Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

GangCache Design #5

Open
wants to merge 49 commits into
base: gang
Choose a base branch
from
Open

GangCache Design #5

wants to merge 49 commits into from

Conversation

Wenshiqi222
Copy link
Collaborator

1、代码架构搭建
2、gang_cache 设计完成

Ⅰ. Describe what this PR does

Ⅱ. Does this pull request fix one issue?

Ⅲ. Describe how to verify it

Ⅳ. Special notes for reviews

V. Checklist

  • I have written necessary docs and comments
  • I have added necessary unit tests and integration tests
  • All checks passed in make test

LambdaHJ and others added 30 commits June 29, 2022 09:55
@LambdaHJ
feat: add read only port support for koordlet (koordinator-sh#320)
b21ea49 
Signed-off-by: 黄金 <heikkihuang@kugou.net>

Co-authored-by: 黄金 <heikkihuang@kugou.net>
@zwzhang0107
add reconciler for runtime hook standalone work mode (koordinator-sh#319
a49ab45 
)

Signed-off-by: zwzhang0107 <zuoweizhang@outlook.com>
@zwzhang0107
add cpuset allocator (koordinator-sh#324)
a6b005f 
Signed-off-by: zwzhang0107 <zuoweizhang@outlook.com>
@cheimu @jasonliu747
Fix wrong cgroup path for PLEG (koordinator-sh#325)
1fa6ec8 
* fix wrong cgroup path when watch pods

Signed-off-by: Cheimu <xerhoneyfc@gmail.com>

* fix import order

Signed-off-by: Cheimu <xerhoneyfc@gmail.com>

* reformat comments

Signed-off-by: Cheimu <xerhoneyfc@gmail.com>

Co-authored-by: Jason Liu <jasonliu747@gmail.com>
@zwzhang0107
add logs for proxy server (koordinator-sh#329)
37a3aec 
Signed-off-by: 佑祎 <zzw261520@alibaba-inc.com>
@saintube
chore: remove useless feature-gates (koordinator-sh#336)
52a06f1 
Signed-off-by: saintube <saintube@foxmail.com>
@jasonliu747
ci: enable CGO when compiling binary (koordinator-sh#334)
f89c582 
Signed-off-by: Jason Liu <jasonliu747@gmail.com>
@zwzhang0107
rename resourceQoS to resourceQOS (koordinator-sh#339)
b8dd567 
Signed-off-by: 佑祎 <zzw261520@alibaba-inc.com>
@saintube
improve koordlet log verbosity (koordinator-sh#338)
6ac04d4 
Signed-off-by: saintube <saintube@foxmail.com>
@cheimu
Add pod uid to pod meta when failover (koordinator-sh#344)
54ed9a5 
* add pod uid to pod meta when failover

Signed-off-by: Cheimu <xerhoneyfc@gmail.com>

* add pod uid when parse request for cri scenario

Signed-off-by: Cheimu <xerhoneyfc@gmail.com>
@novahe
Use the structure as the key of the map instead of string. (koordinat…
1328009 
…or-sh#349)

Signed-off-by: h30003300 <heqian28@huawei.com>
@jasonliu747
koordlet: define GPU metric struct (koordinator-sh#343)
171ad3e 
Signed-off-by: Jason Liu <jasonliu747@gmail.com>
@eahydra
koord-scheduler: support default preferredCPUBindPolicy for LSE/LSR P…
1ab5c99 
…od if not specified (koordinator-sh#354)

Signed-off-by: Joseph <joseph.t.lee@outlook.com>
@jasonliu747
style: unify the command parameter style of koordlet (koordinator-sh#348
0d9d9d4 
)

Signed-off-by: Jason Liu <jasonliu747@gmail.com>
@buptcozy
add fine-grained device scheduling proposal (koordinator-sh#322)
7d46fad 
* add schedule-device-in-card-level.md

Signed-off-by: yangzhang <bupt_cozy@126.com>

* refactor fine-grained device scheduling

Signed-off-by: Joseph <joseph.t.lee@outlook.com>
@cheimu
[koord-runtime-proxy]: fix panic when no hook registered (koordinator…
f81c89c 
…-sh#355)

* fix panic when no hook registered

Signed-off-by: Cheimu <xerhoneyfc@gmail.com>

* refactor the error logs

Signed-off-by: Cheimu <xerhoneyfc@gmail.com>
@eahydra
koord-scheduler: support CPU exclusive policy (koordinator-sh#359)
b78243b 
Signed-off-by: Joseph <joseph.t.lee@outlook.com>
@cheimu
add pod annotations and labels to container request and cache (koordi…
05a8c11 
…nator-sh#362)

Signed-off-by: Cheimu <xerhoneyfc@gmail.com>
@cheimu
fix the loss of new updated resources from UpdateContainerResources r…
b2fcc22 
…equest (koordinator-sh#363)

Signed-off-by: Cheimu <xerhoneyfc@gmail.com>

fix the loss of new updated resources from UpdateContainerResources request
@saintube
add scheduling framework extender (koordinator-sh#365)
993fc21 
Signed-off-by: saintube <saintube@foxmail.com>
@jasonliu747
koordlet: refine initJiffies with default value (koordinator-sh#367)
283c883 
Signed-off-by: Jason Liu <jasonliu747@gmail.com>
@eahydra
add PodMigrationJob CRD proposal (koordinator-sh#358)
42d695f 
Signed-off-by: Joseph <joseph.t.lee@outlook.com>
@buptcozy
add schedule gang md (koordinator-sh#333)
78a4ebb
@eahydra
koord-scheduler: support Node CPU orchestration API (koordinator-sh#360)
8179245 
- support cpu bind policy with FullPCPUsOnly
- support NUMA allocate strategy with MostAllocated/LeastAllocated

