scylladb

mirror of https://github.com/scylladb/scylladb.git synced 2026-06-04 22:13:19 +00:00

Files

Asias He 3c8ed255ac storage_service: Set NORMAL status after token_metadata is replicated

Commit 2d5fb9d109 (gms/gossiper: Replicate changes incrementally to
other shards) changes the way we replicate _token_metadata and
endpoint_state_map. Before they are replicated at the same time, after
they are not any more. This causes a shard in NORMAL status can still be
with a empty _token_metadata.

We saw errors:

   [shard 12] token_metadata - sorted_tokens is empty in first_token_index!

during CorruptThenRepairNemesis.

Fix by setting the gossip status to NORMAL after replication of
_token_metadata, so that once a node is in NORMAL, we can do repair. The
commit 69c81bcc87 (repair: Do not allow repair until node is in NORMAL
status) prevents the early repair operation by checking if a node is in
NORMAL status.

Fixes #3121

Message-Id: <af6a223733d2e11351f1fa35f59eacfa7d65dd30.1516065564.git.asias@scylladb.com>

2018-01-16 09:41:22 +02:00

pager

Merge seatar upstream (seastar namespace)

2017-05-21 12:26:15 +03:00

cache_hitrate_calculator.hh

periodically calculate avg cache hit rate between all shards

2017-06-13 09:57:14 +03:00

client_state.cc

service::client_state: introduce "request copy" copy-constructor

2018-01-09 14:00:03 -05:00

client_state.hh

service::client_state: introduce "request copy" copy-constructor