search for: benefitial

On Thu, Apr 04, 2019 at 11:52:46AM -0400, Michael S. Tsirkin wrote: > I simply love it that you have analysed the individual impact of > each patch! Great job! Thanks! I followed Stefan's suggestions! > > For comparison's sake, it could be IMHO benefitial to add a column > with virtio-net+vhost-net performance. > > This will both give us an idea about whether the vsock layer introduces > inefficiencies, and whether the virtio-net idea has merit. > Sure, I already did TCP tests on virtio-net + vhost, starting qemu in this way: $ q...

On Thu, Apr 04, 2019 at 11:52:46AM -0400, Michael S. Tsirkin wrote: > I simply love it that you have analysed the individual impact of > each patch! Great job! Thanks! I followed Stefan's suggestions! > > For comparison's sake, it could be IMHO benefitial to add a column > with virtio-net+vhost-net performance. > > This will both give us an idea about whether the vsock layer introduces > inefficiencies, and whether the virtio-net idea has merit. > Sure, I already did TCP tests on virtio-net + vhost, starting qemu in this way: $ q...

...ng-your-x-core-cpu which uses http://code.google.com/p/ppss/ for parralel processing. So, can anyone tell me if parralel processing happens automatically on CentOS, or would I need to use this script as well? We mainly have Dual Core & Dual CPU, Dual Core (i.e. 8 cores) servers and it would be benefitial to know whether any applications on the server could automatically use all 8 cores, or whether I need todo something on the servers to get this working? -- Kind Regards Rudi Ahlers SoftDux Website: http://www.SoftDux.com Technical Blog: http://Blog.SoftDux.com Office: 087 805 9573 Cell: 082 554...

On 2018/12/6 ??6:54, Michael S. Tsirkin wrote: > When use_napi is set, let's enable BQLs. Note: some of the issues are > similar to wifi. It's worth considering whether something similar to > commit 36148c2bbfbe ("mac80211: Adjust TSQ pacing shift") might be > benefitial. I've played a similar patch several days before. The tricky part is the mode switching between napi and no napi. We should make sure when the packet is sent and trakced by BQL,? it should be consumed by BQL as well. I did it by tracking it through skb->cb.? And deal with the freeze by...

On 2018/12/6 ??6:54, Michael S. Tsirkin wrote: > When use_napi is set, let's enable BQLs. Note: some of the issues are > similar to wifi. It's worth considering whether something similar to > commit 36148c2bbfbe ("mac80211: Adjust TSQ pacing shift") might be > benefitial. I've played a similar patch several days before. The tricky part is the mode switching between napi and no napi. We should make sure when the packet is sent and trakced by BQL,? it should be consumed by BQL as well. I did it by tracking it through skb->cb.? And deal with the freeze by...

...00, Michael S. Tsirkin wrote: > > > I simply love it that you have analysed the individual impact of > > > each patch! Great job! > > > > Thanks! I followed Stefan's suggestions! > > > > > > > > For comparison's sake, it could be IMHO benefitial to add a column > > > with virtio-net+vhost-net performance. > > > > > > This will both give us an idea about whether the vsock layer introduces > > > inefficiencies, and whether the virtio-net idea has merit. > > > > > > > Sure, I already...

...00, Michael S. Tsirkin wrote: > > > I simply love it that you have analysed the individual impact of > > > each patch! Great job! > > > > Thanks! I followed Stefan's suggestions! > > > > > > > > For comparison's sake, it could be IMHO benefitial to add a column > > > with virtio-net+vhost-net performance. > > > > > > This will both give us an idea about whether the vsock layer introduces > > > inefficiencies, and whether the virtio-net idea has merit. > > > > > > > Sure, I already...

...is set, let's enable BQLs. Note: some of the issues are >>>>>>> similar to wifi. It's worth considering whether something similar to >>>>>>> commit 36148c2bbfbe ("mac80211: Adjust TSQ pacing shift") might be >>>>>>> benefitial. >>>>>> I've played a similar patch several days before. The tricky part is the mode >>>>>> switching between napi and no napi. We should make sure when the packet is >>>>>> sent and trakced by BQL,? it should be consumed by BQL as well. I d...

...is set, let's enable BQLs. Note: some of the issues are >>>>>>> similar to wifi. It's worth considering whether something similar to >>>>>>> commit 36148c2bbfbe ("mac80211: Adjust TSQ pacing shift") might be >>>>>>> benefitial. >>>>>> I've played a similar patch several days before. The tricky part is the mode >>>>>> switching between napi and no napi. We should make sure when the packet is >>>>>> sent and trakced by BQL,? it should be consumed by BQL as well. I d...

...t;>> When use_napi is set, let's enable BQLs. Note: some of the issues are >>>>> similar to wifi. It's worth considering whether something similar to >>>>> commit 36148c2bbfbe ("mac80211: Adjust TSQ pacing shift") might be >>>>> benefitial. >>>> I've played a similar patch several days before. The tricky part is the mode >>>> switching between napi and no napi. We should make sure when the packet is >>>> sent and trakced by BQL,? it should be consumed by BQL as well. >>> I just went ov...

...ael S. Tsirkin wrote: >>> When use_napi is set, let's enable BQLs. Note: some of the issues are >>> similar to wifi. It's worth considering whether something similar to >>> commit 36148c2bbfbe ("mac80211: Adjust TSQ pacing shift") might be >>> benefitial. >> >> I've played a similar patch several days before. The tricky part is the mode >> switching between napi and no napi. We should make sure when the packet is >> sent and trakced by BQL,? it should be consumed by BQL as well. > > I just went over the patch again...

...ael S. Tsirkin wrote: >>> When use_napi is set, let's enable BQLs. Note: some of the issues are >>> similar to wifi. It's worth considering whether something similar to >>> commit 36148c2bbfbe ("mac80211: Adjust TSQ pacing shift") might be >>> benefitial. >> >> I've played a similar patch several days before. The tricky part is the mode >> switching between napi and no napi. We should make sure when the packet is >> sent and trakced by BQL,? it should be consumed by BQL as well. > > I just went over the patch again...

> I agree, which is why I wrote the OggPCM draft when we already have FLAC. > These > formats are not difficult to design or implement, and I think the added > efficiency and simplicity will more than make up for it. Which i looked at... and i'm wondering why on earth it has a sync code in the packet... that's the whole point of putting it in a container. > Now, if

...e BQLs. Note: some of the issues are >>>>>>>>> similar to wifi. It's worth considering whether something similar to >>>>>>>>> commit 36148c2bbfbe ("mac80211: Adjust TSQ pacing shift") might be >>>>>>>>> benefitial. >>>>>>>> I've played a similar patch several days before. The tricky part is the mode >>>>>>>> switching between napi and no napi. We should make sure when the packet is >>>>>>>> sent and trakced by BQL,? it should be cons...

...e BQLs. Note: some of the issues are >>>>>>>>> similar to wifi. It's worth considering whether something similar to >>>>>>>>> commit 36148c2bbfbe ("mac80211: Adjust TSQ pacing shift") might be >>>>>>>>> benefitial. >>>>>>>> I've played a similar patch several days before. The tricky part is the mode >>>>>>>> switching between napi and no napi. We should make sure when the packet is >>>>>>>> sent and trakced by BQL,? it should be cons...

...t;>> When use_napi is set, let's enable BQLs. Note: some of the issues are >>>>> similar to wifi. It's worth considering whether something similar to >>>>> commit 36148c2bbfbe ("mac80211: Adjust TSQ pacing shift") might be >>>>> benefitial. >>>> I've played a similar patch several days before. The tricky part is the mode >>>> switching between napi and no napi. We should make sure when the packet is >>>> sent and trakced by BQL,? it should be consumed by BQL as well. I did it by >>>&gt...

...t;>> When use_napi is set, let's enable BQLs. Note: some of the issues are >>>>> similar to wifi. It's worth considering whether something similar to >>>>> commit 36148c2bbfbe ("mac80211: Adjust TSQ pacing shift") might be >>>>> benefitial. >>>> I've played a similar patch several days before. The tricky part is the mode >>>> switching between napi and no napi. We should make sure when the packet is >>>> sent and trakced by BQL,? it should be consumed by BQL as well. I did it by >>>&gt...

...ael S. Tsirkin wrote: >>> When use_napi is set, let's enable BQLs. Note: some of the issues are >>> similar to wifi. It's worth considering whether something similar to >>> commit 36148c2bbfbe ("mac80211: Adjust TSQ pacing shift") might be >>> benefitial. >> >> I've played a similar patch several days before. The tricky part is the mode >> switching between napi and no napi. We should make sure when the packet is >> sent and trakced by BQL,? it should be consumed by BQL as well. I did it by >> tracking it through s...

...ael S. Tsirkin wrote: >>> When use_napi is set, let's enable BQLs. Note: some of the issues are >>> similar to wifi. It's worth considering whether something similar to >>> commit 36148c2bbfbe ("mac80211: Adjust TSQ pacing shift") might be >>> benefitial. >> >> I've played a similar patch several days before. The tricky part is the mode >> switching between napi and no napi. We should make sure when the packet is >> sent and trakced by BQL,? it should be consumed by BQL as well. I did it by >> tracking it through s...

Now that we have brought the virtio overhead way down with a fast packed ring implementation, we seem to be actually observing TCP drops indicative of bufferbloat. So let's try to enable TSQ. Note: it isn't clear that the default pacing is great for the virt usecase. It's worth trying to play with sk_pacing_shift_update to see what happens. For this reason, and for a more important