Any way to increase speed?

octavious

New Member
I'm wiping SCSI drives with quad-core Netfinity Servers w/ 2GB RAM in DASD 10-drive hot-swap units.
I am benchmarking performance based on:
# of drives, # of drives in each RAID level, wipe method, and operation runtime.

The problem I am experiencing is speed...
I start DBAN, and am using autonuke until I can get the speek issue resolved. I get the same result with all RAID levels (including 0)
The throughput begins at or around 160 MB/s and then it's like the bottom falls out as it tapers down to 5-15 MB/s over the course of 3 minutes, then the process continues at the 5-15 speed +/- 2MB/s

This happens on the Serveraid onboard and planar channels, I've tried all the different striping options, drive speed settings, etc, with no budge in performance

Has anyone played with DBAN and had similar problems? Any suggestions would be much appreciated.

BTW, saw another post RE bad DMA settings resulting to PIO - I'm trying this now. I'll post back regardless, any suggestions still welcome.

Here's one Dmesg.txt:
Linux version 2.4.30-rc3-dban (root@vmsarge) (gcc version 3.3.5 (Debian 1:3.3.5-8)) #1 Sun Mar 27 22:28:19 EST 2005
BIOS-provided physical RAM map:
BIOS-e820: 0000000000000000 - 000000000009c000 (usable)
BIOS-e820: 000000000009c000 - 00000000000a0000 (reserved)
BIOS-e820: 00000000000e0000 - 0000000000100000 (reserved)
BIOS-e820: 0000000000100000 - 000000003fffb000 (usable)
BIOS-e820: 000000003fffb000 - 0000000040000000 (ACPI data)
BIOS-e820: 00000000fec00000 - 00000000fec01000 (reserved)
BIOS-e820: 00000000fee00000 - 00000000fee01000 (reserved)
BIOS-e820: 00000000fffc0000 - 0000000100000000 (reserved)
Warning only 896MB will be used.
Use a HIGHMEM enabled kernel.
896MB LOWMEM available.
On node 0 totalpages: 229376
zone(0): 4096 pages.
zone(1): 225280 pages.
zone(2): 0 pages.
IBM machine detected. Enabling interrupts during APM calls.
Kernel command line: initrd=initrd.gz root=/dev/ram0 init=/rc quiet nuke="dwipe --autonuke" BOOT_IMAGE=kernel.bzi
Initializing CPU#0
Detected 497.793 MHz processor.
Console: colour VGA+ 80x25
Calibrating delay loop... 992.87 BogoMIPS
Memory: 904168k/917504k available (1585k kernel code, 12936k reserved, 637k data, 344k init, 0k highmem)
Dentry cache hash table entries: 131072 (order: 8, 1048576 bytes)
Inode cache hash table entries: 65536 (order: 7, 524288 bytes)
Mount cache hash table entries: 512 (order: 0, 4096 bytes)
Buffer cache hash table entries: 65536 (order: 6, 262144 bytes)
Page-cache hash table entries: 262144 (order: 8, 1048576 bytes)
CPU: L1 I cache: 16K, L1 D cache: 16K
CPU: L2 cache: 1024K
CPU: After generic, caps: 0383fbff 00000000 00000000 00000000
CPU: Common caps: 0383fbff 00000000 00000000 00000000
CPU: Intel Pentium III (Katmai) stepping 02
Enabling fast FPU save and restore... done.
Enabling unmasked SIMD FPU exception support... done.
Checking 'hlt' instruction... OK.
Checking for popad bug... OK.
POSIX conformance testing by UNIFIX
PCI: PCI BIOS revision 2.10 entry at 0xfd4fc, last bus=5
PCI: Using configuration type 1
PCI: Probing PCI hardware
PCI: Probing PCI hardware (bus 00)
PCI: Discovered peer bus 01
Linux NET4.0 for Linux 2.4
Based upon Swansea University Computer Society NET3.039
Starting kswapd
devfs: v1.12c (20020818) Richard Gooch (rgooch@atnf.csiro.au)
devfs: boot_options: 0x1
Serial driver version 5.05c (2001-07-08) with MANY_PORTS SHARE_IRQ SERIAL_PCI enabled
Floppy drive(s): fd0 is 1.44M
FDC 0 is a National Semiconductor PC87306
RAMDISK driver initialized: 16 RAM disks of 4096K size 512 blocksize
Compaq SMART2 Driver (v 2.4.28)
HP CISS Driver (v 2.4.52)
v2.3 : Micro Memory(tm) PCI memory board block driver
Uniform Multi-Platform E-IDE driver Revision: 7.00beta4-2.4
ide: Assuming 33MHz system bus speed for PIO modes; override with idebus=xx
PIIX4: IDE controller at PCI slot 00:13.1
PIIX4: chipset revision 1
PIIX4: not 100% native mode: will probe irqs later
ide0: BM-DMA at 0xffa0-0xffa7, BIOS settings: hda:pio, hdb:pio
hda: CRD-8322B, ATAPI CD/DVD-ROM drive
ide0 at 0x1f0-0x1f7,0x3f6 on irq 14
SCSI subsystem driver Revision: 1.00
Loading Adaptec I2O RAID: Version 2.4 Build 5
Detecting Adaptec I2O RAID controllers...
Red Hat/Adaptec aacraid driver (1.1-3 Mar 27 2005 22:32:23)
scsi1 : IBM PCI ServeRAID 7.10.18 Build 731 <ServeRAID II>
Vendor: IBM Model: SERVERAID Rev: 1.00
Type: Direct-Access ANSI SCSI revision: 02
Vendor: IBM Model: SERVERAID Rev: 1.00
Type: Direct-Access ANSI SCSI revision: 02
Vendor: IBM Model: SERVERAID Rev: 1.00
Type: Direct-Access ANSI SCSI revision: 02
Vendor: IBM Model: SERVERAID Rev: 1.00
Type: Direct-Access ANSI SCSI revision: 02
Vendor: IBM Model: SERVERAID Rev: 1.00
Type: Direct-Access ANSI SCSI revision: 02
Vendor: IBM Model: SERVERAID Rev: 1.00
Type: Direct-Access ANSI SCSI revision: 02
Vendor: IBM Model: SERVERAID Rev: 1.00
Type: Processor ANSI SCSI revision: 02
Vendor: SDR Model: GEM200 Rev: 2
Type: Processor ANSI SCSI revision: 02
scsi: <fdomain> Detection failed (no card)
NCR53c406a: no available ports found
sym53c416.c: Version 1.0.0-ac
Failed initialization of WD-7000 SCSI card!
IBM MCA SCSI: Version 4.0b
IBM MCA SCSI: No Microchannel-bus present --> Aborting.
This machine does not have any IBM MCA-bus
or the MCA-Kernel-support is not enabled!
DC390: 0 adapters found
megaraid: v1.18k (Release Date: Thu Aug 28 10:05:11 EDT 2003)
megaraid: no BIOS enabled.
aec671x_detect:
GDT-HA: Storage RAID Controller Driver. Version: 3.04
GDT-HA: Found 0 PCI Storage RAID Controllers
3ware Storage Controller device driver for Linux v1.02.00.037.
3w-xxxx: No cards found.
nsp32: loading...
libata version 1.10 loaded.
Attached scsi disk sda at scsi1, channel 0, id 0, lun 0
Attached scsi disk sdb at scsi1, channel 0, id 1, lun 0
Attached scsi disk sdc at scsi1, channel 0, id 2, lun 0
Attached scsi disk sdd at scsi1, channel 0, id 3, lun 0
Attached scsi disk sde at scsi1, channel 0, id 4, lun 0
Attached scsi disk sdf at scsi1, channel 0, id 5, lun 0
SCSI device sda: 17772544 512-byte hdwr sectors (9100 MB)
Partition check:
/dev/scsi/host1/bus0/target0/lun0:
SCSI device sdb: 17772544 512-byte hdwr sectors (9100 MB)
/dev/scsi/host1/bus0/target1/lun0:
SCSI device sdc: 17772544 512-byte hdwr sectors (9100 MB)
/dev/scsi/host1/bus0/target2/lun0:
SCSI device sdd: 17772544 512-byte hdwr sectors (9100 MB)
/dev/scsi/host1/bus0/target3/lun0:
SCSI device sde: 17772544 512-byte hdwr sectors (9100 MB)
/dev/scsi/host1/bus0/target4/lun0:
SCSI device sdf: 17772544 512-byte hdwr sectors (9100 MB)
/dev/scsi/host1/bus0/target5/lun0:
Attached scsi generic sg6 at scsi1, channel 0, id 15, lun 0, type 3
Attached scsi generic sg7 at scsi1, channel 2, id 15, lun 0, type 3
RAMDISK: Compressed image found at block 0
Freeing initrd memory: 154k freed
VFS: Mounted root (cramfs filesystem) readonly.
Mounted devfs on /dev
Freeing unused kernel memory: 344k freed

