Buffalo NAS-Central Forums

Welcome to the Linkstation Wiki community
It is currently Fri Aug 17, 2018 4:56 am

All times are UTC+01:00




Post new topic  Reply to topic  [ 15 posts ] 
Author Message
PostPosted: Fri Nov 06, 2009 10:32 pm 
Offline
Newbie

Joined: Mon Apr 16, 2007 11:32 pm
Posts: 19
Location: United Kingdom (Great Britain)
Is there anything I can do to speed up write performance on my lspro gl-250, now running davy_gravy's lovely armel image? I set up my main data partition with ext4, shared it out via samba, and told my backup program to start putting all the data back from my backup drive onto the linkstation - about 200GB of data, and after 48 hours, it was still only 25% done.

I've tried various smb.conf tweaks, but by now I'm not convinced that it's samba that's the problem - I get similarly slow write speeds when trying to put the files on via pureftpd/ftp. With both samba and ftp, writing files goes in jumps - for about 5 seconds, data will seem to be transferring quite quickly, and then it will jam up for about 15 seconds before the next burst goes through. During the freeze period, any ssh session(s) I have to the ls will also be completely unresponsive... but "top" doesn't seem to suggest that the CPU is under any kind of strain.

I've noticed that even just cp'ing a file takes a lot longer than it used to under Freelink, if that's important (even between partitions using ext2/3, so maybe it's not an ext4 problem)

... having said all that, I've noticed that reading a file off of the data partition is still nice and fast. It just seems to be writing that's s-l-o-w

This is in no way a criticism of dg's work - it's fantastic to be able to run a current debian config on my trust old linkstation. I just wonder if anyone has any ideas what I can do? :cry:


Top
   
PostPosted: Sun Nov 08, 2009 6:47 am 
Offline
Regular Member
User avatar

Joined: Mon Oct 08, 2007 6:34 am
Posts: 334
If you don't have this line in your smb.conf give it a try:

Code:
socket options = TCP_NODELAY IPTOS_LOWDELAY SO_RCVBUF=4096 SO_SNDBUF=8192

_________________
KuroHG - UBoot 1.2, foonas-em & Debian Wheezy - 3.4 Kernel
Kurobox Pro - Dave's Lenny-armel
LS-WVL - opened
LS-XHL - Squeeze Bootstrap
LS-VL - Squeeze Bootstrap


Top
   
PostPosted: Sun Nov 08, 2009 3:34 pm 
Offline
Site Admin
User avatar

Joined: Mon Aug 28, 2006 1:15 am
Posts: 2606
nemo700 wrote:
Is there anything I can do to speed up write performance on my lspro gl-250, now running davy_gravy's lovely armel image? :cry:


which kernel are you running?
Code:
uname -r

_________________
LS1 (foonas, nfs, Tranmission & p910nd print server, Firefly for my Roku)
LS-HG500 (Lenny)
Various LS-Pros v1,v2 (unbricked w/ serial & jtag)
KuroPro, LS2 & KuroHG (foonas)
Working on davysweather.dyndns.org lately...

=> wooohooo!
wooohooo!
Unknown command 'wooohooo!' - try 'help'


Top
   
PostPosted: Sun Nov 08, 2009 7:40 pm 
Offline
Newbie

Joined: Mon Apr 16, 2007 11:32 pm
Posts: 19
Location: United Kingdom (Great Britain)
stonie wrote:
If you don't have this line in your smb.conf give it a try:

Code:
socket options = TCP_NODELAY IPTOS_LOWDELAY SO_RCVBUF=4096 SO_SNDBUF=8192


That was my first thought, that there was something wrong with my smb.conf - but I've already tried several variants of "socket options" (culled from various forum threads), including what you suggest, with no luck. Eventually, I even tried getting pureftpd up and running, but that has just the same behaviour as samba - ie bursts of fast write speed, interspersed with long pauses.

This, coupled with the (lack of) speed of copying files between partitions on the ls itself, makes me think it's something internal to the system itself, but I can't think what... :(

davy_gravy wrote:
which kernel are you running?
Code:
uname -r


I did wonder about that, too - but I get the same problem whether I'm running the stock 2.6.29.1 kernel that came with your distribution, or the 2.6.31.1 kernel that deb posted in the long armel thread (which is what I'm currently using)

The only other thought I had was that perhaps there was something wrong with ext4 handling, but I get just as bad performance if I use ext3 instead (maybe even slightly worse)

I'm stumped!


