Re: [Qemu-block] block migration and MAX_IN_FLIGHT_IO

2018-03-07 Thread Peter Lieven
Am 07.03.2018 um 10:47 schrieb Stefan Hajnoczi: > On Wed, Mar 7, 2018 at 7:55 AM, Peter Lieven wrote: >> Am 06.03.2018 um 17:35 schrieb Peter Lieven: >>> Am 06.03.2018 um 17:07 schrieb Stefan Hajnoczi: On Mon, Mar 05, 2018 at 02:52:16PM +, Dr. David Alan Gilbert wrote: > * Peter Lieve

Re: [Qemu-block] block migration and MAX_IN_FLIGHT_IO

2018-03-07 Thread Stefan Hajnoczi
On Wed, Mar 7, 2018 at 7:55 AM, Peter Lieven wrote: > Am 06.03.2018 um 17:35 schrieb Peter Lieven: >> Am 06.03.2018 um 17:07 schrieb Stefan Hajnoczi: >>> On Mon, Mar 05, 2018 at 02:52:16PM +, Dr. David Alan Gilbert wrote: * Peter Lieven (p...@kamp.de) wrote: > Am 05.03.2018 um 12:45 s

Re: [Qemu-block] block migration and MAX_IN_FLIGHT_IO

2018-03-06 Thread Peter Lieven
Am 06.03.2018 um 17:35 schrieb Peter Lieven: > Am 06.03.2018 um 17:07 schrieb Stefan Hajnoczi: >> On Mon, Mar 05, 2018 at 02:52:16PM +, Dr. David Alan Gilbert wrote: >>> * Peter Lieven (p...@kamp.de) wrote: Am 05.03.2018 um 12:45 schrieb Stefan Hajnoczi: > On Thu, Feb 22, 2018 at 12:13

Re: [Qemu-block] block migration and MAX_IN_FLIGHT_IO

2018-03-06 Thread Peter Lieven
Am 06.03.2018 um 17:07 schrieb Stefan Hajnoczi: > On Mon, Mar 05, 2018 at 02:52:16PM +, Dr. David Alan Gilbert wrote: >> * Peter Lieven (p...@kamp.de) wrote: >>> Am 05.03.2018 um 12:45 schrieb Stefan Hajnoczi: On Thu, Feb 22, 2018 at 12:13:50PM +0100, Peter Lieven wrote: > I stumbled a

Re: [Qemu-block] block migration and MAX_IN_FLIGHT_IO

2018-03-06 Thread Peter Lieven
Am 05.03.2018 um 15:52 schrieb Dr. David Alan Gilbert: > * Peter Lieven (p...@kamp.de) wrote: >> Am 05.03.2018 um 12:45 schrieb Stefan Hajnoczi: >>> On Thu, Feb 22, 2018 at 12:13:50PM +0100, Peter Lieven wrote: I stumbled across the MAX_INFLIGHT_IO field that was introduced in 2015 and w

Re: [Qemu-block] block migration and MAX_IN_FLIGHT_IO

2018-03-06 Thread Stefan Hajnoczi
On Mon, Mar 05, 2018 at 02:52:16PM +, Dr. David Alan Gilbert wrote: > * Peter Lieven (p...@kamp.de) wrote: > > Am 05.03.2018 um 12:45 schrieb Stefan Hajnoczi: > > > On Thu, Feb 22, 2018 at 12:13:50PM +0100, Peter Lieven wrote: > > >> I stumbled across the MAX_INFLIGHT_IO field that was introduc

Re: [Qemu-block] block migration and MAX_IN_FLIGHT_IO

2018-03-05 Thread Dr. David Alan Gilbert
* Peter Lieven (p...@kamp.de) wrote: > Am 05.03.2018 um 12:45 schrieb Stefan Hajnoczi: > > On Thu, Feb 22, 2018 at 12:13:50PM +0100, Peter Lieven wrote: > >> I stumbled across the MAX_INFLIGHT_IO field that was introduced in 2015 > >> and was curious what was the reason > >> to choose 512MB as rea

Re: [Qemu-block] block migration and MAX_IN_FLIGHT_IO

2018-03-05 Thread Peter Lieven
Am 05.03.2018 um 12:45 schrieb Stefan Hajnoczi: > On Thu, Feb 22, 2018 at 12:13:50PM +0100, Peter Lieven wrote: >> I stumbled across the MAX_INFLIGHT_IO field that was introduced in 2015 and >> was curious what was the reason >> to choose 512MB as readahead? The question is that I found that the s

Re: [Qemu-block] block migration and MAX_IN_FLIGHT_IO

2018-03-05 Thread Stefan Hajnoczi
On Thu, Feb 22, 2018 at 12:13:50PM +0100, Peter Lieven wrote: > I stumbled across the MAX_INFLIGHT_IO field that was introduced in 2015 and > was curious what was the reason > to choose 512MB as readahead? The question is that I found that the source VM > gets very unresponsive I/O wise > while t

[Qemu-block] block migration and MAX_IN_FLIGHT_IO

2018-02-22 Thread Peter Lieven
Hi, I stumbled across the MAX_INFLIGHT_IO field that was introduced in 2015 and was curious what was the reason to choose 512MB as readahead? The question is that I found that the source VM gets very unresponsive I/O wise while the initial 512MB are read and furthermore seems to stay unreaspo