- 16 Aug, 2022 1 commit
-
-
David Son authored
Signed-off-by:
David Son <davbson@amazon.com>
-
- 12 Aug, 2022 2 commits
-
-
Alexandru-Cezar Sardan authored
Signed-off-by:
Alexandru-Cezar Sardan <alsardan@amazon.com>
-
Alexandru-Cezar Sardan authored
Use the 3-sigma rule for determining the delta percentage for the latency values. Also add the pkt_loss statistic to the parsing. Signed-off-by:
Alexandru-Cezar Sardan <alsardan@amazon.com>
-
- 11 Aug, 2022 1 commit
-
-
Alexandru-Cezar Sardan authored
Refactor the `test_network_latency` test in order to consume baseline values from the config file and not from the hardcoded baselines. Also add the packet loss measurement to the config files. Signed-off-by:
Alexandru-Cezar Sardan <alsardan@amazon.com>
-
- 09 Aug, 2022 3 commits
-
-
Alexandru-Cezar Sardan authored
Signed-off-by:
Alexandru-Cezar Sardan <alsardan@amazon.com>
-
Diana Popa authored
The latest perf baselines for ARM contain 2 entries for ARM: m6g.metal and m6gd.metal. That is because the parse_baselines tool will insert a m6gd.metal one. Replace m6gd.metal with m6g.metal (due to the fact that this is the latest entry) and fix the parse_baselines tool. Signed-off-by:
Diana Popa <dpopa@amazon.com>
-
Diana Popa authored
PR #3080 deleted 8175M Intel processor from vsock's 5.10 config file. This commit puts it back. Signed-off-by:
Diana Popa <dpopa@amazon.com>
-
- 08 Aug, 2022 1 commit
-
-
Diana Popa authored
Also, this commit increases verbosity for snap resume long running performance test. Signed-off-by:
Diana Popa <dpopa@amazon.com>
-
- 05 Aug, 2022 1 commit
-
-
Diana Popa authored
Signed-off-by:
Diana Popa <dpopa@amazon.com>
-
- 04 Aug, 2022 1 commit
-
-
Babis Chalios authored
Signed-off-by:
Babis Chalios <bchalios@amazon.es>
-
- 03 Aug, 2022 2 commits
-
-
Jonathan Woollett-Light authored
Signed-off-by:
Jonathan Woollett-Light <jcawl@amazon.co.uk>
-
Alexandru-Cezar Sardan authored
Add pandas package that can be used to manipulate large datasets in integration tests. Signed-off-by:
Alexandru-Cezar Sardan <alsardan@amazon.com>
-
- 01 Aug, 2022 8 commits
-
-
Ryan Russell authored
Signed-off-by:
Ryan Russell <git@ryanrussell.org>
-
Alexandru-Cezar Sardan authored
The Firecracker version returned by the API should always be the one returned by `git describe --dirty`. This is done to identify Firecracker versions when debugging. The version is embedded in the Firecracker binary by the `build.rs` script by running `git describe --dirty`. The API version test was using different parameters than `build.rs` to get the version and was also discarding the hash, `wip` and `dirty` strings from the version which is not what we want to do. Fixed the test by removing the sanitization part and the `--abbrev=0` parameter. Signed-off-by:
Alexandru-Cezar Sardan <alsardan@amazon.com>
-
Alexandru-Cezar Sardan authored
Signed-off-by:
Alexandru-Cezar Sardan <alsardan@amazon.com>
-
Alexandru-Cezar Sardan authored
Signed-off-by:
Alexandru-Cezar Sardan <alsardan@amazon.com>
-
Alexandru-Cezar Sardan authored
Signed-off-by:
Alexandru-Cezar Sardan <alsardan@amazon.com>
-
Alexandru-Cezar Sardan authored
Remove the helper function that marks the `/firecracker` source dir as safe for git since the config was added to the development container. Having the helper here missed the use case where `cargo build` was called from `devtool build` causing version inconsistencies. Signed-off-by:
Alexandru-Cezar Sardan <alsardan@amazon.com>
-
Alexandru-Cezar Sardan authored
This difference in ownership is validated against by git. https://github.blog/2022-04-12-git-security-vulnerability-announced/ Signed-off-by:
Alexandru-Cezar Sardan <alsardan@amazon.com>
-
Luminita Voicu authored
Signed-off-by:
Luminita Voicu <lumivo@amazon.com>
-
- 28 Jul, 2022 1 commit
-
-
Luminita Voicu authored
Signed-off-by:
Luminita Voicu <lumivo@amazon.com>
-
- 27 Jul, 2022 2 commits
-
-
Alexandru-Cezar Sardan authored
The T2 template lets KVM populate the ARCH_CAPABILITIES MSR by using a copy of the Host information. We sometimes want to force the information contained in that MSR in order to make it look like a less capable processor WRT speculative execution vulnerabilities and mitigations. This is helpful when we want to snapshot a uVM on a newer processor and resume on an older processor. In this case, the software should use only the capabilities that are available in both the newer and older host. Create a new CPU template called T2S which is similar to the T2 template but also sets additional information in the ARCH_CAPABILITIES MSR. We basically set the MSR to expose to the guest a CPU that has the security capabilities of a Skylake CPU, regardless of the host. Also set some bits that were missing from the T2 CPUID config. Adding the MSR information to the cpuid crate is not ideal based on the current implementation. In the end the whole cpuid crate should be refactored to rem...
