Displaying 20 results from an estimated 32 matches for "16core".
2015 Feb 24
4
[PATCH for stable] x86/spinlocks/paravirt: Fix memory corruption on unlock
...ead-after-release by using xadd;
> > the prev head value will include the slowpath flag and indicate if we
> > need to do PV kicking of suspended spinners -- on modern chips xadd
> > isn't (much) more expensive than an add + load.
> >
> > Result:
> > setup: 16core (32 cpu +ht sandy bridge 8GB 16vcpu guest)
> > benchmark overcommit %improve
> > kernbench 1x -0.13
> > kernbench 2x 0.02
> > dbench 1x -1.77
> > dbench 2x -0.63
> >
> > [Jeremy: hinted missing TICKET...
2015 Feb 24
4
[PATCH for stable] x86/spinlocks/paravirt: Fix memory corruption on unlock
...ead-after-release by using xadd;
> > the prev head value will include the slowpath flag and indicate if we
> > need to do PV kicking of suspended spinners -- on modern chips xadd
> > isn't (much) more expensive than an add + load.
> >
> > Result:
> > setup: 16core (32 cpu +ht sandy bridge 8GB 16vcpu guest)
> > benchmark overcommit %improve
> > kernbench 1x -0.13
> > kernbench 2x 0.02
> > dbench 1x -1.77
> > dbench 2x -0.63
> >
> > [Jeremy: hinted missing TICKET...
2020 Jul 16
1
R 4.0 for ARM processors
...et next to my desk, all four
boards. Yes, you could argue that it's merely a toy.... but it's bigger
and cheaper than the AWS box that currently hosts my web site, RStudio
server, and Shiny server!
> Got it. Missed the cluster part earlier and then confused myself
looking for
arm64 16core machines. There aren't any :)
>> For the truly curious, you can view my RPi cluster here:
https://photos.app.goo.gl/kALwoYCVxJ32VgxEA
> Neat :)? Very geek chic!
Patrice
[[alternative HTML version deleted]]
2015 Feb 24
2
[PATCH for stable] x86/spinlocks/paravirt: Fix memory corruption on unlock
...d for
unlock_kick (Linus):
We further avoid the need for a read-after-release by using xadd;
the prev head value will include the slowpath flag and indicate if we
need to do PV kicking of suspended spinners -- on modern chips xadd
isn't (much) more expensive than an add + load.
Result:
setup: 16core (32 cpu +ht sandy bridge 8GB 16vcpu guest)
benchmark overcommit %improve
kernbench 1x -0.13
kernbench 2x 0.02
dbench 1x -1.77
dbench 2x -0.63
[Jeremy: hinted missing TICKET_LOCK_INC for kick]
[Oleg: Moving slowpath flag to head, ticket_equals...
2015 Feb 24
2
[PATCH for stable] x86/spinlocks/paravirt: Fix memory corruption on unlock
...d for
unlock_kick (Linus):
We further avoid the need for a read-after-release by using xadd;
the prev head value will include the slowpath flag and indicate if we
need to do PV kicking of suspended spinners -- on modern chips xadd
isn't (much) more expensive than an add + load.
Result:
setup: 16core (32 cpu +ht sandy bridge 8GB 16vcpu guest)
benchmark overcommit %improve
kernbench 1x -0.13
kernbench 2x 0.02
dbench 1x -1.77
dbench 2x -0.63
[Jeremy: hinted missing TICKET_LOCK_INC for kick]
[Oleg: Moving slowpath flag to head, ticket_equals...
2015 Feb 15
7
[PATCH V5] x86 spinlock: Fix memory corruption on completing completions
...d for
unlock_kick (Linus):
We further avoid the need for a read-after-release by using xadd;
the prev head value will include the slowpath flag and indicate if we
need to do PV kicking of suspended spinners -- on modern chips xadd
isn't (much) more expensive than an add + load.
Result:
setup: 16core (32 cpu +ht sandy bridge 8GB 16vcpu guest)
benchmark overcommit %improve
kernbench 1x -0.13
kernbench 2x 0.02
dbench 1x -1.77
dbench 2x -0.63
[Jeremy: hinted missing TICKET_LOCK_INC for kick]
[Oleg: Moving slowpath flag to head, ticket_equals...
2015 Feb 15
7
[PATCH V5] x86 spinlock: Fix memory corruption on completing completions
...d for
unlock_kick (Linus):
We further avoid the need for a read-after-release by using xadd;
the prev head value will include the slowpath flag and indicate if we
need to do PV kicking of suspended spinners -- on modern chips xadd
isn't (much) more expensive than an add + load.
