Thanx folks, I had a very quick pass on the PDF and it looks good. Maybe some doubts around the fact where it was mentioned that if a Namenode returns a StandbyException or something on similar lines, the Router will retry, I think we have some logic in RouterRpcClient checking for such case, if it is StandByException it does try the other Namenode, but for all other Retryable Exceptions, we return them back to the client & let the client operate according to its Retry Policy, I think we should preserve that behaviour, if the intentions were to change it.
Regarding controlling the concurrency to prevent OOM at the router, maybe we should consider rejecting the client requests beyond a certain limit/backlog & return back a relevant Retriable Exception to the client, so that it can retry on another Router rather than overloading one Router when there are other available, most of the deployments I believe would be running considerable number of Routers Rest I scratched my head for possible scenario where things can go south, but I think mostly the scenarios that came into my mind are covered Nothing blocker from my side, Good Luck!!! -Ayush On Tue, 28 May 2024 at 21:52, Sangjin Lee <sj...@apache.org> wrote: > > Sounds good. Thanks for sharing your findings. > > On Sat, May 25, 2024 at 2:24 AM zhangjian <1361320...@qq.com> wrote: >> >> Hello everyone, I conducted a performance comparison test between sync and >> asynchronous router, and the test results showed that in single ns or multi >> ns scenarios, Asynchronous router in terms of throughput The utilization of >> CPU and thread, as well as the average processing time of client requests, >> are better than those of sync router, especially when downstream ns have >> performance bottlenecks, The performance of the async router is far greater >> than that of the sync router; And in terms of isolation, Asynchronous router >> is also better than sync router. >> Detailed testing PDF: https://issues.apache.org/jira/browse/HDFS-17531 >> Comparison of Async router & sync router performance.pdf >> >> 2024年5月24日 14:13，Yuanbo Liu <liuyuanb...@gmail.com> 写道： >> >> good job! >> >> On Fri, May 24, 2024 at 1:57 AM zhangjian <1361320...@qq.com> wrote: >>> >>> Hello everyone, currently, I have tested the performance of async and sync >>> router for a downstream ns: >>> 1. The throughput, CPU, and thread performance of the async router are >>> better than those of the sync router, and its memory performance is within >>> an acceptable range compared to the synchronous router. >>> 2. Asynchronous router can apply pressure downstream to better utilize the >>> performance of downstream ns, and can almost fill the call queue of >>> downstream ns. >>> >>> Due to the large size of the test result pdf, it cannot be sent via email, >>> please see: https://issues.apache.org/jira/browse/HDFS-17531 >>> >>> > 2024年5月23日 17:03，Xiaoqiao He <hexiaoq...@apache.org> 写道： >>> > >>> > Great. Thanks for your addendum information. >>> > >>> > cc @Ayush Saxena <ayush...@gmail.com> @inigo...@apache.org >>> > <inigo...@apache.org> Any more feedback for this proposal? >>> > >>> > IMO The feature of asynchronous router RPC is a helpful improvement. For >>> > my >>> > internal practice, it will improve the throughput of requests forward >>> > significantly >>> > and is very valuable to push it forward. >>> > Thanks again and good luck! >>> > >>> > Best Regards, >>> > - He Xiaoqiao >>> > >>> > On Wed, May 22, 2024 at 9:59 AM zhangjian <1361320...@qq.com> wrote: >>> > >>> >> Hi, Sangjin Lee, thank you for your attention. I will use my free time to >>> >> do a performance comparison recently. >>> >> >>> >>> 2024年5月22日 03:42，Sangjin Lee <sj...@apache.org> 写道： >>> >>> >>> >>> Thanks for the great proposal, Zhangjian. On point #3, I suspect it >>> >> should >>> >>> be fairly straightforward to create a small isolated synthetic test to >>> >>> prove (or disprove) the benefits of this approach. By driving a >>> >> controlled >>> >>> amount of requests per second, you could see latency, memory, CPU, etc. >>> >>> Ideally, it should show meaningful improvements without much degradation >>> >> in >>> >>> other metrics. Would you be able to spend some time doing that? >>> >>> >>> >>> Thanks, >>> >>> Sangjin >>> >>> >>> >>> On Tue, May 21, 2024 at 5:13 AM zhangjian <1361320...