[ https://issues.apache.org/jira/browse/GIRAPH-301?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13437616#comment-13437616 ]
Eli Reisman commented on GIRAPH-301: ------------------------------------ GIRAPH-301-5 has been tested to the largest scale and spreads the work as evenly as any solution I have tried here yet while speeding up the INPUT_SUPERSTEP by avoiding slow ZK read-iterations for each worker down its split list by trying to set up each worker to find at least its first unclaimed split with minimal contention and without sacrificing locality where a worker might have it available, at least on the first split it reads. In our use case here, where we want to spread the work among many memory-constrained workers, this is the ideal case to avoid overloads and crashes. Very good complement to the original locality patch, probably should have been a feature of that one :) > InputSplit Reservations are clumping, leaving many workers asleep while other > process too many splits and get overloaded. > ------------------------------------------------------------------------------------------------------------------------- > > Key: GIRAPH-301 > URL: https://issues.apache.org/jira/browse/GIRAPH-301 > Project: Giraph > Issue Type: Improvement > Components: bsp, graph, zookeeper > Affects Versions: 0.2.0 > Reporter: Eli Reisman > Assignee: Eli Reisman > Labels: patch > Fix For: 0.2.0 > > Attachments: GIRAPH-301-1.patch, GIRAPH-301-2.patch, > GIRAPH-301-3.patch, GIRAPH-301-4.patch, GIRAPH-301-5.patch > > > With recent additions to the codebase, users here have noticed many workers > are able to load input splits extremely quickly, and this has altered the > behavior of Giraph during INPUT_SUPERSTEP when using the current algorithm > for split reservations. A few workers process multiple splits (often > overwhelming Netty and getting GC errors as they attempt to offload too much > data too quick) while many (often most) of the others just sleep through the > superstep, never successfully participating at all. > Essentially, the current algo is: > 1. scan input split list, skipping nodes that are marked "Finsihed" > 2. grab the first unfinished node in the list (reserved or not) and check its > reserved status. > 3. if not reserved, attempt to reserve & return it if successful. > 4. if the first one you check is already taken, sleep for way too long and > only wake up if another worker finishes a split, then contend with that > worker for another split, while the majority of the split list might sit > idle, not actually checked or claimed by anyone yet. > This does not work. By making a few simple changes (and acknowledging that ZK > reads are cheap, only writes are not) this patch is able to get every worker > involved, and keep them in the game, ensuring that the INPUT_SUPERSTEP passes > quickly and painlessly, and without overwhelming Netty by spreading the > memory load the split readers bear more evenly. If the giraph.splitmb and -w > options are set correctly, behavior is now exactly as one would expect it to > be. > This also results in INPUT_SUPERSTEP passing more quickly, and survive the > INPUT_SUPERSTEP for a given data load on less Hadoop memory slots. > -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa For more information on JIRA, see: http://www.atlassian.com/software/jira