From: "Burakov, Anatoly" <anatoly.burakov@intel.com>
To: David Hunt <david.hunt@intel.com>, dev@dpdk.org
Cc: lei.a.yao@intel.com
Subject: Re: [dpdk-dev] [PATCH v2 3/4] examples/power: allow vms to use lcores over 63
Date: Fri, 14 Dec 2018 12:08:33 +0000 [thread overview]
Message-ID: <6582d776-fe33-7cf7-8715-8f919aa8d71f@intel.com> (raw)
In-Reply-To: <20181214114946.21570-4-david.hunt@intel.com>
On 14-Dec-18 11:49 AM, David Hunt wrote:
> Extending the functionality to allow vms to power manage cores beyond 63.
>
> Signed-off-by: David Hunt <david.hunt@intel.com>
> ---
> examples/vm_power_manager/channel_manager.c | 74 +++++++++------------
> examples/vm_power_manager/channel_manager.h | 30 ++-------
> examples/vm_power_manager/channel_monitor.c | 56 ++++++----------
> examples/vm_power_manager/vm_power_cli.c | 4 +-
> 4 files changed, 57 insertions(+), 107 deletions(-)
>
> diff --git a/examples/vm_power_manager/channel_manager.c b/examples/vm_power_manager/channel_manager.c
> index 71f4a0ccf..8756b53b8 100644
> --- a/examples/vm_power_manager/channel_manager.c
> +++ b/examples/vm_power_manager/channel_manager.c
> @@ -49,7 +49,7 @@ static bool global_hypervisor_available;
> */
> struct virtual_machine_info {
> char name[CHANNEL_MGR_MAX_NAME_LEN];
> - rte_atomic64_t pcpu_mask[CHANNEL_CMDS_MAX_CPUS];
> + uint16_t pcpu_map[CHANNEL_CMDS_MAX_CPUS];
> struct channel_info *channels[CHANNEL_CMDS_MAX_VM_CHANNELS];
> char channel_mask[POWER_MGR_MAX_CPUS];
> uint8_t num_channels;
> @@ -79,7 +79,6 @@ update_pcpus_mask(struct virtual_machine_info *vm_info)
> virVcpuInfoPtr cpuinfo;
> unsigned i, j;
> int n_vcpus;
> - uint64_t mask;
>
> memset(global_cpumaps, 0, CHANNEL_CMDS_MAX_CPUS*global_maplen);
>
> @@ -120,26 +119,23 @@ update_pcpus_mask(struct virtual_machine_info *vm_info)
> vm_info->info.nrVirtCpu = n_vcpus;
> }
> for (i = 0; i < vm_info->info.nrVirtCpu; i++) {
> - mask = 0;
> for (j = 0; j < global_n_host_cpus; j++) {
> - if (VIR_CPU_USABLE(global_cpumaps, global_maplen, i, j) > 0) {
> - mask |= 1ULL << j;
> - }
> + if (VIR_CPU_USABLE(global_cpumaps,
> + global_maplen, i, j) <= 0)
> + continue;
> + rte_spinlock_lock(&(vm_info->config_spinlock));
> + vm_info->pcpu_map[i] = j;
> + rte_spinlock_unlock(&(vm_info->config_spinlock));
This is not an equivalent replacement, because something can happen
inbetween the unlock and subsequent lock. There's no need to lock-unlock
it on every iteration anyway - just lock it before the for (i = 0...)
and unlock it right before return.
> }
> - rte_atomic64_set(&vm_info->pcpu_mask[i], mask);
> }
> return 0;
> }
>
> int
> -set_pcpus_mask(char *vm_name, unsigned int vcpu, char *core_mask)
> +set_pcpu(char *vm_name, unsigned int vcpu, unsigned int pcpu)
> {
<snip>
> --- a/examples/vm_power_manager/channel_manager.h
> +++ b/examples/vm_power_manager/channel_manager.h
> @@ -40,7 +40,6 @@ struct sockaddr_un _sockaddr_un;
> #define MAX_CLIENTS 64
> #define MAX_VCPUS 20
>
> -
> struct libvirt_vm_info {
Unintended whitespace change?
