Monday, 2014-05-05

*** shakamunyi has joined #openstack-marconi00:23
*** shakamunyi has quit IRC00:48
*** shakamunyi has joined #openstack-marconi01:13
*** saikrishna has joined #openstack-marconi01:13
*** saikrishna has quit IRC01:53
*** flwang has quit IRC01:56
*** renlt has joined #openstack-marconi02:15
*** flwang has joined #openstack-marconi02:36
*** shakamunyi has quit IRC02:57
*** cpallares has quit IRC03:18
*** alcabrera|afk has quit IRC04:08
*** alcabrera|afk has joined #openstack-marconi04:20
*** haomaiwang has joined #openstack-marconi04:31
*** haomaiwang has quit IRC04:32
*** haomaiwang has joined #openstack-marconi04:33
*** flwang has quit IRC04:38
*** flwang has joined #openstack-marconi05:12
*** prashanthr_ has joined #openstack-marconi05:22
*** haomai___ has joined #openstack-marconi05:22
*** haomaiwang has quit IRC05:22
*** haomaiwang has joined #openstack-marconi05:26
*** chandan_kumar has joined #openstack-marconi05:26
*** cpallares has joined #openstack-marconi05:27
*** haomai___ has quit IRC05:29
*** cpallares has quit IRC05:32
*** flwang has quit IRC05:49
*** flwang has joined #openstack-marconi05:51
prashanthr_flwang: Hi :)06:18
*** flwang has quit IRC06:22
*** flwang has joined #openstack-marconi06:26
flwangprashanthr_: hi06:40
prashanthr_Thanks a lot for all the help for Gsoc :). Was able to make through :)06:41
flwangmy pleasure06:42
*** flwang has quit IRC06:46
*** flwang has joined #openstack-marconi06:58
*** flwang has quit IRC07:09
*** mkoderer has joined #openstack-marconi07:09
*** flwang has joined #openstack-marconi07:10
*** Manishanker has joined #openstack-marconi07:14
*** jamie_h has joined #openstack-marconi07:24
*** jamie_h has quit IRC07:25
*** flaper87|afk is now known as flaper8707:29
flwangflaper87: hey07:33
flaper87yoy yo07:33
flaper87how are you doing?07:33
flwangflaper87: good07:34
flwangflaper87: not sure if you know that, my travel is cancelled :(07:35
flaper87flwang: damnit :(07:36
flaper87so sad to hear that07:36
*** flwang has quit IRC07:42
*** prashanthr_ has quit IRC07:46
*** openstackgerrit has quit IRC07:53
*** ykaplan has joined #openstack-marconi07:54
*** prashanthr_ has joined #openstack-marconi08:00
*** flwang has joined #openstack-marconi08:19
flwangflaper87: sorry, I was disconnected08:19
flaper87flwang: no worries08:32
flaper87I said, It's sad that you won't be there :(08:32
flwangflaper87: yep08:32
flwanghopefully my next summit travel can be sponsored :)08:33
*** prashanthr_ has quit IRC08:57
*** haomaiwang has quit IRC09:25
*** flwang has quit IRC09:58
*** renlt has quit IRC10:43
*** vkmc has joined #openstack-marconi10:59
*** vkmc has quit IRC10:59
*** vkmc has joined #openstack-marconi10:59
*** haomaiwa_ has joined #openstack-marconi11:21
*** ykaplan has quit IRC11:31
*** ykaplan has joined #openstack-marconi11:59
*** sriram has joined #openstack-marconi12:41
*** flaper87 has quit IRC12:52
*** flaper87|afk has joined #openstack-marconi12:56
*** flaper87|afk is now known as flaper8712:56
*** flaper87 has quit IRC12:56
*** flaper87 has joined #openstack-marconi12:56
*** ChanServ sets mode: +o flaper8712:56
*** amitgandhi has joined #openstack-marconi13:00
*** amitgandhi has quit IRC13:00
*** mwagner_lap has quit IRC13:00
*** amitgandhi has joined #openstack-marconi13:03
*** jchai has joined #openstack-marconi13:04
*** amitgandhi has quit IRC13:09
*** amitgandhi has joined #openstack-marconi13:09
*** flwang has joined #openstack-marconi13:27
*** alcabrera|afk is now known as alcabrera13:28
alcabreraGood morning! :)13:29
flaper87alcabrera: goooooood morning13:31
alcabreraflaper87: heya! How are you? :)13:31
flaper87alcabrera: I'm doing great, you? How was your weekend?13:32
alcabreraIt was wonderful, flaper87. I hung out with Jess a bunch, did a little reading, writing, and cooking!13:32
alcabreraI made a 32-egg egg salad and a whole mega-bowl of cole slaw. Out fridge is happy. <313:32