@qq.com.invalid> >>> >> wrote: >>> >>> >>> >>>> Hi, xiaoqiao he, thank you for your reply. >>> >>>> >>> >>>> 1.Currently, the server and client protocols within router can be >>> >>>> implemented by extends existing protocols and adding asynchronous >>> >>>> functionality, so it will not affect existing synchronization >>> >>>> protocols. >>> >>>> RouterClientNamenodeProtocolServerSideTranslatorPB >>> >>>> RouterClientProtocolTranslatorPB >>> >>>> RouterGetUserMappingsProtocolServerSideTranslatorPB >>> >>>> RouterGetUserMappingsProtocolTranslatorPB >>> >>>> RouterNamenodeProtocolServerSideTranslatorPB >>> >>>> RouterNamenodeProtocolTranslatorPB >>> >>>> RouterRefreshUserMappingsProtocolServerSideTranslatorPB >>> >>>> RouterRefreshUserMappingsProtocolTranslatorPB >>> >>>> >>> >>>> The following issues have implemented asynchronous callbacks for >>> >>>> Rpc.server, but I have not found any other modules to use related >>> >> functions >>> >>>> Server HADOOP-11552 HADOOP-17046 >>> >>>> In the implementation of asynchronous Rpc.client, this issue is >>> >>>> directly >>> >>>> used >>> >>>> Client HADOOP-13226 >>> >>>> Therefore, I believe that asynchronous routers are safe for modifying >>> >> the >>> >>>> RPC protocol, RPC server, and client >>> >>>> >>> >>>> 2. Forwarding requests to multiple downstream ns, the synchronous >>> >>>> router >>> >>>> handler adds requests from multiple downstream ns to the thread pool >>> >>>> (RouterRpcClient.executorService), and then waits for responses from >>> >>>> all >>> >>>> downstream ns before returning. Since threads in the thread pool also >>> >>>> process rpc requests synchronously, similar to a handler, the number of >>> >>>> threads in the thread pool directly affects the performance of >>> >>>> invoiceConcurrent, which in turn affects the performance of the >>> >>>> handler. >>> >>>> In asynchronous router implementation, the handler calls >>> >> invoiceConcurrent >>> >>>> to simply convert a request into multiple requests and add them to the >>> >> asyn >>> >>>> handler thread pool, which can then process the next request in the >>> >>>> call >>> >>>> queue; When a connection thread of a downstream ns receives a response, >>> >> it >>> >>>> will hand it over to the async response for processing. The async >>> >> response >>> >>>> thread will determine whether it has received all responses from the >>> >>>> downstream ns. If it does, it will continue to process the response. >>> >>>> Otherwise, the async response thread will process the next response. >>> >>>> The >>> >>>> asynchronous router uses CompletableFuture.allOf() to implement >>> >>>> asynchronous invoiceConcurrent, and the handler, async handler, async >>> >>>> response, and connection thread still does not need to wait >>> >> synchronously. >>> >>>> In addition, synchronous routers not only have drawbacks in multi ns >>> >>>> environments, but also in single downstream ns situations, it is often >>> >>>> difficult to decide how many handlers to set for the router, setting it >>> >> too >>> >>>> much will waste thread resources, and setting it too small will not be >>> >> able >>> >>>> to give pressure to downstream ns; Asynchronous routers can push >>> >> requests >>> >>>> to downstream ns without considering how to set handlers. Asynchronous >>> >>>> routers can also better connect to more downstream storage services >>> >>>> that >>> >>>> support the HDFS protocol, with better scalability. >>> >>>> >>> >>>> 3.Since I have not yet deployed asynchronous routers to our own >>> >>>> cluster, >>> >>>> there is no performance comparison. However, theoretically, I believe >>> >> that >>> >>>> asynchronous routers will occupy more memory than synchronous routers. >>> >>>> However, I do not believe that it will occupy a lot, especially since >>> >>>> we >>> >>>> can control the maximum number of requests entering the router, as >>> >>>> CompletableFuture is stable and widely used; In other aspects, it >>> >> should be >>> >>>> far superior to synchronous routers, especially in downstream scenarios >>> >>>> with more ns.If anyone is interested, you can also help to make a >>> >>>> performance comparison >>> >>>> >>> >>>>> 2024年5月21日 11:39，Xiaoqiao He <hexiaoq...