What's Changed
- koordlet: fix core sched conflicts with GI and revise API by @saintube in #1829
- koordlet: fix recursively disabling bvt by @saintube in #1848
- koordlet: fix struct type lost of node slo extension by @zwzhang0107 in #1847
- scheduler: fix ElasticQuota creation failure on startup by @eahydra in #1845
- koordlet: eliminate cache GC is not started by @saintube in #1849
- scheduler : supports disable runtime quota by @xulinfei1996 in #1839
- chore(deps): bump actions/cache from 3 to 4 by @dependabot in #1851
- scheduler: optimize ElasticQuota status/metrics sync flow by @eahydra in #1850
- scheduler: fix ElasaticQuota sync status missing decorate used by @jasonliu747 in #1852
- scheduler: fix missing tree id in GetQuotaSummary() by @jasonliu747 in #1853
- scheduler: ElasticQuota runtime is no longer calculated when not needed by @eahydra in #1855
- koord-manager: refactor gpu device resource plugin by @saintube in #1846
- descheduler: fix bug of nodeAnomalyDetector in LowNodeLoad plugin by @bogo-y in #1858
- scheduler: improve plugin args by @eahydra in #1857
- scheduler: improve Coscheduling PreFilter status by @eahydra in #1861
- Add a new adopter by @zhifanggao in #1865
- metrics: seperater metrics as internal and external for slo-controller and koordlet by @zwzhang0107 in #1807
- koordlet: fix metric record err by @ls-2018 in #1868
- scheduler: fix the method of calculating desiredCount in DeviceShare ApplyForAll strategy by @eahydra in #1870
- webhook: add node affinity for pod when MultiQuotaTree on by @shaloulcy in #1864
- webhook: validate network qos config in webhook by @lucming in #1841
- proposal: Resctrl Qos Enhancement Proposal by @kangclzjc in #1798
- koordlet: decouple CUDA dependency Accelerators feature disabled by @saintube in #1876
- koordlet: export mid resource metrics by @j4ckstraw in #1874
- koordlet: revise base collectors and system status check by @saintube in #1877
- koordlet: fix proxy container service and revise cpu.max updater by @saintube in #1885
- webhook: improve node affinity performance for MultiQuotaTree by @shaloulcy in #1872
- scheduler: correct NodeNUMAResource handling with NodeFullPCPUsOnly and preferredCPUBindPolicy by @eahydra in #1891
- koordlet: fix misleading query helper by @saintube in #1893
- chore(deps): bump helm/kind-action from 1.8.0 to 1.9.0 by @dependabot in #1897
- webhook: more checks for netqos by @lucming in #1878
- koorldet: remove logging field from the kubelet configz by @zwzhang0107 in #1907
- proposal: support Job-level preemption by @xulinfei1996 in #1879
- proposal: support Reservation preemption by @xulinfei1996 in #1887
- webhook: fix webhook for root quota creation by @shaloulcy in #1916
- scheduler: fix initializing built-in quota objects by @eahydra in #1917
- Proposal: add proposal for multi tree quota by @shaloulcy in #1902
- webhook: fix validateQuotaTopology for root quota by @shaloulcy in #1918
- webhook: forbid use internal protocols by @ls-2018 in #1911
- webhook: remove some annotation verify by @ls-2018 in #1921
- scheduler: add Reservation restricted options to control allocatable resources by @eahydra in #1894
- koordlet: add metrics for kubelet and resource executor by @zwzhang0107 in #1913
- scheduler: remove the restriction that reservation cannot be preempted by @eahydra in #1859
- scheduler: fix reservation restricted options by @eahydra in #1926
- scheduler: add unschedulable resource for root quota by @shaloulcy in #1925
- scheduler: improve NodeNUMAResource handling node cpu bind policy by @eahydra in #1892
- utils: add metric server client by @zwzhang0107 in #1881
- scheduler: update resourceNames of ReservationInfo by @eahydra in #1930