flaper87wow, sounds like you had a very productive and fun weekend! :D13:33
flaper87glad to hear that13:33
alcabrerahow about you, flaper87?13:34
flaper87I, and I know this is hard to believe, spent the weekend away from my laptop and out in the open.13:35
flaper87hung out w/ GF and friends at the lake, had great food, relaxed etc13:35
alcabreraThat sounds great! :D13:36
alcabreraa little time away from computer is good. <313:36
*** openstackgerrit has joined #openstack-marconi13:36
flaper87yeah, definitely!13:37
flaper87Happy Star Wars day, btw! (A bit late, it was yday)13:37
alcabrerathanks! May the 4th be with you, flaper87. ;)13:37
alcabreraI had a funny moment on Sunday -- related to 'away from computer'13:38
alcabreraI set out to study around 5pm13:38
alcabreraan hour maybe13:38
alcabrerait was 9:30pm when I looked at the book again, and thought, "yeah, I'd rather just keeping talking to my friend and writing"13:38
alcabreraspent the whole time away from computing. :P13:39
alcabrerahonestly surprised myself a bit13:39
*** mpanetta has joined #openstack-marconi13:41
flaper87hehehe, yeah! Sometimes it's good, actually, I know, deep down in my brain, that it's best to just stay away from it. I've become an expert on the art of ignoring my own brain13:41
*** mpanetta has quit IRC13:41
*** malini_afk is now known as malini13:42
*** mpanetta has joined #openstack-marconi13:42
flaper87with all that said, the next 3 months will be a no-stop-geek-work period so13:42
flaper87(at least for me)13:42
alcabrerabusy, busy flaper87!13:43
*** rektide_ is now known as rektide13:44
*** Obulpathi has joined #openstack-marconi13:50
*** Obulpathi has quit IRC13:50
*** Obulpathi has joined #openstack-marconi13:50
*** openstackgerrit has quit IRC13:51
*** cpallares has joined #openstack-marconi13:53
*** cpallares has left #openstack-marconi13:53
*** mpanetta has quit IRC13:54
*** mpanetta_ has joined #openstack-marconi13:54
alcabreraOut for a bit. Catch y'all later!14:00
*** alcabrera is now known as alcabrera|afk14:00
malinijchai: ping14:02
jchaimalini: hello14:02
malinijchai: good morning!!14:02
*** whenry has joined #openstack-marconi14:03
malinijchai: I see we still dont have much luck with xenserver :(14:03
jchaiNo. The job doesn't seem to start now.14:03
malinijchai: can you try posting in #openstack-qa14:04
malinisomebody there might know14:04
jchaiOK. Let me request it once more and if it doesn't run, I'll drop there14:04
malinithanks jchai!14:05
*** ykaplan has quit IRC14:08
flaper87malini: good morning :)14:11
*** Manishanker has quit IRC14:14
sriramgood morning everyone!14:16
sriram\o o/14:16
*** rwsu has joined #openstack-marconi14:18
*** mwagner_lap has joined #openstack-marconi14:18
malinihello flaper87!!14:18
flaper87sriram: gooooood morning14:20
*** cpallares has joined #openstack-marconi14:20
sriramflaper87: good morning :)14:22
maliniflaper87: all set for the trip?14:23
flaper87I have a ticket and a valid passport, that should be enough, right?14:24
*** rossk has joined #openstack-marconi14:26
*** prashanthr_ has joined #openstack-marconi14:27
maliniflaper87: yes :D14:29
malini& laundry the night before the trip, might be good as well :D14:29
maliniI am excited to meet everybody14:30
*** balajiiyer has joined #openstack-marconi14:41
*** rossk has quit IRC14:41
cpallareso/ malini!14:45
malinihello cpallares!!!14:46
cpallaresmalini: Did we decide on a restaurant?14:46
cpallaresmalini: how are you doing? :D14:46
malinicpallares: are you?14:46
malinicpallares:  We are going to meet at the CNN center,& grab something from their food court14:46
cpallaresmalini: I'm doing good too :)14:46
maliniwe might end up going to the centennial park right across the street14:47
malinicpallares: kgriffs|afk will be sending an email on tht14:47
maliniflaper87, kgriffs|afk: We need to add our design session etherpads here
