8 but
> grows over time to around 300). What does it mean (or how can I find out)
> and what can I do about it?
>
>
>
> --
>
> YOOCHOOSE GmbH
>
>
>
> Roland Gude
>
> Software Engineer
>
>
>
> Im Mediapark 8, 50670 Köln
>
>
>
> +49 221 4544151 (Tel)
>
> +49 221 4544159 (Fax)
>
> +49 171 7894057 (Mobil)
>
>
>
>
>
> Email: roland.gude@yoochoose.com
>
> WWW: www.yoochoose.com
>
>
>
> YOOCHOOSE GmbH
>
> Geschäftsführer: Dr. Uwe Alkemper, Michael Friedmann
>
> Handelsregister: Amtsgericht Köln HRB 65275
>
> Ust-Ident-Nr: DE 264 773 520
>
> Sitz der Gesellschaft: Köln
>
>
--
Jonathan Ellis
Project Chair, Apache Cassandra
co-founder of DataStax, the source for professional Cassandra support
http://www.datastax.com