Commit Graph

316 Commits

Author SHA1 Message Date
Miroslav Crnic
de17eee24f core: fix incorrect return in connectHost 2024-04-03 15:08:48 +01:00
Miroslav Crnic
30ee029f7e shuckle: make requests interruptable and pass timeout to all operations
This means that they'll be interrupted at shutdown, rather than holding everything up when shuckle is overloaded.
We also detect idle connection or slow transmitting data.
2024-04-02 18:15:29 +01:00
Francesco Mazzoli
b38dcc550b fsck fixes/logs 2024-03-28 10:04:15 +00:00
Miroslav Crnic
7e394d2d5e SharDBTools: add missing include 2024-03-28 09:29:05 +00:00
Francesco Mazzoli
68c4c03750 Add command to run some checks directly in RocksDB database 2024-03-27 18:45:14 +00:00
Miroslav Crnic
16fb2b3797 shard: auto drop all data in LogsDB if not in use 2024-03-27 17:09:51 +00:00
Miroslav Crnic
8035e003f0 shard: re-enable starting with logsdb 2024-03-27 13:16:32 +00:00
Francesco Mazzoli
8de52aa6c9 Simplify eggsdbtools command parsing/execution 2024-03-27 12:18:16 +00:00
Miroslav Crnic
65e5b6e7ac cdc: shuckle-stats 2024-03-26 09:40:44 +00:00
Miroslav Crnic
f773a88bd9 shard: enable writes 2024-03-26 08:39:17 +00:00
Miroslav Crnic
3c5318e7dc shard: read-only and no logsdb 2024-03-26 05:47:47 +00:00
Francesco Mazzoli
7a5fc9f8a9 Allow to disable shuckle stat inserting 2024-03-25 16:08:54 +00:00
Miroslav Crnic
aebcce4017 logsdb: fix assert for last relased going backwards 2024-03-25 10:31:58 +00:00
Miroslav Crnic
7df0a5da89 shard: cli options now match migration phases for LogsDB, and support manual failover 2024-03-20 15:34:55 +00:00
Saulius Grusnys
fd9079febf Rate limited shuckle endpoint to decom blockservices 2024-03-20 15:16:00 +00:00
Francesco Mazzoli
1cf299bfac Use atomics where appropriate 2024-03-20 13:21:18 +00:00
Francesco Mazzoli
f85714dbba Use pthread_self() to get pthread thread id 2024-03-20 13:11:14 +00:00
Francesco Mazzoli
3a6e498664 Make some Loop methods static 2024-03-20 13:00:18 +00:00
Francesco Mazzoli
9bc7e209e4 Safer ShuckleSock 2024-03-20 11:33:39 +00:00
Francesco Mazzoli
66fe0a2621 Correct pthread_timedjoin_np handling 2024-03-20 11:13:26 +00:00
Francesco Mazzoli
8f1ba6361b Resist interruptions when joining threads 2024-03-20 10:32:42 +00:00
Francesco Mazzoli
66ccba6124 Forward termination signal to main thread 2024-03-20 10:32:42 +00:00
Miroslav Crnic
c25cb696b4 shard: remove protection that only replica 0 can be leader 2024-03-19 16:29:36 +00:00
Francesco Mazzoli
b12cdf7507 Add replicas info to shuckle web ui 2024-03-19 15:55:18 +00:00
Francesco Mazzoli
abd7131e88 Fix BlockServicesCacheDB init 2024-03-19 15:26:19 +00:00
Miroslav Crnic
37539e1c5e eggsdbtools: reduce logging, output stats 2024-03-19 15:15:49 +00:00
Miroslav Crnic
938c845a30 eggsdbtool: cli for shard db comparison 2024-03-19 15:00:01 +00:00
Francesco Mazzoli
6d9da0e595 Remove all remnants of block service cache in ShardDB
The previous code was pretty nasty, it reached into the `ShardDB`
column family from another class. All those keys have been deleted
anyway in production.
2024-03-19 14:27:33 +00:00
Miroslav Crnic
a4c091c7b2 logsdb: log state at flush to have consistent view 2024-03-19 12:44:56 +00:00
Miroslav Crnic
5ce2efb88b shard: increase number of requests processed in loop when LogsDB is on 2024-03-18 18:06:19 +00:00
Miroslav Crnic
096b9cbe6a logsdb: fix for replication path 2024-03-18 17:29:49 +00:00
Miroslav Crnic
0b7d1c30d3 shard: turn on replication writes 2024-03-18 14:19:50 +00:00
Miroslav Crnic
dfcabdba97 LogsDB: tweak catchup timeout 2024-03-18 12:00:27 +00:00
Miroslav Crnic
c8cda7e4db logsdb: periodically log status 2024-03-18 09:44:47 +00:00
Miroslav Crnic
72c1acaea8 xmon: if too many alerts initialize appType to _parent 2024-03-15 19:39:41 +00:00
Miroslav Crnic
27faaa45ae ci: add ability to run with LogsDB, shard: add handling of LogsDB messages 2024-03-15 16:49:39 +00:00
Francesco Mazzoli
3db003a8f6 Fix bug in BlockServicesCacheDB initialization 2024-03-13 12:07:33 +00:00
Miroslav Crnic
ebcdcb650a shard: add support for resetting all data in LogsDB 2024-03-13 11:33:48 +00:00
Francesco Mazzoli
005121bcac Spin block service cache out of ShardDB
This started being a problem since the block service update log
entry does not fit in a UDP packet (it's like 100KB). I think this
approach makes more sense anyway. See comment for `getCache()` for
gotchas.
2024-03-13 11:29:58 +00:00
Francesco Mazzoli
6968c25bc5 Allow : in metrics 2024-03-12 14:04:34 +00:00
Miroslav Crnic
13c5df0131 shard: fix name in xmon and add replica id to tag in metrics 2024-03-12 13:40:35 +00:00
Miroslav Crnic
b240de53b5 shard: distributed log implementation and shard can use it with a flag set 2024-03-12 11:02:04 +00:00
Francesco Mazzoli
e96742c711 Implement readpage, and therefore allow mmap 2024-03-11 15:33:57 +00:00
Francesco Mazzoli
0037e8d10b Print some info about block service flags in shard 2024-03-08 09:18:54 +00:00
Miroslav Crnic
712ed8973e core: simplify implementing custom stop for Loop 2024-02-23 13:52:34 +00:00
Francesco Mazzoli
beb07dbe6e Silence CDC queue alert 2024-02-21 14:57:00 +00:00
Francesco Mazzoli
531f989a06 Correct app type for quiet alert creation 2024-02-20 14:16:52 +00:00
Francesco Mazzoli
e5f133d826 Correct rota for "queue full" alert 2024-02-20 13:55:30 +00:00
Francesco Mazzoli
303421763a Allow to specify rota per alert in C++ 2024-02-20 12:59:42 +00:00
Saulius Grusnys
796e46f466 shuckle to track if blockservices have any files on them (currently t… (#177)
* shuckle to track if blockservices have any files on them (currently there is issue with transient files)
2024-02-20 08:10:51 +00:00