Tim wrote:
Mike McCarty:
From reading Mike's postings over the last several days, it seems he's
one of those that forever argues "I didn't say that", threads are only
between original poster and first respondent and about the original
words spoken, and is adamant that everyone must agree with him.
Well, I'm sorry I impress you that way. I try to choose my words
carefully when posting, and usually mean very much literally
what I say, except when using irony (humorous or otherwise).
I hope what I put in here doesn't sound anything but cordial.
I've read it several times, trying to remove anything which
might sound condemnatory.
What I argued were these points:
(1) ext3 is subject to fragmentation
(2) fragmentation has effects on disc performance for at
least these reasons:
(a) most if not all modern discs actually do
read-ahead and if sequential reads
are taking place, then these can help
since we have parallel processing
in our favor
(b) any caching algorithm has bad cases, and
so one cannot rely on caching to make
up for all effects of fragmentation,
since the caching may make the
performance *worse*
(3) exactly what the effects of fragmentation are depend
heavily on how the file is used, and a fragmented disc
may actually have better response than a contiguous one
(especially with multitasking this is relevant, since
multiple files may be involved)
(4) not all effects of fragmentation are performance
related, and if one is trying to reallocate partitions
it may make sense to have a defragmenter
I did not argue any of these points:
(1) ext3 fragmentation has effects which are noticeable
under most ordinary circumstances to ordinary users
of Linux
(2) the caching algorithm used in Linux is inadequate
for many or any of the users of Linux
(3) I need to have an ext3 defragmentation program
(4) I am being adversely affected by fragmentation
(5) I am worried about or spend time concerned over
fragmentation on my machine
(6) anyone else should be worried about, or spend time
fretting over any effects of fragmentation when
using ext3 with Linux
(7) anything other than what is listed above (unless
I inadvertently overlooked something) in my list of
points I argued (1)-(4).
I have seen people, including you, respond to points I did not argue.
For example, your statement and my reply
>> I don't worry about fragmentation any more than I worry about other
>> technicalities of how the data is put onto the drive.
> Arguing against claims I haven't made.
I never claimed I was "worried" or "troubled" by fragmentation.
What I claimed is that it exists, and it has effects.
Then Ed chimed in with
> *sigh*
> Not true, Mike. Both the original poster and you discussed
> performance:
>https://www.redhat.com/archives/fedora-list/2005-December/msg03298.html
>https://www.redhat.com/archives/fedora-list/2005-December/msg03340.html
I pointed out that "discuss" and "worry about" are not synonymous.
This is an exact quote from my reply to Ed:
Specifically not true. "Discussion" and "worry" are two different
things. I am myself not worried about whatever the effects on
performance might be, since I am not experiencing any problems
with disc performance. I have not made any claims that whatever
performance hits there are are significant to me. Whether they
are significant to others depends on a variety of factors. I also
don't argue that *you* experience problems with disc performance.
Do you disagree that one may discuss something which one does
not consider significant or worrisome? What was significant to
me was what I considered to be counter-factual claims, not
disc performance, and those are what I was responding to.
Counterfactual claims *are* worrisome to me. In pursuing them,
I wound up discussing disc performance. But for me disc
performance is not the issue.
The reason I got into this thread in the first place was that
I saw what seemed to me to be an absolute post that ext3 is inherently
immune to fragmentation, and it just does not/cannot occur. That is
demonstrably false. Another post seemed to flatly state that because
Linux uses caching, any fragmentation is irrelevant except for the first
read of the disc. This is also demonstrably, and even provably, false.
I'm not trying to weasel out, as you can see, since I am here,
in what I hope are very plain words, stating what I have tried
to claim, and what I have not tried to claim, and what my motives
were.
Briefly, my motive is to correct flat statements which seem
to me to be factually incorrect, some of them seeming to
contradict theorems of computer science.
I don't give a rip about the fragmentation on my machine, since
it doesn't seem to cause me any problems whatsoever.
I do care when people make statements to the effect that ext3
is not subject to fragmentation, or that caching can nullify
the effects of fragmentation.
I also care when people argue in reply to me, against points I haven't
made and wouldn't make, responding to words which I did not and would
not use. Especially when I am pretty careful not to say things I don't
intend.
Now, to take your claims about me in turn...
> From reading Mike's postings over the last several days, it seems he's
> one of those that forever argues "I didn't say that", threads are only
I think that I have demonstrated that you, at least, have argued against
points I haven't intended to make. When someone says "I didn't argue
that", people with open minds tend to ask "Oh? Then I must have
misunderstood. What point *did* you intend to make?" Argumentative
and closed minded people tend to draw conclusions and impute motives.
> between original poster and first respondent and about the original
> words spoken,
Since I specifically addressed issues that the OP and the OR did
not discuss, I guess that this doesn't seem quite on the mark, either.
I will confess to trying to guide some of the thread back on track
of helping the poor OP actually get a response which might be
useful to him.
> and is adamant that everyone must agree with him.
I'll give you right here the chance to argue against
any or all of the points (1)-(4) I argue for above
which you believe to be incorrect. I'd be glad to learn
which of my beliefs on these points are inaccurate.
P.S. personal comments are better reserved to personal e-mail,
with a return address which does not give the appearance of
being bogus, don't you think?
Mike
--
p="p=%c%s%c;main(){printf(p,34,p,34);}";main(){printf(p,34,p,34);}
This message made from 100% recycled bits.
You have found the bank of Larn.
I can explain it for you, but I can't understand it for you.
I speak only for myself, and I am unanimous in that!
