[Date Prev][Date Next]   [Thread Prev][Thread Next]   [Thread Index] [Date Index] [Author Index]

Re: Much Slower than 7.2?

Ronald W. Heiby wrote:

Hash: SHA1

Monday, December 23, 2002, 12:11:10 PM, Samuel wrote:

On the x86 arch you can't have a swap device more than 2G. You can
have a goodly number of swap devices. (The max is defined in the kernel source.)

That's a pretty big area to search. I've poked around in what I
thought were some likely spots and didn't find it. I did find
something that claims that the number of swap files is 32 (rather than
the 8 documented in mkswap(8)).

Should be include/linux/swap.h. Looks like it's 32 now. At one point I seem to remember it was 8.

Are you certain the issue is memory related?

No. That was a guess. I've read that the VM system has been in a state of flux for some time. Of course, there's a new gcc in RH 8.0 that could be having an impact, too. I suppose grabbing an old executable off a backup would allow me to eliminate that from consideration. Seems hard to believe that the current gcc would be generating code 8 times slower than it was a couple releases back.

Have you tested things to see if your disk io is as fast as it use
to be? ` hdparm -t /dev/$drive`

Well, I don't really know how fast it used to be. However, it is the
same hardware and filesystem that it was before. The data going into
my compilation process has not changed at all since June, when I did
the 6:50 run. The hdparm test shows a read speed of 34.90 MB/sec.

That's pretty normal. Most ide disks hit 35-40, while high end scsi tend towards 50-60.

There is no such thing as obsolete hardware.
Merely hardware that other people don't want.
(The Second Rule of Hardware Acquisition)
Sam Flory  <sflory rackable com>

[Date Prev][Date Next]   [Thread Prev][Thread Next]   [Thread Index] [Date Index] [Author Index]