From c24dcd9047cc890ea0c7e992f8d6c031484aef41 Mon Sep 17 00:00:00 2001 From: Juri Dispan Date: Sun, 3 Dec 2023 19:14:13 +0100 Subject: [PATCH 01/12] salloc, sattach, sbcast, sdiag, sprio, sshare, strigger, sview: add pages --- pages/linux/salloc.md | 16 ++++++++++++++++ pages/linux/sattach.md | 16 ++++++++++++++++ pages/linux/sbcast.md | 13 +++++++++++++ pages/linux/sdiag.md | 20 ++++++++++++++++++++ pages/linux/sprio.md | 20 ++++++++++++++++++++ pages/linux/sshare.md | 20 ++++++++++++++++++++ pages/linux/strigger.md | 24 ++++++++++++++++++++++++ pages/linux/sview.md | 8 ++++++++ 8 files changed, 137 insertions(+) create mode 100644 pages/linux/salloc.md create mode 100644 pages/linux/sattach.md create mode 100644 pages/linux/sbcast.md create mode 100644 pages/linux/sdiag.md create mode 100644 pages/linux/sprio.md create mode 100644 pages/linux/sshare.md create mode 100644 pages/linux/strigger.md create mode 100644 pages/linux/sview.md diff --git a/pages/linux/salloc.md b/pages/linux/salloc.md new file mode 100644 index 0000000000..db5651ae4e --- /dev/null +++ b/pages/linux/salloc.md @@ -0,0 +1,16 @@ +# salloc + +> Allocate nodes in a cluster and start an interactive shell session or execute a command. +> More information: . + +- Start an interactive shell session on a node in the cluster: + +`salloc` + +- Execute the specified command synchroneously on a node in the cluster: + +`salloc {{ls -a}}` + +- Only allocate nodes fulfiling the specified constraints: + +`salloc --constraint={{(amd|intel)&gpu}}` diff --git a/pages/linux/sattach.md b/pages/linux/sattach.md new file mode 100644 index 0000000000..ec546afea5 --- /dev/null +++ b/pages/linux/sattach.md @@ -0,0 +1,16 @@ +# sattach + +> Attach to a Slurm job step. +> More information: . + +- Make available the IO streams (`stdout`, `stderr`, and `stdin`) of a Slurm job step: + +`sattach {{jobid}}.{{stepid}}` + +- Transmit `stdin` to the specified task only: + +`sattach --input-filter {{task_number}}` + +- Only display `stdin`/`stderr` of the spefified task: + +`sattach --{{output|error}}-filter {{task_number}}` diff --git a/pages/linux/sbcast.md b/pages/linux/sbcast.md new file mode 100644 index 0000000000..16da031689 --- /dev/null +++ b/pages/linux/sbcast.md @@ -0,0 +1,13 @@ +# sbcast + +> Send a file to a job's allocated nodes. +> This command should only be used from within a Slurm batch job. +> More information: . + +- Send a file to all nodes allocated to the current job: + +`sbcast {{path/to/file}} {{path/to/destination}}` + +- Autodetect shared libraries the transmitted file depends upon and transmit them as well: + +`sbcast --send-libs={{yes}} {{path/to/executable}} {{path/to/destination}}` diff --git a/pages/linux/sdiag.md b/pages/linux/sdiag.md new file mode 100644 index 0000000000..edf2fa1a95 --- /dev/null +++ b/pages/linux/sdiag.md @@ -0,0 +1,20 @@ +# sdiag + +> Show information about the execution of `slurmctld`. +> More information: . + +- Show several performance counters related to the execution of `slurmctld`: + +`sdiag --all` + +- Reset performance counters related to the execution of `slurmctld`: + +`sdiag --reset` + +- Specify the output format: + +`sdiag --all --{{json|yaml}}` + +- Specify the cluster to send commands to: + +`sdiag --all --cluster={{cluster_name}}` diff --git a/pages/linux/sprio.md b/pages/linux/sprio.md new file mode 100644 index 0000000000..8feed0daa2 --- /dev/null +++ b/pages/linux/sprio.md @@ -0,0 +1,20 @@ +# sprio + +> View the factors determining a job's scheduling priority +> More information: . + +- View the factors determining all pending job's scheduling priority: + +`sprio` + +- View the factors determining the specified job's scheduling priority: + +`sprio --jobs={{job_id_1,job_id_2,...