Re: [Qemu-block] [PATCH 1/1] mirror: double performance of the bulk stage if the disc is full

2016-07-13 Thread Vladimir Sementsov-Ogievskiy
On 12.07.2016 16:51, Kevin Wolf wrote: Am 12.07.2016 um 11:36 hat Denis V. Lunev geschrieben: From: Vladimir Sementsov-Ogievskiy Mirror can do up to 16 in-flight requests, but actually on full copy (the whole source disk is non-zero) in-flight is always 1. This

Re: [Qemu-block] [PATCH 1/1] mirror: double performance of the bulk stage if the disc is full

2016-07-12 Thread Kevin Wolf
Am 12.07.2016 um 11:36 hat Denis V. Lunev geschrieben: > From: Vladimir Sementsov-Ogievskiy > > Mirror can do up to 16 in-flight requests, but actually on full copy > (the whole source disk is non-zero) in-flight is always 1. This happens > as the request is not limited

Re: [Qemu-block] [PATCH 1/1] mirror: double performance of the bulk stage if the disc is full

2016-07-12 Thread Paolo Bonzini
On 12/07/2016 11:36, Denis V. Lunev wrote: > From: Vladimir Sementsov-Ogievskiy > > Mirror can do up to 16 in-flight requests, but actually on full copy > (the whole source disk is non-zero) in-flight is always 1. This happens > as the request is not limited in size:

[Qemu-block] [PATCH 1/1] mirror: double performance of the bulk stage if the disc is full

2016-07-12 Thread Denis V. Lunev
From: Vladimir Sementsov-Ogievskiy Mirror can do up to 16 in-flight requests, but actually on full copy (the whole source disk is non-zero) in-flight is always 1. This happens as the request is not limited in size: the data occupies maximum available capacity of s->buf.