search for: squeues

1. 566 squeue_enter(squeue_t *sqp, mblk_t *mp, mblk_t *tail, uint32_t cnt, Why cnt is declared as uint32_t (fixed size?) Why not just int or uint_t? 554 * squeue_enter() - enter squeue sqp with mblk mp (which can be 555 * a chain), while tail points to the end and cnt in number of 556 * mblks in the chain. It is not quite clear what is a tail (and why it is needed as well) 558 * For

Folks, I just posted an updated Crossbow virtualization architecture document. The new revision is available at: http://opensolaris.org/os/project/crossbow/Docs/crossbow-virt.pdf The main changes are the addition of support for multiple MAC addresses per client, and an explicit separation between consolidation private and project private MAC API entry points. See in particular the

I''ve been thinking about hardware that has multiple transmit rings ("tx resources"). We really should have a way to expose this up to the stack. And ideally, the stack should guarantee that a given flow will always be sent down using the same hardware tx resource. I''ve heard that crossbow will deliver this, but I can''t find evidence of it in the crossbow

...a short description on assigning priorities to a link (via dladm). Flows will have a similar mechanism (via flowadm). thanks, -venu ---------------------------------------------------------------------------- The components associated with a link or flow, such as Soft Ring Sets, Soft Rings and squeues, have kernel threads processing inbound/outbound packets. The scheduler processes threads based on a thread''s priority level. The priority level of a thread determine how it is scheduled w.r.t other kernel threads. Thus by assigning a priority to a link/flow, we can control how the threa...

Author: Darren Moffat <Darren.Moffat at Sun.COM> Repository: /hg/zfs-crypto/gate Latest revision: 957d30a3607ed9f3cbe490da5894d1e1b2104033 Total changesets: 28 Log message: resync onnv_105 partial for 6713916 Files: usr/src/Makefile.lint usr/src/Targetdirs usr/src/cmd/Makefile usr/src/cmd/Makefile.cmd usr/src/cmd/acctadm/Makefile usr/src/cmd/acctadm/acctadm.xcl

> On Mar 1, 2018, at 9:22 AM, Andrea Di Biagio <andrea.dibiagio at gmail.com> wrote: > > Hi all, > > At Sony we developed an LLVM based performance analysis tool named llvm-mca. We > currently use it internally to statically measure the performance of code, and > to help triage potential problems with target scheduling models. We decided to > post this RFC because

Hi all, At Sony we developed an LLVM based performance analysis tool named llvm-mca. We currently use it internally to statically measure the performance of code, and to help triage potential problems with target scheduling models. We decided to post this RFC because we are interested in the feedback from the community, and we also believe that other people might be interested in a tool like

Reading through this last night got be thinking about how to model control flow.  Given most of my source code tends to be very branchy, be limited to straight line code is quite restrictive.  The main thing is that it requires a lot of hand simplification which can be rather error prone at times. It occurs to me that we could remove the restriction around branches without necessarily fully

Hi Andrea, Thanks for this great RFC ! I've put some high-level comments here, and I'll give more focused comments in the review on Phabricator. On Thu, Mar 1, 2018 at 6:22 PM, Andrea Di Biagio <andrea.dibiagio at gmail.com> wrote: > Hi all, > > At Sony we developed an LLVM based performance analysis tool named > llvm-mca. We > currently use it internally to

Hi Andrew, Thanks for the feedback! On Fri, Mar 2, 2018 at 1:16 AM, Andrew Trick <atrick at apple.com> wrote: > > On Mar 1, 2018, at 9:22 AM, Andrea Di Biagio <andrea.dibiagio at gmail.com> > wrote: > > Hi all, > > At Sony we developed an LLVM based performance analysis tool named > llvm-mca. We > currently use it internally to statically measure the