Commit Graph

2827 Commits

Author SHA1 Message Date
A.J. Beamon 382666d21e Permissions were wrong on installed files. A missing DESTINATION for fdbserver caused the binary to be missing. 2020-05-28 10:33:09 -07:00
A.J. Beamon 96f396ec7f Make sure to build the binary stripping targets when packaging stripped binaries 2020-05-27 16:40:07 -07:00
A.J. Beamon 2f9cd383ea Use stripped executables in packages when not building with debug symbols. 2020-05-21 13:39:55 -07:00
Evan Tschannen 9d1df2aa58 fix: the first CPU estimate could be wrong enough to cause stalls on a newly recruited proxy 2020-05-10 17:50:09 -07:00
Evan Tschannen 3eaa9d6397 fix: do not report datacenter version difference before both datacenters report a correct version 2020-05-10 17:49:09 -07:00
Evan Tschannen 76d4570d5d
Merge pull request #3008 from etschannen/release-6.2
Added logging for parallel peeks from TLogs
2020-04-23 10:27:49 -07:00
Evan Tschannen 91fba9106d ported peek metrics to old tlog 6.0 2020-04-22 23:35:48 -07:00
Evan Tschannen 0a1b2a572f more compile fixes 2020-04-22 14:41:17 -07:00
Evan Tschannen 68906bf3c3 fix compile errors 2020-04-22 14:36:41 -07:00
Evan Tschannen dfb0593ae6 increases priority of status requests 2020-04-22 14:24:59 -07:00
Evan Tschannen d0cc2a1ee4 added logging for parallel peeks on TLogs 2020-04-22 14:24:45 -07:00
Alex Miller 2ce539ef6d Respect flow<->fdbrpc module boundaries.
Which fixes a compilation error due to a circular dependency between
flow.a and fdbrpc.a.  However, this is now done at the cost of newNet2
users have to remember to add Net2FileSystem::stop() as a callback.
2020-04-20 02:53:07 -07:00
A.J. Beamon 197f866824 Don't include internal tools such as fdbcli, backup, and DR in the status client list. 2020-03-23 14:44:04 -07:00
Evan Tschannen 04052226df reverting a change which causes data inconsistency between the primary and secondary 2020-03-17 09:41:44 -07:00
Evan Tschannen ed4d02a3e4
Merge pull request #2812 from etschannen/feature-proxy-mem-limit
Limit the amount of requests the proxy can queue up in memory
2020-03-16 14:56:56 -07:00
Evan Tschannen 2038a56ff4
Merge pull request #2819 from etschannen/feature-first-proxy
A "proxy" class process would not be preferred as the "first proxy" for restore and DR purposes
2020-03-16 13:53:28 -07:00
A.J. Beamon ee3cde0b0d
Merge pull request #2815 from etschannen/feature-timeout-tlog-create
Treat a tlog which takes a long time to create its disk queue as failed
2020-03-16 12:49:33 -07:00
Evan Tschannen a068d4063f renamed ProxyGetConsistentReadVersion 2020-03-16 12:11:32 -07:00
Evan Tschannen 7adc916e18
Merge pull request #2806 from ajbeamon/improve-team-request-performance
Improve performance of get team requests.
