[google-appengine] Large latency spike, need assistance

[Nathan Skone]

Application: hs-hbo
Datastore: High Replication
Normal latencies: 50ms-200ms
Today's latencies: 5000ms-1ms
Idle Instances: ( Automatic – Automatic )
Pending Latency: ( Automatic – Automatic )

Dear Appengine Team,

This morning the latency of my application saw a sudden spike that has made 
it unusable for my company's purposes. How can I get assistance with this 
problem? This is an urgent issue that is directly effecting our customers.

Thank you,
Nathan Skone
DYMO / Mimio - A Newell Rubbermaid Company

-- 
You received this message because you are subscribed to the Google Groups 
"Google App Engine" group.
To view this discussion on the web visit 
https://groups.google.com/d/msg/google-appengine/-/O-GXusXXlzsJ.
To post to this group, send email to google-appengine@googlegroups.com.
To unsubscribe from this group, send email to 
google-appengine+unsubscr...@googlegroups.com.
For more options, visit this group at 
http://groups.google.com/group/google-appengine?hl=en.

Re: [google-appengine] Large latency spike, need assistance

[Takashi Matsuo]

Hi Nathan,

I think it's OK now. Are you still seeing this?

BTW, this list is not a support channel with any kind of SLA. Now
we're offering premier support for that type of demand.
For more details about our premier support, please see:
https://developers.google.com/appengine/docs/premier/

Regards,

-- Takashi

On Thu, Apr 26, 2012 at 2:43 AM, Nathan Skone  wrote:
> Application: hs-hbo
> Datastore: High Replication
> Normal latencies: 50ms-200ms
> Today's latencies: 5000ms-1ms
> Idle Instances: ( Automatic – Automatic )
> Pending Latency: ( Automatic – Automatic )
>
> Dear Appengine Team,
>
> This morning the latency of my application saw a sudden spike that has made
> it unusable for my company's purposes. How can I get assistance with this
> problem? This is an urgent issue that is directly effecting our customers.
>
> Thank you,
> Nathan Skone
> DYMO / Mimio - A Newell Rubbermaid Company
>
> --
> You received this message because you are subscribed to the Google Groups
> "Google App Engine" group.
> To view this discussion on the web visit
> https://groups.google.com/d/msg/google-appengine/-/O-GXusXXlzsJ.
> To post to this group, send email to google-appengine@googlegroups.com.
> To unsubscribe from this group, send email to
> google-appengine+unsubscr...@googlegroups.com.
> For more options, visit this group at
> http://groups.google.com/group/google-appengine?hl=en.



-- 
Takashi Matsuo | Developer Advocate | tmat...@google.com

-- 
You received this message because you are subscribed to the Google Groups 
"Google App Engine" group.
To post to this group, send email to google-appengine@googlegroups.com.
To unsubscribe from this group, send email to 
google-appengine+unsubscr...@googlegroups.com.
For more options, visit this group at 
http://groups.google.com/group/google-appengine?hl=en.

Re: [google-appengine] Large latency spike, need assistance

[alex]

This is not directly related to the original post, but speaking of SLA, I 
was just re-reading it (https://developers.google.com/appengine/sla) and 
this got me thinking:

"*Eligible Application*" means an Application that has been created by 
Customer using the High Replication Datastore setting.

Does this actually include *any* app, even free quota HRD apps? 
"Customer" term is not defined anywhere in the SLA (unless I missed it) so, 
I'm not really sure whether Customer means Billing Administrator (for a 
paid app) or it now relates to App Engine Premier Account only, or both.

Thanks,
Alex.


On Thursday, April 26, 2012 8:58:27 AM UTC+2, Takashi Matsuo (Google) wrote:
>
> Hi Nathan, 
>
> I think it's OK now. Are you still seeing this? 
>
> BTW, this list is not a support channel with any kind of SLA. Now 
> we're offering premier support for that type of demand. 
> For more details about our premier support, please see: 
> https://developers.google.com/appengine/docs/premier/ 
>
> Regards, 
>
> -- Takashi 
>
> On Thu, Apr 26, 2012 at 2:43 AM, Nathan Skone  
> wrote: 
> > Application: hs-hbo 
> > Datastore: High Replication 
> > Normal latencies: 50ms-200ms 
> > Today's latencies: 5000ms-1ms 
> > Idle Instances: ( Automatic – Automatic ) 
> > Pending Latency: ( Automatic – Automatic ) 
> > 
> > Dear Appengine Team, 
> > 
> > This morning the latency of my application saw a sudden spike that has 
> made 
> > it unusable for my company's purposes. How can I get assistance with 
> this 
> > problem? This is an urgent issue that is directly effecting our 
> customers. 
> > 
> > Thank you, 
> > Nathan Skone 
> > DYMO / Mimio - A Newell Rubbermaid Company 
> > 
> > -- 
> > You received this message because you are subscribed to the Google 
> Groups 
> > "Google App Engine" group. 
> > To view this discussion on the web visit 
> > https://groups.google.com/d/msg/google-appengine/-/O-GXusXXlzsJ. 
> > To post to this group, send email to google-appengine@googlegroups.com. 
> > To unsubscribe from this group, send email to 
> > google-appengine+unsubscr...@googlegroups.com. 
> > For more options, visit this group at 
> > http://groups.google.com/group/google-appengine?hl=en. 
>
>
>
> -- 
> Takashi Matsuo | Developer Advocate | tmat...@google.com 
>

-- 
You received this message because you are subscribed to the Google Groups 
"Google App Engine" group.
To view this discussion on the web visit 
https://groups.google.com/d/msg/google-appengine/-/pxLGCIDuMHkJ.
To post to this group, send email to google-appengine@googlegroups.com.
To unsubscribe from this group, send email to 
google-appengine+unsubscr...@googlegroups.com.
For more options, visit this group at 
http://groups.google.com/group/google-appengine?hl=en.

Re: [google-appengine] Large latency spike, need assistance

[Nathan Skone]

Takashi,

The latency spike stopped around 11:30pm PST. Can you tell what caused the 
high latency, and if it is likely to occur again in the future? Occasional 
spikes such as what happened yesterday would make the Google App Engine 
much less useful to my company.

I understand there is no SLA support channel for non-premium accounts. Does 
that mean that us paying customers that cannot justify the extra $500 
monthly fee cannot depend on any support from Google when experiencing 
problems?

Thank you for your response,

Nathan Skone
DYMO / Mimio - A Newell Rubbermaid Company

On Wednesday, April 25, 2012 11:58:27 PM UTC-7, Takashi Matsuo (Google) 
wrote:
>
> Hi Nathan, 
>
> I think it's OK now. Are you still seeing this? 
>
> BTW, this list is not a support channel with any kind of SLA. Now 
> we're offering premier support for that type of demand. 
> For more details about our premier support, please see: 
> https://developers.google.com/appengine/docs/premier/ 
>
> Regards, 
>
> -- Takashi 
>
> On Thu, Apr 26, 2012 at 2:43 AM, Nathan Skone  
> wrote: 
> > Application: hs-hbo 
> > Datastore: High Replication 
> > Normal latencies: 50ms-200ms 
> > Today's latencies: 5000ms-1ms 
> > Idle Instances: ( Automatic – Automatic ) 
> > Pending Latency: ( Automatic – Automatic ) 
> > 
> > Dear Appengine Team, 
> > 
> > This morning the latency of my application saw a sudden spike that has 
> made 
> > it unusable for my company's purposes. How can I get assistance with 
> this 
> > problem? This is an urgent issue that is directly effecting our 
> customers. 
> > 
> > Thank you, 
> > Nathan Skone 
> > DYMO / Mimio - A Newell Rubbermaid Company 
> > 
> > -- 
> > You received this message because you are subscribed to the Google 
> Groups 
> > "Google App Engine" group. 
> > To view this discussion on the web visit 
> > https://groups.google.com/d/msg/google-appengine/-/O-GXusXXlzsJ. 
> > To post to this group, send email to google-appengine@googlegroups.com. 
> > To unsubscribe from this group, send email to 
> > google-appengine+unsubscr...@googlegroups.com. 
> > For more options, visit this group at 
> > http://groups.google.com/group/google-appengine?hl=en. 
>
>
>
> -- 
> Takashi Matsuo | Developer Advocate | tmat...@google.com 
>

