Dan Albert
9ee65009cd
Implement allowing validator boot failure into automation ( #6589 )
...
* Pass allow boot failures through create AND start
* Extend sleep timeout to all nodes
* Add 100 node testcase
* Reduce consistent sleep
2019-10-28 16:43:40 -06:00
Trent Nelson
96e209db49
Colo: Don't fail without a message ( #6558 )
2019-10-28 09:20:49 -06:00
Michael Vines
0c14ca58c7
Invoke on-reboot from cloud startup script to avoid racing with cron ( #6579 )
...
automerge
2019-10-27 10:56:16 -07:00
Pankaj Garg
e174af7838
Use iftop to collect network bandwidth usage ( #6560 )
...
* Use iftop to collect network bandwidth usage
* fix shellcheck
* more shellchecks
* review comments
2019-10-26 00:06:46 -07:00
Michael Vines
be74801236
Add NET_NUM_xyz variables
2019-10-25 23:00:14 -07:00
Michael Vines
e966c96644
Disable sigverify on blockstreamer node
...
This node get overloaded at high TPS trying to manage both a validator
and the blockexplorer. Reduce it's workload by turning off sigverify,
which doesn't really matter since this node doesn't even vote
2019-10-25 21:33:08 -07:00
Dan Albert
a2a9d54985
Increase node start stagger ( #6566 )
2019-10-25 17:35:29 -06:00
Justin Starry
ea2b26e5f5
Fix scp client mint keypair ( #6565 )
2019-10-25 16:23:52 -07:00
Michael Vines
e103789994
Ignore exit code when the first mount fails
2019-10-25 10:11:32 -07:00
Michael Vines
90461245f9
Reduce TdS fees to 1 lamport per sig, and slots_per_epoch/2 ( #6542 )
2019-10-24 20:37:23 -07:00
Michael Vines
1c91c1e880
Remount /mnt/extra-disk on reboot
2019-10-24 20:14:26 -07:00
Dan Albert
dadcb632d8
Specify machine type without necessarily enabling GPU ( #6529 )
...
* Specifiy machine type without necessarily enabling GPU
* Make long arg, extend --enable-gpu to automation
* Set machine types only in one place
* Fixup
* Fixup flag in automation
* Typo
* shellcheck
2019-10-24 15:12:25 -06:00
Michael Vines
2de2fbd5e3
Remove stray setup_secondary_mounts
2019-10-24 13:48:57 -07:00
Michael Vines
14eca5aea6
Remove setup_secondary_mount knowledge from multinode-demo/ ( #6530 )
2019-10-24 13:40:16 -07:00
Justin Starry
7a7abe692e
Add mint keypair to solana clients for convenience ( #6536 )
2019-10-24 14:31:06 -04:00
Justin Starry
88033bccbb
Add mint keypair to validators for convenience ( #6531 )
2019-10-24 12:50:32 -04:00
Michael Vines
35d6196384
Surface nvidia-smi errors in CI
2019-10-23 10:59:30 -07:00
Michael Vines
26b8747014
Exit cleanly for idle clients
2019-10-23 09:56:05 -07:00
Michael Vines
bedb05bdeb
Plumb GEOLOCATION_API_KEY down to the blockexplorer ( #6514 )
2019-10-23 09:53:06 -07:00
Justin Starry
6829b8a6fb
Ensure solana commands are added to idle clients ( #6513 )
2019-10-23 11:15:00 -04:00
Michael Vines
e462a7d1d5
net: Add ability to only start/stop client nodes ( #6503 )
...
* Add info --eval
* net: Add ability to start idle client nodes
2019-10-22 16:08:49 -07:00
Sagar Dhawan
4c515d0ef1
Sagar: Add ssh keys for colo ( #6507 )
2019-10-22 15:59:39 -07:00
Michael Vines
f80a5b8c34
Remove some TODOs ( #6488 )
...
* Remove stale TODOs
* Ban TODO markers from markdown
* Scrub all TODOs from ci/ and book/
2019-10-21 22:25:06 -07:00
Greg Fitzgerald
3b9b9b1500
Rename remaining uses of fullnode to validator ( #6476 )
...
automerge
2019-10-21 20:21:21 -07:00
Dan Albert
00809a67c0
Push perf test results to slack app ( #6371 )
...
