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.
Пользователь Dave Scott <[email protected]> писал: >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 >> [email protected] >> http://lists.xensource.com/mailman/listinfo/xen-api
_______________________________________________ xen-api mailing list [email protected] http://lists.xensource.com/mailman/listinfo/xen-api
