Somewhat related to this thread: when is the practice of *not* using the
-close option when using FILE in pqact recommended? Invariably I find that
omitting its use leads to pqact not being able to keep up with the incoming
stream. This is seen especially well when we are writing the GEFS GRIB2 files
to disk.
_____________________________________________
Kevin Tyle, Systems Administrator
Dept. of Atmospheric & Environmental Sciences
University at Albany
Earth Science 235, 1400 Washington Avenue
Albany, NY 12222
Email: ktyle@xxxxxxxxxx
Phone: 518-442-4578
_____________________________________________
________________________________________
From: ldm-users-bounces@xxxxxxxxxxxxxxxx <ldm-users-bounces@xxxxxxxxxxxxxxxx>
on behalf of Michael Dross <mdross@xxxxxxxxxxxxxxxxxx>
Sent: Wednesday, October 28, 2015 12:02 PM
To: Tom Yoksas; ldm-users@xxxxxxxxxxxxxxxx
Subject: Re: [ldm-users] 20151028: Pqact FILE writes with custom removal?
Is there one type of filesystem that is more efficient at handling these types
file large volumes of finds/creations/deletions?
ie. EXT4, zfs.
- Mike
> On Oct 28, 2015, at 11:56 AM, Tom Yoksas <yoksas@xxxxxxxx> wrote:
>
> All,
>
> re: how to efficiently scour LDM-created data products from disk
>
> If one organizes one's data files into daily directories, the need to
> 'find' each file that should be scoured can be pared down to finding
> which directories+contents need to be scoured. This does not, however,
> get around the fact that deleting large numbers of files
> (e.g., millions for NEXRAD Level III files kept on disk for long
> periods of time) is a _very_ costly endeavor.
>
> Cheers,
>
> Tom
>
>> On 10/28/2015 09:47 AM, Gerry Creager - NOAA Affiliate wrote:
>> How often to you run your scour command? We've exercised scour pretty
>> hard and were able to watch it keep up, if it were run frequently.
>> There's a one-time penalty, if you've been running it, say, daily or
>> less frequently, but if you run it hourly, it should keep up.
>>
>> gerry
>>
>> On Wed, Oct 28, 2015 at 10:39 AM, Steve Emmerson <emmerson@xxxxxxxx
>> <mailto:emmerson@xxxxxxxx>> wrote:
>>
>> LDMers,
>>
>> On Wed, Oct 28, 2015 at 9:28 AM, Donna Cote <d-cote@xxxxxxxx
>> <mailto:d-cote@xxxxxxxx>> wrote:
>>
>> I would like to ask for a more io-friendly scour utility.
>>
>>
>> It's on my list (see <https://github.com/Unidata/LDM/issues/27>.
>> Can't say when I'll get around to it, though.
>>
>> Regards,
>> Steve Emmerson
>>
>> _______________________________________________
>> ldm-users mailing list
>> ldm-users@xxxxxxxxxxxxxxxx <mailto:ldm-users@xxxxxxxxxxxxxxxx>
>> For list information or to unsubscribe, visit:
>> http://www.unidata.ucar.edu/mailing_lists/
>> --
>> Gerry Creager
>> NSSL/CIMMS
>> 405.325.6371
>> ++++++++++++++++++++++
>> “Big whorls have little whorls,
>> That feed on their velocity;
>> And little whorls have lesser whorls,
>> And so on to viscosity.”
>> Lewis Fry Richardson (1881-1953)
>>
>> _______________________________________________
>> ldm-users mailing list
>> ldm-users@xxxxxxxxxxxxxxxx
>> For list information or to unsubscribe, visit:
>> http://www.unidata.ucar.edu/mailing_lists/
>
> --
> +----------------------------------------------------------------------+
> * Tom Yoksas UCAR Unidata Program *
> * (303) 497-8642 (last resort) P.O. Box 3000 *
> * yoksas@xxxxxxxx Boulder, CO 80307 *
> * Unidata WWW Service http://www.unidata.ucar.edu/ *
> +----------------------------------------------------------------------+
>
> _______________________________________________
> ldm-users mailing list
> ldm-users@xxxxxxxxxxxxxxxx
> For list information or to unsubscribe, visit:
> http://www.unidata.ucar.edu/mailing_lists/
_______________________________________________
ldm-users mailing list
ldm-users@xxxxxxxxxxxxxxxx
For list information or to unsubscribe, visit:
http://www.unidata.ucar.edu/mailing_lists/