> const char *vm_name;
> unsigned int pcpus[MAX_VCPUS];
> @@ -82,7 +81,7 @@ struct channel_info {
> struct vm_info {
> char name[CHANNEL_MGR_MAX_NAME_LEN]; /**< VM name */
> enum vm_status status; /**< libvirt status */
--
Thanks,
Anatoly
next prev parent reply other threads:[~2018-12-14 12:08 UTC|newest]
Thread overview: 29+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-11-22 17:02 [dpdk-dev] examples/power: allow use of more than 64 cores David Hunt
2018-11-22 17:02 ` [dpdk-dev] [PATCH v1 1/4] examples/power: change 64-bit masks to arrays David Hunt
2018-12-10 12:18 ` Burakov, Anatoly
2018-12-13 12:03 ` Hunt, David
2018-12-14 11:49 ` [dpdk-dev] [PATCH v2 0/4] examples/power: allow use of more than 64 cores David Hunt
2018-12-14 11:49 ` [dpdk-dev] [PATCH v2 1/4] examples/power: change 64-bit masks to arrays David Hunt
2018-12-14 12:00 ` Burakov, Anatoly
2018-12-14 11:49 ` [dpdk-dev] [PATCH v2 2/4] examples/power: remove mask functions David Hunt
2018-12-14 12:01 ` Burakov, Anatoly
2018-12-14 11:49 ` [dpdk-dev] [PATCH v2 3/4] examples/power: allow vms to use lcores over 63 David Hunt
2018-12-14 12:08 ` Burakov, Anatoly [this message]
2018-12-14 12:29 ` Hunt, David
2018-12-14 11:49 ` [dpdk-dev] [PATCH v2 4/4] examples/power: increase max cores to 256 David Hunt
2018-12-14 13:31 ` [dpdk-dev] [PATCH v3 0/4] examples/power: allow use of more than 64 cores David Hunt
2018-12-14 13:31 ` [dpdk-dev] [PATCH v3 1/4] examples/power: change 64-bit masks to arrays David Hunt
2018-12-14 13:31 ` [dpdk-dev] [PATCH v3 2/4] examples/power: remove mask functions David Hunt
2018-12-14 13:31 ` [dpdk-dev] [PATCH v3 3/4] examples/power: allow vms to use lcores over 63 David Hunt
2018-12-14 13:31 ` [dpdk-dev] [PATCH v3 4/4] examples/power: increase max cores to 256 David Hunt
2018-12-14 13:37 ` [dpdk-dev] [PATCH v3 0/4] examples/power: allow use of more than 64 cores Burakov, Anatoly
2018-12-19 21:25 ` Thomas Monjalon
2018-11-22 17:02 ` [dpdk-dev] [PATCH v1 2/4] examples/power: remove mask functions David Hunt
2018-12-10 12:30 ` Burakov, Anatoly
2018-12-13 12:13 ` Hunt, David
2018-12-13 12:14 ` Burakov, Anatoly
2018-11-22 17:02 ` [dpdk-dev] [PATCH v1 3/4] examples/power: allow vms to use lcores over 63 David Hunt
2018-12-10 13:06 ` Burakov, Anatoly
2018-12-13 16:46 ` Hunt, David
2018-11-22 17:02 ` [dpdk-dev] [PATCH v1 4/4] examples/power: increase MAX_CPUS to 256 David Hunt
2018-12-10 12:31 ` Burakov, Anatoly
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=6582d776-fe33-7cf7-8715-8f919aa8d71f@intel.com \
--to=anatoly.burakov@intel.com \
--cc=david.hunt@intel.com \
--cc=dev@dpdk.org \
--cc=lei.a.yao@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).