-
Luminita Voicu authored
Signed-off-by:
Luminita Voicu <lumivo@amazon.com>
-
- 26 Jul, 2022 1 commit
-
-
Alexandru-Cezar Sardan authored
Allow saving these additional guest writable MSRs to preserve functionality after snapshot and resume: * MSR_MISC_FEATURE_ENABLES to preserve CPUID fault * MSR_K7_HWCR to preserve value written * MSR_KVM_POLL_CONTROL to preserve HLT polling request * MSR_KVM_ASYNC_PF_INT to preserve ASYNC PF interrupt vector Signed-off-by:
Alexandru-Cezar Sardan <alsardan@amazon.com>
-
- 15 Jul, 2022 1 commit
-
-
Aaron O'Mullan authored
Fix casing of `Co-authored-by` and `Signed-off-by` in instructions, since `gitline_rules.py` performs a case-sensitive check Signed-off-by:
Aaron O'Mullan <aaron.omullan@gmail.com>
-
- 14 Jul, 2022 2 commits
-
-
Diana Popa authored
MMDS is GA as of fc v1.1.0, JSON format no longer experimental. Signed-off-by:
Diana Popa <dpopa@amazon.com>
-
Diana Popa authored
We are now following the spectre-meltdown-checker instruction for detecting full retpoline support. We are checking the "retpoline" or "retpolines" are reported by sysfs and that "minimal" is not. Signed-off-by:
Diana Popa <dpopa@amazon.com>
-
- 13 Jul, 2022 1 commit
-
-
Austin Vazquez authored
Changes wording in device-api documentation to explicitly state omission of a required device column will always result in failure with 400 - BadRequest - HTTP response. Signed-off-by:
Austin Vazquez <macedonv@amazon.com>
-
- 12 Jul, 2022 1 commit
-
-
Diana Popa authored
Due to notification suppression having been added after v1.1.0, there is no past release that is snapshot compatible with current one. Signed-off-by:
Diana Popa <dpopa@amazon.com>
-
- 07 Jul, 2022 1 commit
-
-
Jonathan Woollett-Light authored
Signed-off-by:
Jonathan Woollett-Light <jcawl@amazon.co.uk>
-
- 06 Jul, 2022 4 commits
-
-
Jonathan Woollett-Light authored
Signed-off-by:
Jonathan Woollett-Light <jcawl@amazon.co.uk>
-
Jonathan Woollett-Light authored
Some minor tidying of code surrounding error handling. Signed-off-by:
Jonathan Woollett-Light <jcawl@amazon.co.uk>
-
Jonathan Woollett-Light authored
`impl Error` to `err`, `Endpoint` to `endpoint` and `WriteEvent` to `event`. Signed-off-by:
Jonathan Woollett-Light <jcawl@amazon.co.uk>
-
Jonathan Woollett-Light authored
Simplified error propagation by deriving `From` implementations. Signed-off-by:
Jonathan Woollett-Light <jcawl@amazon.co.uk>
-
- 04 Jul, 2022 2 commits
-
-
Jonathan Woollett-Light authored
Signed-off-by:
Jonathan Woollett-Light <jcawl@amazon.co.uk>
-
Jonathan Woollett-Light authored
Signed-off-by:
Jonathan Woollett-Light <jcawl@amazon.co.uk>
-
- 30 Jun, 2022 1 commit
-
-
Colin Percival authored
The downloadable tarball is now in a release-${latest}-$(uname -m) subdirectory. Signed-off-by:
Colin Percival <cperciva@FreeBSD.org>
-
- 29 Jun, 2022 3 commits
-
-
Jonathan Woollett-Light authored
Signed-off-by:
Jonathan Woollett-Light <jcawl@amazon.co.uk>
-
Jonathan Woollett-Light authored
Signed-off-by:
Jonathan Woollett-Light <jcawl@amazon.co.uk>
-
Jonathan Woollett-Light authored
Signed-off-by:
Jonathan Woollett-Light <jcawl@amazon.co.uk>
-