}}` + +- View information for the jobs of specified users and output additional information: + +`sprio --user={{user_name_1,user_name_2,...}} --long` + +- Print the weights for each factor determining job scheduling priority: + +`sprio --weights` diff --git a/pages/linux/sshare.md b/pages/linux/sshare.md new file mode 100644 index 0000000000..b85682d925 --- /dev/null +++ b/pages/linux/sshare.md @@ -0,0 +1,20 @@ +# sshare + +> List the shares of associations to a cluster. +> More information: . + +- List Slurm share information: + +`sshare` + +- Control the output format: + +`sshare --{{parsable|parsable2|json|yaml}}` + +- Control the fields to display: + +`sshare --format={{format_string}}` + +- Display information for the specified users only: + +`sshare --users={{user_id_1,user_id_2,...}}` diff --git a/pages/linux/strigger.md b/pages/linux/strigger.md new file mode 100644 index 0000000000..cfb0ffb85b --- /dev/null +++ b/pages/linux/strigger.md @@ -0,0 +1,24 @@ +# strigger + +> View or modify Slurm trigger information. +> More information: . + +- Register a new trigger. Execute the specified program when the specified event occurs: + +`strigger --set --{{primary_database_failure|primary_slurmdbd_failure|primary_slurmctld_acct_buffer_full|primary_slurmctld_failure|...}} --program={{path/to/executable}}` + +- Execute the specified program when the specified job terminated: + +`strigger --set --jobid={{job_id}} --fini --program={{path/to/executable}}` + +- View active triggers: + +`strigger --get` + +- View active triggers regarding the specified job: + +`strigger --get --jobid={{job_id}}` + +- Clear the specified trigger: + +`strigger --clear {{trigger_id}}` diff --git a/pages/linux/sview.md b/pages/linux/sview.md new file mode 100644 index 0000000000..a0f7ca09a2 --- /dev/null +++ b/pages/linux/sview.md @@ -0,0 +1,8 @@ +# sview + +> Start a GUI to view and modify the state of Slurm. +> More information: . + +- Start a GUI to view and modify the state of Slurm: + +`sview` From 2a14438c5837283333cecfa77d123be75721b57d Mon Sep 17 00:00:00 2001 From: Juri Dispan Date: Sun, 3 Dec 2023 19:24:06 +0100 Subject: [PATCH 02/12] fix typo --- pages/linux/sprio.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/pages/linux/sprio.md b/pages/linux/sprio.md index 8feed0daa2..1dc82ff73b 100644 --- a/pages/linux/sprio.md +++ b/pages/linux/sprio.md @@ -1,6 +1,6 @@ # sprio -> View the factors determining a job's scheduling priority +> View the factors determining a job's scheduling priority. > More information: . - View the factors determining all pending job's scheduling priority: From f3515bbbf732f9c3a7ec24c308338e570e9c8dab Mon Sep 17 00:00:00 2001 From: Juri Dispan Date: Sun, 3 Dec 2023 19:45:16 +0100 Subject: [PATCH 03/12] scrontab, scrun, sh5util: add pages --- pages/linux/scrontab.md | 20 ++++++++++++++++++++ pages/linux/scrun.md | 24 ++++++++++++++++++++++++ pages/linux/sh5util.md | 16 ++++++++++++++++ 3 files