Top
   
PostPosted: Sun Nov 08, 2009 7:55 pm 
Offline
Site Admin
User avatar

Joined: Mon Aug 28, 2006 1:15 am
Posts: 2606
just to check, does uname -a actual return 2.6.31.x ? (for you?)
Code:
armel:~# uname -a
Linux armel.lenny.local 2.6.29.1 #1 PREEMPT Mon Apr 6 22:33:31 CDT 2009 armv5tel GNU/Linux
armel:~#


Have you tried transfers w/ a different host/computer? I'm assuming these is a wired transfer.

Is your router one w/ Gb Enet?

What kind of performance do you get w/ nfs or afp?

This sounds like it could be a problem w/ your local network's settings or topology.

With my armel lenny LSProV2 I get about 13-15MB/sec write. Read from it is 15-20MB sec.

_________________
LS1 (foonas, nfs, Tranmission & p910nd print server, Firefly for my Roku)
LS-HG500 (Lenny)
Various LS-Pros v1,v2 (unbricked w/ serial & jtag)
KuroPro, LS2 & KuroHG (foonas)
Working on davysweather.dyndns.org lately...

=> wooohooo!
wooohooo!
Unknown command 'wooohooo!' - try 'help'


Top
   
PostPosted: Fri Nov 13, 2009 12:48 pm 
Offline
Newbie

Joined: Mon Apr 16, 2007 11:32 pm
Posts: 19
Location: United Kingdom (Great Britain)
davy_gravy wrote:
just to check, does uname -a actual return 2.6.31.x ? (for you?)
Code:
armel:~# uname -a
Linux armel.lenny.local 2.6.29.1 #1 PREEMPT Mon Apr 6 22:33:31 CDT 2009 armv5tel GNU/Linux
armel:~#

Yep -

Code:
Linux LS-GL 2.6.31.1 #1 Thu Oct 1 22:18:33 EST 2009 armv5tel GNU/Linux

(or as above if I switch back to the stock kernel that came with your distrib)

davy_gravy wrote:
Have you tried transfers w/ a different host/computer? I'm assuming these is a wired transfer.

Yes, the connection is wired, and I get the same problem with 2 different computers accessing the ls via samba (both running Windows XP (yeah, yeah, I know))

davy_gravy wrote:
Is your router one w/ Gb Enet?

Yes. I tried playing around with jumbo frames settings on the desktop machine (setting that to 7K, and changing the mtu on the ls to 7000), in case that helped, but that only made things worse, in that the pauses between bursts of copying would be even longer.

I've even swapped out all my old network kit (netgear gs605 + linksys befsx41) for a new router (d-link 655), but that doesn't make any difference either (apart from the fact that I now have a much nicer router :) )

If it helps, here's the output from ifconfig -

Code:
eth0      Link encap:Ethernet  HWaddr 00:16:01:41:85:b1
          inet addr:192.168.1.2  Bcast:192.168.255.255  Mask:255.255.255.0
          inet6 addr: fe80::216:1ff:fe41:581b/64 Scope:Link
          UP BROADCAST RUNNING MULTICAST  MTU:1500  Metric:1
          RX packets:11539103 errors:0 dropped:0 overruns:0 frame:0
          TX packets:6192250 errors:0 dropped:0 overruns:0 carrier:0
          collisions:0 txqueuelen:1000
          RX bytes:4211363296 (3.9 GiB)  TX bytes:359887571 (343.2 MiB)
          Interrupt:21

lo        Link encap:Local Loopback
          inet addr:127.0.0.1  Mask:255.0.0.0
          inet6 addr: ::1/128 Scope:Host
          UP LOOPBACK RUNNING  MTU:16436  Metric:1
          RX packets:8 errors:0 dropped:0 overruns:0 frame:0
          TX packets:8 errors:0 dropped:0 overruns:0 carrier:0
          collisions:0 txqueuelen:0
          RX bytes:576 (576.0 B)  TX bytes:576 (576.0 B)

davy_gravy wrote:
What kind of performance do you get w/ nfs or afp?

Haven't tried this yet, based on the benchmarks below, and the fact that I already tried another network protocol (ftp) that was also slow; I've been too busy with real life to learn all about nfs, afp, and how to get windows to play nicely with them, too :)

Do you really think it's worth a go?

davy_gravy wrote:
This sounds like it could be a problem w/ your local network's settings or topology.

