search for: performancetest

Hi James, I tested (as I wrote a few days ago) the latest PV drivers release, and they seem to work correctly apart of the "Safely remove Xen Net Device Driver" tray icon glitch. I made a series of benchmarks with PassMark''s PerformanceTest on 6 twin concurrent VMs with the PV drivers installed, both with the /GPLPV switch on and off, and on one lonely VM, still in both situations. I tested in particular the disk performance and I noticed a decrease of I/O throughput, while at the same time a significant decrease of the VM CPU utiliz...

...sults by T-test [1], and generate an abundant/meaningful HTML files. It's helpful to check if performance regression exists significantly. If you have interest, we also use this in your netperf testing. Attached analysis results of netperf tests. [1] https://github.com/autotest/virt-test/wiki/PerformanceTesting Thanks, Amos > Also I guess this 1% difference is in the noise, right? > Could you share data about host CPU utilization during > these runs please? -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://lists.linuxfoundation.org/pipermail/virtu...

...Toontown Rewritten: Unhandled page fault on read access to 0x00000000 at address 0x1fea2b7 (thread 0064) 48555 Helm Standalone/VST plugin 32bit version has random content in window, 64bit version works OK 48856 Renegade Ops needs D3DX10GetImageInfoFromMemory implementation 48859 PassMark PerformanceTest 10 crashes during start since wine-4.11 49418 Wargaming.net -> Game Center -> starts with the message: Unable to connect to the content service. Please check you internet connection and try again. 49436 64-bit Diablo III hangs on startup since 5.11 49474 Chaos Legion does not work wi...

On Mon, Dec 16, 2013 at 04:16:29PM -0800, Michael Dalton wrote: > Commit 2613af0ed18a ("virtio_net: migrate mergeable rx buffers to page frag > allocators") changed the mergeable receive buffer size from PAGE_SIZE to > MTU-size, introducing a single-stream regression for benchmarks with large > average packet size. There is no single optimal buffer size for all >

On Mon, Dec 16, 2013 at 04:16:29PM -0800, Michael Dalton wrote: > Commit 2613af0ed18a ("virtio_net: migrate mergeable rx buffers to page frag > allocators") changed the mergeable receive buffer size from PAGE_SIZE to > MTU-size, introducing a single-stream regression for benchmarks with large > average packet size. There is no single optimal buffer size for all >