[sheepdog-users] 50.000 iops per VM

Stefan Priebe s.priebe at profihost.ag
Mon Jul 9 20:13:10 CEST 2012


Hi Christoph,

thanks for your reply.

Am 09.07.2012 16:49, schrieb Christoph Hellwig:
> Before I would like to let you try 29bfdbd6a95fdf8d827e177046dbab12ee342611
> or earlier?
I already tried that. It gives me the same results.

>>> Can you also do a perf record -g on both a storage node and the
>>> kvm box to see if there's anything interesting on them?
>>
>> Option -g is not known by my perf command?
>
> perf record -g records the callgraph, and it's been there for a long
> time.  Did you try that above line or something like perf -g record?
*argh* i really tried -g record ;-( i'm on holiday right now so it will 
take some days. What is the expected output of this command? Should i 
attach it?

>> is a perf record sleep 10 enough? Should i upload then the data file
>> somewhere?
>
> Would be nice to get a slightly long run.
How long

>> Snapshot of perf top from KVM host:
>>   14.96%  [kernel]                     [k] _raw_spin_lock
>
> With the callchains we could expand what spinlock we hammer here.
?!

>>    8.13%  kvm                          [.] 0x00000000001d8084
>
> Also if kvm/qemu is self-build can you build it with -g to get debug
> info?  If not see if there is a qemu-dbg/kvm-dbg or similar package for
> your distribution.

It is self build - i'll do a debug.

>> Snapshot of perf top from sheep node (not acting as the gateway /
>> target for kvm):
>>    2,78%  libgcc_s.so.1         [.] 0x000000000000e72b
>>    2,21%  [kernel]              [k] __schedule
>>    2,14%  [kernel]              [k] ahci_port_intr
>>    2,08%  [kernel]              [k] _raw_spin_lock
>>    1,77%  [kernel]              [k] _raw_spin_lock_irqsave
>>    1,15%  [kernel]              [k] ahci_interrupt
>>    1,11%  [kernel]              [k] ahci_scr_read
>>    0,94%  [kernel]              [k] kmem_cache_alloc
>>    0,90%  [kernel]              [k] _raw_spin_lock_irq
>>    0,81%  [kernel]              [k] menu_select
>>    0,76%  [kernel]              [k] _raw_spin_unlock_irqrestore
>>    0,73%  libpthread-2.11.3.so  [.] pthread_mutex_lock
>>    0,70%  libc-2.11.3.so        [.] vfprintf
>
> Mostly not spending any noticable CPU time, which is quite interesting.

Yes the sheep acting as gateway is taking 20x times more CPU than the 
node sheep processess.

Stefan



More information about the sheepdog-users mailing list