With my armel lenny LSProV2 I get about 13-15MB/sec write. Read from it is 15-20MB sec.

:( Here's what I get using mine -

time to copy a 150MB on to the linkstation via samba - 4 minutes 15 seconds - 0.6MB/sec
time to read that file back off of the linkstation via samba - 11 seconds - 13.6MB/sec
time to cp the file from /dev/sda6 (ext4) to /dev/sda2 (ext3) - 3 minutes 35 seconds - 0.7MB/sec

It's especially this last result that makes me suspicious that this isn't a network problem; what sort of throughput do other people see on their systems?

The only other thought I've had is that perhaps it's a memory problem, but memtest86+ only seems to work at boot-time (...). I've tried using memtester instead. That doesn't find any errors if I ask it to run "memtester 100", but if I try anything much larger than that, memtester is just killed (presumably because the system sees it as a memory-hogging nuisance :) )

edit: thought I might add my /etc/fstab in case that gives any clues, too -

Code:
/dev/sda1  /boot      ext2            noauto,noatime   1 2
/dev/sda2  /         ext3            defaults,noatime,nodiratime   0 1
/dev/sda5  none      swap            sw                        0 0
proc       /proc     proc            defaults                0 0
shm        /dev/shm  tmpfs           nodev,nosuid,noexec    0 0
/dev/sda6  /mnt/disk1  ext4            defaults,noatime,nodiratime 0 0


Top
   
PostPosted: Fri Nov 13, 2009 11:47 pm 
Offline
Site Admin
User avatar

Joined: Mon Aug 28, 2006 1:15 am
Posts: 2606
nemo700 wrote:
time to copy a 150MB on to the linkstation via samba - 4 minutes 15 seconds - 0.6MB/sec
time to read that file back off of the linkstation via samba - 11 seconds - 13.6MB/sec
time to cp the file from /dev/sda6 (ext4) to /dev/sda2 (ext3) - 3 minutes 35 seconds - 0.7MB/sec

It's especially this last result that makes me suspicious that this isn't a network problem; what sort of throughput do other people see on their systems?



That last reading/speed is very suspect... maybe there is some hardware/harddrive problem. That is just too slow for hdd to hdd writing.

Maybe there is some diagnostic tool you can run on it? Are there any messages in the boot log (see dmesg) about dma or sata? Or have you run smarttools on it?

_________________
LS1 (foonas, nfs, Tranmission & p910nd print server, Firefly for my Roku)
LS-HG500 (Lenny)
Various LS-Pros v1,v2 (unbricked w/ serial & jtag)
KuroPro, LS2 & KuroHG (foonas)
Working on davysweather.dyndns.org lately...

=> wooohooo!
wooohooo!
Unknown command 'wooohooo!' - try 'help'


Top
   
PostPosted: Sat Nov 14, 2009 1:58 pm 
Offline
Newbie

Joined: Mon Apr 16, 2007 11:32 pm
Posts: 19
Location: United Kingdom (Great Britain)
davy_gravy wrote:
That last reading/speed is very suspect... maybe there is some hardware/harddrive problem. That is just too slow for hdd to hdd writing.

That's what I thought, too :(

davy_gravy wrote:
Maybe there is some diagnostic tool you can run on it? Are there any messages in the boot log (see dmesg) about dma or sata? Or have you run smarttools on it?

I'm by no means a linux guru, but I can't see anything obviously worrying in dmesg, apart from the couple of non-fatal sounding "Clearing invalid memory bank" messages near the beginning - but maybe wiser eyes than mine can see something screwy -

Code:
[    0.000000] Linux version 2.6.31.1 (root@linky) (gcc version 4.3.2 (Debian 4.3.2-1.1) ) #1 Thu Oct 1 22:18:33 EST 2009
[    0.000000] CPU: Feroceon [41069260] revision 0 (ARMv5TEJ), cr=a0053177
[    0.000000] CPU: VIVT data cache, VIVT instruction cache
[    0.000000] Machine: Buffalo Linkstation Pro/Live
[    0.000000] Clearing invalid memory bank 0KB@0xffffffff
[    0.000000] Clearing invalid memory bank 0KB@0xffffffff
[    0.000000] Clearing invalid memory bank 0KB@0xffffffff
[    0.000000] Ignoring unrecognised tag 0x00000000
[    0.000000] Ignoring unrecognised tag 0x00000000
[    0.000000] Ignoring unrecognised tag 0x00000000
[    0.000000] Ignoring unrecognised tag 0x41000403
[    0.000000] Memory policy: ECC disabled, Data cache writeback
[    0.000000] On node 0 totalpages: 32768
[    0.000000] free_area_init_node: node 0, pgdat c0412750, node_mem_map c0432000
[    0.000000]   Normal zone: 256 pages used for memmap
[    0.000000]   Normal zone: 0 pages reserved
[    0.000000]   Normal zone: 32512 pages, LIFO batch:7
[    0.000000] Built 1 zonelists in Zone order, mobility grouping on.  Total pages: 32512
[    0.000000] Kernel command line: netconsole=6666@192.168.11.150/,@192.168.11.149/ root=/dev/sda2 rw
[    0.000000] PID hash table entries: 512 (order: 9, 2048 bytes)
[    0.000000] Dentry cache hash table entries: 16384 (order: 4, 65536 bytes)
[    0.000000] Inode-cache hash table entries: 8192 (order: 3, 32768 bytes)
[    0.000000] Memory: 128MB = 128MB total
[    0.000000] Memory: 125496KB available (3616K code, 274K data, 128K init, 0K highmem)
[    0.000000] NR_IRQS:64
[    0.000326] Console: colour dummy device 80x30
[    0.000358] console [tty0] enabled
[    0.001041] Calibrating delay loop... 266.24 BogoMIPS (lpj=1331200)
[    0.240467] Mount-cache hash table entries: 512
[    0.241265] CPU: Testing write buffer coherency: ok
[    0.246966] NET: Registered protocol family 16
[    0.250781] Orion ID: MV88F5182-A2. TCLK=166666667.
[    0.288606] bio: create slab <bio-0> at 0
[    0.293471] SCSI subsystem initialized
[    0.293892] libata version 3.00 loaded.
[    0.296175] usbcore: registered new interface driver usbfs
[    0.297117] usbcore: registered new interface driver hub
[    0.297796] usbcore: registered new device driver usb
[    0.305629] NET: Registered protocol family 2
[    0.306528] IP route cache hash table entries: 1024 (order: 0, 4096 bytes)
[    0.309209] TCP established hash table entries: 4096 (order: 3, 32768 bytes)
[    0.309536] TCP bind hash table entries: 4096 (order: 2, 16384 bytes)
[    0.309730] TCP: Hash tables configured (established 4096 bind 4096)
[    0.309813] TCP reno registered
[    0.310103] Switched to high resolution mode on CPU 0
[    0.310606] NET: Registered protocol family 1
[    0.312696] NetWinder Floating Point Emulator V0.97 (double precision)
[    0.316406] VFS: Disk quotas dquot_6.5.2
[    0.316813] Dquot-cache hash table entries: 1024 (order 0, 4096 bytes)
[    0.317730] JFFS2 version 2.2. (NAND) © 2001-2006 Red Hat, Inc.
[    0.318754] msgmni has been set to 245
[    0.321269] alg: No test for stdrng (krng)
[    0.321988] Block layer SCSI generic (bsg) driver version 0.4 loaded (major 253)
[    0.322109] io scheduler noop registered
[    0.322177] io scheduler anticipatory registered
[    0.322250] io scheduler deadline registered
[    0.322455] io scheduler cfq registered (default)
[    0.377367] Serial: 8250/16550 driver, 2 ports, IRQ sharing disabled
[    0.379991] serial8250.0: ttyS0 at MMIO 0xf1012000 (irq = 3) is a 16550A
[    0.382942] serial8250.1: ttyS1 at MMIO 0xf1012100 (irq = 4) is a 16550A
[    0.388145] brd: module loaded
[    0.398207] loop: module loaded
[    0.400242] sata_mv sata_mv.0: version 1.28
[    0.401351] sata_mv sata_mv.0: slots 32 ports 2
[    0.403042] scsi0 : sata_mv
[    0.404187] scsi1 : sata_mv
[    0.404957] ata1: SATA max UDMA/133 irq 29
[    0.405042] ata2: SATA max UDMA/133 irq 29
[    0.405863] MV-643xx 10/100/1000 ethernet driver version 1.4
[    0.407174] mv643xx_eth smi: probed
[    0.412037] net eth0: port 0 with MAC address 00:16:01:41:85:b1
[    0.412599] netconsole: local port 6666
[    0.412679] netconsole: local IP 192.168.11.150
[    0.412747] netconsole: interface eth0
[    0.412811] netconsole: remote port 6666
[    0.412878] netconsole: remote IP 192.168.11.149
[    0.412951] netconsole: remote ethernet address ff:ff:ff:ff:ff:ff
[    0.413037] netconsole: device eth0 not up yet, forcing it
[    0.750147] ata1: SATA link down (SStatus 0 SControl 300)
[    1.260133] ata2: SATA link up 3.0 Gbps (SStatus 123 SControl 300)
[    1.280467] ata2.00: ATA-7: WDC WD2500JS-00NCB1, 10.02E02, max UDMA/133
[    1.280571] ata2.00: 488397168 sectors, multi 0: LBA48 NCQ (depth 31/32)
[    1.300633] ata2.00: configured for UDMA/133
[    1.301519] scsi 1:0:0:0: Direct-Access     ATA      WDC WD2500JS-00N 10.0 PQ: 0 ANSI: 5
[    1.303631] sd 1:0:0:0: [sda] 488397168 512-byte logical blocks: (250 GB/232 GiB)
