Prev: x86: Fix out of order gsi -- add remap_ioapic_gsi_to_irq()
Next: [GIT PULL] perf/core changes for v2.6.34
From: Justin Piszcz on 27 Feb 2010 08:50
Hello,

I have two separate systems and with ext4 I cannot get speeds greater than
~350MiB/s when using ext4 as the filesystem on top of a raid5 or raid0.
It appears to be a bug with ext4 (or its just that ext4 is slower for this
test)?

Each system runs 2.6.33 x86_64.

Can someone please confirm?

Here is ext4:

# dd if=/dev/zero of=bigfile bs=1M count=10240
10240+0 records in
10240+0 records out
10737418240 bytes (11 GB) copied, 29.8556 s, 360 MB/s

The result is the same regardless of the RAID type (RAID-5 or RAID-0)

Note, this is not a bandwidth problem:

# dd if=/dev/zero of=/dev/md0 bs=1M count=10240
10240+0 records in
10240+0 records out
10737418240 bytes (11 GB) copied, 17.6871 s, 607 MB/s

With XFS:

p63:~# mkfs.xfs -f /dev/md0
p63:~# mount /dev/md0 /r1
p63:~# cd /r1
10240+0 records in
10240+0 records out
10737418240 bytes (11 GB) copied, 17.6078 s, 610 MB/s

NOTE: With a HW raid controller (OR using XFS), I can get > 500 MiB/s,
this problem only occurs with SW raid (Linux/mdadm).

Example (3ware 9650SE-16PML RAID-6, 15 drives (using EXT4)
$ dd if=/dev/zero of=bigfile bs=1M count=10240
10240+0 records in
10240+0 records out
10737418240 bytes (11 GB) copied, 21.1729 s, 507 MB/s

Justin.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo(a)vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
From: Neil Brown on 27 Feb 2010 16:10
On Sat, 27 Feb 2010 08:47:48 -0500 (EST)
Justin Piszcz <jpiszcz(a)lucidpixels.com> wrote:

> Hello,
>
> I have two separate systems and with ext4 I cannot get speeds greater than
> ~350MiB/s when using ext4 as the filesystem on top of a raid5 or raid0.
> It appears to be a bug with ext4 (or its just that ext4 is slower for this
> test)?
>
> Each system runs 2.6.33 x86_64.

Could be related to the recent implementation of IO barriers in md.
Can you try mounting your filesystem with
-o barrier=0

and see how that changes the result.

NeilBrown


>
> Can someone please confirm?
>
> Here is ext4:
>
> # dd if=/dev/zero of=bigfile bs=1M count=10240
> 10240+0 records in
> 10240+0 records out
> 10737418240 bytes (11 GB) copied, 29.8556 s, 360 MB/s
>
> The result is the same regardless of the RAID type (RAID-5 or RAID-0)
>
> Note, this is not a bandwidth problem:
>
> # dd if=/dev/zero of=/dev/md0 bs=1M count=10240
> 10240+0 records in
> 10240+0 records out
> 10737418240 bytes (11 GB) copied, 17.6871 s, 607 MB/s
>
> With XFS:
>
> p63:~# mkfs.xfs -f /dev/md0
> p63:~# mount /dev/md0 /r1
> p63:~# cd /r1
> 10240+0 records in
> 10240+0 records out
> 10737418240 bytes (11 GB) copied, 17.6078 s, 610 MB/s
>
> NOTE: With a HW raid controller (OR using XFS), I can get > 500 MiB/s,
> this problem only occurs with SW raid (Linux/mdadm).
>
> Example (3ware 9650SE-16PML RAID-6, 15 drives (using EXT4)
> $ dd if=/dev/zero of=bigfile bs=1M count=10240
> 10240+0 records in
> 10240+0 records out
> 10737418240 bytes (11 GB) copied, 21.1729 s, 507 MB/s
>
> Justin.
> --
> To unsubscribe from this list: send the line "unsubscribe linux-raid" in
> the body of a message to majordomo(a)vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo(a)vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
From: Bill Davidsen on 27 Feb 2010 19:20
Justin Piszcz wrote:
>
>
> On Sun, 28 Feb 2010, Neil Brown wrote:
>
>> On Sat, 27 Feb 2010 08:47:48 -0500 (EST)
>> Justin Piszcz <jpiszcz(a)lucidpixels.com> wrote:
>>
>>> Hello,
>>>
>>> I have two separate systems and with ext4 I cannot get speeds
>>> greater than
>>> ~350MiB/s when using ext4 as the filesystem on top of a raid5 or raid0.
>>> It appears to be a bug with ext4 (or its just that ext4 is slower
>>> for this
>>> test)?
>>>
>>> Each system runs 2.6.33 x86_64.
>>
>> Could be related to the recent implementation of IO barriers in md.
>> Can you try mounting your filesystem with
>> -o barrier=0
>>
>> and see how that changes the result.
>>
>> NeilBrown
>
> Hi Neil,
>
> Thanks for the suggestion, it has been used here:
> http://lkml.org/lkml/2010/2/27/66
>
> Looks like an EXT4 issue as XFS does ~600MiB/s..?
>
> Its strange though, on a single hard disk, I get approximately the
> same speed for XFS and EXT4, but when it comes to scaling across
> multiple disks,
> in RAID-0 or RAID-5 (tested), there is a performance problem as it hits a
> performance problem at ~350MiB/s. I tried multiple chunk sizes but
> nothing
> seemed to made a difference (whether 64KiB or 1024KiB), XFS performs at
> 500-600MiB/s no matter what and EXT4 does not exceed ~350MiB/s.
>
> Is there anyone on any of the lists that gets > 350MiB/s on a mdadm/sw
> raid
> with EXT4?
>
> A single raw disk, no partitions:
> p63:~# dd if=/dev/zero of=/dev/sdm bs=1M count=10240
> 10240+0 records in
> 10240+0 records out
> 10737418240 bytes (11 GB) copied, 92.4249 s, 116 MB/s