changed, 60 insertions(+) create mode 100644 pages/linux/scrontab.md create mode 100644 pages/linux/scrun.md create mode 100644 pages/linux/sh5util.md diff --git a/pages/linux/scrontab.md b/pages/linux/scrontab.md new file mode 100644 index 0000000000..78c64bd97c --- /dev/null +++ b/pages/linux/scrontab.md @@ -0,0 +1,20 @@ +# scrontab + +> Manage Slurm crontab files. +> More information: . + +- Install a new crontab from the specified file: + +`scrontab {{path/to/file}}` + +- [e]dit the crontab of the specified user: + +`scrontab --user={{user_id}} -e` + +- [r]emove the current crontab: + +`scrontab -r` + +- [l]ist the current crontab to `stdout`: + +`scrontab -l` diff --git a/pages/linux/scrun.md b/pages/linux/scrun.md new file mode 100644 index 0000000000..d3ed0924be --- /dev/null +++ b/pages/linux/scrun.md @@ -0,0 +1,24 @@ +# scrun + +> An OCI (Open Container Initiative) runtime proxy for Slurm. +> More information: . + +- Create a container in the current directory: + +`scrun create {{container_id}}` + +- Start a container in a Slurm job: + +`scrun start {{container_id}}` + +- View the state of the specified container: + +`scrun state {{container_id}}` + +- Send the specified signal to a container: + +`scrun kill {{container_id}} {{SIGTERM}}` + +- Delete the specified container: + +`scrun delete {{container_id}}` diff --git a/pages/linux/sh5util.md b/pages/linux/sh5util.md new file mode 100644 index 0000000000..1ace3fb4b2 --- /dev/null +++ b/pages/linux/sh5util.md @@ -0,0 +1,16 @@ +# sh5util + +> Merge HDF5 files (produced by the `sacct_gather_profile` plugin). +> More information: . + +- Merge HDF5 files produced on each allocated node for the specified job (-step): + +`sh5util --jobs={{job_id|job_id.step_id}}` + +- Extract one or more data series from a merged job file: + +`sh5util --jobs={{job_id|job_id.step_id}} --extract -i {{path/to/file.h5}} --series={{Energy|Filesystem|Network|Task}}` + +- Extract one data item from all nodes in a merged job file: + +`sh5util --jobs={{job_id|job_id.step_id}} --item-extract --series={{Energy|Filesystem|Network|Task}} --data={{data_item}}` From b4453fb1b6339fa0fa38e023cb5afcdc0fded887 Mon Sep 17 00:00:00 2001 From: Juri Dispan Date: Sun, 3 Dec 2023 20:06:36 +0100 Subject: [PATCH 04/12] fix syntax --- pages/linux/scrun.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/pages/linux/scrun.md b/pages/linux/scrun.md index d3ed0924be..b7b7924f57 100644 --- a/pages/linux/scrun.md +++ b/pages/linux/scrun.md @@ -21,4 +21,4 @@ - Delete the specified container: -`scrun delete {{container_id}}` +`scrun delete {{container_id}}` From 1a03d5d3a918f8fa5e2608a0f6349de9931e94eb Mon Sep 17 00:00:00 2001 From: Juri Dispan Date: Sun, 3 Dec 2023 20:13:46 +0100 Subject: [PATCH 05/12] fix typos --- pages/linux/salloc.md | 4 ++-- pages/linux/sattach.md | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/pages/linux/salloc.md b/pages/linux/salloc.md index db5651ae4e..35fe470e81 100644 --- a/pages/linux/salloc.md +++ b/pages/linux/salloc.md @@ -7,10 +7,10 @@ `salloc` -- Execute the specified command synchroneously on a node in the cluster: +- Execute the specified command synchronously on a node in the cluster: `salloc {{ls -a}}` -- Only allocate nodes fulfiling the specified constraints: +- Only allocate nodes fulfilling the specified constraints: `salloc --constraint={{(amd|intel)&gpu}}` diff --git a/pages/linux/sattach.md b/pages/linux/sattach.md index ec546afea5..39b1754ff9 100644 --- a/pages/linux/sattach.md +++ b/pages/linux/sattach.md @@ -11,6 +11,6 @@ `sattach --input-filter {{task_number}}` -- Only display `stdin`/`stderr` of the spefified task: +- Only display `stdin`/`stderr` of the specified task: `sattach --{{output|error}}-filter {{task_number}}` From 7ee48dce3a2a02d13b3c1f50e16b3546e67685d5 Mon Sep 17 00:00:00 2001 From: Juri Dispan Date: Tue, 5 Dec 2023 12:21:48 +0100 Subject: [PATCH 06/12] Apply suggestions from code review Co-authored-by: K.B.Dharun Krishna --- pages/linux/sh5util.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/pages/linux/sh5util.md b/pages/linux/sh5util.md index 1ace3fb4b2..50dc25a216 100644 --- a/pages/linux/sh5util.md +++ b/pages/linux/sh5util.md @@ -1,9 +1,9 @@ # sh5util -> Merge HDF5 files (produced by the `sacct_gather_profile` plugin). +> Merge HDF5 files produced by the `sacct_gather_profile` plugin. > More information: . -- Merge HDF5 files produced on each allocated node for the specified job (-step): +- Merge HDF5 files produced on each allocated node for the specified job or step: `sh5util --jobs={{job_id|job_id.step_id}}` From 2b71504c5d8dcdff04d7690054491d6f3d85b778 Mon Sep 17 00:00:00 2001 From: Juri Dispan Date: Sat, 9 Dec 2023 14:49:11 +0100 Subject: [PATCH 07/12] Apply suggestions from code review Co-authored-by: Starbeamrainbowlabs --- pages/linux/salloc.md | 2 +- pages/linux/sprio.md | 2 +- pages/linux/strigger.md | 1 + 3 files changed, 3 insertions(+), 2 deletions(-) diff --git a/pages/linux/salloc.md b/pages/linux/salloc.md index 35fe470e81..978c5b0358 100644 --- a/pages/linux/salloc.md +++ b/pages/linux/salloc.md @@ -1,6 +1,6 @@ # salloc -> Allocate nodes in a cluster and start an interactive shell session or execute a command. +> Start an interactive shell session or execute a command by allocating one or more nodes in a cluster. > More information: . - Start an interactive shell session on a node in the cluster: diff --git a/pages/linux/sprio.md b/pages/linux/sprio.md index 1dc82ff73b..1547aadd2c 100644 --- a/pages/linux/sprio.md +++ b/pages/linux/sprio.md @@ -3,7 +3,7 @@ > View the factors determining a job's scheduling priority. > More information: . -- View the factors determining all pending job's scheduling priority: +- View the factors determining the scheduling priority of all jobs: `sprio` diff --git a/pages/linux/strigger.md b/pages/linux/strigger.md index cfb0ffb85b..1ea39f95f1 100644 --- a/pages/linux/strigger.md +++ b/pages/linux/strigger.md @@ -1,6 +1,7 @@ # strigger > View or modify Slurm trigger information. +> Triggers are actions that are automatically run when a given event occurs on a Slurm cluster. > More information: . - Register a new trigger. Execute the specified program when the specified event occurs: From ec2d4623ae43e9e209bbffdf15a42fde8ddb17e3 Mon Sep 17 00:00:00 2001 From: Juri Dispan Date: Sat, 9 Dec 2023 14:57:21 +0100 Subject: [PATCH 08/12] Update pages/linux/sattach.md --- pages/linux/sattach.