Re: I/O blocked while dirty pages are being flushed

2013-04-09 Thread Jan Kara
On Mon 25-03-13 08:31:43, Fredrik Tolf wrote: > On Sun, 24 Mar 2013, Bart Van Assche wrote: > >On 03/24/13 06:12, Fredrik Tolf wrote: > >>While this flush is running, I find that many a process goes into disk > >>sleep waiting for the flush to complete. This includes the process > >>manipulating th

Re: I/O blocked while dirty pages are being flushed

2013-03-25 Thread Fredrik Tolf
On Sun, 24 Mar 2013, Eric Wong wrote: Fredrik Tolf wrote: It is worth noting, also, that this seems to be a situation introduced somewhere between 2.6.26 and 2.6.32, because I started noticing it when I upgraded from Debian 5.0 to 6.0. I've since tried it on 3.2.0, 3.5.4 and 3.7.1, and it appea

Re: I/O blocked while dirty pages are being flushed

2013-03-25 Thread Fredrik Tolf
On Sun, 24 Mar 2013, Bart Van Assche wrote: On 03/24/13 06:12, Fredrik Tolf wrote: While this flush is running, I find that many a process goes into disk sleep waiting for the flush to complete. This includes the process manipulating the mmapped file whenever it tries to redirty a page currently

Re: I/O blocked while dirty pages are being flushed

2013-03-24 Thread Bart Van Assche
On 03/24/13 06:12, Fredrik Tolf wrote: While this flush is running, I find that many a process goes into disk sleep waiting for the flush to complete. This includes the process manipulating the mmapped file whenever it tries to redirty a page currently waiting to be flushed, but also, for instanc

Re: I/O blocked while dirty pages are being flushed

2013-03-23 Thread Eric Wong
Fredrik Tolf wrote: > It is worth noting, also, that this seems to be a situation > introduced somewhere between 2.6.26 and 2.6.32, because I started > noticing it when I upgraded from Debian 5.0 to 6.0. I've since tried > it on 3.2.0, 3.5.4 and 3.7.1, and it appears in every version. > However, I

I/O blocked while dirty pages are being flushed

2013-03-23 Thread Fredrik Tolf
Dear list, I've got an mmapped file (a Berkeley DB region file) with an access pattern such that it gets some 10-40 MBs of dirtied pages a couple of times per minute. When the VM comes around to flush these pages to disk, that causes loads of problems. Since the dirty pages are rather intersp