[    1.304547] sd 1:0:0:0: [sda] Write Protect is off
[    1.304637] sd 1:0:0:0: [sda] Mode Sense: 00 3a 00 00
[    1.305073] sd 1:0:0:0: [sda] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA
[    1.307070]  sda:
[    1.308319] sd 1:0:0:0: Attached scsi generic sg0 type 0
[    1.312296]  sda1 sda2 sda4 < sda5 sda6 >
[    1.341043] sd 1:0:0:0: [sda] Attached SCSI disk
[    3.519434] eth0: link up, 1000 Mb/s, full duplex, flow control disabled
[    3.530355] console [netcon0] enabled
[    3.535371] netconsole: network logging started
[    3.536473] physmap platform flash device: 00040000 at f4000000
[    3.536791] Found: SST 39LF020
[    3.536937] physmap-flash.0: Found 1 x8 devices at 0x0 in 8-bit bank
[    3.537065] number of JEDEC chips: 1
[    3.537160] cfi_cmdset_0002: Disabling erase-suspend-program due to code brokenness.
[    3.537862] RedBoot partition parsing not available
[    3.539236] mtd: Giving out device 0 to physmap-flash.0
[    3.541686] ehci_hcd: USB 2.0 'Enhanced' Host Controller (EHCI) Driver
[    3.541923] orion-ehci orion-ehci.0: Marvell Orion EHCI
[    3.542221] orion-ehci orion-ehci.0: new USB bus registered, assigned bus number 1
[    3.570150] orion-ehci orion-ehci.0: irq 17, io mem 0xf1050000
[    3.590113] orion-ehci orion-ehci.0: USB 2.0 started, EHCI 1.00
[    3.591305] usb usb1: configuration #1 chosen from 1 choice
[    3.592132] hub 1-0:1.0: USB hub found
[    3.592338] hub 1-0:1.0: 1 port detected
[    3.593409] orion-ehci orion-ehci.1: Marvell Orion EHCI
[    3.593624] orion-ehci orion-ehci.1: new USB bus registered, assigned bus number 2
[    3.620153] orion-ehci orion-ehci.1: irq 12, io mem 0xf10a0000
[    3.640162] orion-ehci orion-ehci.1: USB 2.0 started, EHCI 1.00
[    3.641351] usb usb2: configuration #1 chosen from 1 choice
[    3.642176] hub 2-0:1.0: USB hub found
[    3.642384] hub 2-0:1.0: 1 port detected
[    3.644292] ohci_hcd: USB 1.1 'Open' Host Controller (OHCI) Driver
[    3.644881] uhci_hcd: USB Universal Host Controller Interface driver
[    3.645600] sl811: driver sl811-hcd, 19 May 2005
[    3.646168] Initializing USB Mass Storage driver...
[    3.646939] usbcore: registered new interface driver usb-storage
[    3.647094] USB Mass Storage support registered.
[    3.647840] usbcore: registered new interface driver libusual
[    3.648440] usbcore: registered new interface driver ums-alauda
[    3.649051] usbcore: registered new interface driver ums-cypress
[    3.649661] usbcore: registered new interface driver ums-datafab
[    3.650312] usbcore: registered new interface driver ums-freecom
[    3.650921] usbcore: registered new interface driver ums-isd200
[    3.651519] usbcore: registered new interface driver ums-jumpshot
[    3.652122] usbcore: registered new interface driver ums-karma
[    3.652722] usbcore: registered new interface driver ums-onetouch
[    3.653353] usbcore: registered new interface driver ums-sddr09
[    3.653953] usbcore: registered new interface driver ums-sddr55
[    3.654590] usbcore: registered new interface driver sisusb
[    3.655799] mice: PS/2 mouse device common for all mice
[    3.658786] i2c /dev entries driver
[    3.664091] rtc-rs5c372 0-0032: rs5c372a found, 24hr, driver version 0.6
[    3.664947] rtc-rs5c372 0-0032: rtc core: registered rtc-rs5c372 as rtc0
[    3.667282] device-mapper: ioctl: 4.15.0-ioctl (2009-04-01) initialised: dm-devel@redhat.com
[    3.667543] mv_xor_shared mv_xor_shared.0: Marvell shared XOR driver
[    3.700693] mv_xor mv_xor.0: Marvell XOR: ( xor cpy )
[    3.740329] mv_xor mv_xor.1: Marvell XOR: ( xor fill cpy )
[    3.745009] TCP cubic registered
[    3.745140] NET: Registered protocol family 17
[    3.745279] VFP support v0.3: not present
[    3.747119] registered taskstats version 1
[    3.749079] rtc-rs5c372 0-0032: setting system clock to 2009-11-13 21:23:40 UTC (1258147420)
[    3.749363] md: Waiting for all devices to be available before autodetect
[    3.749491] md: If you don't use raid, use raid=noautodetect
[    3.751191] md: Autodetecting RAID arrays.
[    3.751321] md: Scanned 0 and added 0 devices.
[    3.751417] md: autorun ...
[    3.751500] md: ... autorun DONE.
[    3.772980] kjournald starting.  Commit interval 5 seconds
[    3.773534] EXT3 FS on sda2, internal journal
[    3.773700] EXT3-fs: mounted filesystem with ordered data mode.
[    3.773867] VFS: Mounted root (ext3 filesystem) on device 8:2.
[    3.774241] Freeing init memory: 128K
[   11.546879] Adding 506008k swap on /dev/sda5.  Priority:-1 extents:1 across:506008k
[   11.992495] EXT3 FS on sda2, internal journal
[   15.437689] EXT4-fs (sda6): barriers enabled
[   15.464158] kjournald2 starting: pid 884, dev sda6:8, commit interval 5 seconds
[   15.464700] EXT4-fs (sda6): internal journal on sda6:8
[   15.464896] EXT4-fs (sda6): delayed allocation enabled
[   15.465063] EXT4-fs: file extents enabled
[   15.475968] EXT4-fs: mballoc enabled
[   15.476229] EXT4-fs (sda6): mounted filesystem with ordered data mode

