search for: 1370000

...Just one doubt I have is below: > > We use spinlock to synchronize the work list now which may cause > unnecessary contentions. So this patch switch to use llist to remove > this contention. Pktgen tests shows about 5% improvement: > > Before: > ~1300000 pps > After: > ~1370000 pps > > Signed-off-by: Jason Wang <jasowang at redhat.com> > --- > drivers/vhost/vhost.c | 52 > +++++++++++++++++++++++++-------------------------- > drivers/vhost/vhost.h | 7 ++++--- > 2 files changed, 29 insertions(+), 30 deletions(-) > > diff --git a/drive...

...Just one doubt I have is below: > > We use spinlock to synchronize the work list now which may cause > unnecessary contentions. So this patch switch to use llist to remove > this contention. Pktgen tests shows about 5% improvement: > > Before: > ~1300000 pps > After: > ~1370000 pps > > Signed-off-by: Jason Wang <jasowang at redhat.com> > --- > drivers/vhost/vhost.c | 52 > +++++++++++++++++++++++++-------------------------- > drivers/vhost/vhost.h | 7 ++++--- > 2 files changed, 29 insertions(+), 30 deletions(-) > > diff --git a/drive...

...that this introduces some overheads in > light load case because of the extra start/stop polling, but single > netperf TCP_RR does not notice any change. In a super heavy load case, > e.g using pktgen to inject packet to guest, we get about ~17% > improvement on pps: > > before: ~1370000 pkt/s > after: ~1500000 pkt/s > > Signed-off-by: Jason Wang <jasowang at redhat.com> Acked-by: Michael S. Tsirkin <mst at redhat.com> There is one other possible enhancement: we actually have the wait queue lock taken in _wake_up, but we give it up only to take it again in...

...that this introduces some overheads in > light load case because of the extra start/stop polling, but single > netperf TCP_RR does not notice any change. In a super heavy load case, > e.g using pktgen to inject packet to guest, we get about ~17% > improvement on pps: > > before: ~1370000 pkt/s > after: ~1500000 pkt/s > > Signed-off-by: Jason Wang <jasowang at redhat.com> Acked-by: Michael S. Tsirkin <mst at redhat.com> There is one other possible enhancement: we actually have the wait queue lock taken in _wake_up, but we give it up only to take it again in...

We used to implement the work flushing through tracking queued seq, done seq, and the number of flushing. This patch simplify this by just implement work flushing through another kind of vhost work with completion. This will be used by lockless enqueuing patch. Signed-off-by: Jason Wang <jasowang at redhat.com> --- drivers/vhost/vhost.c | 53

We used to implement the work flushing through tracking queued seq, done seq, and the number of flushing. This patch simplify this by just implement work flushing through another kind of vhost work with completion. This will be used by lockless enqueuing patch. Signed-off-by: Jason Wang <jasowang at redhat.com> --- drivers/vhost/vhost.c | 53

...below: >> We use spinlock to synchronize the work list now which may cause >> unnecessary contentions. So this patch switch to use llist to remove >> this contention. Pktgen tests shows about 5% improvement: >> >> Before: >> ~1300000 pps >> After: >> ~1370000 pps >> >> Signed-off-by: Jason Wang <jasowang at redhat.com> >> --- >> drivers/vhost/vhost.c | 52 >> +++++++++++++++++++++++++-------------------------- >> drivers/vhost/vhost.h | 7 ++++--- >> 2 files changed, 29 insertions(+), 30 deletions(-) [...

Hi all, I am checking the cross references at CRAN and base R, and I am having trouble understanding how to reconcile the documentation and how R help links work. Checking the documentation [1] it seems that in a cross reference such as \link[pkg:x]{text} x should be a topic (created with \alias{topic} in R documentation). But I found some cases exploring the output of tools::base_rdxrefs_db()

...me overheads in >> light load case because of the extra start/stop polling, but single >> netperf TCP_RR does not notice any change. In a super heavy load case, >> e.g using pktgen to inject packet to guest, we get about ~17% >> improvement on pps: >> >> before: ~1370000 pkt/s >> after: ~1500000 pkt/s >> >> Signed-off-by: Jason Wang <jasowang at redhat.com> > Acked-by: Michael S. Tsirkin <mst at redhat.com> > > There is one other possible enhancement: we actually have the wait queue > lock taken in _wake_up, but we give it...

We use spinlock to synchronize the work list now which may cause unnecessary contentions. So this patch switch to use llist to remove this contention. Pktgen tests shows about 5% improvement: Before: ~1300000 pps After: ~1370000 pps Signed-off-by: Jason Wang <jasowang at redhat.com> --- drivers/vhost/vhost.c | 52 +++++++++++++++++++++++++-------------------------- drivers/vhost/vhost.h | 7 ++++--- 2 files changed, 29 insertions(+), 30 deletions(-) diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index...

...a 0193e446 Backtrace: =>0 0x7b8380c2 in kernel32 (+0x280c2) (0x0161889c) 1 0x7d4c3958 in winscard (+0x3957) (0x016188cc) 0x7b8380c2: subl $4,%esp Modules: Module Address Debug info Name (156 modules) PE 400000- bdd000 Deferred topix8 PE be0000- c34000 Deferred msvcr70 PE 1370000- 13f1000 Deferred 4dsli PE 1c80000- 1c9f000 Deferred yapee.4dx PE 1db0000- 1e2c000 Deferred hmcal.4dx PE 1e30000- 1ee5000 Deferred faxpack.4dx PE 1ef0000- 20a5000 Deferred topix crypto.4dx PE 21c0000- 21e1000 Deferred regex plugin.4dx PE 2300000- 2343...

...a 0193e396 Backtrace: =>0 0x7b8380c2 in kernel32 (+0x280c2) (0x0161889c) 1 0x7d4b5958 in winscard (+0x5957) (0x016188cc) 0x7b8380c2: subl $4,%esp Modules: Module Address Debug info Name (156 modules) PE 400000- bdd000 Deferred topix8 PE be0000- c34000 Deferred msvcr70 PE 1370000- 13f1000 Deferred 4dsli PE 1c80000- 1c9f000 Deferred yapee.4dx PE 1db0000- 1e2c000 Deferred hmcal.4dx PE 1e30000- 1ee5000 Deferred faxpack.4dx PE 1ef0000- 20a5000 Deferred topix crypto.4dx PE 21c0000- 21e1000 Deferred regex plugin.4dx PE 2300000- 2343...