From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Wiles, Keith" Subject: Re: [PATCH v2 2/2] eal: roundup tsc frequency when estimating it Date: Sat, 16 Mar 2019 14:42:58 +0000 Message-ID: <86480C64-4ECD-4F4D-968E-5716D02D7D83@intel.com> References: <20181129083138.23029-1-pbhagavatula@caviumnetworks.com> <20190316070302.32432-1-pbhagavatula@marvell.com> <20190316070302.32432-2-pbhagavatula@marvell.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable Cc: Jerin Jacob Kollanukkaran , "stephen@networkplumber.org" , "thomas@monjalon.net" , "dev@dpdk.org" To: Pavan Nikhilesh Bhagavatula Return-path: Received: from mga11.intel.com (mga11.intel.com [192.55.52.93]) by dpdk.org (Postfix) with ESMTP id 34EE3DE0 for ; Sat, 16 Mar 2019 15:43:02 +0100 (CET) In-Reply-To: <20190316070302.32432-2-pbhagavatula@marvell.com> Content-Language: en-US Content-ID: <72207A42BDE96D45B3DFAD439E9DC77E@intel.com> List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Sender: "dev" > On Mar 16, 2019, at 2:03 AM, Pavan Nikhilesh Bhagavatula wrote: >=20 > From: Pavan Nikhilesh >=20 > When estimating tsc frequency using sleep/gettime round it up to the > nearest multiple of 10Mhz for more accuracy. >=20 > Signed-off-by: Pavan Nikhilesh > --- > Useful in case of ARM64 if we enable RTE_ARM_EAL_RDTSC_USE_PMU, > get_tsc_freq_arch() will return 0 as there is no instruction to determine > the clk of PMU and eal falls back to sleep(1). >=20 > lib/librte_eal/common/eal_common_timer.c | 4 ++-- > lib/librte_eal/linuxapp/eal/eal_timer.c | 2 +- > 2 files changed, 3 insertions(+), 3 deletions(-) >=20 > diff --git a/lib/librte_eal/common/eal_common_timer.c b/lib/librte_eal/co= mmon/eal_common_timer.c > index dcf26bfea..1358bbed0 100644 > --- a/lib/librte_eal/common/eal_common_timer.c > +++ b/lib/librte_eal/common/eal_common_timer.c > @@ -69,7 +69,7 @@ estimate_tsc_freq(void) > /* assume that the sleep(1) will sleep for 1 second */ > uint64_t start =3D rte_rdtsc(); > sleep(1); > - return rte_rdtsc() - start; > + return RTE_ALIGN_MUL_NEAR(rte_rdtsc() - start, 1E7); > } >=20 > void > @@ -83,7 +83,7 @@ set_tsc_freq(void) > if (!freq) > freq =3D estimate_tsc_freq(); >=20 > - RTE_LOG(DEBUG, EAL, "TSC frequency is ~%" PRIu64 " KHz\n", freq / 1000)= ; > + RTE_LOG(INFO, EAL, "TSC frequency is ~%" PRIu64 " Hz\n", freq); > eal_tsc_resolution_hz =3D freq; > } >=20 > diff --git a/lib/librte_eal/linuxapp/eal/eal_timer.c b/lib/librte_eal/lin= uxapp/eal/eal_timer.c > index bc8f05199..864d6ef29 100644 > --- a/lib/librte_eal/linuxapp/eal/eal_timer.c > +++ b/lib/librte_eal/linuxapp/eal/eal_timer.c > @@ -248,7 +248,7 @@ get_tsc_freq(void) >=20 > double secs =3D (double)ns/NS_PER_SEC; > tsc_hz =3D (uint64_t)((end - start)/secs); > - return tsc_hz; > + return RTE_ALIGN_MUL_NEAR(tsc_hz, 1E7); Maybe I missed an email about this, but why would I want the TSC hz rounded= here? I do not mind the macro just the fact that we are changing TSC hz va= lue. If the TSC value is wrong then we need to fix the value, but I do not = see it being wrong here. > } > #endif > return 0; > -- > 2.21.0 >=20 Regards, Keith