- koordlet: support NetworkQoS plugin by @l1b0k in #1843
- koordlet: revise cgroupRoot param in podsInformer by @saintube in #1928
- koordlet: optimize perf group cpi collection by @bowen-intel in #1905
- koordlet: support blkio-cost rpct and wpct configuration by @wangxiaoq in #1931
- scheduler: resolve the wrong use of gangmod in gang init phase by @PeterChg in #1934
- Add a new adopter by @j4ckstraw in #1938
- scheduler: revise device allocate logic by @ZiMengSheng in #1927
- webhook: fix concurrent map for quota topology by @shaloulcy in #1940
- koordlet: fix bug that cpu eviction does not take effect by @wangxiaoq in #1932
- scheduler: extend reservation nominator to support reservation preemption by @xulinfei1996 in #1936
- koordlet: fix GetAllPods error and wrong tsdb prometheus registry by @saintube in #1944
- proposal: support pod customizing numa policy by @KunWuLuan in #1910
- manager: add featuregate to remove the restriction of parent quota submit pods by @xulinfei1996 in #1929
- scheduler: improve coscheduling's PostFilter if not collect enough by @eahydra in #1948
- scheduler: fix reservation calc error by @eahydra in #1949
- koordlet: support blkio-cost user cost model configuration by @wangxiaoq in #1942
- scheduler: improve the failed event of Reservation's scheduling by @ZiMengSheng in #1947
- scheduler: pick vf by random by @ZiMengSheng in #1953
- scheduler: give more context to device allocator by @ZiMengSheng in #1958
- descheduler: change the order of check len(lowNodes) and len(sourceNodes) by @bogo-y in #1957
- descheduler: add a cache timeout argument for nodeAnomalyDetectors in lowNodeLoad plugin. by @bogo-y in #1955
- descheduler: only include the overused resources when sorting removable pods by @bogo-y in #1962
- apis: add Recommendation crd by @zwzhang0107 in #1937
- webhook: fix priority admission conflict by @j4ckstraw in #1968
- apis: add Resctrl API by @kangclzjc in #1943
- chore: fix make docker build xxx by @j4ckstraw in #1950
- scheduler : fix deviceshare plugin of add\remove pod by @xulinfei1996 in #1963
- Revert "scheduler : fix deviceshare plugin of add\remove pod (#1963)" by @xulinfei1996 in #1971
- koordlet: record invoke metrics for runtime hook by @saintube in #1961
- scheduler: optimize QueueSort func when Gang and Barepod Coexists by @ZiMengSheng in #1977
- scheduler: fix reservation nominator residual bug by @xulinfei1996 in #1985
- Add codecov token by @FillZpp in #1987
- slo-controller: refactor codes for reading by @hormes in #1973
- CI workflow with codecov token by @FillZpp in #1989
- chores: fix some fmt err by @ls-2018 in #1970
- Revert "scheduler: pick vf by random (#1953)" by @ZiMengSheng in #1986
- proposal: tc plugin for netqos by @lucming in #1976
- scheduler: assure Fairness and DeadlockFree by @ZiMengSheng in #1996
- scheduler: sort gang of same gangGroup by gangId by @ZiMengSheng in #1997
- apis & slo-controller: allow specifying node-wise total bandwidth via annotation by @sjtufl in #1982
- scheduler: no rejecting sbiling when invalid scheduling cycle by @ZiMengSheng in #1999
- descheduler: allow annotated pod pass non-retrievable filter by @ZiMengSheng in #1994
- scheduler: add more quota details used and request in quotaInfo by @xulinfei1996 in #2001
- chores: add security docs by @zwzhang0107 in #2007
- koordlet: add close for querier by @zwzhang0107 in #1995
- koordlet: add extended HTTP handler registry by @saintube in #2006
- chore: fix gpu api in comments by @hormes in #1988
- scheduler: quota info deepcopy withou pod deepcopy by @xulinfei1996 in #2008
- scheduler: refine coscheduling fairness consider gangGroup by @buptcozy in #2004
- scheduler: optimize scheduleCycle logic when notEnoughChildren by @ZiMengSheng in #2011