Result:
setup: 16core (32 cpu +ht sandy bridge 8GB 16vcpu guest)
benchmark overcommit %improve
kernbench 1x -0.13
kernbench 2x 0.02
dbench 1x -1.77
dbench 2x -0.63
[Jeremy: hinted missing TICKET_LOCK_INC for kick]
[Oleg: Moving slowpath flag to head, ticket_equals...
2020 Jul 15
0
R 4.0 for ARM processors
...file cabinet next to my desk, all four boards. Yes, you could argue that it's merely a toy.... but it's bigger and cheaper than the AWS box that currently hosts my web site, RStudio server, and Shiny server!
Got it. Missed the cluster part earlier and then confused myself looking for
arm64 16core machines. There aren't any :)
| For the truly curious, you can view my RPi cluster here:?https://photos.app.goo.gl/kALwoYCVxJ32VgxEA
Neat :) Very geek chic!
| Thanks again, Dirk. Your contributions to Debian and Ubuntu are foundational for my computing platforms.
You're too kind.
C...
2015 Feb 15
0
[PATCH V5] x86 spinlock: Fix memory corruption on completing completions
...further avoid the need for a read-after-release by using xadd;
> the prev head value will include the slowpath flag and indicate if we
> need to do PV kicking of suspended spinners -- on modern chips xadd
> isn't (much) more expensive than an add + load.
>
> Result:
> setup: 16core (32 cpu +ht sandy bridge 8GB 16vcpu guest)
> benchmark overcommit %improve
> kernbench 1x -0.13
> kernbench 2x 0.02
> dbench 1x -1.77
> dbench 2x -0.63
>
> [Jeremy: hinted missing TICKET_LOCK_INC for kick]
> [Oleg:...
2015 Feb 15
0
[PATCH V5] x86 spinlock: Fix memory corruption on completing completions
...further avoid the need for a read-after-release by using xadd;
> the prev head value will include the slowpath flag and indicate if we
> need to do PV kicking of suspended spinners -- on modern chips xadd
> isn't (much) more expensive than an add + load.
>
> Result:
> setup: 16core (32 cpu +ht sandy bridge 8GB 16vcpu guest)
> benchmark overcommit %improve
> kernbench 1x -0.13
> kernbench 2x 0.02
> dbench 1x -1.77
> dbench 2x -0.63
>
> [Jeremy: hinted missing TICKET_LOCK_INC for kick]
> [Oleg:...
2015 Feb 15
0
[PATCH V5] x86 spinlock: Fix memory corruption on completing completions
...d for
unlock_kick (Linus):
We further avoid the need for a read-after-release by using xadd;
the prev head value will include the slowpath flag and indicate if we
need to do PV kicking of suspended spinners -- on modern chips xadd
isn't (much) more expensive than an add + load.
Result:
setup: 16core (32 cpu +ht sandy bridge 8GB 16vcpu guest)
benchmark overcommit %improve
kernbench 1x -0.13
kernbench 2x 0.02
dbench 1x -1.77
dbench 2x -0.63
[Jeremy: hinted missing TICKET_LOCK_INC for kick]
[Oleg: Moving slowpath flag to head, ticket_equals...
2015 Feb 15
0
[PATCH V5] x86 spinlock: Fix memory corruption on completing completions
...d for
unlock_kick (Linus):
We further avoid the need for a read-after-release by using xadd;
the prev head value will include the slowpath flag and indicate if we
need to do PV kicking of suspended spinners -- on modern chips xadd
isn't (much) more expensive than an add + load.
Result:
setup: 16core (32 cpu +ht sandy bridge 8GB 16vcpu guest)
benchmark overcommit %improve
kernbench 1x -0.13
kernbench 2x 0.02
dbench 1x -1.77
dbench 2x -0.63
[Jeremy: hinted missing TICKET_LOCK_INC for kick]
[Oleg: Moving slowpath flag to head, ticket_equals...
2015 Feb 24
0
[PATCH for stable] x86/spinlocks/paravirt: Fix memory corruption on unlock
...further avoid the need for a read-after-release by using xadd;
> the prev head value will include the slowpath flag and indicate if we
> need to do PV kicking of suspended spinners -- on modern chips xadd
> isn't (much) more expensive than an add + load.
>
> Result:
> setup: 16core (32 cpu +ht sandy bridge 8GB 16vcpu guest)
> benchmark overcommit %improve
> kernbench 1x -0.13
> kernbench 2x 0.02
> dbench 1x -1.77
> dbench 2x -0.63
>
> [Jeremy: hinted missing TICKET_LOCK_INC for kick]
> [Oleg: Mov...
2015 Feb 24
0
[PATCH for stable] x86/spinlocks/paravirt: Fix memory corruption on unlock
...further avoid the need for a read-after-release by using xadd;
> the prev head value will include the slowpath flag and indicate if we
> need to do PV kicking of suspended spinners -- on modern chips xadd
> isn't (much) more expensive than an add + load.
>
> Result:
> setup: 16core (32 cpu +ht sandy bridge 8GB 16vcpu guest)
> benchmark overcommit %improve
> kernbench 1x -0.13
> kernbench 2x 0.02
> dbench 1x -1.77
> dbench 2x -0.63
>
> [Jeremy: hinted missing TICKET_LOCK_INC for kick]
> [Oleg: Mov...
2019 Aug 30
2
NFS Server on Centos 7.6.1810 dying without reason
Good morning,
in order to post proper documentation, what logs (or log level) do I
need to troubleshoot a Centos 7.6.1810 3.10.0-957.27.2.el7.x86_64 tha
tis running a NFS server on top LVM on top of XFS on top of VDO on top
of MDAM on a 6 SSD disk RAID6 ?
This physical NFS server is servign 2 NFS v4.2 shares to 2 physical
KVM virtualization hosts.
When remote NFS clients start doing intensive
2015 Feb 24
0
[PATCH for stable] x86/spinlocks/paravirt: Fix memory corruption on unlock
...d;
> > > the prev head value will include the slowpath flag and indicate if we
> > > need to do PV kicking of suspended spinners -- on modern chips xadd
> > > isn't (much) more expensive than an add + load.
> > >
> > > Result:
> > > setup: 16core (32 cpu +ht sandy bridge 8GB 16vcpu guest)
> > > benchmark overcommit %improve
> > > kernbench 1x -0.13
> > > kernbench 2x 0.02
> > > dbench 1x -1.77
> > > dbench 2x -0.63
> > >
> >...
2015 Feb 24
0
[PATCH for stable] x86/spinlocks/paravirt: Fix memory corruption on unlock
...d;
> > > the prev head value will include the slowpath flag and indicate if we
> > > need to do PV kicking of suspended spinners -- on modern chips xadd
> > > isn't (much) more expensive than an add + load.
> > >
> > > Result:
> > > setup: 16core (32 cpu +ht sandy bridge 8GB 16vcpu guest)
> > > benchmark overcommit %improve
> > > kernbench 1x -0.13
> > > kernbench 2x 0.02
> > > dbench 1x -1.77
> > > dbench 2x -0.63
> > >
> >...
2015 Feb 24
0
[PATCH for stable] x86/spinlocks/paravirt: Fix memory corruption on unlock
...by using xadd;
>>> the prev head value will include the slowpath flag and indicate if we
>>> need to do PV kicking of suspended spinners -- on modern chips xadd
>>> isn't (much) more expensive than an add + load.
>>>
>>> Result:
>>> setup: 16core (32 cpu +ht sandy bridge 8GB 16vcpu guest)
>>> benchmark overcommit %improve
>>> kernbench 1x -0.13
>>> kernbench 2x 0.02
>>> dbench 1x -1.77
>>> dbench 2x -0.63
>>>
>>> [Jere...
2015 Feb 24
0
[PATCH for stable] x86/spinlocks/paravirt: Fix memory corruption on unlock
...by using xadd;
>>> the prev head value will include the slowpath flag and indicate if we
>>> need to do PV kicking of suspended spinners -- on modern chips xadd
>>> isn't (much) more expensive than an add + load.
>>>
>>> Result:
>>> setup: 16core (32 cpu +ht sandy bridge 8GB 16vcpu guest)
>>> benchmark overcommit %improve
>>> kernbench 1x -0.13
>>> kernbench 2x 0.02
>>> dbench 1x -1.77
>>> dbench 2x -0.63
>>>
>>> [Jere...
2015 Feb 13
3
[PATCH V4] x86 spinlock: Fix memory corruption on completing completions
...d for
unlock_kick (Linus):
We further avoid the need for a read-after-release by using xadd;
the prev head value will include the slowpath flag and indicate if we
need to do PV kicking of suspended spinners -- on modern chips xadd
isn't (much) more expensive than an add + load.
Result:
setup: 16core (32 cpu +ht sandy bridge 8GB 16vcpu guest)
benchmark overcommit %improve
kernbench 1x -0.13
kernbench 2x 0.02
dbench 1x -1.77
dbench 2x -0.63
[Jeremy: hinted missing TICKET_LOCK_INC for kick]
[Oleg: Moving slowpath flag to head, ticket_equals...