@apache.org> 写道： >>> >>>>> >>> >>>>> Thanks for this great proposal! >>> >>>>> >>> >>>>> Some questions after reviewing the design doc (sorry didn't review PR >>> >>>>> carefully which is too large.) >>> >>>>> 1. This solution will involve RPC framework update, will it affect >>> >> other >>> >>>>> modules and how to >>> >>>>> keep other modules off these changes. >>> >>>>> 2. Some RPC requests should be forward concurrently to all downstream >>> >> NS, >>> >>>>> will it cover >>> >>>>> this case in this solution. >>> >>>>> 3. Considering there is one init-version implementation, did you >>> >> collect >>> >>>>> some benchmark vs >>> >>>>> the current synchronous model of DFSRouter? >>> >>>>> Thanks again. >>> >>>>> >>> >>>>> Best Regards, >>> >>>>> - He Xiaoqiao >>> >>>>> >>> >>>>> On Tue, May 21, 2024 at 11:21 AM zhangjian <1361320...@qq.com.invalid> >>> >>>>> wrote: >>> >>>>> >>> >>>>>> Thank you for your positive attitude towards this feature. You can >>> >> debug >>> >>>>>> the UTs provided in PR to better understand the current asynchronous >>> >>>>>> calling function. >>> >>>>>> >>> >>>>>>> 2024年5月21日 02:04，Simbarashe Dzinamarira <simbadz...@apache.org> 写道： >>> >>>>>>> >>> >>>>>>> Excited to see this feature as well. I'll spend more time >>> >> understanding >>> >>>>>> the >>> >>>>>>> proposal and implementation. >>> >>>>>>> >>> >>>>>>> On Mon, May 20, 2024 at 7:55 AM zhangjian <1361320...@qq.com.invalid >>> >>> >>> >>>>>> wrote: >>> >>>>>>> >>> >>>>>>>> Hi, Yuanbo liu, thank you for your interest in this feature, I >>> >> think >>> >>>>>> the >>> >>>>>>>> difficulty of an asynchronous router is not only to implement >>> >>>>>> asynchronous >>> >>>>>>>> functions, but also to consider the readability and reusability of >>> >> the >>> >>>>>>>> code, so as to facilitate the development of the community. I also >>> >>>>>> planned >>> >>>>>>>> to do the virtual thread you mentioned at the beginning, virtual >>> >>>> Threads >>> >>>>>>>> can achieve asynchronousization elegantly at the code level, but >>> >>>>>>>> the >>> >>>>>>>> biggest problem is that it is not easy to upgrade the jdk version, >>> >> no >>> >>>>>>>> matter in the community or in the actual production environment. >>> >>>>>> Therefore, >>> >>>>>>>> I later used CompletableFuture, which is currently supported by jdk >>> >> 8, >>> >>>>>> to >>> >>>>>>>> achieve asynchronousization. The router is stateless, and the >>> >>>>>>>> router >>> >>>> rpc >>> >>>>>>>> process is very clear. Therefore, even if CompletableFuture itself >>> >> is >>> >>>>>> not >>> >>>>>>>> as readable as the virtual thread, if we design it well, we can >>> >>>>>>>> make >>> >>>> the >>> >>>>>>>> asynchronous process look very clear. >>> >>>>>>>> >>> >>>>>>>> >>> >>>>>>>>> 2024年5月20日 10:56，Yuanbo Liu <liuyuanb...@gmail.com> 写道： >>> >>>>>>>>> >>> >>>>>>>>> Nice to see this feature brought up. I tried to implement this >>> >>>> feature >>> >>>>>> in >>> >>>>>>>>> our internal clusters, and know that it's a very complicated >>> >> feature, >>> >>>>>> CC >>> >>>>>>>>> hdfs-dev to bring more discussion. >>> >>>>>>>>> By the way, I'm not sure whether virtual thread of higher jdk will >>> >>>> help >>> >>>>>>>> in >>> >>>>>>>>> this case. >>> >>>>>>>>> >>> >>>>>>>>> On Mon, May 20, 2024 at 10:10 AM zhangjian >>> >> <1361320...@qq.com.invalid >>> >>>>> >>> >>>>>>>>> wrote: >>> >>>>>>>>> >>> >>>>>>>>>> Hello everyone, currently there are some shortcomings in the RPC >>> >> of >>> >>>>>> HDFS >>> >>>>>>>>>> router： >>> >>>>>>>>>> >>> >>>>>>>>>> Currently the router's handler thread is synchronized, when the >>> >>>>>>>> *handler* thread >>> >>>>>>>>>> adds the call to connection.calls, it needs to wait until the >>> >>>>>>>> *connection* notifies >>> >>>>>>>>>> the call to complete, and then Only after the response is put >>> >>>>>>>>>> into >>> >>>> the >>> >>>>>>>>>> response queue can a new call be obtained from the call queue and >>> >>>>>>>>>> processed. Therefore, the concurrency performance of the router >>> >>>>>>>>>> is >>> >>>>>>>> limited >>> >>>>>>>>>> by the number of handlers; a simple example is as follows: If the >>> >>>>>>>> number of >>> >>>>>>>>>> handlers is 1 and the maximum number of calls in the connection >>> >>>> thread >>> >>>>>>>> is >>> >>>>>>>>>> 