Hey folks,
I just dived into the ARM world with a new N2100, which I installed
with lenny and Martin Michlmayr's DMA-enhanced kernels, version
2.6.26-17lenny1dma1. Now I am synchronising all my data onto the
device, and I am somewhat shocked by the horrific performance.
hdparm states:
Timing cached reads: 324 MB in 2.00 seconds = 161.81 MB/sec
Timing buffered disk reads: 42 MB in 3.02 seconds = 13.90 MB/sec
Which is about 20% of what I expect of SATA drives.
I am using LVM on top of RAID1. I also use that in many other places
and have never encountered a significant performance drop related to
those layers.
If I copy a file on the drive with rsync (due to the nice progress
display, for the sake of demonstration), I cannot get more than
3MB/s of a sustained rate when copying files between directories on
the same drive.
Strangely, if I cut out the reading and write data received from the
network (nc | tar), then the rate *drops* to about 1.5Mb/s. The
network is fine, MII reports 100baseTx-FD, and writing a download to
/dev/null yields maximum transfer rates.
Is this to be expected, or have I possibly misconfigured something
and should be aiming for much higher rates?
The following is dmesg output from the SATA driver initialisation:
sata_sil 0000:00:03.0: version 2.3
sata_sil 0000:00:03.0: Applying R_ERR on DMA activate FIS errata fix
scsi0 : sata_sil
scsi1 : sata_sil
ata1: SATA max UDMA/100 mmio m512@0x800a0000 tf 0x800a0080 irq 29
ata2: SATA max UDMA/100 mmio m512@0x800a0000 tf 0x800a00c0 irq 29
ata1: link is slow to respond, please be patient (ready=-19)
ata1: SATA link up 1.5 Gbps (SStatus 113 SControl 310)
ata1.00: ATA-8: ST31000528AS, CC34, max UDMA/133
ata1.00: 1953525168 sectors, multi 0: LBA48 NCQ (depth 0/32)
ata1.00: configured for UDMA/100
ata2: SATA link up 1.5 Gbps (SStatus 113 SControl 310)
ata2.00: ATA-7: SAMSUNG HD103UJ, 1AA01118, max UDMA7
ata2.00: 1953525168 sectors, multi 0: LBA48 NCQ (depth 0/32)
ata2.00: configured for UDMA/100
scsi 0:0:0:0: Direct-Access ATA ST31000528AS CC34 PQ: 0 ANSI: 5
scsi 1:0:0:0: Direct-Access ATA SAMSUNG HD103UJ 1AA0 PQ: 0 ANSI: 5
Driver 'sd' needs updating - please use bus_type methods
sd 0:0:0:0: [sda] 1953525168 512-byte hardware sectors (1000205 MB)
sd 0:0:0:0: [sda] Write Protect is off
sd 0:0:0:0: [sda] Mode Sense: 00 3a 00 00
sd 0:0:0:0: [sda] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA
sd 0:0:0:0: [sda] 1953525168 512-byte hardware sectors (1000205 MB)
sd 0:0:0:0: [sda] Write Protect is off
sd 0:0:0:0: [sda] Mode Sense: 00 3a 00 00
sd 0:0:0:0: [sda] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA
sda: sda1
sd 0:0:0:0: [sda] Attached SCSI disk
sd 1:0:0:0: [sdb] 1953525168 512-byte hardware sectors (1000205 MB)
sd 1:0:0:0: [sdb] Write Protect is off
sd 1:0:0:0: [sdb] Mode Sense: 00 3a 00 00
sd 1:0:0:0: [sdb] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA
sd 1:0:0:0: [sdb] 1953525168 512-byte hardware sectors (1000205 MB)
sd 1:0:0:0: [sdb] Write Protect is off
sd 1:0:0:0: [sdb] Mode Sense: 00 3a 00 00
sd 1:0:0:0: [sdb] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA
sdb: sdb1
sd 1:0:0:0: [sdb] Attached SCSI disk
--
.''`. martin f. krafft <madduck@d.o> Related projects:
: :' : proud Debian developer http://debiansystem.info
`. `'` http://people.debian.org/~madduck http://vcs-pkg.org
`- Debian - when you have better things to do than fixing systems
"i believe that the moment is near when by a procedure
of active paranoiac thought, it will be possible
to systematise confusion and contribute to
the total discrediting of the world of reality."
-- salvador dali
Attachment:
digital_signature_gpg.asc
Description: Digital signature (see http://martin-krafft.net/gpg/)