> -----Original Message-----
> From: Don Wallwork <d...@xsightlabs.com>
> Sent: Wednesday, May 4, 2022 03:47
> To: Wang, Haiyue <haiyue.w...@intel.com>; dev@dpdk.org
> Cc: step...@networkplumber.org; m...@smartsharesystems.com; Burakov, Anatoly
> <anatoly.bura...@intel.com>;
> dmitry.kozl...@gmail.com; Richardson, Bruce <bruce.richard...@intel.com>;
> honnappa.nagaraha...@arm.com;
> n...@arm.com
> Subject: Re: [PATCH] eal: allow worker lcore stacks to be allocated from
> hugepage memory
>
> On 5/3/2022 9:08 AM, Wang, Haiyue wrote:
> >> -----Original Message-----
> >> From: Don Wallwork <d...@xsightlabs.com>
> >> Sent: Monday, May 2, 2022 22:11
> >> To: dev@dpdk.org
> >> Cc: d...@xsightlabs.com; step...@networkplumber.org;
> >> m...@smartsharesystems.com; Burakov, Anatoly
> >> <anatoly.bura...@intel.com>; dmitry.kozl...@gmail.com; Richardson, Bruce
> <bruce.richard...@intel.com>;
> >> honnappa.nagaraha...@arm.com; n...@arm.com
> >> Subject: [PATCH] eal: allow worker lcore stacks to be allocated from
> >> hugepage memory
> >>
> >> Add support for using hugepages for worker lcore stack memory. The
> >> intent is to improve performance by reducing stack memory related TLB
> >> misses and also by using memory local to the NUMA node of each lcore.
> >>
> >> EAL option '--huge-worker-stack [stack-size-kbytes]' is added to allow
> >> the feature to be enabled at runtime. If the size is not specified,
> >> the system pthread stack size will be used.
> >>
> >> Signed-off-by: Don Wallwork <d...@xsightlabs.com>
> >> ---
> >> lib/eal/common/eal_common_options.c | 31 ++++++++++++++
> >> lib/eal/common/eal_internal_cfg.h | 4 ++
> >> lib/eal/common/eal_options.h | 2 +
> >> lib/eal/linux/eal.c | 65 ++++++++++++++++++++++++++++-
> >> 4 files changed, 100 insertions(+), 2 deletions(-)
> >>
> >> diff --git a/lib/eal/common/eal_common_options.c
> >> b/lib/eal/common/eal_common_options.c
> >> index f247a42455..be9db9ee37 100644
> >> --- a/lib/eal/common/eal_common_options.c
> >> +++ b/lib/eal/common/eal_common_options.c
> >> @@ -103,6 +103,7 @@ eal_long_options[] = {
> >> {OPT_TELEMETRY, 0, NULL, OPT_TELEMETRY_NUM },
> >> {OPT_NO_TELEMETRY, 0, NULL, OPT_NO_TELEMETRY_NUM },
> >> {OPT_FORCE_MAX_SIMD_BITWIDTH, 1, NULL, OPT_FORCE_MAX_SIMD_BITWIDTH_NUM},
> >> + {OPT_HUGE_WORKER_STACK, 2, NULL, OPT_HUGE_WORKER_STACK_NUM },
> >>
> >> {0, 0, NULL, 0 }
> >> };
> >> @@ -1618,6 +1619,22 @@ eal_parse_huge_unlink(const char *arg, struct
> >> hugepage_file_discipline *out)
> >> return -1;
> >> }
> >>
> >> +static int
> >> +eal_parse_huge_worker_stack(const char *arg, size_t
> >> *huge_worker_stack_size)
> >> +{
> >> + size_t worker_stack_size;
> >> + if (arg == NULL) {
> >> + *huge_worker_stack_size = USE_OS_STACK_SIZE;
> >> + return 0;
> >> + }
> >> + worker_stack_size = atoi(arg);
> >> + if (worker_stack_size == 0)
> >> + return -1;
> > Should we also to check "worker_stack_size *1024 < PTHREAD_STACK_MIN" ?
> This may be too restrictive in certain environments. For example,
> memory constrained platforms may require a smaller worker stack size
> than this limit would allow.
Understood, thanks.
> >> +
> >> + *huge_worker_stack_size = worker_stack_size * 1024;
> >> + return 0;
> >> +}
> >> +
> >
> >> --
> >> 2.17.1