Signed-off-by: Joseph <joseph.t.lee@outlook.com>
@jasonliu747
chore: update dockerfile for each module (koordinator-sh#364)
463c409 
Signed-off-by: Jason Liu <jasonliu747@gmail.com>
@dependabot
feat(deps): bump github.com/stretchr/testify from 1.7.5 to 1.8.0 (koo…
6918290 
…rdinator-sh#326)

Bumps [github.com/stretchr/testify](https://github.com/stretchr/testify) from 1.7.5 to 1.8.0.
- [Release notes](https://github.com/stretchr/testify/releases)
- [Commits](stretchr/testify@v1.7.5...v1.8.0)

---
updated-dependencies:
- dependency-name: github.com/stretchr/testify
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>

Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
@dependabot
feat(deps): bump gorm.io/driver/sqlite from 1.3.4 to 1.3.6 (koordinat…
d763879 
…or-sh#347)

Bumps [gorm.io/driver/sqlite](https://github.com/go-gorm/sqlite) from 1.3.4 to 1.3.6.
- [Release notes](https://github.com/go-gorm/sqlite/releases)
- [Commits](go-gorm/sqlite@v1.3.4...v1.3.6)

---
updated-dependencies:
- dependency-name: gorm.io/driver/sqlite
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>

Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
@ZiMengSheng
chore: supply UT for pkg/util and pkg/util/system (koordinator-sh#374)
fa0c35c 
Signed-off-by: wangjianyu <zmsjianyu@gmail.com>
@eahydra
api: add PodMigrationJob API (koordinator-sh#375)
c9cf1a4 
Signed-off-by: Joseph <joseph.t.lee@outlook.com>
@jasonliu747
docs: remove redundant field in Device CRD (koordinator-sh#377)
f2ed65d 
Signed-off-by: Jason Liu <jasonliu747@gmail.com>
jasonliu747 and others added 12 commits July 18, 2022 09:02
@jasonliu747
api: add device crd in scheduling group (koordinator-sh#376)
91cacc4 
Signed-off-by: Jason Liu <jasonliu747@gmail.com>
@hormes
fix auditor test in MacOS (koordinator-sh#379)
b54bb0c 
Signed-off-by: Fansong Zeng <fanster.z@gmail.com>
@ZiMengSheng
koordlet: optimize auditor UT with httptest.Server (koordinator-sh#382)
91d2a4b 
Signed-off-by: wangjianyu <zmsjianyu@gmail.com>
@ZiMengSheng @hormes
docs: add chinese version readme.md (koordinator-sh#380)
d161ee3 
Signed-off-by: wangjianyu <zmsjianyu@gmail.com>

Co-authored-by: Fansong Zeng <fanster.z@gmail.com>
@ZYecho
fix: consider lse/lsr when cpu suppress (koordinator-sh#234) (koordin…
0523d60 
…ator-sh#372)

Signed-off-by: Yue Zhang <huaihuan.zy@alibaba-inc.com>
@jasonliu747
api: add device info into NodeMetric CRD (koordinator-sh#378)
dab5a92 
Signed-off-by: Jason Liu <jasonliu747@gmail.com>
@LambdaHJ
feat: collect gpu metrics (koordinator-sh#361)
4301cc9 
Signed-off-by: 黄金 <huangjin_henan@outlook.com>
@saintube
chore: cleanup resmanager (koordinator-sh#383)
4d9f218 
Signed-off-by: saintube <saintube@foxmail.com>
@saintube
api: update reservation api (koordinator-sh#384)
74de8bd 
Signed-off-by: saintube <saintube@foxmail.com>
@eahydra
add descheduler framework proposal (koordinator-sh#371)
d1fb8c5 
Signed-off-by: Joseph <joseph.t.lee@outlook.com>
@dependabot
feat(deps): bump gorm.io/gorm from 1.23.6 to 1.23.8 (koordinator-sh#351)
f32a0ba 
Bumps [gorm.io/gorm](https://github.com/go-gorm/gorm) from 1.23.6 to 1.23.8.
- [Release notes](https://github.com/go-gorm/gorm/releases)
- [Commits](go-gorm/gorm@v1.23.6...v1.23.8)

---
updated-dependencies:
- dependency-name: gorm.io/gorm
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>

Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
@jasonliu747
fix: remove inline tag for corev1.ResourceList to fix koordinator-sh#390
bf308ed 
 (koordinator-sh#391)

Signed-off-by: Jason Liu <jasonliu747@gmail.com>
@Wenshiqi222 Wenshiqi222 changed the title WIP: Gang scheduling Gang Cache Jul 25, 2022
@Wenshiqi222 Wenshiqi222 changed the title Gang Cache GangCache Design Jul 25, 2022
@Wenshiqi222 Wenshiqi222 force-pushed the gang_wsq branch 5 times, most recently from f25b69d to 633e2fe Compare July 26, 2022 10:02
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.