Himem manager? What Can I do to address this?
It looks like the SCSI card is not initializing? Is that my issue?
 

dajhorn

Member
The throughput begins at or around 160 MB/s and then it's like the bottom falls out as it tapers down to 5-15 MB/s over the course of 3 minutes, then the process continues at the 5-15 speed +/- 2MB/s
This happens because the throughput calculation does not adjust for the first write, which bursts as the buffers are filled. The 5-15 MB/s that you are seeing afterwards is likely an accurate measure of actual maximum unbuffered throughput.


I am benchmarking performance based on:
# of drives, # of drives in each RAID level, wipe method, and operation runtime.
DBAN is an inappropriate tool for general benchmarking. Use something like bonnie instead.

This happens on the Serveraid onboard and planar channels, I've tried all the different striping options, drive speed settings, etc, with no budge in performance.
DBAN is not intended for use with hardware RAID implementations. YMMV. If you must use DBAN with such equipment, then switch the controller to JBOD mode.

BTW, saw another post RE bad DMA settings resulting to PIO - I'm trying this now. I'll post back regardless, any suggestions still welcome.
This issue does not apply to the IBM ServeRAID product.

Himem manager? What Can I do to address this?
Ignore this warning, which is happening because you have more than 896MB of memory in the computer. DBAN is not optimized for large computers.

It looks like the SCSI card is not initializing? Is that my issue?
No.
 
Top