*** kgriffs|afk is now known as kgriffs14:49
kgriffsmalini: thanks for the reminder; I'll set up some pads. Everyone feel free to seed them before your session14:51
flaper87malini: lol at laundry... /me usually prepares his bag 20 mins before leaving14:51
kgriffsI'll send out a notice to the mailing list14:51
malinithanks kgriffs!14:51
kgriffswrt the dinner, watch for an evite14:52
flaper87malini: When is the CNN thing? I know we w.... kgriffs thanks :D14:52
kgriffsmalini, mpanetta_: I had some questions/suggestions about the benchmark you did14:53
kgriffsgot a minute to discuss?14:53
malinikgriffs: sure14:53
kgriffsok, so first off, is journaling enabled (would be in the connection string for MongoDB iirc)14:54
kgriffsflaper87: related question; what is the value of enabling journaling if you are already replicating to multiple secondaries?14:55
flaper87kgriffs: if the master dies before replication happens and you don't have journaling enabled then something may go wrong14:55
flaper87however, we can also consider journal as enough quorum to get a response back from mongo14:56
flaper87that is, as soon as the record is journaled, we can tell mongo to consider the write operation complete14:56
flaper87that's all done with the write concern and putting it in the mongodb URI should be enough. I'm not 100% sure about the URI, I'll check14:57
flaper87kgriffs: I mentioned that we should have a performance hackthon during the summit14:57
flaper87Also, I consider all these journal, replication and scaling bits very deployment-dependent14:58
flaper87(the ones related to the storage driver)14:58
flaper87not saying we shouldn't care. What I'm saying is that we should find a configuration that we can tag as the recommended one14:58
flaper87This setup should take all those bits into consideration but it should also be aware that there are some trade-offs that can't be avoided14:59
kgriffsflaper87: +1 for both performance hackathon and for coming up with deployment recipes for our docs14:59
flaper87and then, around that recommended solution we can have things like: "If you disable journaling you get X and loose Y"14:59
kgriffsflaper87: if we have write concern as "majority" then write's arent' ack'd until they have been replicated, correct? If so, I feel like journaling is less important.15:00
flaper87kgriffs: it depends on the number of nodes you use in the write concern15:00
kgriffsunless you are concerned about catastrophic failure in the DC15:00
* flaper87 gets the docs link15:00
flaper87I would prefer having journal + 1 replica as opposed to all replicas and no journal15:01
kgriffsflaper87: well, consider your have 1 primary and two secondaries.15:01
kgriffsthen majority means primary + 1 secondary15:01
flaper87not necessarily primary, note that journal != primary15:01
*** Obulpathi has quit IRC15:02
flaper87journal means the record is journaled but it may not be present in the db15:02
flaper87... yet.15:02
* flaper87 gets the link for real this tiem15:02
kgriffsflaper87: ok15:02
flaper87(that's for 2.6)15:02
kgriffsok, just to be clear15:03
kgriffsthere is an option in the uri for enabling journaling15:03
kgriffsand once that is enabled, you can also add that in your write concern15:03
flaper87(the link is for 2.6, the rest is valid for other versions >= journal_was_added)15:04
flaper87journaling has to be enabled server side, what you can do in the URI is use journal as write concern15:04
kgriffsso, uri.journal is part of the write concern, and enabling journaling is what you do in the mongo config15:05
kgriffsflaper87: correct?15:05
kgriffsaccording to core/write-concern: "This write concern ensures that MongoDB can recover the data following a shutdown or power interruption."15:06
kgriffsif you have redundant power supplies on the rack as well as backup generator power for your DC, and your secondaries are in different availability zones within the DC, I see very little value to journaling15:06
