Hi, Igniters. I'm working on the implementation of lightweight PME for a baseline node leave case. [1] In my implementation, each node recalculates a new affinity and completes PME locally without distributed communication. This is possible because there are all partitions are distributed according to the baseline topology. And I found two possible blockers to do it without blocking updates:
1. Finalize partitions counter. It seems that we can't correctly collect gaps and process them without completing all txs. See the GridDhtPartitionTopologyImpl#finalizeUpdateCounters method. 2. Apply update counters. We can't correctly set HWM counter if primary left the cluster and sent updates to part of backups. Such updates can be processed later and break guarantee that LWM<=HWM. Is it impossible to leave a baseline node without waiting for all txs completed? 1. https://issues.apache.org/jira/browse/IGNITE-9913 ср, 5 июн. 2019 г. в 12:15, Nikita Amelchev <nsamelc...@gmail.com>: > > Maksim, > > I agree with you that we should implement current issue and do not > allow lightweight PME if there are MOVING partitions in the cluster. > > But now I'm investigating issue about finalizing update counters cause > it assumes that finalizing happens on exchange and all cache updates > are completed. Here we can wrong process update counters gaps and > break recently merged IGNITE-10078. > > And about phase 2, correct me if I misunderstood you. > You suggest do not move primary partitions on rebalancing completing > (do not change affinity assignment)? In this case, nodes recently join > to cluster will not have primary partitions and won't get a load after > rebalancing. > > чт, 30 мая 2019 г. в 19:55, Maxim Muzafarov <maxmu...@gmail.com>: > > > > Igniters, > > > > > > I've looked through Nikita's changes and I think for the current issue > > [1] we should not allow the existence of MOVING partitions in the > > cluster (it must be stable) to run the lightweight PME on BLT node > > leave event occurred to achieve truly unlocked operations and here are > > my thoughts why. > > > > In general, as Nikita mentioned above, the existence of MOVING > > partitions in the cluster means that the rebalance procedure is > > currently running. It owns cache partitions locally and sends in the > > background (with additional timeout) the actual statuses of his local > > partitions to the coordinator node. So, we will always have a lag > > between local node partition states and all other cluster nodes > > partitions states. This lag can be very huge since previous > > #scheduleResendPartitions() is cancelled when a new cache group > > rebalance finished. Without the fair partition states synchronization > > (without full PME) and in case of local affinity recalculation on BLT > > node leave event, other nodes will mark such partitions LOST in most > > of the cases, which in fact are present in the cluster and saved on > > some node under checkpoint. I see that it cannot be solved by saving > > transition states of such partitions on each node. > > > > As for the case when the coordinator will calculate affinity and send > > "full map" to other nodes, I think it is better here to focus on > > designing a new lightweight PME when the rebalancing process finishes. > > Сurrently full distributed PME will occur anyway by the coordinator by > > sending CacheAffinityChaneMessage, but I think we can avoid it here, > > since no new MOVING or OWNING node partition states are introduced and > > all the previous mappings are still valid. We don't need a distributed > > PME if we will leave partition primaries on those nodes where they > > were, just set correct partition statuses via a light discovery > > message. > > > > So, my plan here can be: > > Phase 1. Lightweight PME on BLT node leave on a stable cluster (no > > MOVING partitions); > > Phase 2. Lightweight PME on BLT node finishes its rebalance procedure. > > > > Folks, Nikita, > > WDYT? > > > > [1] https://issues.apache.org/jira/browse/IGNITE-9913 > > > > On Fri, 24 May 2019 at 13:31, Nikita Amelchev <nsamelc...