[
https://issues.apache.org/jira/browse/CASSANDRA-8911?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15411511#comment-15411511
]
Marcus Eriksson commented on CASSANDRA-8911:
--------------------------------------------
Thanks for the early review
bq. I don't entirely get why we need a separate HUGE response, can't we just
page back the data from the mismatching replica in the MBRResponse similar to
ordinary responses?
There are two reasons, first one is that we save one round trip during repair
of a page. Second reason is that it is easier do diff the remote data with the
local data if we are not paging. (ie, we know we are comparing the entire
result, not just a page of it)
bq. While it's handy to have a rows/s metric for repaired rows, I think it
might be more useful for operators to have a repair throttle knob in MB/S (in
line with compaction/stream throughput) rather than rows/s, since the load
imposed by a repairing row can vary between different tables, so it might be a
bit trickier to do capacity planning based on rows/s.
I have not focused on metrics at all yet, and yes we should add more.
bq. Currently we're throttling only at the coordinator, but it would probably
be interesting to use the same rate limiter to also throttle participant
reads/writes.
hmm, maybe makes sense to only throttle on the replicas
bq. Can we make MBROnHeapUnfilteredPartitions a lazy iterator that caches rows
while its traversed?
good point, will fix
bq. Also, can we leverage MBROnHeapUnfilteredPartitions (or similar) to cache
iterated rows on MBRVerbHandler?
yep
bq. Try to generify unfiltered and filtered methods/classes into common
classes/methods when possible (UnfilteredPager, UnfilteredPagersIterator,
getUnfilteredRangeSlice, etc) (this is probably on your TODO but just a
friendly reminder)
yeah, a bunch of todos in the code around this
bq. Right now the service runs a full repair for a table which probably makes
sense for triggered repairs, but when we make that continuous we will probably
need to interleave subrange repair of different tables to ensure fairness (so
big tables don't starvate small table repairs).
Yes, splitting the local ranges in smaller parts based on the size of the
table, then sequentially repairing each part probably makes sense
bq. While repairing other replicas right away will probably get nodes
consistent faster, I wonder if we can make any simplification by repairing only
the coordinator node but since the diffs are already there I don't see any
reason not to do it.
yes we should repair the replicas as well since we know what the replicas need
to be in sync - also, for incremental repair a range is only repaired if we
know that the replicas are in sync
> Consider Mutation-based Repairs
> -------------------------------
>
> Key: CASSANDRA-8911
> URL: https://issues.apache.org/jira/browse/CASSANDRA-8911
> Project: Cassandra
> Issue Type: Improvement
> Reporter: Tyler Hobbs
> Assignee: Marcus Eriksson
> Fix For: 3.x
>
>
> We should consider a mutation-based repair to replace the existing streaming
> repair. While we're at it, we could do away with a lot of the complexity
> around merkle trees.
> I have not planned this out in detail, but here's roughly what I'm thinking:
> * Instead of building an entire merkle tree up front, just send the "leaves"
> one-by-one. Instead of dealing with token ranges, make the leaves primary
> key ranges. The PK ranges would need to be contiguous, so that the start of
> each range would match the end of the previous range. (The first and last
> leaves would need to be open-ended on one end of the PK range.) This would be
> similar to doing a read with paging.
> * Once one page of data is read, compute a hash of it and send it to the
> other replicas along with the PK range that it covers and a row count.
> * When the replicas receive the hash, the perform a read over the same PK
> range (using a LIMIT of the row count + 1) and compare hashes (unless the row
> counts don't match, in which case this can be skipped).
> * If there is a mismatch, the replica will send a mutation covering that
> page's worth of data (ignoring the row count this time) to the source node.
> Here are the advantages that I can think of:
> * With the current repair behavior of streaming, vnode-enabled clusters may
> need to stream hundreds of small SSTables. This results in increased compact
> ion load on the receiving node. With the mutation-based approach, memtables
> would naturally merge these.
> * It's simple to throttle. For example, you could give a number of rows/sec
> that should be repaired.
> * It's easy to see what PK range has been repaired so far. This could make
> it simpler to resume a repair that fails midway.
> * Inconsistencies start to be repaired almost right away.
> * Less special code \(?\)
> * Wide partitions are no longer a problem.
> There are a few problems I can think of:
> * Counters. I don't know if this can be made safe, or if they need to be
> skipped.
> * To support incremental repair, we need to be able to read from only
> repaired sstables. Probably not too difficult to do.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