kgriffswell, at least for messages15:07
kgriffsif this were financial transactions for ATM machines, I would be more concerned. :p15:07
* kgriffs is reading this now:
kgriffsmpanetta_: ping15:08
flaper87kgriffs: you found it first15:08
flaper87kgriffs: that's correct15:09
kgriffsflaper87: it was my future self. Being a transdimensional being has it's advantages.15:09
flaper87I still think there's some value in having journal+1 replica15:10
flaper87well, wait15:10
flaper87actually, now I'm thinking15:10
kgriffsflaper87: you should watch Noein. It will blow your mind.15:11
*** jchai is now known as jchai_afk15:11
kgriffsflaper87: i'm not saying journaling isn't useful, but that it depends on your deployment environment, plus your tolerance for loosing messages15:12
flaper87from a queuing perspective, there's probably little value in journaling since if something bad happens to the master, it'll likely not be up soon-enough for the journal to be useful15:12
flaper87that is, probably messages will be consumed by the time the master node comes back up15:12
flaper87but again, this is very dependent15:12
mpanetta_kgriffs: pong15:13
kgriffsso, we should give some smart guidance in the docs on when you might want to enable journaling, and when you may get away not doing so.15:13
kgriffsmpanetta_: hey, we were wondering whether journaling is enabled on the benchmark cluster for MongoDB. Can you share the mongo config file?15:13
kgriffsalso, can you share the connection string?15:13
mpanetta_The cluster is firewalled, you won't be able to connect15:14
flaper87However, replicating to secondaries may add some latency (depending on the network)15:14
kgriffsflaper87: So, someone like ObjectRocket can enable journaling almost for free. But if you have slower disk I/O, journaling can be pretty costly.15:14
flaper87mpanetta_: how dare you firewall the server from us?15:14
mpanetta_I don't trust robots :P15:14
*** mpanetta_ is now known as mpanetta15:14
flaper87mpanetta: damnit, fair enough15:15
kgriffsmpanetta_: I don't need to connect, just want to see the marconi and mongo conf files15:15
kgriffsmpanetta: hey, I'm not a robot!15:15
kgriffswell.. not all of me15:15
*** jchai_afk is now known as jchai15:15
flaper87kgriffs: re ObjRocket, yes! That's a fair statement15:15
mpanettaAre you the 6 million dollar man?15:15
flaper87kgriffs: if you are, throw 1 this way15:16
flaper87and thanks15:16
flaper87this = my15:16
flaper87(just in case)15:16
kgriffsmpanetta: I'm not at liberty to say what I am, for your safety as well as mine.15:16
mpanetta <--- mongodb.conf template15:16
flaper87mmhhh, how many replicas?15:17
flaper87mpanetta: what's the mongo URI ?15:17
flaper87and why is your username on GH bentwire ?15:18
* flaper87 is now confused15:18
mpanettaflaper87: Because That is the account I created so long ago ;)15:18
mpanettaTh RS is 315:18
kgriffsmpanetta, flaper87, malini: OK, so it looks like journaling is disabled on the benchmark cluster15:18
mpanettaprimary and 2 secondaries15:18
flaper87mpanetta: are read from slaves enabled ?15:18
sriramso for shard creation, this was the URI : mongodb://mng3a-cqt-ord,mng1a-cqt-ord,mng2a-cqt-ord:27017/?replicaSet=test-rs1&w=2&readPreference=secondaryPreferred15:19
flaper87holy crap, mmmh... what have we done?15:19
kgriffsw=2 looks bad15:19
mpanettaIs it?15:19
kgriffsif you loose one secondary, you will deadlock15:19
kgriffsit should be "majority" IMO15:19
mpanettaThe catalog db URI is similar15:20
mpanettaGotta log off my IRC is messed up15:21
*** mpanetta has quit IRC15:21
*** mpanetta has joined #openstack-marconi15:22
kgriffssriram: good morning!15:22
*** mpanetta has joined #openstack-marconi15:23
*** mpanetta has quit IRC15:23
sriramgood morning kgriffs!15:23
