sky2 and hard drive performance

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



  Yesterday I converted my FC4 system from raid0 to raid5. After
creating the raid5 arrays I tested the speed with hdparm while in rescue
mode. I saw awesome speeds.

hdparm -tT /dev/md2

/dev/md2:
 Timing cached reads:   4532 MB in  2.00 seconds = 2265.86 MB/sec
 Timing buffered disk reads:  494 MB in  3.00 seconds = 164.66 MB/sec

  Then after I finished copying all the data over, setup grub, and got
the system back to normal I repeatedly the test in a terminal window.

hdparm -tT /dev/md2

/dev/md2:
 Timing cached reads:   1320 MB in  2.00 seconds = 658.64 MB/sec
 Timing buffered disk reads:  256 MB in  3.01 seconds =  85.10 MB/sec


   I then went back in to rescue mode and found that the speed was the
same as it had been before. Then I booted into single user mode and saw
the same. Next I started up services in the order they would normally
start. After each service I would repeat the test. I started kudzu and
iptables. After each the results were roughly the same. Then I started
network and the performance dropped. My first guess was then the sky2
driver. So I activated the other interfaces, but not the sky2 interface.
The hdparm results were normal. Then I activated the sky2 interface and
it dropped again.

   I do see that the driver can be loaded without a drop in performance,
it is only activating the driver that triggers it. Another thing I see
is that deactivating it doesn't fix the problem. In that I can go from
run level 5 to run level 1, where networking is shut down in the
process, but the performance in run level 1 will still be slow.

  Another potential clue maybe that I didn't see such a drop with raid0
performance when I started using the sky2 driver. So I suspect it is
just an interaction between the raid5 code and the sky2 code.

   Who's bugzilla should bug reports for this driver go into?

   I also wanted to bring up again the crash on reactivation, especially
since I haven't mentioned it to Stephen before.

Unable to handle kernel NULL pointer dereference at 00000000000000e8 RIP:
<ffffffff880aad9f>{:sky2:sky2_tx_complete+230}
PGD 7d481067 PUD 796a7067 PMD 0
Oops: 0000 [1]
CPU 0
Modules linked in: ipv6 dm_mirror dm_mod raid1 raid0 video button
battery ac ohci1394 ieee1394 ohci_hcd ehci_hcd parport_pc parport
i2c_nforce2 i2c_core shpchp snd_intel8x0 snd_emu10k1_synth
snd_emux_synth snd_seq_virmidi snd_seq_midi_emul snd_emu10k1 snd_rawmidi
snd_ac97_codec snd_seq_dummy snd_seq_oss snd_seq_midi_event snd_seq
snd_seq_device snd_pcm_oss snd_mixer_oss snd_pcm snd_timer snd_ac97_bus
snd_page_alloc snd_util_mem snd_hwdep snd soundcore sky2 8139too mii
forcedeth floppy ext3 jbd sata_sil sata_nv libata sd_mod scsi_mod
Pid: 3014, comm: ip Not tainted 2.6.14-1.1644_FC4.netdev.4 #1
RIP: 0010:[<ffffffff880aad9f>]
<ffffffff880aad9f>{:sky2:sky2_tx_complete+230}
RSP: 0018:ffffffff80493058  EFLAGS: 00010292
RAX: 0000000000020000 RBX: ffff81007e9a7800 RCX: 0000000000000001
RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff81007fd41870
RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000001 R12: ffff81007e9a7c00
R13: ffff8100797d0000 R14: 0000000000000008 R15: 0000000000000008
FS:  00002aaaaaabf990(0000) GS:ffffffff804f9000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
CR2: 00000000000000e8 CR3: 0000000079658000 CR4: 00000000000006e0
Process ip (pid: 3014, threadinfo ffff810079036000, task ffff8100797f3800)
Stack: ffffffff80154b00 ffff81007e9a7c28 ffff81007e9a7800 ffff81007e9a7800
       ffff8100032384c0 0000000000000000 00000000ffff21c7 00007fffffa16f10
       ffffffff80493188 ffffffff880ac20e
Call Trace: <IRQ> <ffffffff80154b00>{__do_IRQ+213}
<ffffffff880ac20e>{:sky2:sky2_poll+1949}
       <ffffffff8010eca2>{ret_from_intr+0}
<ffffffff802d2ed8>{net_rx_action+154}
       <ffffffff80136e32>{__do_softirq+74}
<ffffffff8010f69f>{call_softirq+31}
       <ffffffff80110b42>{do_softirq+44} <ffffffff80110b7a>{do_IRQ+52}
       <ffffffff8010eca2>{ret_from_intr+0}  <EOI>
<ffffffff8011d073>{dma_alloc_pages+71}
       <ffffffff8011d052>{dma_alloc_pages+38}
<ffffffff8011d87d>{dma_alloc_coherent+125}
       <ffffffff880aa46f>{:sky2:sky2_up+193} <ffffffff802d2d2b>{dev_open+55}
       <ffffffff802d1f3c>{dev_change_flags+99}
<ffffffff80314be2>{devinet_ioctl+671}
       <ffffffff802d3b18>{dev_ioctl+818} <ffffffff802c8cef>{sock_ioctl+656}
       <ffffffff8018749b>{do_ioctl+27} <ffffffff80187725>{vfs_ioctl


-- 
fedora-devel-list mailing list
fedora-devel-list@xxxxxxxxxx
https://www.redhat.com/mailman/listinfo/fedora-devel-list

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Index of Archives]     [Fedora Announce]     [Fedora Kernel]     [Fedora Testing]     [Fedora Formulas]     [Fedora PHP Devel]     [Kernel Development]     [Fedora Legacy]     [Fedora Maintainers]     [Fedora Desktop]     [PAM]     [Red Hat Development]     [Gimp]     [Yosemite News]
  Powered by Linux