2020-03-16 11:56:45 -07:00
A.J. Beamon fe19f30999
Merge pull request #2813 from etschannen/feature-satellite-usable-regions
do not recruit satellite tlogs when usable regions=1
2020-03-16 11:54:42 -07:00
Evan Tschannen 012344e297 refactor getWorkersForRoleInDatacenter 2020-03-16 11:50:17 -07:00
A.J. Beamon f2defc3a3a
Merge pull request #2814 from etschannen/feature-delay-recovery
Prevent coordinated state from filling up with too many old generations
2020-03-16 11:45:17 -07:00
Evan Tschannen ea98c7a40a added additional timeout on initPersistentState 2020-03-16 11:38:14 -07:00
A.J. Beamon 682b9faa1a
Merge pull request #2817 from etschannen/feature-fix-0-left
fix: do not use priority 0 left when calculating priorities for empty teams
2020-03-16 11:15:12 -07:00
Evan Tschannen 56dee89e6e active generations should include the current one 2020-03-16 11:09:42 -07:00
Evan Tschannen e5d53c863b report in status the number of active generations 2020-03-16 10:29:17 -07:00
Evan Tschannen 818537ed2d
Update fdbserver/masterserver.actor.cpp
Co-Authored-By: A.J. Beamon <ajbeamon@users.noreply.github.com>
2020-03-14 15:04:46 -07:00
Evan Tschannen 0ca89547a5 make sure the number of logRouterTags is larger than the number of satelliteTLogs to avoid having satellites with no data. 2020-03-14 15:02:19 -07:00
Evan Tschannen 04b752b40a Added additional logging related to memory errors (including in status) 2020-03-13 18:31:22 -07:00
Evan Tschannen a71e61f57b fixed compiler issue 2020-03-13 18:22:38 -07:00
Evan Tschannen ebbf4490b3 use a Deque for each priority instead of a priority queue to improve CPU with large numbers of outstanding requests 2020-03-13 18:07:48 -07:00
Evan Tschannen 79d5511149 A "proxy" class process would not be preferred as the "first proxy" for restore and DR purposes 2020-03-13 17:49:02 -07:00
Evan Tschannen 2f2f56020f
Update fdbserver/masterserver.actor.cpp
Co-Authored-By: A.J. Beamon <ajbeamon@users.noreply.github.com>
2020-03-13 15:54:13 -07:00
A.J. Beamon 700b13e5f8 Remember the best team from team requests, which will likely be the best again and can save us some computation. 2020-03-13 15:21:33 -07:00
Evan Tschannen 12f2b32770 added additional logging in data distribution 2020-03-13 15:19:33 -07:00
Evan Tschannen 9e99a00c8f fix: do not use priority 0 left when calculating priorities for empty teams 2020-03-13 13:56:46 -07:00
Evan Tschannen d6d347f665 treat a tlog which takes a long time to create its disk queue as failed 2020-03-13 10:31:59 -07:00
Evan Tschannen a39effa57d delay recoveries after 70 outstanding generations, and stop recoveries after 100 outstanding generations to prevent a death spiral from filling up the coordinated state 2020-03-13 10:28:32 -07:00
Evan Tschannen 4640edf5d6 do not recruit satellite tlogs when usable regions=1 2020-03-13 10:24:52 -07:00
Evan Tschannen 243c268d9d Limit the amount of requests the proxy can queue up in memory 2020-03-13 10:17:49 -07:00
Alex Miller d86a601b84 Add cluster.processes.id.network.tls_policy.hz to status.
This allows monitoring of TLS policy failures, but one has to go scrape
for TLSPolicyFailure trace events to figure out why they're happening.
2020-03-13 02:46:10 -07:00
A.J. Beamon 555db50cd1 Avoid calling into SABTF so frequently. Use a cheaper call that only checks that shards exist. 2020-03-12 11:22:03 -07:00
Evan Tschannen dbfc0cbcc0
Merge pull request #2781 from alexmiller-apple/certificate-refresh
Refresh certificates used for handshaking when they change on disk
2020-03-06 11:12:04 -08:00
Evan Tschannen 98647a61fc
Merge pull request #2784 from ajbeamon/add-resolver-metrics
Add ResolverMetrics trace event
2020-03-06 09:38:30 -08:00
A.J. Beamon faf9101ad4
Update fdbserver/Resolver.actor.cpp
Co-Authored-By: Evan Tschannen <36455792+etschannen@users.noreply.github.com>
2020-03-06 09:20:38 -08:00
Evan Tschannen 1076abdee5 fixed crash when interf was not created 2020-03-05 19:09:08 -08:00
Evan Tschannen 1128666840 added additional logging on the log router 2020-03-05 18:17:06 -08:00
A.J. Beamon 7fb8c3c080 Remove unused variable. 2020-03-05 11:38:30 -08:00
A.J. Beamon effb6d2d49 Add ResolverMetrics trace event 2020-03-05 10:49:21 -08:00
Alex Miller 595dd77ed1 Merge remote-tracking branch 'upstream/release-6.2' into certificate-refresh 2020-03-04 20:25:42 -08:00