-- 
You received this message because you are subscribed to the Google Groups 
"Google App Engine" group.
To view this discussion on the web visit 
https://groups.google.com/d/msg/google-appengine/-/omv0xvTjHnwJ.
To post to this group, send email to google-appengine@googlegroups.com.
To unsubscribe from this group, send email to 
google-appengine+unsubscr...@googlegroups.com.
For more options, visit this group at 
http://groups.google.com/group/google-appengine?hl=en.

Re: [google-appengine] Large latency spike, need assistance

[Takashi Matsuo]

Hi Nathan,

On Fri, Apr 27, 2012 at 1:17 AM, Nathan Skone  wrote:
> Takashi,
>
> The latency spike stopped around 11:30pm PST. Can you tell what caused the
> high latency, and if it is likely to occur again in the future? Occasional
> spikes such as what happened yesterday would make the Google App Engine much
> less useful to my company.

First, are you really sure that the cause is in our side? Do you have
any appstats results which show that any of your RPC calls don't take
longer time than usual? If your RPCs take time, there are several
things you can do to mitigate this. Do you set any deadline on your
datastore calls? If no, you may want to set it appropriately, and when
hitting the deadline, you can return a failure to your web clients and
tell them to retry. Are you using urlfetch service to retrieve
external resources? If so, sometimes those external resources can be
the culprits. If you entirely rely your app's performance on the
memcache service, which has no SLA, your app might see high latency
when the memcache is flushed.

In this particular case, as far as I know, there was no significant
system issue around that time, so I don't think this was a system wide
issue, and in such cases, please understand that we can not offer
reports like that every time to every customers who experienced high
latency(again, premier customers are different, at least to my
knowledge).

> I understand there is no SLA support channel for non-premium accounts. Does
> that mean that us paying customers that cannot justify the extra $500
> monthly fee cannot depend on any support from Google when experiencing
> problems?

No, not at all. There are still several options. You can use a new
feature for reporting production issues in your admin console. You
should be able to see a link 'Report Production Issue' on the right
top side of your admin console, where you can report a production
issue alongside of a screenshot with some highlights and privacy
masks. That way, now you can report issues to us privately without
revealing your app-id.

Of course, you can also post here, then we offer a best effort
support, like this ;)

-- Takashi

>
> Thank you for your response,
>
> Nathan Skone
> DYMO / Mimio - A Newell Rubbermaid Company
>
> On Wednesday, April 25, 2012 11:58:27 PM UTC-7, Takashi Matsuo (Google)
> wrote:
>>
>> Hi Nathan,
>>
>> I think it's OK now. Are you still seeing this?
>>
>> BTW, this list is not a support channel with any kind of SLA. Now
>> we're offering premier support for that type of demand.
>> For more details about our premier support, please see:
>> https://developers.google.com/appengine/docs/premier/
>>
>> Regards,
>>
>> -- Takashi
>>
>> On Thu, Apr 26, 2012 at 2:43 AM, Nathan Skone 
>> wrote:
>> > Application: hs-hbo
>> > Datastore: High Replication
>> > Normal latencies: 50ms-200ms
>> > Today's latencies: 5000ms-1ms
>> > Idle Instances: ( Automatic – Automatic )
>> > Pending Latency: ( Automatic – Automatic )
>> >
>> > Dear Appengine Team,
>> >
>> > This morning the latency of my application saw a sudden spike that has
>> > made
>> > it unusable for my company's purposes. How can I get assistance with
>> > this
>> > problem? This is an urgent issue that is directly effecting our
>> > customers.
>> >
>> > Thank you,
>> > Nathan Skone
>> > DYMO / Mimio - A Newell Rubbermaid Company
>> >
>> > --
>> > You received this message because you are subscribed to the Google
>> > Groups
>> > "Google App Engine" group.
>> > To view this discussion on the web visit
>> > https://groups.google.com/d/msg/google-appengine/-/O-GXusXXlzsJ.
>> > To post to this group, send email to google-appengine@googlegroups.com.
>> > To unsubscribe from this group, send email to
>> > google-appengine+unsubscr...@googlegroups.com.
>> > For more options, visit this group at
>> > http://groups.google.com/group/google-appengine?hl=en.
>>
>>
>>
>> --
>> Takashi Matsuo | Developer Advocate | tmat...@google.com
>
> --
> You received this message because you are subscribed to the Google Groups
> "Google App Engine" group.
> To view this discussion on the web visit
> https://groups.google.com/d/msg/google-appengine/-/omv0xvTjHnwJ.
>
> To post to this group, send email to google-appengine@googlegroups.com.
> To unsubscribe from this group, send email to
> google-appengine+unsubscr...@googlegroups.com.
> For more options, visit this group at
> http://groups.google.com/group/google-appengine?hl=en.



