Commit Graph

2503 Commits

Author SHA1 Message Date
Joshua Boniface 4698edc98e Add MTU value checking and log messages
Ensures that if a specified MTU is more than the maximum it is set to
the maximum instead, and adds warning messages for both situations.
2021-10-09 18:48:56 -04:00
Joshua Boniface 40e7e04aad Fix invalid schema key
Addresses #144
2021-10-09 18:42:33 -04:00
Joshua Boniface 7f074847c4 Add MTU support to network add/modify commands
Addresses #144
2021-10-09 18:06:21 -04:00
Joshua Boniface b0b0b75605 Have VXNetworkInstance set MTU if unset
Makes this explicit in Zookeeper if a network is unset, post-migration
(schema version 6).

Addresses #144
2021-10-09 17:52:57 -04:00
Joshua Boniface 89f62318bd Add MTU to network creation/modification
Addresses #144
2021-10-09 17:51:32 -04:00
Joshua Boniface 925141ed65 Fix migration bugs and invalid vx_mtu
Addresses #144
2021-10-09 17:35:10 -04:00
Joshua Boniface f7a826bf52 Add handlers for client network MTUs
Refactors some of the code in VXNetworkInterface to handle MTUs in a
more streamlined fashion. Also fixes a bug whereby bridge client
networks were being explicitly given the cluster dev MTU which might not
be correct. Now adds support for this option explicitly in the configs,
and defaults to 1500 for safety (the standard Ethernet MTU).

Addresses #144
2021-10-09 17:02:27 -04:00
Joshua Boniface e176f3b2f6 Make n-1 values clearer 2021-10-07 18:11:15 -04:00
Joshua Boniface b339d5e641 Correct levels in TOC 2021-10-07 18:08:28 -04:00
Joshua Boniface d476b13cc0 Correct spelling errors 2021-10-07 18:07:06 -04:00
Joshua Boniface ce8b2c22cc Add documentation sections on IPMI and fencing 2021-10-07 18:05:47 -04:00
Joshua Boniface feab5d3479 Correct flawed conditional in verify_ipmi 2021-10-07 15:11:19 -04:00
Joshua Boniface ee348593c9 Bump version to 0.9.40 2021-10-07 14:42:04 -04:00
Joshua Boniface e403146bcf Correct bad stop_keepalive_timer call 2021-10-07 14:41:12 -04:00
Joshua Boniface bde684dd3a Remove redundant wording from header 2021-10-07 12:20:04 -04:00
Joshua Boniface 992e003500 Replace headers with links in CHANGELOG.md 2021-10-07 12:17:44 -04:00
Joshua Boniface eaeb860a83 Add missing period to changelog sentence 2021-10-07 12:10:35 -04:00
Joshua Boniface 1198ca9f5c Move changelog into dedicated file
The changelog was getting far too long for the README/docs index to
support, so move it into CHANGELOG.md and link to it instead.
2021-10-07 12:09:26 -04:00
Joshua Boniface e79d200244 Bump version to 0.9.39 2021-10-07 11:52:38 -04:00
Joshua Boniface 5b3bb9f306 Add linting to build-and-deploy
Ensures that bad code isn't deployed during testing.
2021-10-07 11:51:05 -04:00
Joshua Boniface 5501586a47 Add limit negation to VM list
When using the "state", "node", or "tag" arguments to a VM list, add
support for a "negate" flag to look for all VMs *not in* the state,
node, or tag state.
2021-10-07 11:50:52 -04:00
Joshua Boniface c160648c5c Add note about fencing at remote sites 2021-10-04 19:58:08 -04:00
Joshua Boniface fa37227127 Correct TOC in architecture page 2021-10-04 01:54:22 -04:00
Joshua Boniface 2cac98963c Correct spelling errors 2021-10-04 01:51:58 -04:00
Joshua Boniface 8e50428707 Double image sizes for example clusters 2021-10-04 01:47:35 -04:00
Joshua Boniface a4953bc6ef Adjust toc_depth for RTD theme 2021-10-04 01:45:05 -04:00
Joshua Boniface 3c10d57148 Revamp about and architecture docs
Makes these a little simpler to follow and provides some more up-to-date
information based on recent tests and developments.
2021-10-04 01:42:08 -04:00
Joshua Boniface 26d8551388 Adjust bump-version changelog heading level 2021-10-04 01:41:48 -04:00
Joshua Boniface 57342541dd Move changelog headers down one more level 2021-10-04 01:41:22 -04:00
Joshua Boniface 50f8afd749 Adjust indent of index/README versions 2021-10-04 00:33:24 -04:00
Joshua Boniface 3449069e3d Bump version to 0.9.38 2021-10-03 22:32:41 -04:00
Joshua Boniface cb66b16045 Correct latency units and format name 2021-10-03 17:06:34 -04:00
Joshua Boniface 8edce74b85 Revamp test result display
Instead of showing CLAT percentiles, which are very hard to interpret
and understand, instead use the main latency buckets.
2021-10-03 15:49:01 -04:00
Joshua Boniface e9b69c4124 Revamp postinst for the API daemon
Ensures that the worker is always restarted and make the NOTE
conditional more specific.
2021-10-03 15:15:26 -04:00
Joshua Boniface 3948206225 Tweak fio tests for benchmarks
1. Remove ramp_time as this was giving very strange results.

