Ecosyste.ms: Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / koordinator-sh/koordinator issues and pull requests

#2279 - scheduler: support allocating from reservation when no resource matched

Pull Request - State: closed - Opened by saintube 4 days ago - 3 comments
Labels: lgtm, approved

#2278 - feat: add GetNodeMetric in statesInformer interface

Pull Request - State: open - Opened by j4ckstraw 7 days ago - 1 comment

#2277 - scheduler: update dingtalk QR Code

Pull Request - State: closed - Opened by ZiMengSheng 8 days ago - 2 comments
Labels: lgtm, approved

#2276 - koordlet: supply rdma devices

Pull Request - State: open - Opened by ZiMengSheng 9 days ago

#2276 - koordlet: supply rdma devices

Pull Request - State: open - Opened by ZiMengSheng 9 days ago

#2275 - koordlet: rdma device inject

Pull Request - State: open - Opened by ZiMengSheng 9 days ago - 1 comment

#2273 - feat: fill up metric host application memory usage with page cache

Pull Request - State: open - Opened by j4ckstraw 11 days ago - 3 comments

#2272 - gpu: support strict gpu share with hami

Pull Request - State: open - Opened by ZiMengSheng 14 days ago - 1 comment

#2271 - chore(deps): bump codecov/codecov-action from 4 to 5

Pull Request - State: open - Opened by dependabot[bot] 14 days ago
Labels: dependencies

#2268 - [question]cgroup有哪些参数，koordinator使用了哪些，能做个汇总么

Issue - State: open - Opened by 13567436138 14 days ago - 1 comment
Labels: kind/question

#2265 - [question]blkioQOS用了哪些技术，没有文档介绍相关内容

Issue - State: open - Opened by 13567436138 15 days ago
Labels: kind/question

#2263 - [question] GroupQuotaManager字段totalResourceExceptSystemAndDefaultUsed在计算配额树runtime时是否不准确

Issue - State: open - Opened by fanzetian 15 days ago - 1 comment
Labels: area/koord-scheduler, kind/question

#2262 - scheduler: setFailedPlugin when plugin transformer failed

Pull Request - State: closed - Opened by ZiMengSheng 16 days ago - 2 comments
Labels: lgtm, approved

#2261 - [BUG]精细化cpu编排文档似乎和代码实现对不上

Issue - State: open - Opened by YoghurtFree 16 days ago - 1 comment
Labels: documentation, kind/bug

#2260 - feat(deps): bump github.com/golang-jwt/jwt/v4 from 4.5.0 to 4.5.1

Pull Request - State: open - Opened by dependabot[bot] 16 days ago
Labels: dependencies

#2259 - koordlet: export host application cpu and memory usage for prometheus

Pull Request - State: closed - Opened by yangfeiyu20102011 17 days ago - 4 comments
Labels: lgtm, approved

#2258 - [question]RebindResource还在概念中么，代码里没找到，md里有

Issue - State: open - Opened by 13567436138 18 days ago - 1 comment
Labels: documentation, kind/question

#2257 - koord-manager: mv slo-controller metrics to util

Pull Request - State: closed - Opened by zwzhang0107 18 days ago - 2 comments
Labels: lgtm, approved

#2256 - [question]有没有slo-controller-config的全量配置内容

Issue - State: closed - Opened by 13567436138 18 days ago
Labels: kind/question

#2254 - [question] 几张图看不懂

Issue - State: open - Opened by 13567436138 19 days ago
Labels: documentation, kind/question

#2253 - koord-manager: consider NodeReserved when calculate mid resource.

Pull Request - State: open - Opened by tan90github 22 days ago - 11 comments
Labels: lgtm

#2252 - scheduler: fix deviceshare with reservation-ignored pods

Pull Request - State: closed - Opened by saintube 23 days ago - 3 comments
Labels: lgtm, approved

#2251 - koordlet: add ReadMemoryUsage method to improve generality of cgroup reader interface

Pull Request - State: closed - Opened by yangfeiyu20102011 24 days ago - 1 comment
Labels: lgtm, approved

#2250 - api: supply id for minor meaningless device

Pull Request - State: open - Opened by ferris-cx 24 days ago - 3 comments

#2249 - add rdma device controller

Pull Request - State: open - Opened by ferris-cx 24 days ago - 1 comment

#2246 - scheduler: gang scheduling add closeHistoryEvaluate annotation

Pull Request - State: closed - Opened by LY-today 25 days ago - 2 comments

#2245 - gpu: setting default gpu partition policy

Pull Request - State: closed - Opened by ZiMengSheng 28 days ago - 4 comments
Labels: lgtm, approved

#2244 - [proposal] gang strategy enhancement

Issue - State: open - Opened by LY-today 28 days ago - 6 comments
Labels: area/koord-scheduler, kind/proposal

#2243 - scheduler: support besteffort policy

Pull Request - State: closed - Opened by ZiMengSheng about 1 month ago - 3 comments
Labels: lgtm, approved

#2242 - scheduler: fix scaling factor 100 for burstable pod

Pull Request - State: closed - Opened by ZiMengSheng about 1 month ago - 3 comments
Labels: lgtm, approved

#2241 - scheduler: optimize reservation perf with lazy restoring

Pull Request - State: closed - Opened by saintube about 1 month ago - 3 comments
Labels: lgtm, approved

#2240 - koord-manager: refactor oversale resource calculate logic.

