Page Faults slower in 2.6.25-rc9 than 2.6.23

Page Faults slower in 2.6.25-rc9 than 2.6.23

[Ross Biro]

I don't know if this has been noticed before.  I was benchmarking my
page table relocation code and I noticed that on 2.6.25-rc9 page
faults take 10% more time than on 2.6.22.  This is using lmbench
running on an intel x86_64 system.  The good news is that the page
table relocation code now only adds a 1.6% slow down to page faults.

    Ross

2.6.25-rc9:

File & VM system latencies in microseconds - smaller is better
-------------------------------------------------------------------------------
Host                 OS   0K File      10K File     Mmap    Prot   Page   100fd
                        Create Delete Create Delete Latency Fault  Fault  selct
--------- ------------- ------ ------ ------ ------ ------- ----- ------- -----
ipnn2     Linux 2.6.25-   13.9 7.6111  103.4 9.7453   926.0 0.711 2.14250 2.552
ipnn2     Linux 2.6.25-   13.7 7.6243  310.7 9.6574   932.0 0.750 2.15970 2.555
ipnn2     Linux 2.6.25-   13.9 7.6831  192.5   10.0   927.0 0.760 2.21310 2.553
ipnn2     Linux 2.6.25-   13.9 7.5739   98.4 9.5330   927.0 0.703 2.17610 2.554
ipnn2     Linux 2.6.25-   14.6 7.6429   39.1   10.8   935.0 0.763 2.17250 2.552
ipnn2     Linux 2.6.25-   14.1 7.8777  129.8 9.9375   930.0 0.782 2.26460 2.559
ipnn2     Linux 2.6.25-   14.8 7.9639  623.8 8.2042   927.0 0.773 2.21510 2.557
ipnn2     Linux 2.6.25-   14.4 7.5842  622.3 8.3272   920.0 0.745 2.22210 2.558
ipnn2     Linux 2.6.25-   14.2 7.6339   45.7   10.2   935.0 0.675 2.23860 2.554
ipnn2     Linux 2.6.25-   14.1 7.7175  263.7   10.1   929.0 0.762 2.22350 2.556
ipnn2     Linux 2.6.25-   13.9 8.1230  378.2 9.4343   975.0 0.752 2.25920 2.554


2.6.23:
File & VM system latencies in microseconds - smaller is better
-------------------------------------------------------------------------------
Host                 OS   0K File      10K File     Mmap    Prot   Page   100fd
                        Create Delete Create Delete Latency Fault  Fault  selct
--------- ------------- ------ ------ ------ ------ ------- ----- ------- -----
ipnn2     Linux 2.6.23-                               218.0 0.912 1.94010 2.626
ipnn2     Linux 2.6.23-                               219.0 1.095 1.96400 2.597
ipnn2     Linux 2.6.23-                               219.0 0.774 1.96640 2.603
ipnn2     Linux 2.6.23-                               221.0 0.946 1.99950 2.601
ipnn2     Linux 2.6.23-                               219.0 0.902 1.99160 2.733
ipnn2     Linux 2.6.23-                               217.0 0.904 2.04790 2.601
ipnn2     Linux 2.6.23-                               225.0 0.893 1.99620 2.600

Page Faults slower in 2.6.25-rc9 than 2.6.23

[Ross Biro]

I don't know if this has been noticed before.  I was benchmarking my
page table relocation code and I noticed that on 2.6.25-rc9 page
faults take 10% more time than on 2.6.22.  This is using lmbench
running on an intel x86_64 system.  The good news is that the page
table relocation code now only adds a 1.6% slow down to page faults.

    Ross

2.6.25-rc9:

File & VM system latencies in microseconds - smaller is better
-------------------------------------------------------------------------------
Host                 OS   0K File      10K File     Mmap    Prot   Page   100fd
                        Create Delete Create Delete Latency Fault  Fault  selct
--------- ------------- ------ ------ ------ ------ ------- ----- ------- -----
ipnn2     Linux 2.6.25-   13.9 7.6111  103.4 9.7453   926.0 0.711 2.14250 2.552
ipnn2     Linux 2.6.25-   13.7 7.6243  310.7 9.6574   932.0 0.750 2.15970 2.555
ipnn2     Linux 2.6.25-   13.9 7.6831  192.5   10.0   927.0 0.760 2.21310 2.553
ipnn2     Linux 2.6.25-   13.9 7.5739   98.4 9.5330   927.0 0.703 2.17610 2.554
ipnn2     Linux 2.6.25-   14.6 7.6429   39.1   10.8   935.0 0.763 2.17250 2.552
ipnn2     Linux 2.6.25-   14.1 7.8777  129.8 9.9375   930.0 0.782 2.26460 2.559
ipnn2     Linux 2.6.25-   14.8 7.9639  623.8 8.2042   927.0 0.773 2.21510 2.557
ipnn2     Linux 2.6.25-   14.4 7.5842  622.3 8.3272   920.0 0.745 2.22210 2.558
ipnn2     Linux 2.6.25-   14.2 7.6339   45.7   10.2   935.0 0.675 2.23860 2.554
ipnn2     Linux 2.6.25-   14.1 7.7175  263.7   10.1   929.0 0.762 2.22350 2.556
ipnn2     Linux 2.6.25-   13.9 8.1230  378.2 9.4343   975.0 0.752 2.25920 2.554


2.6.23:
File & VM system latencies in microseconds - smaller is better
-------------------------------------------------------------------------------
Host                 OS   0K File      10K File     Mmap    Prot   Page   100fd
                        Create Delete Create Delete Latency Fault  Fault  selct
--------- ------------- ------ ------ ------ ------ ------- ----- ------- -----
ipnn2     Linux 2.6.23-                               218.0 0.912 1.94010 2.626
ipnn2     Linux 2.6.23-                               219.0 1.095 1.96400 2.597
ipnn2     Linux 2.6.23-                               219.0 0.774 1.96640 2.603
ipnn2     Linux 2.6.23-                               221.0 0.946 1.99950 2.601
ipnn2     Linux 2.6.23-                               219.0 0.902 1.99160 2.733
ipnn2     Linux 2.6.23-                               217.0 0.904 2.04790 2.601
ipnn2     Linux 2.6.23-                               225.0 0.893 1.99620 2.600

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: Page Faults slower in 2.6.25-rc9 than 2.6.23

[Hugh Dickins]

On Tue, 29 Apr 2008, Ross Biro wrote:
> I don't know if this has been noticed before.  I was benchmarking my
> page table relocation code and I noticed that on 2.6.25-rc9 page
> faults take 10% more time than on 2.6.22.  This is using lmbench
> running on an intel x86_64 system.  The good news is that the page
> table relocation code now only adds a 1.6% slow down to page faults.

Do you have CONFIG_CGROUP_MEM_RES_CTLR=y in 2.6.25?
That added about 20% to my lmbench "Page Fault" tests (with
adverse effect on several others e.g. the fork, exec, sh group).

Try the same kernel with boot option "cgroup_disable=memory",
that should recoup most (but not quite all) of the slowdown;
or rebuild with n to CGROUP_MEM_RES_CTLR.

But your "Mmap Latency" went up 425% ??

Hugh

> 
>     Ross
> 
> 2.6.25-rc9:
> 
> File & VM system latencies in microseconds - smaller is better
> -------------------------------------------------------------------------------
> Host                 OS   0K File      10K File     Mmap    Prot   Page   100fd
>                         Create Delete Create Delete Latency Fault  Fault  selct
> --------- ------------- ------ ------ ------ ------ ------- ----- ------- -----
> ipnn2     Linux 2.6.25-   13.9 7.6111  103.4 9.7453   926.0 0.711 2.14250 2.552
> ipnn2     Linux 2.6.25-   13.7 7.6243  310.7 9.6574   932.0 0.750 2.15970 2.555
> ipnn2     Linux 2.6.25-   13.9 7.6831  192.5   10.0   927.0 0.760 2.21310 2.553
> ipnn2     Linux 2.6.25-   13.9 7.5739   98.4 9.5330   927.0 0.703 2.17610 2.554
> ipnn2     Linux 2.6.25-   14.6 7.6429   39.1   10.8   935.0 0.763 2.17250 2.552
> ipnn2     Linux 2.6.25-   14.1 7.8777  129.8 9.9375   930.0 0.782 2.26460 2.559
> ipnn2     Linux 2.6.25-   14.8 7.9639  623.8 8.2042   927.0 0.773 2.21510 2.557
> ipnn2     Linux 2.6.25-   14.4 7.5842  622.3 8.3272   920.0 0.745 2.22210 2.558
> ipnn2     Linux 2.6.25-   14.2 7.6339   45.7   10.2   935.0 0.675 2.23860 2.554
> ipnn2     Linux 2.6.25-   14.1 7.7175  263.7   10.1   929.0 0.762 2.22350 2.556
> ipnn2     Linux 2.6.25-   13.9 8.1230  378.2 9.4343   975.0 0.752 2.25920 2.554
> 
> 
> 2.6.23:
> File & VM system latencies in microseconds - smaller is better
> -------------------------------------------------------------------------------
> Host                 OS   0K File      10K File     Mmap    Prot   Page   100fd
>                         Create Delete Create Delete Latency Fault  Fault  selct
> --------- ------------- ------ ------ ------ ------ ------- ----- ------- -----
> ipnn2     Linux 2.6.23-                               218.0 0.912 1.94010 2.626
> ipnn2     Linux 2.6.23-                               219.0 1.095 1.96400 2.597
> ipnn2     Linux 2.6.23-                               219.0 0.774 1.96640 2.603
> ipnn2     Linux 2.6.23-                               221.0 0.946 1.99950 2.601
> ipnn2     Linux 2.6.23-                               219.0 0.902 1.99160 2.733
> ipnn2     Linux 2.6.23-                               217.0 0.904 2.04790 2.601
> ipnn2     Linux 2.6.23-                               225.0 0.893 1.99620 2.600

Re: Page Faults slower in 2.6.25-rc9 than 2.6.23

[Hugh Dickins]

On Tue, 29 Apr 2008, Ross Biro wrote:
> I don't know if this has been noticed before.  I was benchmarking my
> page table relocation code and I noticed that on 2.6.25-rc9 page
> faults take 10% more time than on 2.6.22.  This is using lmbench
> running on an intel x86_64 system.  The good news is that the page
> table relocation code now only adds a 1.6% slow down to page faults.

Do you have CONFIG_CGROUP_MEM_RES_CTLR=y in 2.6.25?
That added about 20% to my lmbench "Page Fault" tests (with
adverse effect on several others e.g. the fork, exec, sh group).

Try the same kernel with boot option "cgroup_disable=memory",
that should recoup most (but not quite all) of the slowdown;
or rebuild with n to CGROUP_MEM_RES_CTLR.

But your "Mmap Latency" went up 425% ??

Hugh

> 
>     Ross
> 
> 2.6.25-rc9:
> 
> File & VM system latencies in microseconds - smaller is better
> -------------------------------------------------------------------------------
> Host                 OS   0K File      10K File     Mmap    Prot   Page   100fd
>                         Create Delete Create Delete Latency Fault  Fault  selct
> --------- ------------- ------ ------ ------ ------ ------- ----- ------- -----
> ipnn2     Linux 2.6.25-   13.9 7.6111  103.4 9.7453   926.0 0.711 2.14250 2.552
> ipnn2     Linux 2.6.25-   13.7 7.6243  310.7 9.6574   932.0 0.750 2.15970 2.555
> ipnn2     Linux 2.6.25-   13.9 7.6831  192.5   10.0   927.0 0.760 2.21310 2.553
> ipnn2     Linux 2.6.25-   13.9 7.5739   98.4 9.5330   927.0 0.703 2.17610 2.554
> ipnn2     Linux 2.6.25-   14.6 7.6429   39.1   10.8   935.0 0.763 2.17250 2.552
> ipnn2     Linux 2.6.25-   14.1 7.8777  129.8 9.9375   930.0 0.782 2.26460 2.559
> ipnn2     Linux 2.6.25-   14.8 7.9639  623.8 8.2042   927.0 0.773 2.21510 2.557
> ipnn2     Linux 2.6.25-   14.4 7.5842  622.3 8.3272   920.0 0.745 2.22210 2.558
> ipnn2     Linux 2.6.25-   14.2 7.6339   45.7   10.2   935.0 0.675 2.23860 2.554
> ipnn2     Linux 2.6.25-   14.1 7.7175  263.7   10.1   929.0 0.762 2.22350 2.556
> ipnn2     Linux 2.6.25-   13.9 8.1230  378.2 9.4343   975.0 0.752 2.25920 2.554
> 
> 
> 2.6.23:
> File & VM system latencies in microseconds - smaller is better
> -------------------------------------------------------------------------------
> Host                 OS   0K File      10K File     Mmap    Prot   Page   100fd
>                         Create Delete Create Delete Latency Fault  Fault  selct
> --------- ------------- ------ ------ ------ ------ ------- ----- ------- -----
> ipnn2     Linux 2.6.23-                               218.0 0.912 1.94010 2.626
> ipnn2     Linux 2.6.23-                               219.0 1.095 1.96400 2.597
> ipnn2     Linux 2.6.23-                               219.0 0.774 1.96640 2.603
> ipnn2     Linux 2.6.23-                               221.0 0.946 1.99950 2.601
> ipnn2     Linux 2.6.23-                               219.0 0.902 1.99160 2.733
> ipnn2     Linux 2.6.23-                               217.0 0.904 2.04790 2.601
> ipnn2     Linux 2.6.23-                               225.0 0.893 1.99620 2.600

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: Page Faults slower in 2.6.25-rc9 than 2.6.23

[Ross Biro]

On Tue, Apr 29, 2008 at 9:57 AM, Hugh Dickins <hugh@veritas.com> wrote:
>  Do you have CONFIG_CGROUP_MEM_RES_CTLR=y in 2.6.25?
>  That added about 20% to my lmbench "Page Fault" tests (with
>  adverse effect on several others e.g. the fork, exec, sh group).

I don't have config cgroups set.  I do have fake numa on, but I'm
pretty sure it was on for 2.6.23 as well.

# CONFIG_CGROUPS is not set
CONFIG_GROUP_SCHED=y
CONFIG_FAIR_GROUP_SCHED=y
# CONFIG_RT_GROUP_SCHED is not set
CONFIG_USER_SCHED=y
# CONFIG_CGROUP_SCHED is not set
C

    Ross

Re: Page Faults slower in 2.6.25-rc9 than 2.6.23

[Ross Biro]

On Tue, Apr 29, 2008 at 9:57 AM, Hugh Dickins <hugh@veritas.com> wrote:
>  Do you have CONFIG_CGROUP_MEM_RES_CTLR=y in 2.6.25?
>  That added about 20% to my lmbench "Page Fault" tests (with
>  adverse effect on several others e.g. the fork, exec, sh group).

I don't have config cgroups set.  I do have fake numa on, but I'm
pretty sure it was on for 2.6.23 as well.

# CONFIG_CGROUPS is not set
CONFIG_GROUP_SCHED=y
CONFIG_FAIR_GROUP_SCHED=y
# CONFIG_RT_GROUP_SCHED is not set
CONFIG_USER_SCHED=y
# CONFIG_CGROUP_SCHED is not set
C

    Ross

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: Page Faults slower in 2.6.25-rc9 than 2.6.23

[Balbir Singh]

On Tue, Apr 29, 2008 at 7:27 PM, Hugh Dickins <hugh@veritas.com> wrote:
> On Tue, 29 Apr 2008, Ross Biro wrote:
>  > I don't know if this has been noticed before.  I was benchmarking my
>  > page table relocation code and I noticed that on 2.6.25-rc9 page
>  > faults take 10% more time than on 2.6.22.  This is using lmbench
>  > running on an intel x86_64 system.  The good news is that the page
>  > table relocation code now only adds a 1.6% slow down to page faults.
>
>  Do you have CONFIG_CGROUP_MEM_RES_CTLR=y in 2.6.25?
>  That added about 20% to my lmbench "Page Fault" tests (with
>  adverse effect on several others e.g. the fork, exec, sh group).
>

Hmm.. strange.. I don't remember the overhead being so bad (I'll
relook at my old numbers). I'll try and git-bisect this one


>  Try the same kernel with boot option "cgroup_disable=memory",
>  that should recoup most (but not quite all) of the slowdown;
>  or rebuild with n to CGROUP_MEM_RES_CTLR.
>
>  But your "Mmap Latency" went up 425% ??
>

That's really way of the mark

>  Hugh
>

Balbir

Re: Page Faults slower in 2.6.25-rc9 than 2.6.23

[Balbir Singh]

On Tue, Apr 29, 2008 at 7:27 PM, Hugh Dickins <hugh@veritas.com> wrote:
> On Tue, 29 Apr 2008, Ross Biro wrote:
>  > I don't know if this has been noticed before.  I was benchmarking my
>  > page table relocation code and I noticed that on 2.6.25-rc9 page
>  > faults take 10% more time than on 2.6.22.  This is using lmbench
>  > running on an intel x86_64 system.  The good news is that the page
>  > table relocation code now only adds a 1.6% slow down to page faults.
>
>  Do you have CONFIG_CGROUP_MEM_RES_CTLR=y in 2.6.25?
>  That added about 20% to my lmbench "Page Fault" tests (with
>  adverse effect on several others e.g. the fork, exec, sh group).
>

Hmm.. strange.. I don't remember the overhead being so bad (I'll
relook at my old numbers). I'll try and git-bisect this one


>  Try the same kernel with boot option "cgroup_disable=memory",
>  that should recoup most (but not quite all) of the slowdown;
>  or rebuild with n to CGROUP_MEM_RES_CTLR.
>
>  But your "Mmap Latency" went up 425% ??
>

That's really way of the mark

>  Hugh
>

Balbir

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: Page Faults slower in 2.6.25-rc9 than 2.6.23

[Ross Biro]

On Tue, Apr 29, 2008 at 10:52 AM, Balbir Singh
<balbir@linux.vnet.ibm.com> wrote:
>  Hmm.. strange.. I don't remember the overhead being so bad (I'll
>  relook at my old numbers). I'll try and git-bisect this one

I'm checking 2.6.24 now.  A quick run of 2.6.25-rc9 without fake numa
showed no real change.

    Ross

Re: Page Faults slower in 2.6.25-rc9 than 2.6.23

[Ross Biro]

On Tue, Apr 29, 2008 at 10:52 AM, Balbir Singh
<balbir@linux.vnet.ibm.com> wrote:
>  Hmm.. strange.. I don't remember the overhead being so bad (I'll
>  relook at my old numbers). I'll try and git-bisect this one

I'm checking 2.6.24 now.  A quick run of 2.6.25-rc9 without fake numa
showed no real change.

    Ross

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: Page Faults slower in 2.6.25-rc9 than 2.6.23

[Hugh Dickins]

On Tue, 29 Apr 2008, Ross Biro wrote:
> On Tue, Apr 29, 2008 at 10:52 AM, Balbir Singh
> <balbir@linux.vnet.ibm.com> wrote:
> >  Hmm.. strange.. I don't remember the overhead being so bad (I'll
> >  relook at my old numbers). I'll try and git-bisect this one
> 
> I'm checking 2.6.24 now.  A quick run of 2.6.25-rc9 without fake numa
> showed no real change.

Worth checking 2.6.24, yes.  But you've already made it clear that
you do NOT have mem cgroups in your 2.6.25-rc9, so Balbir (probably)
need not worry about your regression: my guess was wrong on that.

Hugh

Re: Page Faults slower in 2.6.25-rc9 than 2.6.23

[Hugh Dickins]

On Tue, 29 Apr 2008, Ross Biro wrote:
> On Tue, Apr 29, 2008 at 10:52 AM, Balbir Singh
> <balbir@linux.vnet.ibm.com> wrote:
> >  Hmm.. strange.. I don't remember the overhead being so bad (I'll
> >  relook at my old numbers). I'll try and git-bisect this one
> 
> I'm checking 2.6.24 now.  A quick run of 2.6.25-rc9 without fake numa
> showed no real change.

Worth checking 2.6.24, yes.  But you've already made it clear that
you do NOT have mem cgroups in your 2.6.25-rc9, so Balbir (probably)
need not worry about your regression: my guess was wrong on that.

Hugh

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: Page Faults slower in 2.6.25-rc9 than 2.6.23

[Ross Biro]

On Tue, Apr 29, 2008 at 11:32 AM, Hugh Dickins <hugh@veritas.com> wrote:
>> I'm checking 2.6.24 now.  A quick run of 2.6.25-rc9 without fake numa
>> showed no real change.
>

2.6.24 is slower as well.  I can't say for sure it's the full 10%
without more work than it's worth.  But it is definitely significantly
slower than 2.6.23.

    Ross

Re: Page Faults slower in 2.6.25-rc9 than 2.6.23

[Ross Biro]

On Tue, Apr 29, 2008 at 11:32 AM, Hugh Dickins <hugh@veritas.com> wrote:
>> I'm checking 2.6.24 now.  A quick run of 2.6.25-rc9 without fake numa
>> showed no real change.
>

2.6.24 is slower as well.  I can't say for sure it's the full 10%
without more work than it's worth.  But it is definitely significantly
slower than 2.6.23.

    Ross

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: Page Faults slower in 2.6.25-rc9 than 2.6.23

[Balbir Singh]

Hugh Dickins wrote:
> On Tue, 29 Apr 2008, Ross Biro wrote:
>> On Tue, Apr 29, 2008 at 10:52 AM, Balbir Singh
>> <balbir@linux.vnet.ibm.com> wrote:
>>>  Hmm.. strange.. I don't remember the overhead being so bad (I'll
>>>  relook at my old numbers). I'll try and git-bisect this one
>> I'm checking 2.6.24 now.  A quick run of 2.6.25-rc9 without fake numa
>> showed no real change.
> 
> Worth checking 2.6.24, yes.  But you've already made it clear that
> you do NOT have mem cgroups in your 2.6.25-rc9, so Balbir (probably)
> need not worry about your regression: my guess was wrong on that.
> 

Aah.. Yes... but I am definitely interested in figuring out the root cause for
the regression.

-- 
	Warm Regards,
	Balbir Singh
	Linux Technology Center
	IBM, ISTL

Re: Page Faults slower in 2.6.25-rc9 than 2.6.23

[Balbir Singh]

Hugh Dickins wrote:
> On Tue, 29 Apr 2008, Ross Biro wrote:
>> On Tue, Apr 29, 2008 at 10:52 AM, Balbir Singh
>> <balbir@linux.vnet.ibm.com> wrote:
>>>  Hmm.. strange.. I don't remember the overhead being so bad (I'll
>>>  relook at my old numbers). I'll try and git-bisect this one
>> I'm checking 2.6.24 now.  A quick run of 2.6.25-rc9 without fake numa
>> showed no real change.
> 
> Worth checking 2.6.24, yes.  But you've already made it clear that
> you do NOT have mem cgroups in your 2.6.25-rc9, so Balbir (probably)
> need not worry about your regression: my guess was wrong on that.
> 

Aah.. Yes... but I am definitely interested in figuring out the root cause for
the regression.

-- 
	Warm Regards,
	Balbir Singh
	Linux Technology Center
	IBM, ISTL

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: Page Faults slower in 2.6.25-rc9 than 2.6.23

[Ross Biro]

On Tue, Apr 29, 2008 at 12:42 PM, Balbir Singh
<balbir@linux.vnet.ibm.com> wrote:
> Aah.. Yes... but I am definitely interested in figuring out the root cause for
> the regression.

I can't reproduce the 2.6.23 results.  I'm going to run the benchmarks
a few more times, but I'm suspecting something changed with the
hardware.

    Ross

Re: Page Faults slower in 2.6.25-rc9 than 2.6.23

[Ross Biro]

On Tue, Apr 29, 2008 at 12:42 PM, Balbir Singh
<balbir@linux.vnet.ibm.com> wrote:
> Aah.. Yes... but I am definitely interested in figuring out the root cause for
> the regression.

I can't reproduce the 2.6.23 results.  I'm going to run the benchmarks
a few more times, but I'm suspecting something changed with the
hardware.

    Ross

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: Page Faults slower in 2.6.25-rc9 than 2.6.23

[Ross Biro]

On Tue, Apr 29, 2008 at 1:00 PM, Ross Biro <rossb@google.com> wrote:
> > Aah.. Yes... but I am definitely interested in figuring out the root cause for
>  > the regression.
>
>  I can't reproduce the 2.6.23 results.  I'm going to run the benchmarks
>  a few more times, but I'm suspecting something changed with the
>  hardware.

The 2.6.23 results have been consistant with 2.6.24 results and
lmbench has crashed my test machine at least once.  I'm guessing some
sort of memory error causing a lot of ECC and slowing things down.

    Ross

Re: Page Faults slower in 2.6.25-rc9 than 2.6.23

[Ross Biro]

On Tue, Apr 29, 2008 at 1:00 PM, Ross Biro <rossb@google.com> wrote:
> > Aah.. Yes... but I am definitely interested in figuring out the root cause for
>  > the regression.
>
>  I can't reproduce the 2.6.23 results.  I'm going to run the benchmarks
>  a few more times, but I'm suspecting something changed with the
>  hardware.

The 2.6.23 results have been consistant with 2.6.24 results and
lmbench has crashed my test machine at least once.  I'm guessing some
sort of memory error causing a lot of ECC and slowing things down.

    Ross

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: Page Faults slower in 2.6.25-rc9 than 2.6.23

[KAMEZAWA Hiroyuki]

On Tue, 29 Apr 2008 09:10:36 -0400
"Ross Biro" <rossb@google.com> wrote:

> I don't know if this has been noticed before.  I was benchmarking my
> page table relocation code and I noticed that on 2.6.25-rc9 page
> faults take 10% more time than on 2.6.22.  This is using lmbench
> running on an intel x86_64 system.  The good news is that the page
> table relocation code now only adds a 1.6% slow down to page faults.
> 

It seems lmbench's pagefault program uses 'page fault by READ'.
Then, this patch affects. (this patch was added at 2.6.24-rc?.)
==
http://git.kernel.org/?p=linux/kernel/git/torvalds/linux-2.6.git;a=commit;h=557ed1fa2620dc119adb86b34c614e152a629a80
==
By it, ZERO_PAGE is not used for page fault in anonymous mapping.
So it seems an expexted result.

Thanks,
-Kame

>     Ross
> 
> 2.6.25-rc9:
> 
> File & VM system latencies in microseconds - smaller is better
> -------------------------------------------------------------------------------
> Host                 OS   0K File      10K File     Mmap    Prot   Page   100fd
>                         Create Delete Create Delete Latency Fault  Fault  selct
> --------- ------------- ------ ------ ------ ------ ------- ----- ------- -----
> ipnn2     Linux 2.6.25-   13.9 7.6111  103.4 9.7453   926.0 0.711 2.14250 2.552
> ipnn2     Linux 2.6.25-   13.7 7.6243  310.7 9.6574   932.0 0.750 2.15970 2.555
> ipnn2     Linux 2.6.25-   13.9 7.6831  192.5   10.0   927.0 0.760 2.21310 2.553
> ipnn2     Linux 2.6.25-   13.9 7.5739   98.4 9.5330   927.0 0.703 2.17610 2.554
> ipnn2     Linux 2.6.25-   14.6 7.6429   39.1   10.8   935.0 0.763 2.17250 2.552
> ipnn2     Linux 2.6.25-   14.1 7.8777  129.8 9.9375   930.0 0.782 2.26460 2.559
> ipnn2     Linux 2.6.25-   14.8 7.9639  623.8 8.2042   927.0 0.773 2.21510 2.557
> ipnn2     Linux 2.6.25-   14.4 7.5842  622.3 8.3272   920.0 0.745 2.22210 2.558
> ipnn2     Linux 2.6.25-   14.2 7.6339   45.7   10.2   935.0 0.675 2.23860 2.554
> ipnn2     Linux 2.6.25-   14.1 7.7175  263.7   10.1   929.0 0.762 2.22350 2.556
> ipnn2     Linux 2.6.25-   13.9 8.1230  378.2 9.4343   975.0 0.752 2.25920 2.554
> 
> 
> 2.6.23:
> File & VM system latencies in microseconds - smaller is better
> -------------------------------------------------------------------------------
> Host                 OS   0K File      10K File     Mmap    Prot   Page   100fd
>                         Create Delete Create Delete Latency Fault  Fault  selct
> --------- ------------- ------ ------ ------ ------ ------- ----- ------- -----
> ipnn2     Linux 2.6.23-                               218.0 0.912 1.94010 2.626
> ipnn2     Linux 2.6.23-                               219.0 1.095 1.96400 2.597
> ipnn2     Linux 2.6.23-                               219.0 0.774 1.96640 2.603
> ipnn2     Linux 2.6.23-                               221.0 0.946 1.99950 2.601
> ipnn2     Linux 2.6.23-                               219.0 0.902 1.99160 2.733
> ipnn2     Linux 2.6.23-                               217.0 0.904 2.04790 2.601
> ipnn2     Linux 2.6.23-                               225.0 0.893 1.99620 2.600
> 
> --
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to majordomo@kvack.org.  For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: Page Faults slower in 2.6.25-rc9 than 2.6.23

[KAMEZAWA Hiroyuki]

On Tue, 29 Apr 2008 09:10:36 -0400
"Ross Biro" <rossb@google.com> wrote:

> I don't know if this has been noticed before.  I was benchmarking my
> page table relocation code and I noticed that on 2.6.25-rc9 page
> faults take 10% more time than on 2.6.22.  This is using lmbench
> running on an intel x86_64 system.  The good news is that the page
> table relocation code now only adds a 1.6% slow down to page faults.
> 

It seems lmbench's pagefault program uses 'page fault by READ'.
Then, this patch affects. (this patch was added at 2.6.24-rc?.)
==
http://git.kernel.org/?p=linux/kernel/git/torvalds/linux-2.6.git;a=commit;h=557ed1fa2620dc119adb86b34c614e152a629a80
==
By it, ZERO_PAGE is not used for page fault in anonymous mapping.
So it seems an expexted result.

Thanks,
-Kame

>     Ross
> 
> 2.6.25-rc9:
> 
> File & VM system latencies in microseconds - smaller is better
> -------------------------------------------------------------------------------
> Host                 OS   0K File      10K File     Mmap    Prot   Page   100fd
>                         Create Delete Create Delete Latency Fault  Fault  selct
> --------- ------------- ------ ------ ------ ------ ------- ----- ------- -----
> ipnn2     Linux 2.6.25-   13.9 7.6111  103.4 9.7453   926.0 0.711 2.14250 2.552
> ipnn2     Linux 2.6.25-   13.7 7.6243  310.7 9.6574   932.0 0.750 2.15970 2.555
> ipnn2     Linux 2.6.25-   13.9 7.6831  192.5   10.0   927.0 0.760 2.21310 2.553
> ipnn2     Linux 2.6.25-   13.9 7.5739   98.4 9.5330   927.0 0.703 2.17610 2.554
> ipnn2     Linux 2.6.25-   14.6 7.6429   39.1   10.8   935.0 0.763 2.17250 2.552
> ipnn2     Linux 2.6.25-   14.1 7.8777  129.8 9.9375   930.0 0.782 2.26460 2.559
> ipnn2     Linux 2.6.25-   14.8 7.9639  623.8 8.2042   927.0 0.773 2.21510 2.557
> ipnn2     Linux 2.6.25-   14.4 7.5842  622.3 8.3272   920.0 0.745 2.22210 2.558
> ipnn2     Linux 2.6.25-   14.2 7.6339   45.7   10.2   935.0 0.675 2.23860 2.554
> ipnn2     Linux 2.6.25-   14.1 7.7175  263.7   10.1   929.0 0.762 2.22350 2.556
> ipnn2     Linux 2.6.25-   13.9 8.1230  378.2 9.4343   975.0 0.752 2.25920 2.554
> 
> 
> 2.6.23:
> File & VM system latencies in microseconds - smaller is better
> -------------------------------------------------------------------------------
> Host                 OS   0K File      10K File     Mmap    Prot   Page   100fd
>                         Create Delete Create Delete Latency Fault  Fault  selct
> --------- ------------- ------ ------ ------ ------ ------- ----- ------- -----
> ipnn2     Linux 2.6.23-                               218.0 0.912 1.94010 2.626
> ipnn2     Linux 2.6.23-                               219.0 1.095 1.96400 2.597
> ipnn2     Linux 2.6.23-                               219.0 0.774 1.96640 2.603
> ipnn2     Linux 2.6.23-                               221.0 0.946 1.99950 2.601
> ipnn2     Linux 2.6.23-                               219.0 0.902 1.99160 2.733
> ipnn2     Linux 2.6.23-                               217.0 0.904 2.04790 2.601
> ipnn2     Linux 2.6.23-                               225.0 0.893 1.99620 2.600
> 
> --
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to majordomo@kvack.org.  For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: Page Faults slower in 2.6.25-rc9 than 2.6.23

[Hugh Dickins]

On Wed, 30 Apr 2008, KAMEZAWA Hiroyuki wrote:
> On Tue, 29 Apr 2008 09:10:36 -0400
> "Ross Biro" <rossb@google.com> wrote:
> > I don't know if this has been noticed before.  I was benchmarking my
> > page table relocation code and I noticed that on 2.6.25-rc9 page
> > faults take 10% more time than on 2.6.22.  This is using lmbench
> > running on an intel x86_64 system.  The good news is that the page
> > table relocation code now only adds a 1.6% slow down to page faults.
> 
> It seems lmbench's pagefault program uses 'page fault by READ'.
> Then, this patch affects. (this patch was added at 2.6.24-rc?.)
> ==
> http://git.kernel.org/?p=linux/kernel/git/torvalds/linux-2.6.git;a=commit;h=557ed1fa2620dc119adb86b34c614e152a629a80
> ==
> By it, ZERO_PAGE is not used for page fault in anonymous mapping.

I'd wondered about that one too, but no: lmbench lat_pagefault uses
a shared mmap of an ordinary file (not /dev/zero), so the ZERO_PAGE
changes should have no effect on it whatsoever.

I notice that test is expecting msync(,,MS_INVALIDATE) to do something
it's never done on Linux (a kind of drop caches for the range).  We've
never done anything with MS_INVALIDATE, beyond permitting the flag:
I think you find problems however you try to go about implementing
it (and it might even originate from a UNIX which couldn't do shared
mmap coherently).  So I wonder if that test is erratic because of it.

Hugh

Re: Page Faults slower in 2.6.25-rc9 than 2.6.23

[Hugh Dickins]

On Wed, 30 Apr 2008, KAMEZAWA Hiroyuki wrote:
> On Tue, 29 Apr 2008 09:10:36 -0400
> "Ross Biro" <rossb@google.com> wrote:
> > I don't know if this has been noticed before.  I was benchmarking my
> > page table relocation code and I noticed that on 2.6.25-rc9 page
> > faults take 10% more time than on 2.6.22.  This is using lmbench
> > running on an intel x86_64 system.  The good news is that the page
> > table relocation code now only adds a 1.6% slow down to page faults.
> 
> It seems lmbench's pagefault program uses 'page fault by READ'.
> Then, this patch affects. (this patch was added at 2.6.24-rc?.)
> ==
> http://git.kernel.org/?p=linux/kernel/git/torvalds/linux-2.6.git;a=commit;h=557ed1fa2620dc119adb86b34c614e152a629a80
> ==
> By it, ZERO_PAGE is not used for page fault in anonymous mapping.

I'd wondered about that one too, but no: lmbench lat_pagefault uses
a shared mmap of an ordinary file (not /dev/zero), so the ZERO_PAGE
changes should have no effect on it whatsoever.

I notice that test is expecting msync(,,MS_INVALIDATE) to do something
it's never done on Linux (a kind of drop caches for the range).  We've
never done anything with MS_INVALIDATE, beyond permitting the flag:
I think you find problems however you try to go about implementing
it (and it might even originate from a UNIX which couldn't do shared
mmap coherently).  So I wonder if that test is erratic because of it.

Hugh

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>