*** whenry has quit IRC15:23
kgriffssriram: thanks for helping with the benchmarking project15:23
*** mpanetta has joined #openstack-marconi15:23
kgriffssriram: and... you will be at the summit, right?15:24
sriramsure, and of course :)15:24
kgriffsso, I have been making myself a lot of thoughts about benchmarking. I looked at rally, and also have been thinking about Mike's suggestions.15:24
kgriffssriram: what do you think about this idea:15:25
kgriffsCreate a POC marconi-bench project. The project would take one of our primary messaging patterns, and simulate it using python-marconiclient, but patched to use gevent version of requests15:26
sriramthat sounds really cool!15:26
mpanettaI had a suggestion? :P15:27
kgriffsthen, we sample metrics and pipe them to either beekeeper or graphite. Samples would go in the load generators, the consumers, as well as in some WSGI middleware and maybe even at the DB driver layer15:27
kgriffsmpanetta: your suggestion to benchmark end-to-end scenarios so the results where more meaningful15:27
mpanettaAh yes15:28
mpanettaI have slept since then :P15:28
kgriffsI don't believe rally is up to the task today, but we could contribute to the project and get it there eventually15:28
*** whenry has joined #openstack-marconi15:28
kgriffsfirst step is to do a POC so we can have a baseline of what we want to achieve. plus, I'd like this sooner than we would be able to do it via Rally.15:29
kgriffsso, my plan is15:29
kgriffs1. POC15:29
kgriffs2. Work with rally to build out necessary support15:29
kgriffs3. merge POC with rally15:29
kgriffsflaper87, malini: thoughts?15:29
mpanettaWHat is rally again?15:29
*** haomaiwa_ has quit IRC15:29
mpanettaIs that the OS BM tool?15:29
*** haomaiwang has joined #openstack-marconi15:30
kgriffsalso, I mentioned beekeeper:
* flaper87 reads backlog15:31
malinikgriffs: tht is a good idea15:32
maliniit will help us get more stats than just per api calls15:33
flaper87kgriffs: it's a good idea.15:33
flaper87I'd also like to run other queuing systems benches on MArconi15:33
flaper87that is, the known existing benchmark rules for messaging systems15:34
flaper87take them, translate them to marconi and run them15:34
maliniboris-42: do you have any thoughts on this?15:34
kgriffsflaper87: ok15:34
kgriffsmalini: is boris-42 on the Rally team?15:34
kgriffsflaper87: ^^^15:37
*** haomaiwang has quit IRC15:37
kgriffsI think it would be good for some of us to attend that. We should connect with Boris and chat with him afterwards to share our use cases for Rally and find out what gaps Rally has that we can help with.15:38
kgriffssriram: ^^^15:38
mpanettaI can go.15:38
kgriffsmpanetta: seet.15:38
*** haomaiwa_ has joined #openstack-marconi15:38
kgriffsI just added it to my own agenda15:38
sriramYes, I'll go as well15:39
kgriffsok, so about that POC15:39
kgriffshow far can we get working on this today and tomorrow? I want to help too. Let me bring up a pad15:39
*** haomaiwa_ has quit IRC15:43
*** openstackgerrit has joined #openstack-marconi15:43
malinikgriffs: I talked to boris-42 a while back & rally was not yet ready to support our 2000 rps then15:44
*** rossk has joined #openstack-marconi15:44
maliniWe shuld sync up with the rally folks again during the summit15:45
kgriffswe will also need rally to be able to run different types of clients simultaneously - It wasn't clear from their docs whether Rally can do that yet.15:48
malinikgriffs: what do you mean by 'diff types of client' ?15:49
kgriffslike, we need some message producers running at the same time as some consumers, and we want to measure the rate that messages are being produced as well as consumed.15:50
kgriffsbasically, modeling a more real-world use case15:50
malinibut tht will vary depending on the app tht uses Marconi, rt?15:51
maliniare we looking at metrics for real crazy fast prod & consumer ?15:52
