Re: Performance problem (I/O)

From: Peter da Silva (peter_at_abbnm.com)
Date: 03/20/04

  • Next message: Bob Harris: "Re: Performance problem (I/O)" 
    Date: Sat, 20 Mar 2004 00:12:23 +0000 (UTC)

    In article <harris-DCF0F6.18530419032004@cacnews.cac.cpqcorp.net>,
    Bob Harris <harris@zk3.dec.com> wrote:
    > Not having cylinder groups may not have anything to do with small file
    > write performance. This could be due to the way the last 8K allocation
    > of a small file is managed. For space efficency, files under 150K tend
    > to have the last 8K of the file stored in a frag of from 1K to 7K in
    > length. But while the is being written, a full 8K is allocated. When
    > the file is closed, the size of the file is checked and if a 10% saving
    > in space can be obtained by turning the last 8K into a frag, then a frag
    > is allocated, the end of the flie copied to the frag, and then the
    > original 8K is deallocated.

    UFS does that kind of thing as well, and for the case of small files (<8K)
    the write should be completed and the close performed before anything hits
    the disk... I wouldn't expect actual disk writes for the 8k blocks.

    > In the newer versions of Tru64 UNIX, there is chfsets option to disable
    > this and make all files created from that point forward allocation
    > storage in multiples of 8K. For older versions there is a global
    > variable that can be patched in the kernel to disable frag'ing of a file.

    Huh, I'll see what that does. You know the variable name? 

    -- 
I've seen things you people can't imagine. Chimneysweeps on fire over the roofs
of London. I've watched kite-strings glitter in the sun at Hyde Park Gate.  All
these things will be lost in time, like chalk-paintings in the rain.   `-_-'
Time for your nap.  | Peter da Silva | Har du kramat din varg, idag?    'U`
  • Next message: Bob Harris: "Re: Performance problem (I/O)"

    Relevant Pages

    • Re: Performance problem (I/O)
      ... until after the frag has been created, and just what I/O really occurs. ... allocation will involve modifications of the SBM, ... file) and a transaction will be written to the log. ...
      (comp.unix.tru64)
    • Re: [Lit.] Buffer overruns
      ... part of the issue with page backing store allocation policy is whether ... once a disk location is allocated on ... you can still overcommit a no-dup policy ... ... unixes during the 90s that had "lazy" swap but a dup policty (once ...
      (sci.crypt)
    • Re: ldev lists in classes - DISC
      ... the MPE/iX file space allocation policies but I do remember using a trick on ... You would create a number of disk entries for one disk and few ... MPE/iX R&D Architect ... > If the user wanted to artificially load LDev 2 more heavily, ...
      (comp.sys.hp.mpe)
    • Linux VFS architecture questions
      ... fragmenting the allocation bitmap, catalog file, etc, such that each 1/8 or so of the disk contains its own allocation bitmap describing its contents, its own set of files or directories, etc. ... The allocator would largely try to keep individual btree fragments cohesive, such that one of the 1/8th divisions of the disk would only have pertinent data for itself. ... I'm trying to write up a "Linux Disk-Based Filesystem Developers Guide" based on what I learn, but it's remarkably sparse so far. ...
      (Linux-Kernel)
    • Re: Increase in granularity
      ... for the software to aggregate 8 of these, to form 4096-byte allocation ... making the biggest disk it can manage a gigabyte in size. ... that's a small disk by today's standards, that "standard" file system is ...
      (alt.usage.english)