[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

RE: [Xen-API] Disaster recovery in XCP



Good day.

We actually got a uuid list of running VM at failure point and do xe vm-start 
uuid=...; in cycle and we found it can not be performed parallely (I tried to 
split list to 4-5 part and process them independently but xapi simply queued 
those commands and we got no gain in speed.
 

ÐÐÐÑÐÐÐÐÑÐÐÑ Dave Scott <Dave.Scott@xxxxxxxxxxxxx> ÐÐÑÐÐ:

>Hi George,
>
>Could you describe how your VMs are being restarted? Is it by "xe vm-start 
>--multiple"? We should at some point properly parallelise "--multiple" VM 
>starts, since xapi supports it.
>
>Cheers,
>Dave
>
>> Good day.
>> 
>> Few weeks ago we met an hang in our storage system and reboot all hosts
>> in affected pool.
>> 
>> During 'whole pool boot' I found XCP is pretty slow on pool recovery -
>> it starts VM one-by-one.
>> 
>> It takes a lots of time. I thought, can we starts VM in parallel one-on
>> every host (one VM at time at every available host in the pool)? This
>> will speedup startup process significantly....
>> 
>> 
>> 
>> _______________________________________________
>> xen-api mailing list
>> xen-api@xxxxxxxxxxxxxxxxxxx
>> http://lists.xensource.com/mailman/listinfo/xen-api
_______________________________________________
xen-api mailing list
xen-api@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/mailman/listinfo/xen-api

 


Rackspace

Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.