* [Qemu-devel] [PATCH] migration: Increase default max_downtime from 30ms to 300ms @ 2014-03-27 3:57 Alexey Kardashevskiy 2014-03-27 9:01 ` Markus Armbruster 2014-06-06 12:50 ` Amit Shah 0 siblings, 2 replies; 10+ messages in thread From: Alexey Kardashevskiy @ 2014-03-27 3:57 UTC (permalink / raw) To: qemu-devel; +Cc: Alexey Kardashevskiy, Paolo Bonzini, Dr . David Alan Gilbert The existing timeout is 30ms which on 100MB/s (1Gbit) gives us 3MB/s rate maximum. If we put some load on the guest, it is easy to get page dirtying rate too big so live migration will never complete. In the case of libvirt that means that the guest will be stopped anyway after a timeout specified in the "virsh migrate" command and this normally generates even bigger delay. This changes max_downtime to 300ms which seems to be more reasonable value. Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru> --- migration.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/migration.c b/migration.c index e0e24d4..02bbce9 100644 --- a/migration.c +++ b/migration.c @@ -144,7 +144,7 @@ void process_incoming_migration(QEMUFile *f) * the choice of nanoseconds is because it is the maximum resolution that * get_clock() can achieve. It is an internal measure. All user-visible * units must be in seconds */ -static uint64_t max_downtime = 30000000; +static uint64_t max_downtime = 300000000; uint64_t migrate_max_downtime(void) { -- 1.8.4.rc4 ^ permalink raw reply related [flat|nested] 10+ messages in thread
* Re: [Qemu-devel] [PATCH] migration: Increase default max_downtime from 30ms to 300ms 2014-03-27 3:57 [Qemu-devel] [PATCH] migration: Increase default max_downtime from 30ms to 300ms Alexey Kardashevskiy @ 2014-03-27 9:01 ` Markus Armbruster [not found] ` <53494FD0.8020009@ozlabs.ru> 2014-06-06 12:50 ` Amit Shah 1 sibling, 1 reply; 10+ messages in thread From: Markus Armbruster @ 2014-03-27 9:01 UTC (permalink / raw) To: Alexey Kardashevskiy Cc: Paolo Bonzini, Juan Quintela, qemu-devel, Dr . David Alan Gilbert Adding Juan. Alexey Kardashevskiy <aik@ozlabs.ru> writes: > The existing timeout is 30ms which on 100MB/s (1Gbit) gives us > 3MB/s rate maximum. If we put some load on the guest, it is easy to > get page dirtying rate too big so live migration will never complete. > In the case of libvirt that means that the guest will be stopped > anyway after a timeout specified in the "virsh migrate" command and > this normally generates even bigger delay. > > This changes max_downtime to 300ms which seems to be more > reasonable value. > > Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru> > --- > migration.c | 2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) > > diff --git a/migration.c b/migration.c > index e0e24d4..02bbce9 100644 > --- a/migration.c > +++ b/migration.c > @@ -144,7 +144,7 @@ void process_incoming_migration(QEMUFile *f) > * the choice of nanoseconds is because it is the maximum resolution that > * get_clock() can achieve. It is an internal measure. All user-visible > * units must be in seconds */ > -static uint64_t max_downtime = 30000000; > +static uint64_t max_downtime = 300000000; > > uint64_t migrate_max_downtime(void) > { ^ permalink raw reply [flat|nested] 10+ messages in thread
[parent not found: <53494FD0.8020009@ozlabs.ru>]
[parent not found: <53604D73.1040905@ozlabs.ru>]
* Re: [Qemu-devel] [PATCH] migration: Increase default max_downtime from 30ms to 300ms [not found] ` <53604D73.1040905@ozlabs.ru> @ 2014-05-05 9:17 ` Alexey Kardashevskiy 2014-05-05 11:20 ` Juan Quintela 1 sibling, 0 replies; 10+ messages in thread From: Alexey Kardashevskiy @ 2014-05-05 9:17 UTC (permalink / raw) To: Markus Armbruster Cc: Paolo Bonzini, Juan Quintela, qemu-devel, Dr . David Alan Gilbert On 04/30/2014 11:10 AM, Alexey Kardashevskiy wrote: > On 04/13/2014 12:38 AM, Alexey Kardashevskiy wrote: >> On 03/27/2014 08:01 PM, Markus Armbruster wrote: >>> Adding Juan. >> >> >> Ping? > > > Ping? > > Ping? >> >>> >>> Alexey