-- 
Takashi Matsuo | Developer Advocate | tmat...@google.com

-- 
You received this message because you are subscribed to the Google Groups 
"Google App Engine" group.
To post to this group, send email to google-appengine@googlegroups.com.
To unsubscribe from this group, send email to 
google-appengine+unsubscr...@googlegroups.com.
For more options, visit this group at 
http://groups.google.com/group/google-appengine?hl=en.

Re: [google-appengine] Large latency spike, need assistance

[Barry Hunter]

Isn't this thing par for the course. They can happen occasionally.

Eg.
https://developers.google.com/appengine/articles/handling_datastore_errors

On Mon, May 7, 2012 at 7:57 PM, Nathan Skone  wrote:
> Takashi,
>
> The latency spike has hit again. This time I have appstats turned on, which
> is revealing some of the large latencies.  For example, here is a screenshot
> from appstats showing that a db.key on a single key object taking over 7
> seconds!
>
> Also attached is a screenshot showing a single memcache.get (on a single
> key) taking over 1 second.
>
> What is causing this problem and how can I make it go away?
>
> Thanks,
> Nathan
>
>
> On Thursday, April 26, 2012 11:08:16 AM UTC-7, Takashi Matsuo (Google)
> wrote:
>>
>> Hi Nathan,
>>
>> On Fri, Apr 27, 2012 at 1:17 AM, Nathan Skone 
>> wrote:
>> > Takashi,
>> >
>> > The latency spike stopped around 11:30pm PST. Can you tell what caused
>> > the
>> > high latency, and if it is likely to occur again in the future?
>> > Occasional
>> > spikes such as what happened yesterday would make the Google App Engine
>> > much
>> > less useful to my company.
>>
>> First, are you really sure that the cause is in our side? Do you have
>> any appstats results which show that any of your RPC calls don't take
>> longer time than usual? If your RPCs take time, there are several
>> things you can do to mitigate this. Do you set any deadline on your
>> datastore calls? If no, you may want to set it appropriately, and when
>> hitting the deadline, you can return a failure to your web clients and
>> tell them to retry. Are you using urlfetch service to retrieve
>> external resources? If so, sometimes those external resources can be
>> the culprits. If you entirely rely your app's performance on the
>> memcache service, which has no SLA, your app might see high latency
>> when the memcache is flushed.
>>
>> In this particular case, as far as I know, there was no significant
>> system issue around that time, so I don't think this was a system wide
>> issue, and in such cases, please understand that we can not offer
>> reports like that every time to every customers who experienced high
>> latency(again, premier customers are different, at least to my
>> knowledge).
>>
