Just a followup on your post to linux-scsi...
H/W:
2xPII@300Mhz system (but not SMP), 256MB memory, Adaptec 2944UW Diff as
SCSI controller.
S/W:
Fresh out of the box RH 5.2 (2.0.36) system
...
scsi1 : Adaptec AHA274x/284x/294x (EISA/VLB/PCI-Fast SCSI) 5.1.2/3.2.4
<Adaptec AHA-2944 Ultra SCSI host adapter>
...
scsi : 3 hosts.
Vendor: MEGADRV Model: EV1000 Rev: 0205
Type: Direct-Access ANSI SCSI revision: 02
Detected scsi disk sda at scsi1, channel 0, id 5, lun 0
(scsi1:0:5:0) Synchronous at 40.0 Mbyte/sec, offset 8.
SCSI device sda: hdwr sector= 512 bytes. Sectors= 318620160 [155576 MB] [155.6 GB]
sda: sda1
...
mkfs of /dev/sda1 succeeds (after a pretty long wait):
ds3.nas.nasa.gov > df -k /dev/sda1
Filesystem 1024-blocks Used Available Capacity Mounted on
/dev/sda1 142447991 13 134482551 0% /mnt
ds3.nas.nasa.gov > lmdd of=/mnt/fred3 bs=8k count=40000
312.50 MB in 19.33 seconds (16.1641 MB/sec)
(these unit is a large RAID-V box- the 16MB/s at 300MB, which blows the
buffer cache is about half of what this box has been measured doing).
ds3.nas.nasa.gov > lmdd if=/mnt/fred3 bs=64k
312.50 MB in 23.26 seconds (13.4335 MB/sec)
Reads are a little worse.
But I'd say that, yes, large 130GB or larger filesystems work. I suspect
that the problems you were experiencing had more to do with large amounts
of primary memory. I believe that archives of linux-kernel can tell you
what these issues are for 2.0.X kernels.
-matt
-
To unsubscribe from this list: send the line "unsubscribe linux-scsi" in
the body of a message to [EMAIL PROTECTED]