Kardashevskiy <aik@ozlabs.ru> writes: >>> >>>> The existing timeout is 30ms which on 100MB/s (1Gbit) gives us >>>> 3MB/s rate maximum. If we put some load on the guest, it is easy to >>>> get page dirtying rate too big so live migration will never complete. >>>> In the case of libvirt that means that the guest will be stopped >>>> anyway after a timeout specified in the "virsh migrate" command and >>>> this normally generates even bigger delay. >>>> >>>> This changes max_downtime to 300ms which seems to be more >>>> reasonable value. >>>> >>>> Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru> >>>> --- >>>> migration.c | 2 +- >>>> 1 file changed, 1 insertion(+), 1 deletion(-) >>>> >>>> diff --git a/migration.c b/migration.c >>>> index e0e24d4..02bbce9 100644 >>>> --- a/migration.c >>>> +++ b/migration.c >>>> @@ -144,7 +144,7 @@ void process_incoming_migration(QEMUFile *f) >>>> * the choice of nanoseconds is because it is the maximum resolution that >>>> * get_clock() can achieve. It is an internal measure. All user-visible >>>> * units must be in seconds */ >>>> -static uint64_t max_downtime = 30000000; >>>> +static uint64_t max_downtime = 300000000; >>>> >>>> uint64_t migrate_max_downtime(void) >>>> { >> >> > > -- Alexey ^ permalink raw reply [flat|nested] 10+ messages in thread
* Re: [Qemu-devel] [PATCH] migration: Increase default max_downtime from 30ms to 300ms [not found] ` <53604D73.1040905@ozlabs.ru> 2014-05-05 9:17 ` Alexey Kardashevskiy @ 2014-05-05 11:20 ` Juan Quintela 2014-06-04 8:13 ` Alexey Kardashevskiy 1 sibling, 1 reply; 10+ messages in thread From: Juan Quintela @ 2014-05-05 11:20 UTC (permalink / raw) To: Alexey Kardashevskiy Cc: Paolo Bonzini, Markus Armbruster, Dr . David Alan Gilbert, qemu-devel Alexey Kardashevskiy <aik@ozlabs.ru> wrote: > On 04/13/2014 12:38 AM, Alexey Kardashevskiy wrote: >> On 03/27/2014 08:01 PM, Markus Armbruster wrote: >>> Adding Juan. >> >> >> Ping? Patch is OK for me. As sender says, with guests doing anything/bigger than 1GB RAM is basically implosible to get into the 30ms downtime. Later, Juan. > > > Ping? > > >> >>> >>> Alexey Kardashevskiy <aik@ozlabs.ru> writes: >>> >>>> The existing timeout is 30ms which on 100MB/s (1Gbit) gives us >>>> 3MB/s rate maximum. If we put some load on the guest, it is easy to >>>> get page dirtying rate too big so live migration will never complete. >>>> In the case of libvirt that means that the guest will be stopped >>>> anyway after a timeout specified in the "virsh migrate" command and >>>> this normally generates even bigger delay. >>>> >>>> This changes max_downtime to 300ms which seems to be more >>>> reasonable value. >>>> >>>> Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru> >>>> --- >>>> migration.c | 2 +- >>>> 1 file changed, 1 insertion(+), 1 deletion(-) >>>> >>>> diff --git a/migration.c b/migration.c >>>> index e0e24d4..02bbce9 100644 >>>> --- a/migration.c >>>> +++ b/migration.c >>>> @@ -144,7 +144,7 @@ void process_incoming_migration(QEMUFile *f) >>>> * the choice of nanoseconds is because it is the maximum resolution that >>>> * get_clock() can achieve. It is an internal measure. All user-visible >>>> * units must be in seconds */ >>>> -static uint64_t max_downtime = 30000000; >>>> +static uint64_t max_downtime = 300000000; >>>> >>>> uint64_t migrate_max_downtime(void) >>>> { >> >> ^ permalink raw reply [flat|nested] 10+ messages in thread
