+1 — This is the best solution.
The only thing I would change would be to add:
TimeoutStartSec=300
Or something similar.
This leaves the maintenance of starting applications where it belongs (in
systems, not in GPFS). You can use the same technique for other VFS types (like
NFS if you needed). You can check for any file on the file system you want, so
you could just put a dotfile in the root of each waited-for file system and
look for that. You an even chase your symlink if you want (removing the
parameter completely).
As a recovering sysadmin, this makes me smile.
--
Stephen
> On Mar 14, 2019, at 5:36 PM, Trafford, Tyler <[email protected]> wrote:
>
> I use the following:
>
> [Unit]
> Description=Foo
> After=gpfs.service
>
> [Service]
> ExecStartPre=/bin/bash -c 'until [ -d /gpfs/%I/apps/services/foo ]; do sleep
> 20s; done'
> ExecStart=/usr/sbin/runuser -u root /gpfs/%I/apps/services/foo/bin/runme
>
> [Install]
> WantedBy=multi-user.target
>
>
> Then I can drop it on multiple systems (with the same app layout), and run:
>
> systemctl enable foo@fs1
> or
> systemctl enable foo@fs2
>
> The "%I" gets replaced by what is after that "@".
>
> --
> Tyler Trafford
> [email protected]
>
> ________________________________________
> From: [email protected]
> <[email protected]> on behalf of Stephen R Buchanan
> <[email protected]>
> Sent: Thursday, March 14, 2019 3:58 PM
> To: [email protected]
> Subject: [gpfsug-discuss] Systemd configuration to wait for mount of SS
> filesystem
>
> I searched the list archives with no obvious results.
>
> I have an application that runs completely from a Spectrum Scale filesystem
> that I would like to start automatically on boot, obviously after the SS
> filesystem mounts, on multiple nodes. There are groups of nodes for dev,
> test, and production, (separate clusters) and the target filesystems are
> different between them (and are named differently, so the paths are
> different), but all nodes have an identical soft link from root (/) that
> points to the environment-specific path. (see below for details)
>
> My first effort before I did any research was to try to simply use a
> directive of After=gpfs.service which anyone who has tried it will know that
> the gpfs.service returns as "started" far in advance (and independently of)
> when filesystems are actually mounted.
>
> What I want is to be able to deploy a systemd service-unit and path-unit pair
> of files (that are as close to identical as possible across the environments)
> that wait for /appbin/builds/ to be available (/[dev|tst|prd]01/ to be
> mounted) and then starts the application. The problem is that systemd.path
> units, specifically the 'PathExists=' directive, don't follow symbolic links,
> so I would need to customize the path unit file for each environment with the
> full (real) path. There are other differences between the environments that I
> believe I can handle by specifying an EnvironmentFile directive -- but that
> would come from the SS filesystem so as to be a single reference point, so it
> can't help with the path unit.
>
> Any suggestions are welcome and appreciated.
>
> dev:(path names have been slightly generalized, but the structure is
> identical)
> SS filesystem: /dev01
> full path: /dev01/app-bin/user-tree/builds/
> soft link: /appbin/ -> /dev01/app-bin/user-tree/
>
> test:
> SS filesystem: /tst01
> full path: /tst01/app-bin/user-tree/builds/
> soft link: /appbin/ -> /tst01/app-bin/user-tree/
>
> prod:
> SS filesystem: /prd01
> full path: /prd01/app-bin/user-tree/builds/
> soft link: /appbin/ -> /prd01/app-bin/user-tree/
>
>
> Stephen R. Wall Buchanan
> Sr. IT Specialist
> IBM Data & AI North America Government Expert Labs
> +1 (571) 299-4601
> [email protected]
>
> _______________________________________________
> gpfsug-discuss mailing list
> gpfsug-discuss at spectrumscale.org
> http://gpfsug.org/mailman/listinfo/gpfsug-discuss
_______________________________________________
gpfsug-discuss mailing list
gpfsug-discuss at spectrumscale.org
http://gpfsug.org/mailman/listinfo/gpfsug-discuss