All seems to be well at the SMART level, too -

Code:
root@LS-GL:/etc/apt# smartctl -H /dev/sda
smartctl version 5.38 [armv5tel-unknown-linux-gnu] Copyright (C) 2002-8 Bruce Allen
Home page is http://smartmontools.sourceforge.net/

=== START OF READ SMART DATA SECTION ===
SMART overall-health self-assessment test result: PASSED
Please note the following marginal Attributes:
ID# ATTRIBUTE_NAME          FLAG     VALUE WORST THRESH TYPE      UPDATED  WHEN_FAILED RAW_VALUE
190 Airflow_Temperature_Cel 0x0022   062   040   045    Old_age   Always   In_the_past 38

At least, I don't think that's anything to worry about (it sounds like sda might have got a bit hot under the collar once upon a time). After running both a short and long test -

Code:

root@LS-GL:/etc/apt# smartctl -l selftest /dev/sda
smartctl version 5.38 [armv5tel-unknown-linux-gnu] Copyright (C) 2002-8 Bruce Allen
Home page is http://smartmontools.sourceforge.net/

=== START OF READ SMART DATA SECTION ===
SMART Self-test log structure revision number 1
Num  Test_Description    Status                  Remaining  LifeTime(hours)  LBA_of_first_error
# 1  Extended offline    Completed without error       00%     22230         -
# 2  Short offline       Completed without error       00%     22229         -

...so... :?:


Top
   
PostPosted: Sat Nov 14, 2009 2:04 pm 
Offline
Site Admin
User avatar

Joined: Mon Aug 28, 2006 1:15 am
Posts: 2606
hmmm, I don't see anything wrong there ... dunno ...