* Re: [Qemu-devel] [PATCH] migration: Increase default max_downtime from 30ms to 300ms 2014-05-05 11:20 ` Juan Quintela @ 2014-06-04 8:13 ` Alexey Kardashevskiy 2014-06-04 10:25 ` Juan Quintela 0 siblings, 1 reply; 10+ messages in thread From: Alexey Kardashevskiy @ 2014-06-04 8:13 UTC (permalink / raw) To: quintela Cc: Paolo Bonzini, Markus Armbruster, Dr . David Alan Gilbert, qemu-devel On 05/05/2014 09:20 PM, Juan Quintela wrote: > Alexey Kardashevskiy <aik@ozlabs.ru> wrote: >> On 04/13/2014 12:38 AM, Alexey Kardashevskiy wrote: >>> On 03/27/2014 08:01 PM, Markus Armbruster wrote: >>>> Adding Juan. >>> >>> >>> Ping? > > Patch is OK for me. Who else needs to be ok to get this in upstream? :) Thanks! > As sender says, with guests doing anything/bigger than 1GB RAM is > basically implosible to get into the 30ms downtime. > > Later, Juan. > >> >> >> Ping? >> >> >>> >>>> >>>> Alexey Kardashevskiy <aik@ozlabs.ru> writes: >>>> >>>>> The existing timeout is 30ms which on 100MB/s (1Gbit) gives us >>>>> 3MB/s rate maximum. If we put some load on the guest, it is easy to >>>>> get page dirtying rate too big so live migration will never complete. >>>>> In the case of libvirt that means that the guest will be stopped >>>>> anyway after a timeout specified in the "virsh migrate" command and >>>>> this normally generates even bigger delay. >>>>> >>>>> This changes max_downtime to 300ms which seems to be more >>>>> reasonable value. >>>>> >>>>> Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru> >>>>> --- >>>>> migration.c | 2 +- >>>>> 1 file changed, 1 insertion(+), 1 deletion(-) >>>>> >>>>> diff --git a/migration.c b/migration.c >>>>> index e0e24d4..02bbce9 100644 >>>>> --- a/migration.c >>>>> +++ b/migration.c >>>>> @@ -144,7 +144,7 @@ void process_incoming_migration(QEMUFile *f) >>>>> * the choice of nanoseconds is because it is the maximum resolution that >>>>> * get_clock() can achieve. It is an internal measure. All user-visible >>>>> * units must be in seconds */ >>>>> -static uint64_t max_downtime = 30000000; >>>>> +static uint64_t max_downtime = 300000000; >>>>> >>>>> uint64_t migrate_max_downtime(void) >>>>> { >>> >>> -- Alexey ^ permalink raw reply [flat|nested] 10+ messages in thread
* Re: [Qemu-devel] [PATCH] migration: Increase default max_downtime from 30ms to 300ms 2014-06-04 8:13 ` Alexey Kardashevskiy @ 2014-06-04 10:25 ` Juan Quintela 2014-06-04 10:26 ` Paolo Bonzini 0 siblings, 1 reply; 10+ messages in thread From: Juan Quintela @ 2014-06-04 10:25 UTC (permalink / raw) To: Alexey Kardashevskiy Cc: peter.maydell, Paolo Bonzini, Markus Armbruster, Dr . David Alan Gilbert, qemu-devel Alexey Kardashevskiy <aik@ozlabs.ru> wrote: > On 05/05/2014 09:20 PM, Juan Quintela wrote: >> Alexey Kardashevskiy <aik@ozlabs.ru> wrote: >>> On 04/13/2014 12:38 AM, Alexey Kardashevskiy wrote: >>>> On 03/27/2014 08:01 PM, Markus Armbruster wrote: >>>>> Adding Juan. >>>> >>>> >>>> Ping? >> >> Patch is OK for me. > > > > Who else needs to be ok to get this in upstream? :) Thanks! Peter? David? Paolo? (I think to remember that they are ok with it) Thanks, Juan. ^ permalink raw reply [flat|nested] 10+ messages in thread
* Re: [Qemu-devel] [PATCH] migration: Increase default max_downtime from 30ms to 300ms 2014-06-04 10:25 ` Juan Quintela @ 2014-06-04 10:26 ` Paolo Bonzini 0 siblings, 0 replies; 10+ messages in thread From: Paolo Bonzini @ 2014-06-04 10:26 UTC (permalink / raw) To: quintela, Alexey Kardashevskiy Cc: peter.maydell, Markus Armbruster, Dr . David Alan Gilbert, qemu-devel Il 04/06/2014 12:25, Juan Quintela ha scritto: >> > >> > Who else needs to be ok to get this in upstream? :) Thanks! > Peter? > David? > Paolo? (I think to remember that they are ok with it) Certainly okay by me. Paolo ^ permalink raw reply [flat|nested] 10+ messages in thread
* Re: [Qemu-devel] [PATCH] migration: Increase default max_downtime from 30ms to 300ms 2014-03-27 3:57 [Qemu-devel] [PATCH] migration: Increase default max_downtime from 30ms to 300ms Alexey Kardashevskiy 2014-03-27 9:01 ` Markus Armbruster @ 2014-06-06 12:50 ` Amit Shah 2014-06-06 16:48 ` Alexey Kardashevskiy 1 sibling, 1 reply; 10+ messages in thread From: Amit Shah @ 2014-06-06 12:50 UTC (permalink / raw) To: Alexey Kardashevskiy; +Cc: Paolo Bonzini, qemu-devel, Dr . David Alan Gilbert On (Thu) 27 Mar 2014 [14:57:26], Alexey Kardashevskiy wrote: > The existing timeout is 30ms which on 100MB/s (1Gbit) gives us > 3MB/s rate maximum. If we put some load on the guest, it is easy to > get page dirtying rate too big so live migration will never complete. > In the case of libvirt that means that the guest will be stopped > anyway after a timeout specified in the "virsh migrate" command and > this normally generates even bigger delay. > > This changes max_downtime to 300ms which seems to be more > reasonable value. > > Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru> Reviewed-by: Amit Shah <amit.shah@redhat.com> Amit ^ permalink raw reply [flat|nested] 10+ messages in thread
