On Sat, Sep 8, 2018 at 10:02 AM Olof Johansson wrote:
>
> Hi,
>
> On Fri, Sep 7, 2018 at 12:21 AM, Eric Dumazet wrote:
> > On Fri, Sep 7, 2018 at 12:03 AM Eric Dumazet wrote:
> >
> >> Problem is : we have platforms with more than 100 cpus, and
> >> sk_memory_allocated() cost will be too expensiv
Hi,
On Fri, Sep 7, 2018 at 12:21 AM, Eric Dumazet wrote:
> On Fri, Sep 7, 2018 at 12:03 AM Eric Dumazet wrote:
>
>> Problem is : we have platforms with more than 100 cpus, and
>> sk_memory_allocated() cost will be too expensive,
>> especially if the host is under memory pressure, since all cpus
On Fri, Sep 7, 2018 at 12:03 AM Eric Dumazet wrote:
> Problem is : we have platforms with more than 100 cpus, and
> sk_memory_allocated() cost will be too expensive,
> especially if the host is under memory pressure, since all cpus will
> touch their private counter.
>
> per cpu variables do not
On Thu, Sep 6, 2018 at 11:20 PM Olof Johansson wrote:
>
> Hi,
>
> On Thu, Sep 6, 2018 at 8:32 PM, Herbert Xu
> wrote:
> > On Thu, Sep 06, 2018 at 12:33:58PM -0700, Eric Dumazet wrote:
> >> On Thu, Sep 6, 2018 at 12:21 PM Olof Johansson wrote:
> >> >
> >> > Today these are all global shared vari
Hi,
On Thu, Sep 6, 2018 at 8:32 PM, Herbert Xu wrote:
> On Thu, Sep 06, 2018 at 12:33:58PM -0700, Eric Dumazet wrote:
>> On Thu, Sep 6, 2018 at 12:21 PM Olof Johansson wrote:
>> >
>> > Today these are all global shared variables per protocol, and in
>> > particular tcp_memory_allocated can get h
On Thu, Sep 06, 2018 at 12:33:58PM -0700, Eric Dumazet wrote:
> On Thu, Sep 6, 2018 at 12:21 PM Olof Johansson wrote:
> >
> > Today these are all global shared variables per protocol, and in
> > particular tcp_memory_allocated can get hot on a system with
> > large number of CPUs and a substantial
On Thu, Sep 6, 2018 at 12:21 PM Olof Johansson wrote:
>
> Today these are all global shared variables per protocol, and in
> particular tcp_memory_allocated can get hot on a system with
> large number of CPUs and a substantial number of connections.
>
> Moving it over to a per-cpu variable makes i
Today these are all global shared variables per protocol, and in
particular tcp_memory_allocated can get hot on a system with
large number of CPUs and a substantial number of connections.
Moving it over to a per-cpu variable makes it significantly cheaper,
and the added overhead when summing up th
