> > OK. Back to the fs again, same command, different device. Still
> > glacially slow (and still running), only now the whole box is at a
> > standstill, too. cat /proc/cpuinfo takes about 3 minutes (!) to
> > complete, I'm still waiting for top to launch (15min and counting).
> > I'll leave mke2fs running for now ...
>
> What's the state of your array at this point - is it resyncing?
Yes. Didn't think it would matter (much). Never did before.
> o how about making filesystem(s) on individual disks first, to see
> how that will work out? Maybe on each of them in parallel? :)
Running. System is perfectly responsive during 4x mke2fs -j -q on raw devices.
Done. Upper bound for duration is 8 minutes (probaby much lower,
forgot to let it beep on completion), which is much better than the 2
hours with the syncing RAID.
chris@jesus:~$ cat /proc/interrupts
CPU0 CPU1
0: 4939 1920632 IO-APIC-edge timer
1: 113 133 IO-APIC-edge i8042
6: 0 3 IO-APIC-edge floppy
7: 0 0 IO-APIC-edge parport0
8: 0 1 IO-APIC-edge rtc
9: 0 0 IO-APIC-fasteoi acpi
12: 0 4 IO-APIC-edge i8042
14: 0 182 IO-APIC-edge ide0
19: 87 34 IO-APIC-fasteoi ohci_hcd:usb1,
ohci_hcd:usb2, firewire_ohci
24: 10142 57 IO-APIC-fasteoi eth0
26: 1041479 267 IO-APIC-fasteoi sata_promise
27: 0 0 IO-APIC-fasteoi sata_promise
28: 7141 2789 IO-APIC-fasteoi aic7xxx
NMI: 0 0
LOC: 1925715 1925691
ERR: 0
chris@jesus:~$ vmstat 2
procs -----------memory---------- ---swap-- -----io---- -system-- ----cpu----
r b swpd free buff cache si so bi bo in cs us sy id wa
3 4 0 12716 1770264 9972 0 0 1034 4902 196 883 0 9 78 13
0 4 0 11404 1771260 9972 0 0 0 150156 544 874 0 26 28 46
0 4 0 11836 1771016 10024 0 0 0 147500 544 682 0 26 26 48
0 4 0 12572 1770036 10108 0 0 0 131022 515 506 0 25 13 62
0 4 0 12864 1769688 10000 0 0 0 146822 539 809 0 26 23 51
0 4 0 12132 1769988 9956 0 0 0 145942 536 900 0 26 15 59
0 4 0 12520 1770324 9976 0 0 0 144638 536 820 0 26 32 42
top - 17:08:55 up 2:12, 2 users, load average: 4.37, 3.13, 1.49
Tasks: 78 total, 1 running, 77 sleeping, 0 stopped, 0 zombie
Cpu(s): 1.3%us, 8.1%sy, 0.0%ni, 41.6%id, 46.0%wa, 0.7%hi, 2.3%si, 0.0%st
Mem: 2063940k total, 2051316k used, 12624k free, 1746616k buffers
I hope you can interpret that :)
> o try --assume-clean when creating the array
mke2fs (same command as in first post) now running on fresh
--assumed-clean array w/o crypto. System is only marginally less
responsive than under idle load, if at all.
But inode table writing speed is only about 8-10/second. For the
single disk case I couldn't read the numbers fast enough.
chris@jesus:~$ cat /proc/interrupts
CPU0 CPU1
0: 7485 2227196 IO-APIC-edge timer
1: 113 133 IO-APIC-edge i8042
6: 0 3 IO-APIC-edge floppy
7: 0 0 IO-APIC-edge parport0
8: 0 1 IO-APIC-edge rtc
9: 0 0 IO-APIC-fasteoi acpi
12: 0 4 IO-APIC-edge i8042
14: 0 182 IO-APIC-edge ide0
19: 101 39 IO-APIC-fasteoi ohci_hcd:usb1,
ohci_hcd:usb2, firewire_ohci
24: 15656 57 IO-APIC-fasteoi eth0
26: 1211165 267 IO-APIC-fasteoi sata_promise
27: 0 0 IO-APIC-fasteoi sata_promise
28: 7892 2938 IO-APIC-fasteoi aic7xxx
NMI: 0 0
LOC: 2234843 2234819
ERR: 0
chris@jesus:~$ vmstat 2
procs -----------memory---------- ---swap-- -----io---- -system-- ----cpu----
r b swpd free buff cache si so bi bo in cs us sy id wa
0 1 0 12996 1811456 10860 0 0 912 4824 194 867 0 9 78 13
0 0 0 11532 1812992 10832 0 0 0 12924 532 4992 0 11 61 28
0 1 0 11092 1813376 10804 0 0 0 13316 535 5201 0 9 51 40
0 0 0 12968 1811584 10832 0 0 0 12570 518 4890 0 9 58 32
0 1 0 11724 1812736 10816 0 0 0 12818 508 5337 0 10 52 38
0 0 0 12780 1811712 10804 0 0 0 13994 546 5055 0 9 52 40
top - 17:26:37 up 2:29, 2 users, load average: 2.89, 2.12, 1.42
Tasks: 75 total, 2 running, 73 sleeping, 0 stopped, 0 zombie
Cpu(s): 0.0%us, 10.1%sy, 0.0%ni, 55.6%id, 33.7%wa, 0.2%hi, 0.3%si, 0.0%st
Mem: 2063940k total, 2052148k used, 11792k free, 1812288k buffers
>From vmstat I gather that total write throughput is an order of
magnitude slower than on the 4 raw disks in parallel. Naturally the
mke2fs on the raid isn't parallelized but it should still be
sequential enough to get the max for a single disk (~60-40MB/s),
right?
Thanks for helping.
C.
--
To unsubscribe from this list: send the line "unsubscribe linux-raid" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
