Pull fresh master from base #1

antilles · 2024-01-09T13:24:54+03:00

antilles commented

2024-01-09 13:24:54 +03:00

There is no content yet.

antilles added 28 commits 2024-01-09 13:24:54 +03:00

575475de71 Do not ignore loopback addresses for OSD network (to make ECMP setups with frr possible)

1a704e06ab Allow multiple interfaces with the same IP address, for "simple routed" full mesh network

dc615403d9 Do not warn on EPIPE in client unless log_level is raised explicitly

7cea642f4a Fix vitastor-nbd image existence check not working because of non-zeroed inode_watch fields

7239cfb91a Parse log_level in cluster_client

95631773b6 Remove pve-storage-portal-dns-list format for vitastor_etcd_address

4ece4dfdd0 Fix mon not using values from config when /config/global is not present

178bb0e701 Prevent re-entry into timerfd set_nearest

1299373988 Use the same etcd_ws_keepalive_interval in OSD and mon

f72f14e6a7 Clear old PG states, history, and OSD states on etcd state reload

Also add protection from etcd watcher messages being split into multiple websocket
messages - I'm not sure if etcd actually does that, but it's better to have extra
protection anyway.

Also check that all etcd watchers are started in the keepalive routine, otherwise
it sometimes tries to revive etcd watchers starting with revision=1 which obviously
always fails because this revision is nearly always compacted.

All these changes should fix an old rarely reproduced bug where SOMETIMES OSDs
didn't react to PG config changes which was leading to offline pools on node reboot.
It happened on the full reload of state from etcd.

2f38adeb3d Restart dead VDUSE daemons at regular intervals

dcc76eee15 Add a parity chunk count change test script

d84dee7098 Track recovery op latencies + refactor into a structure

751935ddd8 WIP Auto-tune recovery speed

5ca7cde612 Experiment/WIP: Try to track "secondary" recovery ops separately

1edf86ed26 Aggregate recovery delay using simple mean over last 10 observations (EWMA is shit)

f757a35a8d Retry PG changes without re-running lpsolve when pool configuration and OSD tree don't change

OSDs often change their /pg/history keys during rebalance, so monitor receives additional
transaction failures from etcd if it re-runs lpsolve which sometimes may even lead to monitor
being unable to apply PG changes at all until rebalance completes

d5a6fa6dd7 Fix possible crash on print_slow when bs_op is NULL

8b8c1179a7 Use a separate used_blocks counter for free space stats to hide possibly delayed on-flush deallocation

e600bbc151 Fix flapping move_reappear test by adding an fsync before stopping PG

ec7dcd1be5 Do not apply very large recovery pauses during tests

c4928e6ecd Protect from try_send completing the operation immediately

Fixes a possible use-after-free in case of continue_ops() calling try_send(),
then connect_peer() -> set_timer() -> trigger_nearest() -> handle_op_part() -> continue_ops() again

99ee8596ea Rename min/max_util to util_low/high

a6ab54b1ba Do not allow negative util_low/high

c17f76a3e4 Add documentation for recovery auto-tuning

48b5f871e0 Add Contributor License Aggrement in Russian and English

2f6b9c0306 Remove etcd parameter from default command examples

2f228fa96a Only treat data partitions as existing OSDs in vitastor-disk prepare

antilles merged commit f94f76ca89 into master

2024-01-09 13:25:13 +03:00

antilles referenced this issue from a commit

2024-01-09 13:25:18 +03:00

Merge pull request 'Pull fresh master from base' (#1) from vitalif/vitastor:master into master

Sign in to join this conversation.