On Mar 4, 2:29 am, Brett Slatkin <brett-appeng...@google.com> wrote: > Hi Alex, > > We're aware of elevated Serving and Datastore latencies and are > working hard to rectify the situation. We're very sorry for any > trouble this is causing your application and others. Thanks for your > patience. > > -Brett >
Brett, I appreciate hearing from you that you are aware of these issues. And I hope to hear soon a confirmation that issues have been solved. Anyways, I'd like to know that once you are aware of such problems you would let us know so we don't panic, wake up in the middle of the night and start calling people to debug the application to finally figure out that there is nothing we can do. It is the same story as the maintenance window announcement. I had to scan the forum many times to find it out, when normally it should have been on the front page in large font. And it is the same story with the datastore outage last week which was reported as memcache throughput issues while I've clearly shown that the datastore was unusable. I hate criticizing, but I really hope that you'll take away what is to be learnt from this and that the service (including the community management) will get better soon. Bests, ./alex > On Tue, Mar 3, 2009 at 12:39 PM, Alex Popescu > > <the.mindstorm.mailingl...@gmail.com> wrote: > > > Hi, > > > I'm seeing that most of the datastore ops are being slow lately by > > about an order of magnitude slower. > > > Here is a set of numbers from now: > > > 03-03 12:25PM 46.104 200 2296ms 1398ms-cpu 0kb > > 03-03 12:25PM 15.755 200 2025ms 1330ms-cpu 0kb > > 03-03 12:22PM 59.116 200 2519ms 1375ms-cpu 0kb > > 03-03 12:22PM 50.280 200 3550ms 1419ms-cpu 0kb > > 03-03 12:22PM 40.446 200 3743ms 1330ms-cpu 0kb > > 03-03 12:22PM 33.069 200 4966ms 1575ms-cpu 0kb > > 03-03 12:22PM 24.450 200 5079ms 1552ms-cpu 0kb > > 03-03 12:22PM 09.252 200 2525ms 1309ms-cpu 0kb > > 03-03 12:22PM 01.147 200 2487ms 1353ms-cpu 0kb > > 03-03 12:21PM 43.116 200 6286ms 1641ms-cpu 0kb > > 03-03 12:20PM 43.931 200 879ms 1110ms-cpu 0kb > > 03-03 12:10PM 23.405 200 5081ms 1575ms-cpu 0kb > > 03-03 12:10PM 12.014 200 5394ms 1552ms-cpu 0kb > > 03-03 12:10PM 00.713 200 5384ms 1552ms-cpu 0kb > > 03-03 12:09PM 48.420 200 3503ms 1197ms-cpu 0kb > > 03-03 12:09PM 45.042 200 4086ms 1486ms-cpu 0kb > > 03-03 12:06PM 51.240 200 126ms 115ms-cpu 0kb > > 03-03 12:06PM 46.039 200 3289ms 1464ms-cpu 0kb > > 03-03 12:06PM 38.422 200 5202ms 1464ms-cpu 0kb > > 03-03 12:06PM 31.616 200 4431ms 1464ms-cpu 0kb > > > and here is the same operation yesterday: > > > 03-03 03:14AM 11.589 200 94ms 76ms-cpu 0kb > > 03-03 03:14AM 09.001 200 93ms 93ms-cpu 0kb > > 03-03 03:14AM 07.035 200 130ms 100ms-cpu 0kb > > 03-03 03:14AM 04.682 200 89ms 78ms-cpu 0kb > > 03-03 03:13AM 59.604 200 865ms 1087ms-cpu 0kb > > 03-03 03:12AM 34.688 200 93ms 79ms-cpu 0kb > > 03-03 03:12AM 31.917 200 85ms 75ms-cpu 0kb > > 03-03 03:12AM 29.498 200 107ms 97ms-cpu 0kb > > 03-03 03:12AM 28.233 200 104ms 88ms-cpu 0kb > > 03-03 03:11AM 39.239 200 124ms 96ms-cpu 0kb > > 03-03 03:11AM 16.987 200 131ms 129ms-cpu 0kb > > 03-03 03:11AM 12.991 200 1601ms 1087ms-cpu 0kb > > 03-03 03:10AM 28.677 200 107ms 96ms-cpu 0kb > > 03-03 03:10AM 19.079 200 127ms 152ms-cpu 0kb > > 03-03 03:09AM 57.002 200 142ms 116ms-cpu 0kb > > > The operation is performed in the same conditions and the data set is > > the equivalent in size. > > > The appid is dailycloud. I'm looking forward to hearing the reasons > > for this degradation of the datastore performance. > > > ./alex --~--~---------~--~----~------------~-------~--~----~ 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 -~----------~----~----~----~------~----~------~--~---