>> > I understand there is no SLA support channel for non-premium accounts.
>> > Does
>> > that mean that us paying customers that cannot justify the extra $500
>> > monthly fee cannot depend on any support from Google when experiencing
>> > problems?
>>
>> No, not at all. There are still several options. You can use a new
>> feature for reporting production issues in your admin console. You
>> should be able to see a link 'Report Production Issue' on the right
>> top side of your admin console, where you can report a production
>> issue alongside of a screenshot with some highlights and privacy
>> masks. That way, now you can report issues to us privately without
>> revealing your app-id.
>>
>> Of course, you can also post here, then we offer a best effort
>> support, like this ;)
>>
>> -- Takashi
>>
>> >
>> > Thank you for your response,
>> >
>> > Nathan Skone
>> > DYMO / Mimio - A Newell Rubbermaid Company
>> >
>> > On Wednesday, April 25, 2012 11:58:27 PM UTC-7, Takashi Matsuo (Google)
>> > wrote:
>> >>
>> >> Hi Nathan,
>> >>
>> >> I think it's OK now. Are you still seeing this?
>> >>
>> >> BTW, this list is not a support channel with any kind of SLA. Now
>> >> we're offering premier support for that type of demand.
>> >> For more details about our premier support, please see:
>> >> https://developers.google.com/appengine/docs/premier/
>> >>
>> >> Regards,
>> >>
>> >> -- Takashi
>> >>
>> >> On Thu, Apr 26, 2012 at 2:43 AM, Nathan Skone 
>> >> wrote:
>> >> > Application: hs-hbo
>> >> > Datastore: High Replication
>> >> > Normal latencies: 50ms-200ms
>> >> > Today's latencies: 5000ms-1ms
>> >> > Idle Instances: ( Automatic – Automatic )
>> >> > Pending Latency: ( Automatic – Automatic )
>> >> >
>> >> > Dear Appengine Team,
>> >> >
>> >> > This morning the latency of my application saw a sudden spike that
>> >> > has
>> >> > made
>> >> > it unusable for my company's purposes. How can I get assistance with
>> >> > this
>> >> > problem? This is an urgent issue that is directly effecting our
>> >> > customers.
>> >> >
>> >> > Thank you,
>> >> > Nathan Skone
>> >> > DYMO / Mimio - A Newell Rubbermaid Company
>> >> >
>> >> > --
>> >> > You received this message because you are subscribed to the Google
>> >> > Groups
>> >> > "Google App Engine" group.
>> >> > To view this discussion on the web visit
>> >> > https://groups.google.com/d/msg/google-appengine/-/O-GXusXXlzsJ.
>> >> > To post to this group, send email to
>> >> > google-appengine@googlegroups.com.
>> >> > To unsubscribe from this group, send email to
>> >> > google-appengine+unsubscr...@googlegroups.com.
>> >> > For more options, visit this group at
>> >> > http://groups.google.com/group/google-appengine?hl=en.
>> >>
>> >>
>> >>
>> >> --
>> >> Takas