* Re: [Qemu-devel] [PATCH] migration: Increase default max_downtime from 30ms to 300ms 2014-06-06 12:50 ` Amit Shah @ 2014-06-06 16:48 ` Alexey Kardashevskiy 2014-06-09 5:22 ` Amit Shah 0 siblings, 1 reply; 10+ messages in thread From: Alexey Kardashevskiy @ 2014-06-06 16:48 UTC (permalink / raw) To: Amit Shah; +Cc: Paolo Bonzini, qemu-devel, Dr . David Alan Gilbert On 06/06/2014 10:50 PM, Amit Shah wrote: > On (Thu) 27 Mar 2014 [14:57:26], Alexey Kardashevskiy wrote: >> The existing timeout is 30ms which on 100MB/s (1Gbit) gives us >> 3MB/s rate maximum. If we put some load on the guest, it is easy to >> get page dirtying rate too big so live migration will never complete. >> In the case of libvirt that means that the guest will be stopped >> anyway after a timeout specified in the "virsh migrate" command and >> this normally generates even bigger delay. >> >> This changes max_downtime to 300ms which seems to be more >> reasonable value. >> >> Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru> > > Reviewed-by: Amit Shah <amit.shah@redhat.com> Cool, thanks! But what is next? The patch is > 2 months old and it is simple and everything but it did not make it to any tree so far :) -- Alexey ^ permalink raw reply [flat|nested] 10+ messages in thread
* Re: [Qemu-devel] [PATCH] migration: Increase default max_downtime from 30ms to 300ms 2014-06-06 16:48 ` Alexey Kardashevskiy @ 2014-06-09 5:22 ` Amit Shah 0 siblings, 0 replies; 10+ messages in thread From: Amit Shah @ 2014-06-09 5:22 UTC (permalink / raw) To: Alexey Kardashevskiy, Juan Quintela Cc: Paolo Bonzini, qemu-devel, Dr . David Alan Gilbert On (Sat) 07 Jun 2014 [02:48:14], Alexey Kardashevskiy wrote: > On 06/06/2014 10:50 PM, Amit Shah wrote: > > On (Thu) 27 Mar 2014 [14:57:26], Alexey Kardashevskiy wrote: > >> The existing timeout is 30ms which on 100MB/s (1Gbit) gives us > >> 3MB/s rate maximum. If we put some load on the guest, it is easy to > >> get page dirtying rate too big so live migration will never complete. > >> In the case of libvirt that means that the guest will be stopped > >> anyway after a timeout specified in the "virsh migrate" command and > >> this normally generates even bigger delay. > >> > >> This changes max_downtime to 300ms which seems to be more > >> reasonable value. > >> > >> Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru> > > > > Reviewed-by: Amit Shah <amit.shah@redhat.com> > > Cool, thanks! > > But what is next? The patch is > 2 months old and it is simple and > everything but it did not make it to any tree so far :) I'll pester Juan to get it in :-) Amit ^ permalink raw reply [flat|nested] 10+ messages in thread
end of thread, other threads:[~2014-06-09 5:23 UTC | newest]
Thread overview: 10+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2014-03-27 3:57 [Qemu-devel] [PATCH] migration: Increase default max_downtime from 30ms to 300ms Alexey Kardashevskiy
2014-03-27 9:01 ` Markus Armbruster
[not found] ` <53494FD0.8020009@ozlabs.ru>
[not found] ` <53604D73.1040905@ozlabs.ru>
2014-05-05 9:17 ` Alexey Kardashevskiy
2014-05-05 11:20 ` Juan Quintela
2014-06-04 8:13 ` Alexey Kardashevskiy
2014-06-04 10:25 ` Juan Quintela
2014-06-04 10:26 ` Paolo Bonzini
2014-06-06 12:50 ` Amit Shah
2014-06-06 16:48 ` Alexey Kardashevskiy
2014-06-09 5:22 ` Amit Shah
This is a public inbox, see mirroring instructions for how to clone and mirror all data and code used for this inbox; as well as URLs for NNTP newsgroup(s).