kgriffsmalini: well, I'd like to be able to spin up enough load generator processes and consumer processes to max out the benchmark deployment of Marconi15:56
kgriffsbasically, we need enough generators to feed X consumers15:56
kgriffswe will have to experiment to figure out the numbers. :p15:56
maliniwe need a virtual white board *-)15:57
kgriffsX greenlets across Y processes across Z VMs15:57
kgriffsmmm. I should diagram this15:57
kgriffsmalini: also need your approval if you agree ^^^15:58
kgriffsI want to do this before I cut a new pypi release15:58
openstackgerritA change was merged to openstack/python-marconiclient: Updated from global requirements
*** prashanthr_ has quit IRC16:05
boris-42malini I'm here=)16:08
boris-42kgriffs ping16:10
boris-42kgriffs what do you mean by different type of clients?16:11
kgriffsboris-42: so, we would like to simulate an end-to-end scenario. We would have X client that are producing messages as fast as they can, and Y clients that are consuming those messages.16:13
kgriffsso you have two different behaviors happening concurrently16:14
boris-42kgriffs hm it will be a bit tricky16:15
flaper87kgriffs: but we already bumpped the version16:15
flaper87I guess we'll have to do the milestone-proposed thing16:15
kgriffsflaper87: but we did not tag it yet16:15
boris-42kgriffs e.g. benchmark in rally meaning is some function that will be repeated multiply times (from randomly chosen user)16:16
boris-42kgriffs and there is another thing called benchmark context16:16
boris-42kgriffs it allows you to build any environment before running benchmark and cleanup it after running16:17
flaper87kgriffs: +@16:17
kgriffsboris-42: so, I guess what we would need is for the ability to run N of those benchmarks/environments simultaneously16:17
flaper87erm, +216:17
* flaper87 has to go through 10 proxies to use gerrit16:18
flaper87this is insane16:18
kgriffsboris-42: not sure if I am understanding correctly. I'd love to meet with you during the summit to discuss in detail16:18
boris-42kgriffs i have desing seesion16:18
kgriffsflaper87: WAH?16:18
boris-42kgriffs about rally16:18
flaper87kgriffs: yeah, just like that. my ISP hasn't fixed the blocked IP "issue"16:19
*** chandan_kumar has quit IRC16:19
boris-42kgriffs btw rally is run on every patch in keystone in glance16:19
boris-42kgriffs take a look here
*** balajiiyer has quit IRC16:20
kgriffsboris-42: cool. I'd love to run benchmarks on Marconi for every patch16:20
maliniboris-42: do these run against devstack?16:20
boris-42malini yep16:21
boris-42malini kgriffs  so take a look at this file16:21
kgriffsboris-42: for the moment we are going to do a POC benchmark but our plan is to migrate to rally16:21
boris-42kgriffs malini
boris-42kgriffs malini  you can specify here any amount of benchmarks with any load16:21
boris-42and result will be in this job check-rally-dsvm-keystone16:21
boris-42in case of keystone16:22
malini it'll be a good if boris-42 can look at our POC idea, to make sure it can integrate well into Rally16:22
openstackgerritA change was merged to openstack/python-marconiclient: chore: Classify as Beta (was pre-alpha)
boris-42malini kgriffs  and you are getting output like here
boris-42^ open in chrome=)16:22
boris-42malini yep it will be nice=)16:23
boris-42malini actually we don't support at this moment versioning cause we are trying to adopt rally16:23
boris-42malini to meet everybody requierments16:23
boris-42malini so generating big load16:24
boris-42malini aka 2k request per sec will be hard in gates16:24
boris-42malini cause at this moment we can request only one node from nodepool16:24
boris-42malini and marconi will work on the same node with rally16:25
boris-42malini so it may make troubles16:25
maliniboris-42: does rally have distributed load gen?16:25
boris-42malini we are working in that direction16:25
boris-42malini actually there are 3 separated task16:25
boris-421. visualization of data16:25