* Add script to publish testnet results to slack
* Obscure webhook URL
* fixup
* Replace read with cat redirection
* Turn back on net restart
* Pick nits
* Make symlink before trying to delete its contents
* Display test config in slack and pick Trents nit not to maybe rm -rf /*
* Clean up results print
* Minor nits
* Turn the test settings back up to 11
* typo
* Shellcheck
* Just a few more fields
* fix payload formatting
* Del clear-config.sh
* Mount secondary
* Add commit SHA link and Grafana time range URL
* Add fancy buttons instead of text URLs
* Tighten up test config display
* Fixup display nits
* chellsheck
* Rebase and fix typo
2019-10-21 20:00:17 -04:00
Michael Vines
3fb70b8d47
Ban XXX, TBD, FIXME comments ( #6486 )
2019-10-21 16:43:11 -07:00
Trent Nelson
564c14a2c6
net.sh: Ensure external disk link is setup before cleaning config dir ( #6481 )
...
automerge
2019-10-21 15:38:58 -07:00
sakridge
6996f45d54
Print machine hostname in log ( #6480 )
...
automerge
2019-10-21 14:59:03 -07:00
sakridge
b1c2c6009e
Exclude net/log in rsync script ( #6475 )
...
automerge
2019-10-21 14:06:36 -07:00
Trent Nelson
934f69b660
Colo verbosity ( #6473 )
...
automerge
2019-10-21 13:49:12 -07:00
Sunny Gleason
951e1f8b48
feat: grant access to sunny@ ( #6471 )
2019-10-21 11:17:06 -07:00
Greg Fitzgerald
9232057e95
Rename replicator to archiver ( #6464 )
...
* Rename replicator to archiver
* cargo fmt
* Fix grammar
2019-10-21 11:29:37 -06:00
Trent Nelson
0fc3c7eee2
Bump Trent's keys... ( #6445 )
...
automerge
2019-10-18 15:42:50 -07:00
Michael Vines
6f58bdfcb1
Remove validator sanity check ( #6435 )
...
automerge
2019-10-18 08:26:08 -07:00
Pankaj Garg
854c62e208
Reduce kernel networking buffer for rmem and wmem ( #6422 )
...
automerge
2019-10-17 14:52:24 -07:00
Trent Nelson
1759968c1e
Colo: Put NVMe disks to use ( #6357 )
...
automerge
2019-10-17 14:44:45 -07:00
Dan Albert
b4ed88e0f7
Fail faster on boot up ( #6412 )
2019-10-17 12:26:12 -04:00
Michael Vines
2d351d3952
Prevent ping stats header from confusing buildkite log folding
2019-10-16 13:36:16 -07:00
Michael Vines
605b477e06
Permit finding more nodes than expected (./gce.sh config)
2019-10-16 13:21:00 -07:00
Michael Vines
b7af5f08d6
Avoid more non-standard ping. macOS 💔
2019-10-16 10:35:41 -07:00
Michael Vines
781dfd9dc4
Drop non-standard ping -o option
2019-10-16 10:05:46 -07:00
Michael Vines
9267931ef6
Add support for preemptible GCP instances
2019-10-16 08:10:31 -07:00
Michael Vines
37a29b979f
--force
2019-10-15 15:12:25 -07:00
Michael Vines
d89174ee82
Default to no client nodes to avoid unnecesary cost
2019-10-15 14:37:52 -07:00
Michael Vines
8bc9d8988f
-
2019-10-15 07:58:40 -07:00
Michael Vines
f7279804b4
Ensure solana-cli has a keypair
2019-10-15 07:47:45 -07:00
Michael Vines
169b772398
Show validators during net sanity
2019-10-14 20:38:51 -07:00
Trent Nelson
b75438ff32
gce.sh: Unwind allocation upon failure ( #6343 )
...
automerge
2019-10-14 09:36:20 -07:00
Trent Nelson
82fea9ce73
net.sh: Add support for selecting validator GPU mode ( #6326 )
...
automerge
2019-10-14 09:33:32 -07:00
Greg Fitzgerald
322fcea6e5
More fullnode to validator renaming ( #6337 )
2019-10-11 13:30:52 -06:00