_________________
LS1 (foonas, nfs, Tranmission & p910nd print server, Firefly for my Roku)
LS-HG500 (Lenny)
Various LS-Pros v1,v2 (unbricked w/ serial & jtag)
KuroPro, LS2 & KuroHG (foonas)
Working on davysweather.dyndns.org lately...

=> wooohooo!
wooohooo!
Unknown command 'wooohooo!' - try 'help'


Top
   
PostPosted: Sun Nov 15, 2009 1:00 am 
Offline
Newbie

Joined: Mon Apr 16, 2007 11:32 pm
Posts: 19
Location: United Kingdom (Great Britain)
davy_gravy wrote:
hmmm, I don't see anything wrong there ... dunno ...

Well, thanks for trying. I'm off on holiday tomorrow, so will see if anyone else has any ideas by the time I get back. Me, I'm completely stumped...


Top
   
PostPosted: Tue Dec 15, 2009 2:32 pm 
Offline
Newbie

Joined: Mon May 25, 2009 4:11 pm
Posts: 30
I haven't seen any speed losses in going to newer kernels. Just if you use a 2.6.32 and debian, you will need to alter the nfs-kernel-server start script. (there is a known bug http://bugs.debian.org/550153).

I get around 10mb/s ish both ways i think. ( i only use 100mb/s not gige).


Top
   
PostPosted: Tue Feb 09, 2010 1:53 am 
Offline
Regular Member

Joined: Sat Nov 11, 2006 10:56 am
Posts: 714
As a compare im moveing 1.5tb ish atm with rsync
HS-DHGL 1.20 Jap firmware to HS-CHLv2 1.24
95% cpu time on DHGL
60% cpu time on CHL

398gig in 13 hours 10mins


Top
   
PostPosted: Sat Feb 20, 2010 6:26 pm 
Offline
Newbie

Joined: Thu Sep 04, 2008 2:56 am
Posts: 28
I've been having similar issues and found some error messages when I perused the log files. I note that one printing error which I find interesting because my smb.conf does not have printing shares.

I do have my KURO HG set up for a share and it works well. I was wondering if it might be a conflict developed due to more than one server?

How do you address setting up a print que for my LS PRO (without a printer) to point to the KURO box? I'm thinking this error traffic might be impacting my performance which is pretty slow (about 3MB/s).

Paul


Top
   
PostPosted: Sat Feb 20, 2010 11:07 pm 
Offline
Newbie

Joined: Thu Sep 04, 2008 2:56 am
Posts: 28
I researched this a little and rediscovered davy_gravy's original lenny package. One of the notes advised to install CUPS if you install Samba since otherwise there is a lot of network scrambling. I don't think my paraphrasing is entirely correct but the point is make sure CUPS is up too along with Samba. I just installed CUPS because I noticed an error regarding printing in my smbd logs. So I ran it down to this. Now I did a 1 gig copy from my ubuntu desktop off the LS PRO and got an informal 11MB/s way better than the 2-3 I had been getting.

Paulk


Top
   
PostPosted: Mon Mar 08, 2010 5:51 pm 
Offline
Newbie

Joined: Mon Apr 16, 2007 11:32 pm
Posts: 19
Location: United Kingdom (Great Britain)
Seeing as I started this thread, I might just as well check in to report the latest...

Despite trying all sorts of things (as listed above, and other things besides), I never did find a software fix for this. In the end, I just swapped the hard drive out for a different one and rebuilt the system from scratch - all seems well now, so despite smarttools telling me everything was fine, I have to wonder.

Anyway, thanks all for your help :up:


Top
   
Display posts from previous:  Sort by  
Post new topic  Reply to topic  [ 15 posts ] 

All times are UTC+01:00


Who is online

Users browsing this forum: No registered users and 4 guests


You cannot post new topics in this forum
You cannot reply to topics in this forum
You cannot edit your posts in this forum
You cannot delete your posts in this forum
You cannot post attachments in this forum

Search for:
Powered by phpBB® Forum Software © phpBB Limited