Yaming Kuang

Setup Namesapce for HomeReplication Long running -- Done sds-tess30-18. Test framework to accept real drives for each replicas -- in progress

ReplDev doesn't distinguish whether alloc writes are from same shard or not. From HomeStore we want to parallel those allocation on different chunks, and only sequentialize for allocation/writes on same...

Problem Statement: ================ 1. Push data channel, we need to do grpc max data upper limit control, which is similar to what Fetch data channel has done (e.g. config value...

0. Keep I/O running. 1. Restart random member (either leader or follower) -- Randomly enable flip points below to hit either incremental or baseline resync: -- Setup flip point for...

recover meta block crashes sometimes in github CI and local machine build

3

/home/runner/.conan/data/homestore/6.0.1/_/_/build/64eb2822c4463ffd57405ab6c52e9954705502c6/src/lib/meta/meta_blk_service.cpp:1126: void homestore::MetaBlkService::recover_meta_block(homestore::meta_blk*): Assertion `0' failed. [03/25/24 19:47:05+00:00] [critical] [test_meta_blk_mgr] [7169] [meta_blk_service.cpp:1126] ******************** Assertion failure: =====> Expected '726044547' to be == to '3060308851' [type=Test_Rand_Load], CRC mismatch: 726044547/3060308851, on mblk bid:...

-- Run I/O load with some time and do a intentional crash and verify the append_blk_allocator last append offset should be recovered correct after replay logs.

old member re-joining after a crash or shutdown for sometime which makes its last committed lsn not in scope of existing quorum, in other words, can't do incremental resync. Phase-1:...