10, then even if the connection thread can send 10 requests to >>> >>>>>>>>>> the >>> >>>>>>>>>> downstream ns, since the number of handlers is 1, the router can >>> >>>> only >>> >>>>>>>>>> process one request after another. >>> >>>>>>>>>> >>> >>>>>>>>>> Since the performance of router rpc is mainly limited by the >>> >> number >>> >>>> of >>> >>>>>>>>>> handlers, the most effective way to improve rpc performance >>> >>>> currently >>> >>>>>>>> is to >>> >>>>>>>>>> increase the number of handlers. Letting the router create a >>> >>>>>>>>>> large >>> >>>>>>>> number >>> >>>>>>>>>> of handler threads will also increase the number of thread >>> >> switches >>> >>>>>> and >>> >>>>>>>>>> cannot maximize the use of machine performance. >>> >>>>>>>>>> >>> >>>>>>>>>> There are usually multiple ns downstream of the router. If the >>> >>>> handler >>> >>>>>>>>>> forwards the request to an ns with poor performance, it will >>> >>>>>>>>>> cause >>> >>>> the >>> >>>>>>>>>> handler to wait for a long time. Due to the reduction of >>> >>>>>>>>>> available >>> >>>>>>>>>> handlers, the router's ability to handle ns requests with normal >>> >>>>>>>>>> performance will be reduced. From the perspective of the client, >>> >> the >>> >>>>>>>>>> performance of the downstream ns of the router has deteriorated >>> >>>>>>>>>> at >>> >>>>>> this >>> >>>>>>>>>> time. We often find that the call queue of the downstream ns is >>> >> not >>> >>>>>>>> high, >>> >>>>>>>>>> but the call queue of the router is very high. >>> >>>>>>>>>> >>> >>>>>>>>>> Therefore, although the main function of the router is to >>> >>>>>>>>>> federate >>> >>>> and >>> >>>>>>>>>> handle requests from multiple NSs, the current synchronous RPC >>> >>>>>>>> performance >>> >>>>>>>>>> cannot satisfy the scenario where there are many NSs downstream >>> >>>>>>>>>> of >>> >>>> the >>> >>>>>>>>>> router. Even if the concurrent performance of the router can be >>> >>>>>>>> improved by >>> >>>>>>>>>> increasing the number of handlers, it is still relatively slow. >>> >> More >>> >>>>>>>>>> threads will increase the CPU context switching time, and in fact >>> >>>> many >>> >>>>>>>> of >>> >>>>>>>>>> the handler threads are in a blocked state, which is undoubtedly >>> >>>>>>>>>> a >>> >>>>>>>> waste of >>> >>>>>>>>>> thread resources. When a request enters the router, there is no >>> >>>>>>>> guarantee >>> >>>>>>>>>> that there will be a running handler at this time. >>> >>>>>>>>>> >>> >>>>>>>>>> >>> >>>>>>>>>> Therefore, I consider asynchronous router rpc. Please view the >>> >>>> issues: >>> >>>>>>>>>> https://issues.apache.org/jira/browse/HDFS-17531 for the >>> >> complete >>> >>>>>>>>>> solution. >>> >>>>>>>>>> >>> >>>>>>>>>> And you can also view this PR: >>> >>>>>>>> https://github.com/apache/hadoop/pull/6838, >>> >>>>>>>>>> which is just a demo, but it completes the core asynchronous RPC >>> >>>>>>>> function. >>> >>>>>>>>>> If you think asynchronous routing is feasible, we can consider >>> >>>>>> splitting >>> >>>>>>>>>> this PR for easy review in the future. >>> >>>>>>>>>> >>> >>>>>>>>>> The PDF is attached and can also be viewed through issues. >>> >>>>>>>>>> >>> >>>>>>>>>> Welcome everyone to exchange and discuss! >>> >>>>>>>>>> >>> >>>>>>>> >>> >>>>>>>> >>> >>>>>>>> >>> >> --------------------------------------------------------------------- >>> >>>>>>>> To unsubscribe, e-mail: common-dev-unsubscr...@hadoop.apache.org >>> >>>>>>>> For additional commands, e-mail: common-dev-h...@hadoop.apache.org >>> >>>>>>>> >>> >>>>>>>> >>> >>>>>> >>> >>>>>> >>> >>>>>> --------------------------------------------------------------------- >>> >>>>>> To unsubscribe, e-mail: hdfs-dev-unsubscr...@hadoop.apache.org >>> >>>>>> For additional commands, e-mail: hdfs-dev-h...@hadoop.apache.org >>> >>>>>> >>> >>>>>> >>> >>>> >>> >>>> >>> >>>> --------------------------------------------------------------------- >>> >>>> To unsubscribe, e-mail: common-dev-unsubscr...@hadoop.apache.org >>> >>>> For additional commands, e-mail: common-dev-h...@hadoop.apache.org >>> >>>> >>> >>>> >>> >>> >>> >> >>> >> >>> > >> >> --------------------------------------------------------------------- To unsubscribe, e-mail: common-dev-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-dev-h...@hadoop.apache.org
