We're running SoGE 8.1.9, and are seeing some odd behavior from an array
job. It's going beyond its allowed concurrency:
$ qstat -j 1166285
.
maximum concurrency: 600
.
$ qstat -j 1166285 | grep -c usage
3556
One slightly odd thing is that the job wasn't submitted with a contiguous
set of tasks -- there are a lot of gaps (partial list follows):
1166285 0.00000 Human_pepa modpipe qw 04/14/2020 18:15:40 1
6651-6668:1,29848-29851:1,29853,29854,29856,29857,29859,29862,29863-29867:2,29868-29872:1,29874-29876:1,29878-29890:1,29892-29899:1,29901-29905:1,29907-29909:1,29912-29916:2,29917,29918,29920-29923:1,29925,29926,29928,29929,29931-29936:1,29940,29941,29943-29947:2,29948,29949,29951-29953:1,29957-29962:1,29964,29966,29967-29970:1,29972-29981:1,29983,29985,29988,29990,29991,29992,29994-30002:1,30004,30007,30008,30010,30011,30013,30014-30017:1,30020-30030:1,30032-30035:1,30037,30038,30041,30046,30047-30065:1,30067-30074:1,30076-30124:1,30126,30128,30129,30132,30133,30135,30136-30144:1,30146-30156:1,30159-30201:1,30203-30206:1,30208-30211:1,30213-30219:1,30222,30223,30225-30229:2,30230-30232:1,30236-30239:1,30241-30249:1,30251,30252,30254-30259:1,30261,30262,30264-30267:1,30269-30275:1,30277,30278,30280-30284:1,30287,30288,30290-30294:1,30297,30299,30300-30304:1,30307-30314:1,30316-30319:1,30322-30325:1,303!
28-30330:1,30332
but obviously that shouldn't matter. Any hints as to where we should
look? Thanks.
--
Joshua Baker-LePain
Wynton Cluster Sysadmin
UCSF
_______________________________________________
users mailing list
users@gridengine.org
https://gridengine.org/mailman/listinfo/users