Re: [google-appengine] Large latency spike, need assistance

[Ronoaldo José de Lana Pereira]

Hello Takashi,

Is there a way to set a deadline for memcache? Does the pattern:

get from cache:
  if not there, get from datastore:
store in cache

.. in a scenario where the memcache is down and the timeout to see that it 
is down will degrade the app performance instead of make it better?

As we can see on the status dashboard, there was a huge increase in 
memcache and datastore latency:


 

  


Em quinta-feira, 26 de abril de 2012 15h08min16s UTC-3, Takashi Matsuo 
(Google) escreveu:
>
> Hi Nathan, 
>
> On Fri, Apr 27, 2012 at 1:17 AM, Nathan Skone  
> wrote: 
> > Takashi, 
> > 
> > The latency spike stopped around 11:30pm PST. Can you tell what caused 
> the 
> > high latency, and if it is likely to occur again in the future? 
> Occasional 
> > spikes such as what happened yesterday would make the Google App Engine 
> much 
> > less useful to my company. 
>
> First, are you really sure that the cause is in our side? Do you have 
> any appstats results which show that any of your RPC calls don't take 
> longer time than usual? If your RPCs take time, there are several 
> things you can do to mitigate this. Do you set any deadline on your 
> datastore calls? If no, you may want to set it appropriately, and when 
> hitting the deadline, you can return a failure to your web clients and 
> tell them to retry. Are you using urlfetch service to retrieve 
> external resources? If so, sometimes those external resources can be 
> the culprits. If you entirely rely your app's performance on the 
> memcache service, which has no SLA, your app might see high latency 
> when the memcache is flushed. 
>
> In this particular case, as far as I know, there was no significant 
> system issue around that time, so I don't think this was a system wide 
> issue, and in such cases, please understand that we can not offer 
> reports like that every time to every customers who experienced high 
> latency(again, premier customers are different, at least to my 
> knowledge). 
>
> > I understand there is no SLA support channel for non-premium accounts. 
> Does 
> > that mean that us paying customers that cannot justify the extra $500 
> > monthly fee cannot depend on any support from Google when experiencing 
> > problems? 
>
> No, not at all. There are still several options. You can use a new 
> feature for reporting production issues in your admin console. You 
> should be able to see a link 'Report Production Issue' on the right 
> top side of your admin console, where you can report a production 
> issue alongside of a screenshot with some highlights and privacy 
> masks. That way, now you can report issues to us privately without 
> revealing your app-id. 
>
> Of course, you can also post here, then we offer a best effort 
> support, like this ;) 
>
> -- Takashi 
>
> > 
> > Thank you for your response, 
> > 
> > Nathan Skone 
> > DYMO / Mimio - A Newell Rubbermaid Company 
> > 
> > On Wednesday, April 25, 2012 11:58:27 PM UTC-7, Takashi Matsuo (Google) 
> > wrote: 
> >> 
> >> Hi Nathan, 
> >> 
> >> I think it's OK now. Are you still seeing this? 
> >> 
> >> BTW, this list is not a support channel with any kind of SLA. Now 
> >> we're offering premier support for that type of demand. 
> >> For more details about our premier support, please see: 
> >> https://developers.google.com/appengine/docs/premier/ 
> >> 
> >> Regards, 
> >> 
> >> -- Takashi 
> >> 
> >> On Thu, Apr 26, 2012 at 2:43 AM, Nathan Skone  
> >> wrote: 
> >> > Application: hs-hbo 
> >> > Datastore: High Replication 
> >> > Normal latencies: 50ms-200ms 
> >> > Today's latencies: 5000ms-1ms 
> >> > Idle Instances: ( Automatic – Automatic ) 
> >> > Pending Latency: ( Automatic – Automatic ) 
> >> > 
> >> > Dear Appengine Team, 
> >> > 
> >> > This morning the latency of my application saw a sudden spike that 
> has 
> >> > made 
> >> > it unusable for my company's purposes. How can I get assistance with 
> >> > this 
> >> > problem? This is an urgent issue that is directly effecting our 
> >> > customers. 
> >> > 
> >> > Thank you, 
> >> > Nathan Skone 
> >> > DYMO / Mimio - A Newell Rubbermaid Company 
> >> > 
> >> > -- 
> >> > You received this message because you are subscribed to the Google 
> >> > Groups 
> >> > "Google App Engine" group. 
> >> > To view this discussion on the web visit 
> >> > https://groups.google.com/d/msg/google-appengine/-/O-GXusXXlzsJ. 
> >> > To post to this group, send email to 
> google-appengine@googlegroups.com. 
> >> > To unsubscribe from this group, send email to 
> >> > google-appengine+unsubscr...@googlegroups.com. 
> >> > For more options, visit this group at 
> >> > http://groups.google.com/group/google-appengine?hl=en. 
> >> 
> >> 
> >> 
> >> -- 
> >> Takashi Matsuo | Developer Advocate | tmat..

Re: [google-appengine] Large latency spike, need assistance

[Takashi Matsuo]

Hi Ronoaldo,

A good question!

Looking through the Python memcache API, some methods like
get_multi_async() or set_multi_async() on the Client class receive rpc
object as a keyword argument, so you can pass an rpc object with a
particular deadline. For more details, please refer to our doc at:
https://developers.google.com/appengine/docs/python/memcache/clientclass

Thanks,

On Wed, May 9, 2012 at 6:19 AM, Ronoaldo José de Lana Pereira <
rpere...@beneficiofacil.com.br> wrote:

> Hello Takashi,
>
> Is there a way to set a deadline for memcache? Does the pattern:
>
> get from cache:
>   if not there, get from datastore:
> store in cache
>
> .. in a scenario where the memcache is down and the timeout to see that it
> is down will degrade the app performance instead of make it better?
>
> As we can see on the status dashboard, there was a huge increase in
> memcache and datastore latency:
>
>
> 
>  
> 
>
>
>
> Em quinta-feira, 26 de abril de 2012 15h08min16s UTC-3, Takashi Matsuo
> (Google) escreveu:
>
>> Hi Nathan,
>>
>> On Fri, Apr 27, 2012 at 1:17 AM, Nathan Skone 
>> wrote:
>> > Takashi,
>> >
>> > The latency spike stopped around 11:30pm PST. Can you tell what caused
>> the
>> > high latency, and if it is likely to occur again in the future?
>> Occasional
>> > spikes such as what happened yesterday would make the Google App Engine
>> much
>> > less useful to my company.
>>
>> First, are you really sure that the cause is in our side? Do you have
>> any appstats results which show that any of your RPC calls don't take
>> longer time than usual? If your RPCs take time, there are several
>> things you can do to mitigate this. Do you set any deadline on your
>> datastore calls? If no, you may want to set it appropriately, and when
>> hitting the deadline, you can return a failure to your web clients and
>> tell them to retry. Are you using urlfetch service to retrieve
>> external resources? If so, sometimes those external resources can be
>> the culprits. If you entirely rely your app's performance on the
>> memcache service, which has no SLA, your app might see high latency
>> when the memcache is flushed.
>>
>> In this particular case, as far as I know, there was no significant
>> system issue around that time, so I don't think this was a system wide
>> issue, and in such cases, please understand that we can not offer
>> reports like that every time to every customers who experienced high
>> latency(again, premier customers are different, at least to my
>> knowledge).
>>
>> > I understand there is no SLA support channel for non-premium accounts.
>> Does
>> > that mean that us paying customers that cannot justify the extra $500
>> > monthly fee cannot depend on any support from Google when experiencing
>> > problems?
>>
>> No, not at all. There are still several options. You can use a new
>> feature for reporting production issues in your admin console. You
>> should be able to see a link 'Report Production Issue' on the right
>> top side of your admin console, where you can report a production
>> issue alongside of a screenshot with some highlights and privacy
>> masks. That way, now you can report issues to us privately without
>> revealing your app-id.
>>
>> Of course, you can also post here, then we offer a best effort
>> support, like this ;)
>>
>> -- Takashi
>>
>> >
>> > Thank you for your response,
>> >
>> > Nathan Skone
>> > DYMO / Mimio - A Newell Rubbermaid Company
>> >
>> > On Wednesday, April 25, 2012 11:58:27 PM UTC-7, Takashi Matsuo (Google)
>> > wrote:
>> >>
>> >> Hi Nathan,
>> >>
>> >> I think it's OK now. Are you still seeing this?
>> >>
>> >> BTW, this list is not a support channel with any kind of SLA. Now
>> >> we're offering premier support for that type of demand.
>> >> For more details about our premier support, please see:
>> >> https://developers.google.com/**appengine/docs/premier/
>> >>
>> >> Regards,
>> >>
>> >> -- Takashi
>> >>
>> >> On Thu, Apr 26, 2012 at 2:43 AM, Nathan Skone 
>> >> wrote:
>> >> > Application: hs-hbo
>> >> > Datastore: High Replication
>> >> > Normal latencies: 50ms-200ms
>> >> > Today's latencies: 5000ms-1ms
>> >> > Idle Instances: ( Automatic – **Automatic )
>> >> > Pending Latency: ( Automatic – **Automatic )
>> >> >
>> >> > Dear Appengine Team,
>> >> >
>> >> > This morning the latency of my application saw a sudden spike that
>> has
>> >> > made
>> >> > it unusable for my company's purposes. How can I get assistance with
>> >> > this
>> >> > problem? This is an urgent issue that is directly effecting our
>> >> > customers.
>> >> >
>> >> > Thank you,
>> >> > Nathan Skone
>> >> > DYMO / Mimio - A Newell Rubbermaid Company
>> >> >
>> >> > --
>> >> > You received this message becau