- scheduler: fix panic of podGroup and pod delete order issue by @buptcozy in #2012
- fix panic of podGroup and pod delete order issue2 by @buptcozy in #2013
- scheduler: refine restricted topology policy by @ZiMengSheng in #2010
- koordlet: revise node topology reporting for the kubelet cpu manager by @saintube in #2015
- koordlet: support cri-o container runtime by @georgexiang in #1983
- scheduler: try best to distribute cpu and memory evenly across numa by @ZiMengSheng in #2017
- scheduler: remove invalid hint in which some numaNode lack resource by @ZiMengSheng in #2018
- chores: add openssf best practices badge into README by @songtao98 in #2023
- webhook: optimize webhook patchResponse function by @ZiMengSheng in #2025
- utils: change metrics server util pkg name by @zwzhang0107 in #2016
- descheduler: Add detail logs for nonRemovable pods by @zwForrest in #2000
- chore: fix some nit error by @googs1025 in #2027
- chore(deps): bump golangci/golangci-lint-action from 3 to 5 by @dependabot in #2022
- scheduler: coscheduling plugin only record gang OnceResourceSatisfied… by @xulinfei1996 in #2029
- scheduler: fix that cpu should be preferred if numa policy is restricted by @KunWuLuan in #2033
- koordlet: add NRI reconnect by @kangclzjc in #1972
- scheduler: support numa topology policy on pod by @KunWuLuan in #1939
- all: migrate to 1.28.7 by @ZiMengSheng in #2038
- scheduler: coscheduling plugin sync scheduled in controller by @xulinfei1996 in #2032
- koordlet: add nri remove by @kangclzjc in #2046
- ci: fix scheduler e2e workflow after 1.28 upgradation by @saintube in #2053
- koordlet: change CollectContainerThrottledMetric with duration=2*collectoInterval by @zwzhang0107 in #2054
- koordlet: skip the container which is not running in cpuBurst applyCFSQuotaBurst by @yangfeiyu20102011 in #2055
- koordlet: fix BlkioReconcile file close by @testwill in #2056
- koordlet: revise flaky test in pleg by @saintube in #2060
- scheduler: support empty reservation affinity by @ZiMengSheng in #2059
- koordlet: fix flaky test in pleg by @saintube in #2061
- scheduler: add reservation level event by @zwzhang0107 in #2063
- scheduler: make gang quickCheck earlier by @ZiMengSheng in #2064
- scheduler: make device topology alignment switchable by @ZiMengSheng in #2044
- scheduler: remove unused imports by @ZiMengSheng in #2065
- koordlet: fix nri reconnect params by @saintube in #2067
- scheduler: fix fairness ut by @ZiMengSheng in #2069
- manager: only sync label when label key exists by @ZiMengSheng in #2070
- fix some reservationAffinity related error by @ZiMengSheng in #2072
- koordlet: reduce unnecessary call of Err() for better performance by @yangfeiyu20102011 in #2071
- koordlet: add resctrl updater by @kangclzjc in #2052
- koordlet: kill container after calling eviction api success by @j4ckstraw in #1759
- koord-scheduler: fix gpu name to nvidia/gpu in reservation level event by @zwzhang0107 in #2073
- koord-scheduler: add a parameter to mark whether scheduling is allowed on node with expired nodemetric by @lucming in #2076
New Contributors
- @zhifanggao made their first contribution in #1865
- @ls-2018 made their first contribution in #1868
- @l1b0k made their first contribution in #1843
- @PeterChg made their first contribution in #1934
- @sjtufl made their first contribution in #1982
- @georgexiang made their first contribution in #1983
- @zwForrest made their first contribution in #2000
- @googs1025 made their first contribution in #2027
- @yangfeiyu20102011 made their first contribution in #2055
- @testwill made their first contribution in #2056
Full Changelog: v1.4.0...v1.5.0
Contributors
eahydra, l1b0k, and 27 other contributors