2. Up the runtime to 75 seconds to compensate.

3. Print the fio command to the console to validate.
2021-10-03 15:06:18 -04:00
Joshua Boniface a09578fcf5 Add benchmark format to list 2021-10-03 15:05:58 -04:00
Joshua Boniface 73be807b84 Adjust ETA for benchmarks 2021-10-02 04:51:01 -04:00
Joshua Boniface 4a9805578e Add format parsing for format 1 storage benchmarks 2021-10-02 04:46:44 -04:00
Joshua Boniface f70f052df1 Add version 2 benchmark list formatting 2021-10-02 02:47:17 -04:00
Joshua Boniface 1e8841ce69 Handle benchmark running state properly 2021-10-02 01:54:51 -04:00
Joshua Boniface 9c7d39d523 Fix missing argument in database insert 2021-10-02 01:49:47 -04:00
Joshua Boniface 011490bcca Update to storage benchmark format 1
1. Runs `fio` with the `--format=json` option and removes all terse
format parsing from the results.

2. Adds a 15-second ramp time to minimize wonky ramp-up results.

3. Sets group_reporting, which isn't necessary with only a single job,
but is here for consistency.
2021-10-02 01:41:08 -04:00
Joshua Boniface 8de63b2785 Fix handling of array of information
With a benchmark info we only ever want test one, so pass only that to
the formatter. Simplifies the format function.
2021-10-02 01:28:39 -04:00
Joshua Boniface 8f8f00b2e9 Avoid versioning benchmark lists
This wouldn't work since each individual test is versioned. Instead add
a placeholder for later once additional format(s) are defined.
2021-10-02 01:25:18 -04:00
Joshua Boniface 1daab49b50 Add format option to benchmark info
Allows specifying of raw json or json-pretty formats in addition to the
"pretty" formatted option.
2021-10-02 01:13:50 -04:00
Joshua Boniface 9f6041b9cf Add benchmark format function support
Allows choosing different list and info functions based on the benchmark
version found. Currently only implements "legacy" version 0 with more to
be added.
2021-10-02 01:07:25 -04:00
Joshua Boniface 5b27e438a9 Add test format versioning to storage benchmarks
Adds a test_format database column and a value in the API return for the
test format version, starting at 0 for the existing format as of 0.9.37.

References #143
2021-10-02 00:55:27 -04:00
Joshua Boniface 3e8a85b029 Load benchmark results as JSON
Load the JSON at the API side instead of client side, because that's
what the API doc says it is and it just makes more sense.
2021-09-30 23:40:24 -04:00
Joshua Boniface 19ac1e17c3 Bump version to 0.9.37 2021-09-30 02:08:14 -04:00
Joshua Boniface 252175fb6f Revamp benchmark tests
1. Move to a time-based (60s) benchmark to avoid these taking an absurd
amount of time to show the same information.

2. Eliminate the 256k random benchmarks, since they don't really add
anything.

3. Add in a 4k single-queue benchmark as this might provide valuable
insight into latency.

4. Adjust the output to reflect the above changes.

While this does change the benchmarking, this should not invalidate any
existing benchmarks since most of the test suit is unchanged (especially
the most important 4M sequential and 4K random tests). It simply removes
an unused entry and adds a more helpful one. The time-based change
should not significantly affect the results either, just reduces the
total runtime for long-tests and increase the runtime for quick tests to
provide a better picture.
2021-09-29 20:51:30 -04:00