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/pages/linux/sattach.md b/pages/linux/sattach.md index 39b1754ff9..abdd91b5dc 100644 --- a/pages/linux/sattach.md +++ b/pages/linux/sattach.md @@ -11,6 +11,6 @@ `sattach --input-filter {{task_number}}` -- Only display `stdin`/`stderr` of the specified task: +- Only redirect `stdin`/`stderr` of the specified task: `sattach --{{output|error}}-filter {{task_number}}` From 454f33493a294fcaee6d694b32ba2029ec500a65 Mon Sep 17 00:00:00 2001 From: Juri Dispan Date: Sat, 9 Dec 2023 15:00:06 +0100 Subject: [PATCH 09/12] Update pages/linux/scrontab.md --- pages/linux/scrontab.md | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/pages/linux/scrontab.md b/pages/linux/scrontab.md index 78c64bd97c..65264736e0 100644 --- a/pages/linux/scrontab.md +++ b/pages/linux/scrontab.md @@ -7,6 +7,10 @@ `scrontab {{path/to/file}}` +- [e]dit the crontab of the current user: + +`scrontab -e` + - [e]dit the crontab of the specified user: `scrontab --user={{user_id}} -e` From add13d9af6ab8f60629359226ab2f3f3cc87df21 Mon Sep 17 00:00:00 2001 From: Juri Dispan Date: Sat, 9 Dec 2023 15:00:30 +0100 Subject: [PATCH 10/12] Update pages/linux/scrontab.md Co-authored-by: Starbeamrainbowlabs --- pages/linux/scrontab.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/pages/linux/scrontab.md b/pages/linux/scrontab.md index 65264736e0..c97abbb1f3 100644 --- a/pages/linux/scrontab.md +++ b/pages/linux/scrontab.md @@ -19,6 +19,6 @@ `scrontab -r` -- [l]ist the current crontab to `stdout`: +- Print the crontab of the current user to `stdout`: `scrontab -l` From f219ebd9903cf61bb85c7d198b50fc5510daeb54 Mon Sep 17 00:00:00 2001 From: Juri Dispan Date: Sat, 9 Dec 2023 15:21:17 +0100 Subject: [PATCH 11/12] Apply suggestions from code review Co-authored-by: Starbeamrainbowlabs --- pages/linux/sdiag.md | 2 +- pages/linux/sprio.md | 8 ++++++-- 2 files changed, 7 insertions(+), 3 deletions(-) diff --git a/pages/linux/sdiag.md b/pages/linux/sdiag.md index edf2fa1a95..5f5df241ac 100644 --- a/pages/linux/sdiag.md +++ b/pages/linux/sdiag.md @@ -3,7 +3,7 @@ > Show information about the execution of `slurmctld`. > More information: . -- Show several performance counters related to the execution of `slurmctld`: +- Show all performance counters related to the execution of `slurmctld`: `sdiag --all` diff --git a/pages/linux/sprio.md b/pages/linux/sprio.md index 1547aadd2c..aafcdcda7b 100644 --- a/pages/linux/sprio.md +++ b/pages/linux/sprio.md @@ -11,9 +11,13 @@ `sprio --jobs={{job_id_1,job_id_2,...}}` -- View information for the jobs of specified users and output additional information: +- Output additional information: -`sprio --user={{user_name_1,user_name_2,...}} --long` +`sprio --long` + +- View information for the jobs of specified users: + +`sprio --user={{user_name_1,user_name_2,...}}` - Print the weights for each factor determining job scheduling priority: From deb08e1302759602dc92707164584550d3e63895 Mon Sep 17 00:00:00 2001 From: Juri Dispan Date: Sat, 9 Dec 2023 15:22:58 +0100 Subject: [PATCH 12/12] remove tailing whitespace --- pages/linux/salloc.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/pages/linux/salloc.md b/pages/linux/salloc.md index 978c5b0358..cd5d71ead7 100644 --- a/pages/linux/salloc.md +++ b/pages/linux/salloc.md @@ -1,6 +1,6 @@ # salloc -> Start an interactive shell session or execute a command by allocating one or more nodes in a cluster. +> Start an interactive shell session or execute a command by allocating one or more nodes in a cluster. > More information: . - Start an interactive shell session on a node in the cluster: