* spin_lock contention in shrink_inactive_list
@ 2013-05-29 18:45 Bernd Schubert
0 siblings, 0 replies; only message in thread
From: Bernd Schubert @ 2013-05-29 18:45 UTC (permalink / raw)
To: linux-mm
Hi all,
we got a report about a system where fhgfs has a rather high latency
(fhgfs is running on top of xfs) and while investigating the system I
noticed that the system was rather cpu bound.
I'm not sure, but somehow CPU usage went down after disabling swap.
Is the lock contention a known issue?
kernel version: 3.8.2
> spin_lock
> # Overhead Command Shared Object Symbol
> # ........ ............... ............................................................................................. ..............................................................................................................................
> #
> 63.93% fhgfs-storage/M [kernel.kallsyms] 0xffffffff815d31bd k [k] _raw_spin_lock_irq
> |
> --- _raw_spin_lock_irq
> |
> |--99.44%-- shrink_inactive_list
> | shrink_lruvec
> | shrink_zone
> | shrink_zones
> | do_try_to_free_pages
> | try_to_free_pages
> | __alloc_pages_slowpath
> | __alloc_pages_nodemask
> | |
> | |--99.98%-- alloc_pages_current
> | | |
> | | |--100.00%-- __page_cache_alloc
> | | | |
> | | | |--100.00%-- grab_cache_page_write_begin
> | | | | xfs_vm_write_begin
> | | | | generic_perform_write
> | | | | generic_file_buffered_write
> | | | | xfs_file_buffered_aio_write
> | | | | xfs_file_aio_write
> | | | | do_sync_write
> | | | | vfs_write
> | | | | sys_write
> | | | | system_call_fastpath
> | | | | 0x2aaaaba8f4ed
> | | | --0.00%-- [...]
> | | --0.00%-- [...]
> | --0.02%-- [...]
> --0.56%-- [...]
>
> 3.73% fhgfs-storage/M [kernel.kallsyms] 0xffffffff815d3533 k [k] _raw_spin_lock_irqsave
> |
> --- _raw_spin_lock_irqsave
> |
> |--97.82%-- pagevec_lru_move_fn
> | |
> | |--91.28%-- __pagevec_lru_add
> | | |
> | | |--86.17%-- __lru_cache_add
> | | | add_to_page_cache_lru
> | | | grab_cache_page_write_begin
> | | | xfs_vm_write_begin
> | | | generic_perform_write
> | | | generic_file_buffered_write
> | | | xfs_file_buffered_aio_write
> | | | xfs_file_aio_write
> | | | do_sync_write
> | | | vfs_write
Thanks,
Bernd
--
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>
^ permalink raw reply [flat|nested] only message in thread
only message in thread, other threads:[~2013-05-29 18:45 UTC | newest]
Thread overview: (only message) (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2013-05-29 18:45 spin_lock contention in shrink_inactive_list Bernd Schubert
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.