Re: NFS file truncating

From: pSeries AIX Geek (aixgeek@YAHOO.COM)
Date: Thu Feb 12 2004 - 17:37:15 EST


The percentage that a file system is full is rarely
the problem. Free space is more important than
percentage.

The behavior you're seeing is consistent with
fragmentation, especially if you've got a lot of file
creations and deletions. The next time this happens,
it would be interesting to see if an immediate
defragfs immediately clears up the problem.

You might get to the point where, even though you've
got free space, you just can't ever get the file
system to a point where you've got contiguous free
space, and then you'll have to look at free space.

pAG

--- cbaker@GOODYEAR.COM wrote:
> I do not seem to have any problems creating files on
> this filesystem. For
> that matter, I don't usually have problems with this
> rcp of files of all
> sizes into this filesystem via NFS. But, a few
> times a week, for the past
> couple of weeks, files will not copy completely over
> and I will be left
> with all files larger than 4 MB being truncated to
> exactly 4 MB.
>
> Could it be that even though I have over 70 GB free
> in this JFS, I am over
> 95% full?
>
> Christopher M. Baker
> Senior Technical Support Analyst
> DSE/TCO
> Goodyear Tire and Rubber Company
>
> =================================================
> Contains Confidential and/or Proprietary
> Information.
> May not be copied or disseminated without the
> expressed
> written consent of The Goodyear Tire & Rubber
> Company.
> =================================================
>
>
>
>
> pSeries AIX Geek
> <aixgeek@YAHOO.C To:
> aix-l@Princeton.EDU
> OM> cc:
> (bcc: Chris Baker/NA/GDYR)
> Sent by: IBM AIX
> Subject: Re: NFS file truncating
> Discussion List
> <aix-l@Princeton
> .EDU>
>
>
> 02/12/2004 11:57
> AM
> Please respond
> to IBM AIX
> Discussion List
>
>
>
>
>
>
> So what happens now when you try to create a file
> >4MB?
>
> It looks like from your successive defragfs runs
> that
> it becomes more and more efficient.
>
> -pAG
>
> --- cbaker@GOODYEAR.COM wrote:
> > Here is the completed output of "defragfs -r"
> > followed bu a few "defragfs"
> >
> > > defragfs -r /hpc/light-5
> > statistics before running defragfs:
> > number of free fragments 9200753
> > number of allocated fragments 203316111
> > number of free spaces shorter than a block 88506
> > number of free fragments in short free spaces
> 460607
> >
> > statistics after running defragfs:
> > number of free spaces shorter than a block 56651
> > number of free fragments in short free spaces
> 378252
> >
> > other statistics:
> > number of fragments moved 912128
> > number of logical blocks moved 298731
> > number of allocation attempts 67055
> > number of exact matches 22711
> >
> >
> > > defragfs /hpc/light-5
> > statistics before running defragfs:
> > number of free fragments 9146354
> > number of allocated fragments 203370510
> > number of free spaces shorter than a block 88511
> > number of free fragments in short free spaces
> 460720
> >
> > statistics after running defragfs:
> > number of free spaces shorter than a block 56794
> > number of free fragments in short free spaces
> 378493
> >
> > other statistics:
> > number of fragments moved 782335
> > number of logical blocks moved 290520
> > number of allocation attempts 66536
> > number of exact matches 22732
> >
> >
> > > defragfs /hpc/light-5
> > statistics before running defragfs:
> > number of free fragments 8634952
> > number of allocated fragments 203881912
> > number of free spaces shorter than a block 57272
> > number of free fragments in short free spaces
> 380907
> >
> > statistics after running defragfs:
> > number of free spaces shorter than a block 53739
> > number of free fragments in short free spaces
> 372284
> >
> > other statistics:
> > number of fragments moved 99185
> > number of logical blocks moved 65488
> > number of allocation attempts 11215
> > number of exact matches 2401
> >
> >
> > > defragfs /hpc/light-5
> > statistics before running defragfs:
> > number of free fragments 7042121
> > number of allocated fragments 205474743
> > number of free spaces shorter than a block 52943
> > number of free fragments in short free spaces
> 375240
> >
> > statistics after running defragfs:
> > number of free spaces shorter than a block 52575
> > number of free fragments in short free spaces
> 373720
> >
> > other statistics:
> > number of fragments moved 68578
> > number of logical blocks moved 27565
> > number of allocation attempts 4508
> > number of exact matches 446
> >
> >
> >
> >
> > Christopher M. Baker
> > Senior Technical Support Analyst
> > DSE/TCO
> > Goodyear Tire and Rubber Company
> >
> > =================================================
> > Contains Confidential and/or Proprietary
> > Information.
> > May not be copied or disseminated without the
> > expressed
> > written consent of The Goodyear Tire & Rubber
> > Company.
> > =================================================
> >
> >
> >
> >
> > cbaker@GOODYEAR.
> > COM To:
> > aix-l@Princeton.EDU
> > Sent by: IBM AIX cc:
> > (bcc: Chris Baker/NA/GDYR)
> > Discussion List
> > Subject: Re: NFS file truncating
> > <aix-l@Princeton
> > .EDU>
> >
> >
> > 02/11/2004 06:29
> > PM
> > Please respond
> > to IBM AIX
> > Discussion List
> >
> >
> >
> >
> >
> >
> > /dev/nfs5lv00 1700134912 73600168 96% 337928
> > 3% /hpc/light-5
> >
> > rdsnfs5:root: /
> > > defragfs -q /hpc/light-5
> > statistics before running defragfs:
> > number of free fragments 9199989
> > number of allocated fragments 203316875
> > number of free spaces shorter than a block 88510
> > number of free fragments in short free spaces
> 460609
> >
>
=== message truncated ===

__________________________________
Do you Yahoo!?
Yahoo! Finance: Get your refund fast by filing online.
http://taxes.yahoo.com/filing.html



This archive was generated by hypermail 2.1.7 : Wed Apr 09 2008 - 22:17:35 EDT