@gmail.com> wrote: > > > > > > Hello, Igniters! > > > > > > I am working on the implementation of lightweight PME for the case of > > > a BLT node leave. [1] > > > > > > There is a question: whether to allow lightweight PME if the cluster > > > has MOVING partitions? > > > > > > The problems that may happen if allow: > > > - Nodes can differently select the primary node from current OWNING > > > backups. > > > - One part of nodes can mark a partition as LOST and another one as > > > OWNING. > > > > > > We can take states of the partitions from the node2part map. The root > > > cause of those problems is that when rebalancing ends (get the last > > > message), it updates partition state of the local node to OWNING (and > > > schedules partitions resend). This may lead to different affinity > > > re-calculations on nodes. > > > > > > I see two solutions: > > > > > > 1. Nodes will store “moving-owning” transition of partitions state > > > until the rebalancing ends. Each node will locally recalculate the > > > affinity on node left event. > > > 2. The coordinator will calculate affinity and send "full map" to > > > nodes. In this case, nodes still should wait for topology change event > > > (to get correct topology in discovery). > > > > > > If disallow lightweight PME when the cluster has MOVING partitions - > > > there are no problems and it works fine. > > > > > > Any thoughts? > > > > > > 1. https://issues.apache.org/jira/browse/IGNITE-9913 > > > > > > пт, 29 мар. 2019 г. в 15:00, Nikita Amelchev <nsamelc...@gmail.com>: > > > > > > > > Pavel, > > > > I have provided MTCGA bot status in Jira issue comments. [1] > > > > > > > > Eduard, > > > > Yes, for current implementation it will be distributed PME if > > > > in-memory caches configured. > > > > > > > > 1. https://issues.apache.org/jira/browse/IGNITE-9913 > > > > > > > > пт, 29 мар. 2019 г. в 14:49, Eduard Shangareev > > > > <eduard.shangar...@gmail.com>: > > > > > > > > > > Nikita, > > > > > > > > > > It sounds cool. But I didn't get about in-memory caches. The baseline > > > > > is > > > > > not used for their affinity calculation. > > > > > So, this improvement would be switched off for them or completely > > > > > (when > > > > > such caches are presented), wouldn't it? > > > > > > > > > > On Thu, Mar 28, 2019 at 3:14 PM Pavel Kovalenko <jokse...@gmail.com> > > > > > wrote: > > > > > > > > > > > Hi Nikita, > > > > > > > > > > > > Thank you for your work. This is great improvement. I'll take look > > > > > > on it in > > > > > > next couple of days. Could you please run TC and provide MTCGA bot > > > > > > status > > > > > > about this change? > > > > > > > > > > > > чт, 28 мар. 2019 г. в 14:29, Nikita Amelchev <nsamelc...@gmail.com>: > > > > > > > > > > > > > Hello, Igniters! > > > > > > > > > > > > > > I have implemented lightweight version of partitions map exchange > > > > > > > for > > > > > > > the case when the baseline node leaves topology. [1] > > > > > > > > > > > > > > If partitions are assigned according to the baseline topology and > > > > > > > server node leaves there's no actual need to perform distributed > > > > > > > PME. > > > > > > > Every cluster will recalculate new affinity assignments and > > > > > > > partition > > > > > > > states locally. There is no need to wait for partitions released > > > > > > > and > > > > > > > PME will be started immediately. > > > > > > > > > > > > > > I have benchmarked duration of PME under yardstick load. PME > > > > > > > duration > > > > > > > was decreased up to 10 times and the maximum latency of > > > > > > > transactions > > > > > > > was decreased up to 4-5 times. See details in Jira issue > > > > > > > comments. [1] > > > > > > > > > > > > > > Could some expert of PME take a look at my changes? [2] > > > > > > > > > > > > > > 1. https://issues.apache.org/jira/browse/IGNITE-9913 > > > > > > > 2. https://reviews.ignite.apache.org/ignite/review/IGNT-CR-1027 > > > > > > > > > > > > > > -- > > > > > > > Best wishes, > > > > > > > Amelchev Nikita > > > > > > > > > > > > > > > > > > > > > > > > > > > > > -- > > > > Best wishes, > > > > Amelchev Nikita > > > > > > > > > > > > -- > > > Best wishes, > > > Amelchev Nikita > > > > -- > Best wishes, > Amelchev Nikita -- Best wishes, Amelchev Nikita