I hate to say it, but I don't think this measures anything useful. When
I was doing similar things I got great variabilty in my results until I
learned about the fdatasync option so you measure the actual speed to
the destination and not the disk cache. After that my results were far
slower and reproducible.

--
Bill Davidsen <davidsen(a)tmr.com>
"We can't solve today's problems by using the same thinking we
used in creating them." - Einstein

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo(a)vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
From: Bill Davidsen on 28 Feb 2010 09:30
Justin Piszcz wrote:
>
>
> On Sat, 27 Feb 2010, Bill Davidsen wrote:
>
>> Justin Piszcz wrote:
>>>
>>>
>>> On Sun, 28 Feb 2010, Neil Brown wrote:
>>>
>>>> On Sat, 27 Feb 2010 08:47:48 -0500 (EST)
>>>> Justin Piszcz <jpiszcz(a)lucidpixels.com> wrote:
>>>>
>>>>> Hello,
>>>>>
>>>>> I have two separate systems and with ext4 I cannot get speeds
>>>>> greater than
>>>>> ~350MiB/s when using ext4 as the filesystem on top of a raid5 or
>>>>> raid0.
>>>>> It appears to be a bug with ext4 (or its just that ext4 is slower
>>>>> for this
>>>>> test)?
>>>>>
>>>>> Each system runs 2.6.33 x86_64.
>>>>
>>>> Could be related to the recent implementation of IO barriers in md.
>>>> Can you try mounting your filesystem with
>>>> -o barrier=0
>>>>
>>>> and see how that changes the result.
>>>>
>>>> NeilBrown
>>>
>>> Hi Neil,
>>>
>>> Thanks for the suggestion, it has been used here:
>>> http://lkml.org/lkml/2010/2/27/66
>>>
>>> Looks like an EXT4 issue as XFS does ~600MiB/s..?
>>>
>>> Its strange though, on a single hard disk, I get approximately the
>>> same speed for XFS and EXT4, but when it comes to scaling across
>>> multiple disks,
>>> in RAID-0 or RAID-5 (tested), there is a performance problem as it
>>> hits a
>>> performance problem at ~350MiB/s. I tried multiple chunk sizes but
>>> nothing
>>> seemed to made a difference (whether 64KiB or 1024KiB), XFS performs at
>>> 500-600MiB/s no matter what and EXT4 does not exceed ~350MiB/s.
>>>
>>> Is there anyone on any of the lists that gets > 350MiB/s on a
>>> mdadm/sw raid
>>> with EXT4?
>>>
>>> A single raw disk, no partitions:
>>> p63:~# dd if=/dev/zero of=/dev/sdm bs=1M count=10240
>>> 10240+0 records in
>>> 10240+0 records out
>>> 10737418240 bytes (11 GB) copied, 92.4249 s, 116 MB/s
>>
>> I hate to say it, but I don't think this measures anything useful.
>> When I was doing similar things I got great variabilty in my results
>> until I learned about the fdatasync option so you measure the actual
>> speed to the destination and not the disk cache. After that my
>> results were far slower and reproducible.
>
> fdatasync:
> http://lkml.indiana.edu/hypermail/linux/kernel/1002.3/01507.html
>
I wasn't expecting a huge change in value, your data size is large. But
thanks, the total time without sync can be off by at least seconds,
making it hard to duplicate results. You missed nothing this time.

Did you use any of the options with ext4? I found about 15-20% with
options, but I didn't take good enough notes to quote now. :-(
That doesn't mean there wasn't more, I tested on FC9, ext4 was
experimental then.

--
Bill Davidsen <davidsen(a)tmr.com>
"We can't solve today's problems by using the same thinking we
used in creating them." - Einstein

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo(a)vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
From: Mike Snitzer on 28 Feb 2010 09:40
On Sun, Feb 28, 2010 at 4:45 AM, Justin Piszcz <jpiszcz(a)lucidpixels.com> wrote:
>
>
> On Sat, 27 Feb 2010, Bill Davidsen wrote:
>
>> Justin Piszcz wrote:
>>>
>>>
>>> On Sun, 28 Feb 2010, Neil Brown wrote:
>>>
>>>> On Sat, 27 Feb 2010 08:47:48 -0500 (EST)
>>>> Justin Piszcz <jpiszcz(a)lucidpixels.com> wrote:
>>>>
>>>>> Hello,
>>>>>
>>>>> I have two separate systems and with ext4 I cannot get speeds greater
>>>>> than
>>>>> ~350MiB/s when using ext4 as the filesystem on top of a raid5 or raid0.
>>>>> It appears to be a bug with ext4 (or its just that ext4 is slower for
>>>>> this
>>>>> test)?
>>>>>
>>>>> Each system runs 2.6.33 x86_64.
>>>>
>>>> Could be related to the recent implementation of IO barriers in md.
>>>> Can you try mounting your filesystem with
>>>> �-o barrier=0
>>>>
>>>> and see how that changes the result.
>>>>
>>>> NeilBrown
>>>
>>> Hi Neil,
>>>
>>> Thanks for the suggestion, it has been used here:
>>> http://lkml.org/lkml/2010/2/27/66
>>>
>>> Looks like an EXT4 issue as XFS does ~600MiB/s..?
>>>
>>> Its strange though, on a single hard disk, I get approximately the same
>>> speed for XFS and EXT4, but when it comes to scaling across multiple disks,
>>> in RAID-0 or RAID-5 (tested), there is a performance problem as it hits a
>>> performance problem at ~350MiB/s. �I tried multiple chunk sizes but
>>> nothing
>>> seemed to made a difference (whether 64KiB or 1024KiB), XFS performs at
>>> 500-600MiB/s no matter what and EXT4 does not exceed ~350MiB/s.
>>>
>>> Is there anyone on any of the lists that gets > 350MiB/s on a mdadm/sw
>>> raid
>>> with EXT4?
>>>
>>> A single raw disk, no partitions:
>>> p63:~# dd if=/dev/zero of=/dev/sdm bs=1M count=10240
>>> 10240+0 records in
>>> 10240+0 records out
>>> 10737418240 bytes (11 GB) copied, 92.4249 s, 116 MB/s
>>
>> I hate to say it, but I don't think this measures anything useful. When I
>> was doing similar things I got great variabilty in my results until I
>> learned about the fdatasync option so you measure the actual speed to the
>> destination and not the disk cache. After that my results were far slower
>> and reproducible.
>
> fdatasync:
> http://lkml.indiana.edu/hypermail/linux/kernel/1002.3/01507.html

How did you format the ext3 and ext4 filesystems?

Did you use mkfs.ext[34] -E stride and stripe-width accordingly?
AFAIK even older versions of mkfs.xfs will probe for this info but
older mkfs.ext[34] won't (though new versions of mkfs.ext[34] will,
using the Linux "topology" info).
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo(a)vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
 |  Next  |  Last
Pages: 1 2
Prev: x86: Fix out of order gsi -- add remap_ioapic_gsi_to_irq()
Next: [GIT PULL] perf/core changes for v2.6.34