Pull Request - State: closed - Opened by tan90github about 1 month ago - 5 comments
Labels: lgtm, approved

#2239 - scheduler: add downgrade strategy for empty 'aggregated' on cold koor…

Pull Request - State: closed - Opened by clay-wangzhi about 1 month ago - 2 comments
Labels: lgtm, approved

#2238 - util: add defaulting to blkio qos to improve robustness

Pull Request - State: closed - Opened by zqzten about 1 month ago - 2 comments
Labels: lgtm, approved

#2237 - webhook: Support setting quota admission to zero for special usage scenarios, such as temporarily pausing pod submissions.

Pull Request - State: closed - Opened by TaoYang526 about 1 month ago - 6 comments
Labels: lgtm, approved

#2236 - [BUG] The checksums files published are not usable

Issue - State: open - Opened by rbauduin about 1 month ago
Labels: area/runtime-proxy, kind/bug

#2235 - util: fix incorrect comparison for resource.go#LessThanOrEqualCompletely

Pull Request - State: closed - Opened by TaoYang526 about 1 month ago - 6 comments
Labels: lgtm, approved

#2234 - Reasonableness of resource estimates

Issue - State: open - Opened by LY-today about 1 month ago - 1 comment
Labels: area/koord-scheduler, kind/proposal

#2233 - scheduler: consider pod requests when gpu&RDMA joint allocate

Pull Request - State: closed - Opened by ZiMengSheng about 1 month ago - 2 comments
Labels: lgtm, approved

#2231 - [proposal]koord-scheduler：Hope that the Aggregated of the load perception plug-in in Koord-SCHEDULER can take effect when starting

Issue - State: closed - Opened by clay-wangzhi about 1 month ago - 2 comments
Labels: area/koord-scheduler, kind/proposal

#2230 - scheduler: fix shared gpu pod allocated minor of -1

Pull Request - State: closed - Opened by ZiMengSheng about 1 month ago - 2 comments
Labels: lgtm, approved

#2229 - scheduler: support secondary device well planned

Pull Request - State: closed - Opened by ZiMengSheng about 1 month ago - 3 comments
Labels: lgtm, approved

#2228 - scheduler: fix gpu shared bug

Pull Request - State: closed - Opened by ZiMengSheng about 1 month ago - 3 comments
Labels: lgtm, approved

#2227 - scheduler: fix partition binpack disorder

Pull Request - State: closed - Opened by ZiMengSheng about 1 month ago - 2 comments
Labels: lgtm, approved

#2226 - scheduler: allocate tolerate numa-meaning-less device

Pull Request - State: closed - Opened by ZiMengSheng about 1 month ago - 3 comments
Labels: lgtm, approved

#2225 - koord-descheduler: fix prod pod excessive eviction when node recover to normal

Pull Request - State: closed - Opened by JBinin about 2 months ago - 4 comments
Labels: lgtm, approved

#2224 - scheduler: support reserving pods resources

Pull Request - State: closed - Opened by saintube about 2 months ago - 2 comments
Labels: lgtm, approved

#2223 - scheduler: support amd

Pull Request - State: closed - Opened by ZiMengSheng about 2 months ago - 3 comments
Labels: lgtm, approved

#2222 - add the end-to-end solution of RDMA devices

Pull Request - State: closed - Opened by ferris-cx about 2 months ago

#2221 - scheduler: optimize GPU allocate logic

Pull Request - State: closed - Opened by ZiMengSheng about 2 months ago - 2 comments
Labels: lgtm, approved

#2220 - [BUG] Elasticquota failed to update due to velasticquota verification

Issue - State: open - Opened by qinfustu about 2 months ago - 10 comments
Labels: area/koord-manager, kind/bug

#2219 - apis: GPU Partition related

Pull Request - State: closed - Opened by ZiMengSheng about 2 months ago - 4 comments
Labels: lgtm, approved

#2218 - [BUG] enablePprof command line option is useless

Issue - State: open - Opened by j4ckstraw about 2 months ago
Labels: help wanted, area/koordlet, kind/bug

#2217 - scheduler: recover gang check in preFilter

Pull Request - State: closed - Opened by ZiMengSheng about 2 months ago - 1 comment
Labels: lgtm, approved

#2216 - scheduler: recover gang check in preFilter

Pull Request - State: closed - Opened by ZiMengSheng about 2 months ago

#2215 - [proposal] Support Preferred Reservation Affinity

Issue - State: open - Opened by saintube 2 months ago
Labels: area/koord-scheduler, kind/proposal

#2214 - [BUG] While scheduling a reservation, reservation-ignored pods should not be counted in the node requested

Issue - State: open - Opened by saintube 2 months ago
Labels: area/koord-scheduler, kind/bug

