From bf17d60d314bcf37e362922b8d174a9e484027c1 Mon Sep 17 00:00:00 2001 From: Kevin Date: Wed, 30 Oct 2024 10:40:18 +0000 Subject: [PATCH 1/3] Update reservation instructions --- docs/user-guide/scheduler.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/docs/user-guide/scheduler.md b/docs/user-guide/scheduler.md index 3820e45cc..81b7b1bd3 100644 --- a/docs/user-guide/scheduler.md +++ b/docs/user-guide/scheduler.md @@ -2283,7 +2283,7 @@ CUs if you fail to use them due to a job issue unless this issue is due to a sys To request a reservation you complete a form on SAFE: 1. [Log into SAFE](https://safe.epcc.ed.ac.uk) - 2. Under the "Login accounts" menu, choose the "Request reservation" option + 2. Under the "Apply" menu, choose the "Request reservation" option On the first page, you need to provide the following: @@ -2291,6 +2291,7 @@ On the first page, you need to provide the following: - The end time and date of the reservation. - Your justification for the reservation -- this must be provided or the request will be rejected. - The number of nodes required. + - The machine name (ARCHER2) under resource type. On the second page, you will need to specify which username you wish the reservation to be charged against and, once the username has been selected, the budget you want to charge the reservation to. From f6c78a47d2a0d317e3900a20b2466836dd718f27 Mon Sep 17 00:00:00 2001 From: Kevin Date: Wed, 30 Oct 2024 10:41:52 +0000 Subject: [PATCH 2/3] Minor format updates --- docs/user-guide/scheduler.md | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/docs/user-guide/scheduler.md b/docs/user-guide/scheduler.md index 81b7b1bd3..77f1143fe 100644 --- a/docs/user-guide/scheduler.md +++ b/docs/user-guide/scheduler.md @@ -218,7 +218,7 @@ lists the active QoS on ARCHER2. | taskfarm | 16 | 24 hrs | 128 | 32 | standard | Maximum of 256 nodes in use by any one user at any time | | short | 32 | 20 mins | 16 | 4 | standard | | | long | 64 | 96 hrs | 16 | 16 | standard | Minimum walltime of 24 hrs, maximum 512 nodes in use by any one user at any time, maximum of 2048 nodes in use by QoS | - | largescale | 5860 | 12 hrs | 8 | 1 | standard | Minimum job size of 1025 nodes | + | largescale | 5860 | 12 hrs | 8 | 1 | standard | Minimum job size of 1025 nodes | | lowpriority | 2048 | 24 hrs | 16 | 16 | standard | Jobs not charged but requires at least 1 CU in budget to use. | | serial | 32 cores and/or 128 GB memory | 24 hrs | 32 | 4 | serial | Jobs not charged but requires at least 1 CU in budget to use. Maximum of 32 cores and/or 128 GB in use by any one user at any time. | | reservation | Size of reservation | Length of reservation | No limit | no limit | standard | | @@ -768,7 +768,7 @@ in partition standard You can use the `squeue` command to show the current estimated start time for a job. Please note that it is just an estimate, the actual start time may differ as the scheduler status when the start time was estimated may be different due to subsequent changes to -the scheduler state. To return the estimated start time for a job you spacify the +the scheduler state. To return the estimated start time for a job you spacify the job ID with the `--jobs=` and `--Format=StartTime` options. For example, to show the estimated start time for job `123456`, you would use: @@ -780,7 +780,7 @@ squeue --jobs=123456 --Format=StartTime The output from this command would look like: ``` -START_TIME +START_TIME 2024-09-25T13:07:00 ``` @@ -2333,7 +2333,7 @@ Capability Days are made up of different parts: !!! tip Any jobs left in the queues when Capability Days finish will be deleted. -### pre-Capability Day session +### pre-Capability Day session The pre-Capability Day session is typically available directly before the full Capability Day session and allows short test jobs to prepare for Capability Day. From 03a03e5a7a976b38801f3a06e1a70a13ce692d11 Mon Sep 17 00:00:00 2001 From: Kevin Date: Thu, 31 Oct 2024 10:50:36 +0000 Subject: [PATCH 3/3] Spelling --- docs/user-guide/scheduler.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/user-guide/scheduler.md b/docs/user-guide/scheduler.md index 77f1143fe..0aaf8cedc 100644 --- a/docs/user-guide/scheduler.md +++ b/docs/user-guide/scheduler.md @@ -768,7 +768,7 @@ in partition standard You can use the `squeue` command to show the current estimated start time for a job. Please note that it is just an estimate, the actual start time may differ as the scheduler status when the start time was estimated may be different due to subsequent changes to -the scheduler state. To return the estimated start time for a job you spacify the +the scheduler state. To return the estimated start time for a job you specify the job ID with the `--jobs=` and `--Format=StartTime` options. For example, to show the estimated start time for job `123456`, you would use: