New: 2.6.18->2.6.32->2.6.33 huge regression in performance
A message that is not in the archive (sent off-list or not yet received): [email protected]/
Andrew Morton
maintainer(switched to email. Please respond via emailed reply-to-all, not via the bugzilla web interface).
Quoted 18 lines · On Tue, 23 Mar 2010 16:13:25 GMT [email protected] wrote:
https://bugzilla.kernel.org/show_bug.cgi?id=15618
Summary: 2.6.18->2.6.32->2.6.33 huge regression in performance Product: Process Management Version: 2.5 Kernel Version: 2.6.32 Platform: All OS/Version: Linux Tree: Mainline Status: NEW Severity: high Priority: P1 Component: Other AssignedTo: [email protected] ReportedBy: [email protected] Regression: No
Quoted 5 lines
We have benchmarked some multithreaded code here on 16-core/4-way opteron 8356 host on number of kernels (see below) and found strange results. Up to 8 threads we didn't see any noticeable differences in performance, but starting from 9 threads performance diverges substantially. I provide here results for 14 threads
lolz. Catastrophic meltdown. Thanks for doing all that work - at a guess I'd say it's mmap_sem. Perhaps with some assist from the CPU scheduler.
If you change the config to set CONFIG_RWSEM_GENERIC_SPINLOCK=n, CONFIG_RWSEM_XCHGADD_ALGORITHM=y does it help?
Anyway, there's a testcase in bugzilla and it looks like we got us some work to do.
Quoted 86 lines
2.6.18-164.11.1.el5 (centos)
user time: ~60 sec
sys time: ~12 sec2.6.32.9-70.fc12.x86_64 (fedora-12)
user time: ~60 sec
sys time: ~75 sec2.6.33-0.46.rc8.git1.fc13.x86_64 (fedora-12 + rawhide kernel)
user time: ~60 sec
sys time: ~300 secIn all three cases real time regress corresponding to giving numbers.
Binary used for all three cases is exactly the same (compiled on centos). Setups for all three cases so identical as possible (last two - the same fedora-12 setup booted with different kernels).
What can be reason of this regress in performance? Is it possible to tune something to recover performance on 2.6.18 kernel?
I perf'ed on 2.6.32.9-70.fc12.x86_64 kernel
report (top part only):
43.64% dve22lts-mc [kernel] [k]
_spin_lock_irqsave32.93% dve22lts-mc ./dve22lts-mc [.]DBSLLlookup_ret5.37% dve22lts-mc ./dve22lts-mc [.] SuperFastHash 3.76% dve22lts-mc/lib64/libc-2.11.1.so[.]__GI_memcpy2.60% dve22lts-mc [kernel] [k]clear_page_c1.60% dve22lts-mc ./dve22lts-mc [.]index_next_dfsstat:
129875.554435 task-clock-msecs # 10.210 CPUs
1883 context-switches # 0.000 M/sec
17 CPU-migrations # 0.000 M/sec
2695310 page-faults # 0.021 M/sec
298370338040 cycles # 2297.356 M/sec
130581778178 instructions # 0.438 IPC
42517143751 cache-references # 327.368 M/sec
101906904 cache-misses # 0.785 M/seccallgraph(top part only):
53.09% dve22lts-mc [kernel] [k]
_spin_lock_irqsave| |--49.90%-- __down_read_trylock | down_read_trylock | do_page_fault | page_fault | | | |--99.99%-- __GI_memcpy | | | | | |--84.28%-- (nil) | | | | | |--9.78%-- 0x100000000 | | | | | --5.94%-- 0x1 | --0.01%--[...]
| |--49.39%-- __up_read | up_read | | | |--100.00%-- do_page_fault | | page_fault | | | | | |--99.99%-- __GI_memcpy | | | | | | | |--84.18%-- (nil) | | | | | | | |--10.13%-- 0x100000000 | | | | | | | --5.69%-- 0x1 | | --0.01%--[...]
| --0.00%--[...]
--0.72%--
Quoted 13 lines
[...]
On 2.6.33 I see similar picture with spin-lock plus addition of a lot of time spent in cgroup related kernel calls.
If it is necessary, I can attach binary for tests.
Signature · 3 lines
Configure bugmail: https://bugzilla.kernel.org/userprefs.cgi?tab=email ------- You are receiving this mail because: ------- You are on the CC list for the bug.
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
Quoted 2 lines · Andrew Morton
lolz. Catastrophic meltdown. Thanks for doing all that work - at a guess I'd say it's
mmap_sem. [...]
Looks like we dont need to guess, just look at the call graph profile (a'ka the smoking gun):
Quoted 24 lines
Quoted 24 lines
I perf'ed on 2.6.32.9-70.fc12.x86_64 kernel
[...]
callgraph(top part only):
53.09% dve22lts-mc [kernel] [k]
_spin_lock_irqsave| |--49.90%-- __down_read_trylock | down_read_trylock | do_page_fault | page_fault | | | |--99.99%-- __GI_memcpy | | | | | |--84.28%-- (nil) | | | | | |--9.78%-- 0x100000000 | | | | | --5.94%-- 0x1 | --0.01%--[...]
Quoted 16 lines
Quoted 15 lines
| |--49.39%-- __up_read | up_read | | | |--100.00%-- do_page_fault | | page_fault | | | | | |--99.99%-- __GI_memcpy | | | | | | | |--84.18%-- (nil) | | | | | | | |--10.13%-- 0x100000000 | | | | | | | --5.69%-- 0x1 | | --0.01%--Quoted 1 line
[...]
It shows a very brutal amount of page fault invoked mmap_sem spinning overhead.
Quoted 1 line
Perhaps with some assist from the CPU scheduler.
Doesnt look like it, the perf stat numbers show that the scheduler is only very lightly involved:
Quoted 2 lines
Quoted 2 lines
129875.554435 task-clock-msecs # 10.210 CPUs
1883 context-switches # 0.000 M/sec
a context switch only every ~68 milliseconds.
Ingo
Ingo
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
Quoted 3 lines · Ingo Molnar
It shows a very brutal amount of page fault invoked
mmap_semspinning overhead.
Isn't this already fixed? It's the same old "x86-64 rwsemaphores are using the shit-for-brains generic version" thing, and it's fixed by
1838ef1 x86-64, rwsem: 64-bit xadd rwsem implementation 5d0b723 x86: clean up rwsem type system 59c33fa x86-32: clean up rwsem inline asm statements
NOTE! None of those are in 2.6.33 - they were merged afterwards. But they are in 2.6.34-rc1 (and obviously current -git). So Anton would have to compile his own kernel to test his load.
We could mark them as stable material if the load in question is a real load rather than just a test-case. On one of the random page-fault benchmarks the rwsem fix was something like a 400% performance improvement, and it was apparently visible in real life on some crazy SGI "initialize huge heap concurrently on lots of threads" load.
Side note: the reason the spinlock sucks is because of the fair ticket locks, it really does all the wrong things for the rwsem code. That's why old kernels don't show it - the old unfair locks didn't show the same kind of behavior.
Linus
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
Quoted 10 lines · Linus Torvalds
Quoted 3 lines · Ingo Molnar
It shows a very brutal amount of page fault invoked
mmap_semspinning overhead.Isn't this already fixed? It's the same old "x86-64 rwsemaphores are using the shit-for-brains generic version" thing, and it's fixed by
Quoted 7 lines
1838ef1 x86-64, rwsem: 64-bit xadd rwsem implementation 5d0b723 x86: clean up rwsem type system 59c33fa x86-32: clean up rwsem inline asm statements
NOTE! None of those are in 2.6.33 - they were merged afterwards. But they are in 2.6.34-rc1 (and obviously current -git). So Anton would have to compile his own kernel to test his load.
Thanks for info, I will try it now.
Quoted 5 lines
We could mark them as stable material if the load in question is a real load rather than just a test-case. On one of the random page-fault benchmarks the rwsem fix was something like a 400% performance improvement, and it was apparently visible in real life on some crazy SGI "initialize huge heap concurrently on lots of threads" load.
It is not just a test-case, it is real-life code. With real-life problems on 2.6.32 and later :)
Anton.
Quoted 11 lines · Linus Torvalds
Quoted 3 lines · Ingo Molnar
It shows a very brutal amount of page fault invoked
mmap_semspinning overhead.Isn't this already fixed? It's the same old "x86-64 rwsemaphores are using the shit-for-brains generic version" thing, and it's fixed by
1838ef1 x86-64, rwsem: 64-bit xadd rwsem implementation 5d0b723 x86: clean up rwsem type system 59c33fa x86-32: clean up rwsem inline asm statements
Ah, indeed!
Quoted 3 lines
NOTE! None of those are in 2.6.33 - they were merged afterwards. But they are in 2.6.34-rc1 (and obviously current -git). So Anton would have to compile his own kernel to test his load.
another option is to run the rawhide kernel via something like:
yum update --enablerepo=development kernel
this will give kernel-2.6.34-0.13.rc1.git1.fc14.x86_64, which has those changes included.
OTOH that kernel has debugging [lockdep] enabled so it might not be comparable.
Quoted 10 lines
We could mark them as stable material if the load in question is a real load rather than just a test-case. On one of the random page-fault benchmarks the rwsem fix was something like a 400% performance improvement, and it was apparently visible in real life on some crazy SGI "initialize huge heap concurrently on lots of threads" load.
Side note: the reason the spinlock sucks is because of the fair ticket locks, it really does all the wrong things for the rwsem code. That's why old kernels don't show it - the old unfair locks didn't show the same kind of behavior.
Yeah.
Ingo
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
Quoted 10 lines · Ingo Molnar
Quoted 3 lines
NOTE! None of those are in 2.6.33 - they were merged afterwards. But they are in 2.6.34-rc1 (and obviously current -git). So Anton would have to compile his own kernel to test his load.
another option is to run the rawhide kernel via something like:
yum update --enablerepo=development kernelthis will give kernel-2.6.34-0.13.rc1.git1.fc14.x86_64, which has those changes included.
I will apply this commits to 2.6.32, I afraid current OFED (which I need also) will not work on 2.6.33+.
Anton.
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
Andrew Morton
maintainerQuoted 6 lines · On Tue, 23 Mar 2010 19:03:36 +0100 Anton Starikov <[email protected]>…
Quoted 4 lines · Ingo Molnar
Quoted 3 lines
NOTE! None of those are in 2.6.33 - they were merged afterwards. But they are in 2.6.34-rc1 (and obviously current -git). So Anton would have to compile his own kernel to test his load.
Quoted 9 lines
Quoted 6 lines
another option is to run the rawhide kernel via something like:
yum update --enablerepo=development kernelthis will give kernel-2.6.34-0.13.rc1.git1.fc14.x86_64, which has those changes included.
I will apply this commits to 2.6.32, I afraid current OFED (which I need also) will not work on 2.6.33+.
You should be able to simply set CONFIG_RWSEM_GENERIC_SPINLOCK=n, CONFIG_RWSEM_XCHGADD_ALGORITHM=y by hand, as I mentioned earlier?
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
Quoted 5 lines · Andrew Morton
Quoted 2 lines
I will apply this commits to 2.6.32, I afraid current OFED (which I need also) will not work on 2.6.33+.
You should be able to simply set
CONFIG_RWSEM_GENERIC_SPINLOCK=n,CONFIG_RWSEM_XCHGADD_ALGORITHM=yby hand, as I mentioned earlier?
Hm. I tried, but when I do "make oldconfig", then it gets rewritten, so I assume that it conflicts with some other setting from default fedora kernel config. trying to figure out which one exactly.
Anton.
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
Quoted 8 lines · Anton Starikov
Quoted 5 lines · Andrew Morton
Quoted 2 lines
I will apply this commits to 2.6.32, I afraid current OFED (which I need also) will not work on 2.6.33+.
You should be able to simply set
CONFIG_RWSEM_GENERIC_SPINLOCK=n,CONFIG_RWSEM_XCHGADD_ALGORITHM=yby hand, as I mentioned earlier?Hm. I tried, but when I do "make oldconfig", then it gets rewritten, so I assume that it conflicts with some other setting from default fedora kernel config. trying to figure out which one exactly.
Have you tracked this down yet? I just got the patches applied against an older kernel and am running into the same issue.
Thanks,
Robin
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
Quoted 5 lines · Robin Holt
Quoted 4 lines · Anton Starikov
Quoted 3 lines · Andrew Morton
Quoted 2 lines
I will apply this commits to 2.6.32, I afraid current OFED (which I need also) will not work on 2.6.33+.
Quoted 7 lines
Quoted 4 lines
Quoted 2 lines
You should be able to simply set
CONFIG_RWSEM_GENERIC_SPINLOCK=n,CONFIG_RWSEM_XCHGADD_ALGORITHM=yby hand, as I mentioned earlier?Hm. I tried, but when I do "make oldconfig", then it gets rewritten, so I assume that it conflicts with some other setting from default fedora kernel config. trying to figure out which one exactly.
Have you tracked this down yet? I just got the patches applied against an older kernel and am running into the same issue.
I decided to not track down this issue and just applied patches. I understood that with this patches there is no need to change this config options. Am I wrong?
Anton
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
Quoted 11 lines · Anton Starikov
Quoted 8 lines · Robin Holt
Quoted 7 lines · Anton Starikov
Quoted 5 lines · Andrew Morton
Quoted 2 lines
I will apply this commits to 2.6.32, I afraid current OFED (which I need also) will not work on 2.6.33+.
You should be able to simply set
CONFIG_RWSEM_GENERIC_SPINLOCK=n,CONFIG_RWSEM_XCHGADD_ALGORITHM=yby hand, as I mentioned earlier?
Quoted 6 lines
Quoted 4 lines
Quoted 1 line
Hm. I tried, but when I do "make oldconfig", then it gets rewritten, so I assume that it conflicts with some other setting from default fedora kernel config. trying to figure out which one exactly.
Have you tracked this down yet? I just got the patches applied against an older kernel and am running into the same issue.
I decided to not track down this issue and just applied patches. I understood that with this patches there is no need to change this config options. Am I wrong?
We might need to also apply:bafaecd11df15ad5b1e598adc7736afcd38ee13d
Robin
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
Quoted 14 lines · Robin Holt
Quoted 13 lines · Anton Starikov
Quoted 10 lines · Robin Holt
Quoted 8 lines · Anton Starikov
Quoted 5 lines · Andrew Morton
Quoted 2 lines
I will apply this commits to 2.6.32, I afraid current OFED (which I need also) will not work on 2.6.33+.
You should be able to simply set
CONFIG_RWSEM_GENERIC_SPINLOCK=n,CONFIG_RWSEM_XCHGADD_ALGORITHM=yby hand, as I mentioned earlier?Hm. I tried, but when I do "make oldconfig", then it gets rewritten, so I assume that it conflicts with some other setting from default fedora kernel config. trying to figure out which one exactly.
Quoted 7 lines
Quoted 4 lines
Quoted 2 lines
Have you tracked this down yet? I just got the patches applied against an older kernel and am running into the same issue.
I decided to not track down this issue and just applied patches. I understood that with this patches there is no need to change this config options. Am I wrong?
We might need to also apply:
bafaecd11df15ad5b1e598adc7736afcd38ee13d
For the record, these are the patches I have applied to a 2.6.32 kernel from a vendor:
59c33fa7791e9948ba467c2b83e307a0d087ab495d0b7235d83eefdafda300656e97d368afcafc9a1838ef1d782f7527e6defe87e180598622d2d0710d1622d7f526311d87d7da2ee7dd14b73e45d3fcbafaecd11df15ad5b1e598adc7736afcd38ee13d
A quick look at the disassembly makes it look like we are using the rwsem_64, et al.
Robin
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
Quoted 5 lines · Robin Holt
Quoted 4 lines · Anton Starikov
Quoted 3 lines · Andrew Morton
Quoted 2 lines
I will apply this commits to 2.6.32, I afraid current OFED (which I need also) will not work on 2.6.33+.
Quoted 7 lines
Quoted 4 lines
Quoted 2 lines
You should be able to simply set
CONFIG_RWSEM_GENERIC_SPINLOCK=n,CONFIG_RWSEM_XCHGADD_ALGORITHM=yby hand, as I mentioned earlier?Hm. I tried, but when I do "make oldconfig", then it gets rewritten, so I assume that it conflicts with some other setting from default fedora kernel config. trying to figure out which one exactly.
Have you tracked this down yet? I just got the patches applied against an older kernel and am running into the same issue.
I think you can prevent overwriting this options if you set them in arch/x86/configs/x86_64_defconfig
Anton
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
Quoted 3 lines · Andrew Morton
You should be able to simply set
CONFIG_RWSEM_GENERIC_SPINLOCK=n,CONFIG_RWSEM_XCHGADD_ALGORITHM=yby hand, as I mentioned earlier?
No. Doesn't work. The XADD code simply never worked on x86-64, which is why those three commits I pointed at are required.
Oh, and you need one more commit (at least) in addition to the three I already mentioned - the one that actually adds the x86-64 wrappers and Kconfig option:
bafaecd x86-64: support native xadd rwsem implementation
so the minimal list of commits (on top of 2.6.33) is at least
59c33fa x86-32: clean up rwsem inline asm statements 5d0b723 x86: clean up rwsem type system bafaecd x86-64: support native xadd rwsem implementation 1838ef1 x86-64, rwsem: 64-bit xadd rwsem implementation
and I just verified that they at least cherry-pick cleanly (in that order). I _think_ it would be good to also do
0d1622d x86-64, rwsem: Avoid store forwarding hazard in __downgrade_write
but that one is a small detail, not anything fundamentally important.
Linus
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
Quoted 2 lines
I will apply this commits to 2.6.32, I afraid current OFED (which I need also) will not work on 2.6.33+.
What do you need from OFED that is not in 2.6.34-rc1?
Signature · 9 lines
Roland Dreier <[email protected]> For corporate legal information go to: http://www.cisco.com/web/about/doing_business/legal/cri/index.html -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
Quoted 4 lines · Roland Dreier
Quoted 2 lines
I will apply this commits to 2.6.32, I afraid current OFED (which I need also) will not work on 2.6.33+.
What do you need from OFED that is not in 2.6.34-rc1?
I didn't go too 2.6.34-rc1.
I tried 2.6.33, mlx4 driver which comes with kernel produces panic on my hardwire. And OFED-1.5 doesn't support this kernel (probably it still can be compiled, didn't check).
Anton.
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
Quoted 10 lines · Linus Torvalds
Quoted 3 lines · Ingo Molnar
It shows a very brutal amount of page fault invoked
mmap_semspinning overhead.Isn't this already fixed? It's the same old "x86-64 rwsemaphores are using the shit-for-brains generic version" thing, and it's fixed by
Quoted 7 lines
1838ef1 x86-64, rwsem: 64-bit xadd rwsem implementation 5d0b723 x86: clean up rwsem type system 59c33fa x86-32: clean up rwsem inline asm statements
NOTE! None of those are in 2.6.33 - they were merged afterwards. But they are in 2.6.34-rc1 (and obviously current -git). So Anton would have to compile his own kernel to test his load.
Applied mentioned patches. Things didn't improve too much.
before:
prog: Total exploration time 9.880 real 60.620 user 76.970 sys
after:
prog: Total exploration time 9.020 real 59.430 user 66.190 sys
perf report:
38.58% prog [kernel] [k] _spin_lock_irqsave
37.42% prog ./prog [.] DBSLLlookup_ret
6.22% prog ./prog [.] SuperFastHash
3.65% prog /lib64/libc-2.11.1.so [.] __GI_memcpy
2.09% prog ./anderson.6.dve2C [.] get_successors
1.75% prog [kernel] [k] clear_page_c
1.73% prog ./prog [.] index_next_dfs
0.71% prog [kernel] [k] handle_mm_fault
0.38% prog ./prog [.] cb_hook
0.33% prog ./prog [.] get_local
0.32% prog [kernel] [k] page_faultAnton.
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
Quoted 31 lines · Anton Starikov
Quoted 10 lines · Linus Torvalds
Quoted 3 lines · Ingo Molnar
It shows a very brutal amount of page fault invoked
mmap_semspinning overhead.Isn't this already fixed? It's the same old "x86-64 rwsemaphores are using the shit-for-brains generic version" thing, and it's fixed by
Quoted 7 lines
1838ef1 x86-64, rwsem: 64-bit xadd rwsem implementation 5d0b723 x86: clean up rwsem type system 59c33fa x86-32: clean up rwsem inline asm statements
NOTE! None of those are in 2.6.33 - they were merged afterwards. But they are in 2.6.34-rc1 (and obviously current -git). So Anton would have to compile his own kernel to test his load.
Applied mentioned patches. Things didn't improve too much.
before:
prog: Total exploration time 9.880 real 60.620 user 76.970 sysafter:
prog: Total exploration time 9.020 real 59.430 user 66.190 sysperf report:
Quoted 11 lines
38.58% prog [kernel] [k] _spin_lock_irqsave
37.42% prog ./prog [.] DBSLLlookup_ret
6.22% prog ./prog [.] SuperFastHash
3.65% prog /lib64/libc-2.11.1.so [.] __GI_memcpy
2.09% prog ./anderson.6.dve2C [.] get_successors
1.75% prog [kernel] [k] clear_page_c
1.73% prog ./prog [.] index_next_dfs
0.71% prog [kernel] [k] handle_mm_fault
0.38% prog ./prog [.] cb_hook
0.33% prog ./prog [.] get_local
0.32% prog [kernel] [k] page_faultCould you verify with a callgraph profile what that spin_lock_irqsave() is? If those rwsem patches were successfull mmap_sem should no longer have a spinlock to content on, in which case it might be another lock.
If not, something went wrong with backporting those patches.
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
I attach here callgraph.
Also I checked kernel source, actual code which was compiled is exactly what should be after patches.
Do I miss something?
Quoted 49 lines · Peter Zijlstra
Quoted 31 lines · Anton Starikov
Quoted 10 lines · Linus Torvalds
Quoted 3 lines · Ingo Molnar
It shows a very brutal amount of page fault invoked
mmap_semspinning overhead.Isn't this already fixed? It's the same old "x86-64 rwsemaphores are using the shit-for-brains generic version" thing, and it's fixed by
Quoted 7 lines
1838ef1 x86-64, rwsem: 64-bit xadd rwsem implementation 5d0b723 x86: clean up rwsem type system 59c33fa x86-32: clean up rwsem inline asm statements
NOTE! None of those are in 2.6.33 - they were merged afterwards. But they are in 2.6.34-rc1 (and obviously current -git). So Anton would have to compile his own kernel to test his load.
Applied mentioned patches. Things didn't improve too much.
before:
prog: Total exploration time 9.880 real 60.620 user 76.970 sysafter:
prog: Total exploration time 9.020 real 59.430 user 66.190 sysperf report:
Quoted 11 lines
38.58% prog [kernel] [k] _spin_lock_irqsave 37.42% prog ./prog [.] DBSLLlookup_ret 6.22% prog ./prog [.] SuperFastHash 3.65% prog /lib64/libc-2.11.1.so [.] __GI_memcpy 2.09% prog ./anderson.6.dve2C [.] get_successors 1.75% prog [kernel] [k] clear_page_c 1.73% prog ./prog [.] index_next_dfs 0.71% prog [kernel] [k] handle_mm_fault 0.38% prog ./prog [.] cb_hook 0.33% prog ./prog [.] get_local 0.32% prog [kernel] [k] page_faultCould you verify with a callgraph profile what that
spin_lock_irqsave()is? If those rwsem patches were successfullmmap_semshould no longer have a spinlock to content on, in which case it might be another lock.If not, something went wrong with backporting those patches.
Quoted 17 lines · Anton Starikov
Quoted 14 lines · Linus Torvalds
Quoted 3 lines · Ingo Molnar
It shows a very brutal amount of page fault invoked
mmap_semspinning overhead.Isn't this already fixed? It's the same old "x86-64 rwsemaphores are using the shit-for-brains generic version" thing, and it's fixed by
1838ef1 x86-64, rwsem: 64-bit xadd rwsem implementation 5d0b723 x86: clean up rwsem type system 59c33fa x86-32: clean up rwsem inline asm statements
Quoted 6 lines
Quoted 3 lines
NOTE! None of those are in 2.6.33 - they were merged afterwards. But they are in 2.6.34-rc1 (and obviously current -git). So Anton would have to compile his own kernel to test his load.
Applied mentioned patches. Things didn't improve too much.
Yeah, I missed at least one commit, namely
bafaecd x86-64: support native xadd rwsem implementation
which is the one that actually makes x86-64 able to use the xadd version.
Linus
I think we got a winner!
Problem seems to be fixed.
Just for record, I used next patches:
59c33fa7791e9948ba467c2b83e307a0d087ab495d0b7235d83eefdafda300656e97d368afcafc9a1838ef1d782f7527e6defe87e180598622d2d0714126faf0ab7417fbc6eb99fb0fd407e01e9e9dfebafaecd11df15ad5b1e598adc7736afcd38ee13d0d1622d7f526311d87d7da2ee7dd14b73e45d3fc
Thanks,
Anton.
Quoted 28 lines · Linus Torvalds
Quoted 17 lines · Anton Starikov
Quoted 14 lines · Linus Torvalds
Quoted 3 lines · Ingo Molnar
It shows a very brutal amount of page fault invoked
mmap_semspinning overhead.Isn't this already fixed? It's the same old "x86-64 rwsemaphores are using the shit-for-brains generic version" thing, and it's fixed by
1838ef1 x86-64, rwsem: 64-bit xadd rwsem implementation 5d0b723 x86: clean up rwsem type system 59c33fa x86-32: clean up rwsem inline asm statements
Quoted 6 lines
Quoted 3 lines
NOTE! None of those are in 2.6.33 - they were merged afterwards. But they are in 2.6.34-rc1 (and obviously current -git). So Anton would have to compile his own kernel to test his load.
Applied mentioned patches. Things didn't improve too much.
Quoted 7 lines
Yeah, I missed at least one commit, namely
bafaecd x86-64: support native xadd rwsem implementation
which is the one that actually makes x86-64 able to use the xadd version.
Linus
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
Quoted 5 lines · Anton Starikov
I think we got a winner!
Problem seems to be fixed.
Quoted 8 lines
Just for record, I used next patches:
59c33fa7791e9948ba467c2b83e307a0d087ab495d0b7235d83eefdafda300656e97d368afcafc9a1838ef1d782f7527e6defe87e180598622d2d0714126faf0ab7417fbc6eb99fb0fd407e01e9e9dfebafaecd11df15ad5b1e598adc7736afcd38ee13d0d1622d7f526311d87d7da2ee7dd14b73e45d3fc
Ok. If you have performance numbers for before/after these patches for your actual workload, I'd suggest posting them to [email protected], and maybe those rwsem fixes will get back-ported.
The patches are pretty small, and should be fairly safe. So they are certainly stable material.
Linus
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
Tomorrow I will try to patch and check 2.6.33 and see are this patches enough to restore performance or not, because on 2.6.33 kernel performance issue also used to involve somehow crgoup business (and performance was terrible even comparing to broken 2.6.32). If it will not fix 2.6.33, then I will ask to reopen the bug, otherwise I will post to stable@.
Thanks again for help,
Anton.
Quoted 25 lines · Linus Torvalds
Quoted 5 lines · Anton Starikov
I think we got a winner!
Problem seems to be fixed.
Quoted 8 lines
Just for record, I used next patches:
59c33fa7791e9948ba467c2b83e307a0d087ab495d0b7235d83eefdafda300656e97d368afcafc9a1838ef1d782f7527e6defe87e180598622d2d0714126faf0ab7417fbc6eb99fb0fd407e01e9e9dfebafaecd11df15ad5b1e598adc7736afcd38ee13d0d1622d7f526311d87d7da2ee7dd14b73e45d3fcOk. If you have performance numbers for before/after these patches for your actual workload, I'd suggest posting them to [email protected], and maybe those rwsem fixes will get back-ported.
The patches are pretty small, and should be fairly safe. So they are certainly stable material.
Linus
Quoted 17 lines · Linus Torvalds
Quoted 5 lines · Anton Starikov
I think we got a winner!
Problem seems to be fixed.
Quoted 8 lines
Just for record, I used next patches:
59c33fa7791e9948ba467c2b83e307a0d087ab495d0b7235d83eefdafda300656e97d368afcafc9a1838ef1d782f7527e6defe87e180598622d2d0714126faf0ab7417fbc6eb99fb0fd407e01e9e9dfebafaecd11df15ad5b1e598adc7736afcd38ee13d0d1622d7f526311d87d7da2ee7dd14b73e45d3fc
Quoted 6 lines
Ok. If you have performance numbers for before/after these patches for your actual workload, I'd suggest posting them to [email protected], and maybe those rwsem fixes will get back-ported.
The patches are pretty small, and should be fairly safe. So they are certainly stable material.
We havent had any stability problems with them, except one trivial build bug, so -stable would be nice.
Ingo
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
Quoted 3 lines · Ingo Molnar
We havent had any stability problems with them, except one trivial build bug, so -stable would be nice.
Oh, you're right. There was that UML build bug. But I think that was included in the list of commits Anton had - commit 4126faf0ab ("x86: Fix breakage of UML from the changes in the rwsem system").
Linus
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
Yes, it is included into my list.
When I will submit it into stable, I will include it also.
Anton
Quoted 4 lines · Linus Torvalds
Quoted 1 line · Ingo Molnar
Quoted 8 lines
Quoted 2 lines
We havent had any stability problems with them, except one trivial build bug, so -stable would be nice.
Oh, you're right. There was that UML build bug. But I think that was included in the list of commits Anton had - commit
4126faf0ab("x86: Fix breakage of UML from the changes in the rwsem system").Linus
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
Quoted 8 lines · Linus Torvalds
Quoted 3 lines · Ingo Molnar
We havent had any stability problems with them, except one trivial build bug, so -stable would be nice.
Oh, you're right. There was that UML build bug. But I think that was included in the list of commits Anton had - commit
4126faf0ab("x86: Fix breakage of UML from the changes in the rwsem system").
It would be also nice to get that change into 2.6.32 stable. That is widely used on larger systems.
-Andi
Signature · 1 line
[email protected] -- Speaking for myself only.
Quoted 3 lines · Andi Kleen
It would be also nice to get that change into 2.6.32 stable. That is widely used on larger systems.
Looking at the changes to the files in question, it looks like it should all apply cleanly to 2.6.32, so I don't see any reason not to backport further back.
Somebody should double-check, though.
Linus
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
Quoted 4 lines · Linus Torvalds
Quoted 1 line · Andi Kleen
Quoted 8 lines
Quoted 2 lines
It would be also nice to get that change into 2.6.32 stable. That is widely used on larger systems.
Looking at the changes to the files in question, it looks like it should all apply cleanly to 2.6.32, so I don't see any reason not to backport further back.
Somebody should double-check, though.
I have queued them all up for .33 and .32-stable kernel releases now.
thanks,
greg k-h
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
Andrew Morton
maintainerQuoted 4 lines · On Tue, 23 Mar 2010 18:34:09 +0100 Ingo Molnar <[email protected]> wrote:
It shows a very brutal amount of page fault invoked
mmap_semspinning overhead.
Yes. Note that we fall off a cliff at nine threads on a 16-way. As soon as a core gets two threads scheduled onto it? Probably triggered by an MM change, possibly triggered by a sched change which tickled a preexisting MM shortcoming. Who knows.
Anton, we have an executable binary in the bugzilla report but it would be nice to also have at least a description of what that code is actually doing. A quick strace shows quite a lot of mprotect activity. A pseudo-code walkthrough, perhaps?
Thanks.
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
Quoted 4 lines · Andrew Morton
Anton, we have an executable binary in the bugzilla report but it would be nice to also have at least a description of what that code is actually doing. A quick strace shows quite a lot of mprotect activity. A pseudo-code walkthrough, perhaps?
Right now can't say too much about the code (we just gave a chance to neighbor group to run their code on our cluster, so I'm totally unfriendly with this code). I will forward your question to them.
But probably right now you can get more information (including sources) here http://fmt.cs.utwente.nl/tools/ltsmin/
Anton
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
Quoted 10 lines · Andrew Morton
Quoted 4 lines · On Tue, 23 Mar 2010 18:34:09 +0100 Ingo Molnar <[email protected]> wrote:
It shows a very brutal amount of page fault invoked
mmap_semspinning overhead.Yes. Note that we fall off a cliff at nine threads on a 16-way. As soon as a core gets two threads scheduled onto it?
it's AMD Opterons so no SMT.
My (wild) guess would be that 8 cpus can still do cacheline ping-pong reasonably efficiently, but it starts breaking down very seriously with 9 or more cores bouncing the same single cache-line.
Breakdowns in scalability are usually very non-linear, for hardware and software reasons. '8 threads' sounds like a hw limit to me. From the scheduler POV there's no big difference between 8 or 9 CPUs used [this is non-HT] - with 8 or 7 cores still idle.
Ingo
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
Although case is solved, I will post description for testcase program. Just in case someone wonder or would like to keep it for some later tests.
------------------------------------------------------------------------
It is a parallel model checker. The command line you used does reachability on the state space of mode anderson.6, meaning that it searches through all possible states (int vectors). Each thread gets a vector from the queue, calculates its successor states and puts them in a lock-less static hash table (pseudo BFS exploration because the threads each have there own queue).
How did ingo run the binary? Because the static table size should be chosen to fit into memory. "-s 27" allocates 2^27 * (|vector| + 1 ) * sizeof(int) bytes. |vector| is equal to 19 for anderson.6, ergo the table size is 10GB. This could explain the huge number of page faults ingo gets.
But anyway, you can imagine that the code is quiet jumpy and has a big memory footprint, so the page faults may also be normal.
------------------------------------------------------------------------
Quoted 6 lines · Andrew Morton
Anton, we have an executable binary in the bugzilla report but it would be nice to also have at least a description of what that code is actually doing. A quick strace shows quite a lot of mprotect activity. A pseudo-code walkthrough, perhaps?
Thanks.
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
Quoted 33 lines · Andrew Morton
(switched to email. Please respond via emailed reply-to-all, not via the bugzilla web interface).
Quoted 18 lines · On Tue, 23 Mar 2010 16:13:25 GMT [email protected] wrote:
https://bugzilla.kernel.org/show_bug.cgi?id=15618
Summary: 2.6.18->2.6.32->2.6.33 huge regression in performance Product: Process Management Version: 2.5 Kernel Version: 2.6.32 Platform: All OS/Version: Linux Tree: Mainline Status: NEW Severity: high Priority: P1 Component: Other AssignedTo: [email protected] ReportedBy: [email protected] Regression: NoQuoted 5 lines
We have benchmarked some multithreaded code here on 16-core/4-way opteron 8356 host on number of kernels (see below) and found strange results. Up to 8 threads we didn't see any noticeable differences in performance, but starting from 9 threads performance diverges substantially. I provide here results for 14 threads
lolz. Catastrophic meltdown. Thanks for doing all that work - at a guess I'd say it's
mmap_sem. Perhaps with some assist from the CPU scheduler.
Quoted 6 lines
If you change the config to set
CONFIG_RWSEM_GENERIC_SPINLOCK=n,CONFIG_RWSEM_XCHGADD_ALGORITHM=ydoes it help?Anyway, there's a testcase in bugzilla and it looks like we got us some work to do.
<snip>
I had an "opportunity" to investigate page fault behavior on 2.6.18+ [RHEL5.4] on an 8-socket Istanbul system earlier this year. When I saw this mail, I collected up the data I had from that adventure and ran additional tests on 2.6.33 and 2.6.34-rc1. I have attached plots for what "per node" and "system wide" page fault scalability.
The per node plot [#1] shows the page fault rate of 1 to 6 [nr_cores_per_socket] tasks [processes] and threads faulting in a fixed GB/task at the same time on a single socket. The system wide plot [#3] show 1 to 48 [nr_sockets * nr_cores_per_socket] tasks and threads again
faulting in a fixed GB/task... For the latter test, I load one core
per socket at at time, then add the 2nd core per socket, ... In all cases, the individual tasks/threads are fork()ed/pthread_create()d by a parent bound to the cpu where they'll run to obtain node-local kernel data structures. The tests run with SCHED_FIFO.
I plot both "faults per wall clock second"--the aggregate rate--and "faults per cpu second" or normalized rate. The per node scalability doesn't look all that different across the 3 releases, especially the faults per cpu seconds curves. However, in the system wide multi-threaded tests, 2.6.33 is an anomaly compared to both 2.6.18+ and 2.6.34-rc1. The 2.6.18+ and 2.6.34.rc1 multi-threaded tests show a lot of noise and, of course, a lot lower fault rate relative the the multi-task tests. I aborted the 2.6.33 system wide multi-threaded test at 32 threads because it was just taking too long.
Unfortunately, with this many curves, the legends obscure much of the plot. So, rather than bloat this message any more, I've packaged up the raw data along with plots with and without legends and placed the tarball here:
http://free.linux.hp.com/~lts/Pft/
That directory also contains the source for the version of the pft test used, along with the scripts used to run the tests and plot the results. Note that some manual editing of the "plot annotations" in the raw data was required to generate several different plots from the same data.
The pft test is a highly, uh, "evolved" version of pft.c that Christoph Lameter pointed me at a few years ago. This version requires a patched libnuma with the v2 api. The required patch to the numactl-2.0.3 package is included in the test tarball. [I've contacted Cliff about getting the patch into 2.0.4.]
Lee