bob
bob copied to clipboard
qoollo
Distributed BLOB storage
Probably we should panic on JoinError or at least convert it to request error here: https://github.com/qoollo/bob/blob/485f91706cce23afdaa82e16f45ad8d455882d9e/bob/src/cluster/operations.rs#L46
When all nodes in cluster starting simultaneously, some can be faster than another. The faster ones marks the connection to slower ones as not available. This status will only change...
If ping received then it would be good to immediately run reconnection logic if the node is not in connected state
Related issue in Pearl: https://github.com/qoollo/pearl/issues/188
Closes #576. Closes #585.
Warnings: ``` Node.js 12 actions are deprecated. For more information see: https://github.blog/changelog/2022-09-22-github-actions-all-actions-will-begin-running-on-node16-instead-of-node12/. Please update the following actions to use Node.js 16: actions/checkout@v2, actions-rs/toolchain@v1, actions-rs/cargo@v1 ``` ``` The `set-output` command is...
It is perfectly valid to place vdisk replicas on a single node, but on different physical disks. Currently, `Virtual::get_operation` (https://github.com/qoollo/bob/blob/master/bob-common/src/mapper.rs#L185) returns only the first physical disk containing vdisk replica. Thus...
Performance degrade from 25000 RPS to 10000 RPS. This can be connected with write lock acquisition or be a problem in `add_to_parents`. https://github.com/qoollo/bob/blob/master/bob-backend/src/pearl/group.rs#L228