#2212 - apis: fix type of MinResources in podgroup

Pull Request - State: closed - Opened by zwzhang0107 2 months ago - 2 comments
Labels: lgtm, approved

#2211 - scheduler: optimize performance on transformer extension and Skip status

Pull Request - State: closed - Opened by saintube 2 months ago - 3 comments
Labels: lgtm, approved

#2210 - [proposal] Decouple Reservation plugin for the koord-scheduler

Issue - State: open - Opened by saintube 2 months ago - 1 comment
Labels: good first issue, help wanted, area/koord-scheduler, kind/proposal

#2209 - scheduler: optimize numa affinity store

Pull Request - State: closed - Opened by ZiMengSheng 2 months ago - 3 comments
Labels: lgtm, approved

#2208 - [proposal] Cleanup node labels casting while matching a reservation affinity

Issue - State: open - Opened by saintube 2 months ago
Labels: area/koord-scheduler, kind/proposal

#2207 - scheduler: support reservation name, taints and tolerations

Pull Request - State: closed - Opened by saintube 2 months ago - 2 comments
Labels: lgtm, approved

#2206 - koordlet: support change pod CPUQOS by annotations

Pull Request - State: open - Opened by j4ckstraw 3 months ago - 3 comments

#2204 - scheduler: support pod preemption from numa awareless reservation

Pull Request - State: closed - Opened by ZiMengSheng 3 months ago - 3 comments
Labels: lgtm, approved

#2203 - [BUG] koord-descheduler: failed job never delete from arbitrator

Issue - State: open - Opened by songtao98 3 months ago
Labels: kind/bug

#2202 - [proposal] Resource recommendation support for workloads like jobs/vcjobs/rayjobs

Issue - State: open - Opened by GhangZh 3 months ago
Labels: kind/proposal

#2201 - koord-manager: nodeslo-controller enqueue request when node labels updated

Pull Request - State: closed - Opened by chengjoey 3 months ago - 5 comments
Labels: lgtm, approved

#2200 - koord-descheduler: fix descheduler object limiter with multiple profiles

Pull Request - State: open - Opened by songtao98 3 months ago - 1 comment

#2199 - scheduler: support devices of the same node gpuMem not equal

Pull Request - State: closed - Opened by ZiMengSheng 3 months ago - 7 comments
Labels: lgtm, approved

#2196 - koord-descheduler: fix migration controller max unavailable computing algorigthm

Pull Request - State: closed - Opened by songtao98 3 months ago - 5 comments
Labels: size/XS, lgtm, approved

#2194 - The center side scheduling results and device allocation results make dp aware of lightweight methods

Issue - State: open - Opened by ferris-cx 3 months ago - 2 comments
Labels: kind/proposal

#2193 - koordlet: fix wrong msg in calculateBESuppressCPU

Pull Request - State: closed - Opened by yangfeiyu20102011 3 months ago - 2 comments
Labels: size/XS, lgtm, approved

#2192 - apis: add protobuf for reservation

Pull Request - State: closed - Opened by zwzhang0107 3 months ago - 3 comments
Labels: lgtm, approved, size/M

#2190 - scheduler: fix ElasticQuota state's Clone

Pull Request - State: closed - Opened by saintube 3 months ago - 5 comments
Labels: lgtm, approved, size/M

#2189 - scheduler: fix panic when nonimatingInfo nil

Pull Request - State: closed - Opened by ZiMengSheng 3 months ago - 3 comments
Labels: lgtm, approved, size/M

#2188 - scheduler: support amd

Pull Request - State: closed - Opened by ZiMengSheng 3 months ago - 3 comments
Labels: size/S

#2187 - [proposal] Extended resource RDMA resource registration, scheduling, and allocation

Issue - State: open - Opened by ferris-cx 3 months ago
Labels: kind/proposal

#2186 - apis: add reservation name, taints and tolerations in ReservationAffinitty

Pull Request - State: closed - Opened by zwzhang0107 3 months ago - 4 comments
Labels: lgtm, approved, size/M

#2185 - [question] GPU visibility inside the pod does not take effect

Issue - State: closed - Opened by ferris-cx 3 months ago - 5 comments
Labels: area/koordlet, area/koord-scheduler, area/runtime-proxy, kind/question

#2184 - [proposal] Reservation Affinity supports the reservation name

Issue - State: closed - Opened by saintube 3 months ago - 1 comment
Labels: area/koord-scheduler, kind/proposal

#2183 - [proposal] Reservation supports taints and tolerations

Issue - State: closed - Opened by saintube 3 months ago - 1 comment
Labels: area/koord-scheduler, kind/proposal

#2182 - scheduler: permit other plugin to set numaAffinity

Pull Request - State: closed - Opened by ZiMengSheng 3 months ago - 2 comments
Labels: lgtm, approved, size/M

#2181 - [proposal] Provide an evolvable End to End Solution for Koordinator Device Management

Issue - State: open - Opened by ZiMengSheng 3 months ago - 7 comments
Labels: area/koordlet, area/koord-scheduler, area/koord-manager, kind/proposal, area/api-machinery