Re: [OSM-talk] Upload slowness - what's going on?
As said before: great explanation and great work. These are complicated tasks, so thanks to the whole OWG for managing all this. nebulon42 signature.asc Description: OpenPGP digital signature ___ talk mailing list talk@openstreetmap.org https://lists.openstreetmap.org/listinfo/talk
[OSM-talk] weeklyOSM 303 is online in English
The weekly round-up of OSM news, issue # XXX, is now available online in English, giving as always a summary of all things happening in the openstreetmap world: http://www.weeklyosm.eu/en/archives/7456 - Highlights ... - *... “*urban mappers*” and a regulation bill, which tries to regulate a lot more than Indian bounderies in India* - ... an *official map which is significantly outdated in Mexico* - *... Open Cage data blog interviewed Brian Prangle and Rob Nickerson in the UK * - *... Simone Cortesi and "Wikimusesums" in Napels, Italy* - *... **more than 4000 km of bicycle routes crowedsourced in less than two weeks *in * Mainz, Germany * ... and much more ... Enjoy! weeklyOSM is brought to you by ... https://wiki.openstreetmap.org/wiki/WeeklyOSM#Languages -- ## Manfred Reiter - - ## www.weeklyOSM.eu ___ talk mailing list talk@openstreetmap.org https://lists.openstreetmap.org/listinfo/talk
Re: [OSM-talk] [Osmf-talk] Upload slowness - what's going on?
On 13.05.2016 15:58, Tom Hughes wrote: On 13/05/16 14:43, Maarten Deen wrote: On 2016-05-13 14:59, Grant Slater wrote: Kudos for the very clear explanation. Over today (for at least the weekend) we are switching to the new frontend & backend servers in York (Bytemark). London Imperial will be offline from approximately 5pm (GMT+1) for the first weekend of power maintenance. Is my understanding correct that this will put all servers in York and eliminate the latency and therefore the slowness? As of now everything is running in York so that we are ready for the power to go off in London over the weekend. On Monday we plan to move service back to London though I will probably try and keep the uploads going through the backend servers at York to see if that improves the speed issues seen this week. In due course the new database server in London will likely become the master with the one in York as a slave for servicing reads but with the ability to flip the master over if we need to run from York for some reason. Am I also correct to assume that the current situation is only because of this move (and prompted by the maintenance at Imperial) and is not planned to be a permanent setup? Well long term we want to have things spread over multiple sites so that we can cope with a data centre going down and part of this is us learning the best way to split things up and arrange things so that we can achieve redundancy without impacting other things. So there will likely be some tinkering and experimentation over the coming weeks as we try different things to see what works best. Tom It has got a name: business continuity [1] and disaster recovery [2]. I read a company in Louisiana could survive a hurricane Katrina because it moved a mirror server to the city of Houston, in another state, Texas, just days before the disaster. They had enough of items to ship physically from the warehouse in Louisiana, and the order processing system continued to work from Texas without interruption. [1] https://en.wikipedia.org/wiki/Business_continuity [2] https://en.wikipedia.org/wiki/Disaster_recovery ___ talk mailing list talk@openstreetmap.org https://lists.openstreetmap.org/listinfo/talk
Re: [OSM-talk] Upload slowness - what's going on?
On 13/05/16 14:43, Maarten Deen wrote: On 2016-05-13 14:59, Grant Slater wrote: Kudos for the very clear explanation. Over today (for at least the weekend) we are switching to the new frontend & backend servers in York (Bytemark). London Imperial will be offline from approximately 5pm (GMT+1) for the first weekend of power maintenance. Is my understanding correct that this will put all servers in York and eliminate the latency and therefore the slowness? As of now everything is running in York so that we are ready for the power to go off in London over the weekend. On Monday we plan to move service back to London though I will probably try and keep the uploads going through the backend servers at York to see if that improves the speed issues seen this week. In due course the new database server in London will likely become the master with the one in York as a slave for servicing reads but with the ability to flip the master over if we need to run from York for some reason. Am I also correct to assume that the current situation is only because of this move (and prompted by the maintenance at Imperial) and is not planned to be a permanent setup? Well long term we want to have things spread over multiple sites so that we can cope with a data centre going down and part of this is us learning the best way to split things up and arrange things so that we can achieve redundancy without impacting other things. So there will likely be some tinkering and experimentation over the coming weeks as we try different things to see what works best. Tom -- Tom Hughes (t...@compton.nu) http://compton.nu/ ___ talk mailing list talk@openstreetmap.org https://lists.openstreetmap.org/listinfo/talk
Re: [OSM-talk] Upload slowness - what's going on?
On 2016-05-13 14:59, Grant Slater wrote: Kudos for the very clear explanation. Over today (for at least the weekend) we are switching to the new frontend & backend servers in York (Bytemark). London Imperial will be offline from approximately 5pm (GMT+1) for the first weekend of power maintenance. Is my understanding correct that this will put all servers in York and eliminate the latency and therefore the slowness? Am I also correct to assume that the current situation is only because of this move (and prompted by the maintenance at Imperial) and is not planned to be a permanent setup? Regards, Maarten ___ talk mailing list talk@openstreetmap.org https://lists.openstreetmap.org/listinfo/talk
Re: [OSM-talk] Upload slowness - what's going on?
Hi Grant, Thank you for the technical explanation and especially for all the efforts improving the infrastructure! It's unfortunate uploads are so much slower now, but if the whole setup is more reliable/redundant, that's a small price to pay. Polyglot 2016-05-13 14:59 GMT+02:00 Grant Slater : > Hi All, > > On Monday 9th May 2016 the master OSM database server was moved to > York (Bytemark) from London (Imperial). > This was to avoid multiple upcoming weekends of planned power testing > & maintenance at the Imperial data centre. For the last few years > Imperial has housed all our main critical systems including master & > slave DB servers and frontend & backend web/api servers. We also added > 4 new frontend/backend web/api server to York on Monday. > > We now have the master database server in York and the secondary > database server in Imperial. We also have a warm standby slave db in > AWS Ireland. A fourth SSD (NVMe) based DB server was delivered > yesterday (Thursday), but it needs testing (burn-in, reliability, > performance etc) before we can start using it. Slave DB servers can be > promoted to master if required. > > The slave db servers serve Web/API read traffic and writes go to the > master. When the frontend + backend servers were in the same data > centre as the master db server the latency was <1ms. We now run a VPN > to connect the servers up and the latency is ~8ms Imperial to > Bytemark. Currently we are using the frontend & backends server at > Imperial (closest to slave db read server) and sending writes over the > VPN to Bytemark. The extra 8ms roundtrip is triggered multiple times > based on the size of the upload changeset, this is the root cause for > the slower uploads. The link between Imperial & Bytemark can handle > gigabit speeds. Over the last few days we've been tweaking the VPN > settings to get optimal latency & throughput over the links. > > Over today (for at least the weekend) we are switching to the new > frontend & backend servers in York (Bytemark). London Imperial will be > offline from approximately 5pm (GMT+1) for the first weekend of power > maintenance. > > In summary: The slow uploads are a known issue and we'll fix as soon > as practical. Our main concern has been setting up multiple data > center redundancy to avoid extended downtime. > > Here is the list of all core hardware and hosting locations: > https://hardware.openstreetmap.org/ > > Hope that answers the questions. ;-) > > Photos or it didn't happen: > * Syncing & powering down before we start London -> York DB move: > https://twitter.com/OSM_Tech/status/729582996685213696 > * Staged photo of racking up the master DB server at Bytemark: > https://twitter.com/OSM_Tech/status/729693392737832961 > * Testing the new Frontend / Backend servers a week ago: > https://twitter.com/OSM_Tech/status/728286193696292865 > > Bytemark are a fantastic hosting company and their ongoing support of > the OpenStreetMap project is highly commendable. Please support them > ;-) https://twitter.com/bytemark/status/729698435339853824 > > Kind regards, > > Grant > Part of the OSM Ops team. > > > On 13 May 2016 at 11:44, Tim Waters wrote: > > I believe the Dev mailing list may have some of your technical answers > > https://lists.openstreetmap.org/pipermail/dev/2016-May/thread.html > > > > It appears from that list that the database servers are now a few > > hundreds of miles from where the web servers are, causing the increase > > in latency. I do not know if this is a permanent change, the thread on > > osm-dev does seem to indicate that things are still in flux. > > > > Tim > > > > > > > > On 13 May 2016 at 06:02, Ben Discoe wrote: > >> Several of us have noticed radically slowly upload speed for > >> changesets, roughly since the server move on May 9. Like, as > >> painfully slow as it used to be, it's now several times slower. > >> > >> It's been discussed with @OSM_Tech on twitter, in this thread: > >> https://twitter.com/OSM_Tech/status/730857486618664960 > >> > >> Before I get too hysterical, can somebody tell me what happened, and > >> can it be fixed? > >> > >> OSM_Tech's mysterious message: > >> "Large uploads will take around 3 times longer. Small uploads extra > >> delay should be minimal." > >> > >> Does this mean that something did change? It is database writes that > >> are taking so much longer? Changesets with as few as 400 object are > >> taking several times longer, what constitutes "large" vs. "small"? > >> Can it be fixed? Can I donate large sums of money somewhere to help > >> it get fixed? > >> > >> Thanks, > >> Ben > >> > >> ___ > >> talk mailing list > >> talk@openstreetmap.org > >> https://lists.openstreetmap.org/listinfo/talk > > > > ___ > > talk mailing list > > talk@openstreetmap.org > > https://lists.openstreetmap.org/listinfo/talk > > ___ > talk mailing lis
Re: [OSM-talk] Upload slowness - what's going on?
Hi All, On Monday 9th May 2016 the master OSM database server was moved to York (Bytemark) from London (Imperial). This was to avoid multiple upcoming weekends of planned power testing & maintenance at the Imperial data centre. For the last few years Imperial has housed all our main critical systems including master & slave DB servers and frontend & backend web/api servers. We also added 4 new frontend/backend web/api server to York on Monday. We now have the master database server in York and the secondary database server in Imperial. We also have a warm standby slave db in AWS Ireland. A fourth SSD (NVMe) based DB server was delivered yesterday (Thursday), but it needs testing (burn-in, reliability, performance etc) before we can start using it. Slave DB servers can be promoted to master if required. The slave db servers serve Web/API read traffic and writes go to the master. When the frontend + backend servers were in the same data centre as the master db server the latency was <1ms. We now run a VPN to connect the servers up and the latency is ~8ms Imperial to Bytemark. Currently we are using the frontend & backends server at Imperial (closest to slave db read server) and sending writes over the VPN to Bytemark. The extra 8ms roundtrip is triggered multiple times based on the size of the upload changeset, this is the root cause for the slower uploads. The link between Imperial & Bytemark can handle gigabit speeds. Over the last few days we've been tweaking the VPN settings to get optimal latency & throughput over the links. Over today (for at least the weekend) we are switching to the new frontend & backend servers in York (Bytemark). London Imperial will be offline from approximately 5pm (GMT+1) for the first weekend of power maintenance. In summary: The slow uploads are a known issue and we'll fix as soon as practical. Our main concern has been setting up multiple data center redundancy to avoid extended downtime. Here is the list of all core hardware and hosting locations: https://hardware.openstreetmap.org/ Hope that answers the questions. ;-) Photos or it didn't happen: * Syncing & powering down before we start London -> York DB move: https://twitter.com/OSM_Tech/status/729582996685213696 * Staged photo of racking up the master DB server at Bytemark: https://twitter.com/OSM_Tech/status/729693392737832961 * Testing the new Frontend / Backend servers a week ago: https://twitter.com/OSM_Tech/status/728286193696292865 Bytemark are a fantastic hosting company and their ongoing support of the OpenStreetMap project is highly commendable. Please support them ;-) https://twitter.com/bytemark/status/729698435339853824 Kind regards, Grant Part of the OSM Ops team. On 13 May 2016 at 11:44, Tim Waters wrote: > I believe the Dev mailing list may have some of your technical answers > https://lists.openstreetmap.org/pipermail/dev/2016-May/thread.html > > It appears from that list that the database servers are now a few > hundreds of miles from where the web servers are, causing the increase > in latency. I do not know if this is a permanent change, the thread on > osm-dev does seem to indicate that things are still in flux. > > Tim > > > > On 13 May 2016 at 06:02, Ben Discoe wrote: >> Several of us have noticed radically slowly upload speed for >> changesets, roughly since the server move on May 9. Like, as >> painfully slow as it used to be, it's now several times slower. >> >> It's been discussed with @OSM_Tech on twitter, in this thread: >> https://twitter.com/OSM_Tech/status/730857486618664960 >> >> Before I get too hysterical, can somebody tell me what happened, and >> can it be fixed? >> >> OSM_Tech's mysterious message: >> "Large uploads will take around 3 times longer. Small uploads extra >> delay should be minimal." >> >> Does this mean that something did change? It is database writes that >> are taking so much longer? Changesets with as few as 400 object are >> taking several times longer, what constitutes "large" vs. "small"? >> Can it be fixed? Can I donate large sums of money somewhere to help >> it get fixed? >> >> Thanks, >> Ben >> >> ___ >> talk mailing list >> talk@openstreetmap.org >> https://lists.openstreetmap.org/listinfo/talk > > ___ > talk mailing list > talk@openstreetmap.org > https://lists.openstreetmap.org/listinfo/talk ___ talk mailing list talk@openstreetmap.org https://lists.openstreetmap.org/listinfo/talk
Re: [OSM-talk] Upload slowness - what's going on?
I believe the Dev mailing list may have some of your technical answers https://lists.openstreetmap.org/pipermail/dev/2016-May/thread.html It appears from that list that the database servers are now a few hundreds of miles from where the web servers are, causing the increase in latency. I do not know if this is a permanent change, the thread on osm-dev does seem to indicate that things are still in flux. Tim On 13 May 2016 at 06:02, Ben Discoe wrote: > Several of us have noticed radically slowly upload speed for > changesets, roughly since the server move on May 9. Like, as > painfully slow as it used to be, it's now several times slower. > > It's been discussed with @OSM_Tech on twitter, in this thread: > https://twitter.com/OSM_Tech/status/730857486618664960 > > Before I get too hysterical, can somebody tell me what happened, and > can it be fixed? > > OSM_Tech's mysterious message: > "Large uploads will take around 3 times longer. Small uploads extra > delay should be minimal." > > Does this mean that something did change? It is database writes that > are taking so much longer? Changesets with as few as 400 object are > taking several times longer, what constitutes "large" vs. "small"? > Can it be fixed? Can I donate large sums of money somewhere to help > it get fixed? > > Thanks, > Ben > > ___ > talk mailing list > talk@openstreetmap.org > https://lists.openstreetmap.org/listinfo/talk ___ talk mailing list talk@openstreetmap.org https://lists.openstreetmap.org/listinfo/talk
Re: [OSM-talk] Upload slowness - what's going on?
Their response is indeed so vague that I suspect even they don't know what's happening ;) Certainly, when you use JOSM, you can choose how much objects to upload at once. Small bundles (100...200) seem to work better. You can experiment with it. Michał On Fri, May 13, 2016 at 7:02 AM, Ben Discoe wrote: > Several of us have noticed radically slowly upload speed for > changesets, roughly since the server move on May 9. Like, as > painfully slow as it used to be, it's now several times slower. > > It's been discussed with @OSM_Tech on twitter, in this thread: > https://twitter.com/OSM_Tech/status/730857486618664960 > > Before I get too hysterical, can somebody tell me what happened, and > can it be fixed? > > OSM_Tech's mysterious message: > "Large uploads will take around 3 times longer. Small uploads extra > delay should be minimal." > > Does this mean that something did change? It is database writes that > are taking so much longer? Changesets with as few as 400 object are > taking several times longer, what constitutes "large" vs. "small"? > Can it be fixed? Can I donate large sums of money somewhere to help > it get fixed? > > Thanks, > Ben > > ___ > talk mailing list > talk@openstreetmap.org > https://lists.openstreetmap.org/listinfo/talk ___ talk mailing list talk@openstreetmap.org https://lists.openstreetmap.org/listinfo/talk