[gpfsug-discuss] Best of spectrum scale

[Jonathan Buzzard]

On 08/09/2020 18:37, IBM Spectrum Scale wrote:
> I think it is incorrect to assume that a command that continues
> after detecting the working directory has been removed is going to
> cause damage to the file system.

No I am not assuming it will cause damage. I am making the fairly 
reasonable assumption that any command which fails has an increased 
probability of causing damage to the file system over one that completes 
successfully.

> Further, there is no a priori means to confirm if the lack of a 
> working directory will cause the command to fail.

Which is why baling out is a more sensible default that ploughing on
regardless.

> I will agree that there may be admins that would prefer the command 
> fail fast and allow them to restart the command anew, but I suspect 
> there are admins that prefer the command press ahead in hopes that
> it can complete successfully and not require another execution.

I am sure that there are inexperienced admins who have yet to be battle 
scared that would want such reckless default behaviour. Pandering to 
their naivety is not a sensible approach IMHO.

The downside if a large file system (and production GPFS file systems 
tend to be large) going "puff" is so massive that the precaution 
principle should apply.

One wonders if we are seeing the difference between a US and European 
mindset here.

> I'm sure we can conjure scenarios that support both points of view.
> Perhaps what is desired is a message that more clearly describes what
> is being undertaken.  For example, "The current working directory, 
> <directory_name>, no longer exists.  Execution continues."
> 

That is what --force is for. If you are sufficiently reckless that you 
want something to continue in the event of a possible error you have the 
option to stick that on every command you run. Meanwhile the sane admins 
get a system that defaults to proceeding in the safer manner possible.


JAB.

-- 
Jonathan A. Buzzard                         Tel: +44141-5483420
HPC System Administrator, ARCHIE-WeSt.
University of Strathclyde, John Anderson Building, Glasgow. G4 0NG