boris-422. storing big amount of data16:26
boris-423. doing this stuff with distributed load gen (yahoo is going to integrate task flow in rally so we will be able to do it)16:26
boris-42I am working on point 2 and thinking about point 116:26
boris-42when we finish all these steps we will be able to produce distributed load16:27
boris-42but we will have still issues with gates16:27
boris-42malini cause we have only one node => no need in distributed load generator16:27
malinithanks boris-42! Hope to meet you at the summit16:28
boris-42malini me too=)16:28
boris-42malini kgriffs  so guys my thoughts are next16:28
*** Obulpathi has joined #openstack-marconi16:28
boris-42malini kgriffs  we should start with adding marconi client to rally and making first simple benchmark16:28
boris-42malini kgriffs  that just put something to queue and consume from one user16:28
boris-42malini kgriffs so you'll get familiar with rally and we will be able to better understand what we actually need16:29
malinisure boris-42! We'll try to get something simple done, before the summit16:30
boris-42malini kgriffs  I think that distributed load generator is not only one change that is required in rally16:30
boris-42malini so let's make it today?)16:30
boris-42malini simple benchmarks are quite easy (copy-paste stuff)16:30
maliniboris-42: I am necks down in something else :(16:31
boris-42malini heh16:31
boris-42malini so when you will have about 1hrs16:31
boris-42malini or even less just ping me=)16:31
malinisure I will16:31
boris-42malini I'll help to start=)16:32
malinithanks boris-42!16:32
boris-42malini np16:32
boris-42kgriffs malini  btw does devstack install marconi ?16:32
boris-42malini kgriffs  I mean in gates?16:32
maliniboris-42: only in our experimental jobs & at the marconi jenkins pipeline16:32
boris-42malini ahh16:33
boris-42malini we will need to add dsvm-with-marconi job16:33
boris-42malini and one more rally job16:33
boris-42malini to be able to run rally or use experimental one16:33
maliniboris-42: we have a dsvm job16:34
boris-42malini nice=)16:34
boris-42malini ok then no worries about running rally against it=)16:34
*** Obulpathi has quit IRC16:40
kgriffsmpanetta, malini: are you doing LB on the benchmark deployment?16:44
kgriffsor is it a single web head?16:44
kgriffsmpanetta: haproxy or something else?16:44
mpanettacloud LB16:44
kgriffsoh. What do you think about using haproxy? That would give the community one less "black-box" piece to factor into when digesting the results16:46
kgriffsalso gives us a little bit more consistent results, I would think, since we would own more of the box than we get as one of many tenants in cloud LB16:46
kgriffs(more noisy neighbor in cloud LB)16:46
*** reed has joined #openstack-marconi16:49
kgriffsmpanetta: p.s. - are you benchmarking with SSL termination?16:51
kgriffsand keystone auth?16:51
mpanettaI think they disabled keystone auth16:51
mpanettaYou would have to ask sriram that16:51
kgriffssriram: ^^^16:51
mpanettano ssl term AFAIK16:52
kgriffsmpanetta: how many web heads? 4?16:52
*** Obulpathi has joined #openstack-marconi16:57
*** Obulpathi has quit IRC16:58
*** Obulpathi has joined #openstack-marconi16:59
*** alcabrera|afk is now known as alcabrera17:04
*** balajiiyer has joined #openstack-marconi17:04
sriramkeystone auth was in place. 4 web heads, behind a loab balancer, with a mongo replica set17:09
*** openstackgerrit has quit IRC17:20
*** openstackgerrit has joined #openstack-marconi17:25
kgriffssriram: memcached for caching keystone auth?17:25
kgriffssriram: ssl termination?17:26
sriramno ssl, just ip17:29
*** abettadapur has joined #openstack-marconi17:31
*** Obulpathi has quit IRC17:53
kgriffssriram: memcached is colocated on each web head?18:02
sriramyes, they are colocated.18:04
kgriffsok. Do you have time today and tomorrow to work on this POC with me?
sriramsure, can I let you know about this soon?18:18
kgriffssriram: yeah, just ping me. I was going to work on it myself, but wanted to see who would be able to help divide up the work18:20
kgriffsflaper87: "git push gerrit 0.0.1"18:20
kgriffs ! [remote rejected] 0.0.1 -> 0.0.1 (prohibited by Gerrit)18:20
* kgriffs is a sad panda18:21
kgriffsmpanetta: can you help me? I'd like to set up a graphite box that our benchmarking cluster can push to18:23
kgriffsI'd also like to set up haproxy instead of using cloud LB18:23
mpanettaI don't think I have enough time to do that :(18:47
kgriffsI can do the legwork. let me ping you.18:50
flaper87kgriffs: you'll have to ping ttx19:05
flaper87I think they never gave you / me access19:05
kgriffsstrange. why did it work last time for 0.0.1a1 ?19:05
flaper87kgriffs: because he did it :)19:05
kgriffsmm, my name is on the last tag19:06
* kgriffs is confused19:06
flaper87oh, mmh19:06
flaper87then, no idea19:06
*** Obulpathi has joined #openstack-marconi19:23
*** Obulpathi has quit IRC19:24
*** Obulpathi has joined #openstack-marconi19:24
*** ametts has joined #openstack-marconi19:28
*** AAzza has joined #openstack-marconi19:28
*** malini is now known as malini_afk19:38
*** megan_w|afk is now known as megan_w19:41
*** AAzza has quit IRC19:45
*** cpallares has quit IRC19:50
kgriffsflaper87: I pinged ttx earlier, no response. Can you help me try to reach him? If we both keep pinging him, we'll have a better chance getting this resolved sooner rather than later.19:52
kgriffsflaper87: p.s. - we should add a doc to the wiki on how to release19:52
kgriffsflaper87: like this
flaper87kgriffs: IIRC he's off on vacation20:08
flaper87but yeah, I'll try tor each him tomorrow20:08
flaper87re the wiki page, the process is the same for everyone, I wonder why that page is not in some common place20:09
flaper87perhaps we should update the existing one20:09
*** reed has quit IRC20:09
*** reed has joined #openstack-marconi20:12
*** kgriffs is now known as kgriffs|afk20:13
*** abettadapur has quit IRC20:15
*** alcabrera is now known as alcabrera|afk20:17
*** megan_w is now known as megan_w|afk20:27
*** sriram has quit IRC20:30
*** megan_w|afk is now known as megan_w20:32
*** balajiiyer has left #openstack-marconi20:32
*** kgriffs|afk is now known as kgriffs20:50
*** mpanetta has quit IRC20:53
amitgandhikgriffs: flaper87: forgot the etherpad link for places we should incorporate marconi, but lets add mistral to that list - they use task queues21:07
*** boris-42 has quit IRC21:15
*** boris-42 has joined #openstack-marconi21:16
*** jchai has quit IRC21:18
*** amitgandhi has quit IRC21:48
*** mwagner_lap has quit IRC21:48
*** Obulpathi has quit IRC22:03
*** megan_w is now known as megan_w|afk22:08
*** vkmc has quit IRC22:54
*** kgriffs is now known as kgriffs|afk23:31
*** flaper87 is now known as flaper87|afk23:43
*** mwagner_lap has joined #openstack-marconi23:50

Generated by 2.14.0 by Marius Gedminas - find it at!