DPDK patches and discussions
 help / color / mirror / Atom feed
From: Pavan Nikhilesh Bhagavatula <pbhagavatula@marvell.com>
To: Jerin Jacob Kollanukkaran <jerinj@marvell.com>,
	"keith.wiles@intel.com" <keith.wiles@intel.com>,
	"stephen@networkplumber.org" <stephen@networkplumber.org>,
	"thomas@monjalon.net" <thomas@monjalon.net>
Cc: "dev@dpdk.org" <dev@dpdk.org>,
	Pavan Nikhilesh Bhagavatula <pbhagavatula@marvell.com>
Subject: [dpdk-dev] [PATCH v3 2/2] eal: roundup tsc frequency when estimating
Date: Sat, 16 Mar 2019 19:01:54 +0000	[thread overview]
Message-ID: <20190316190119.6142-2-pbhagavatula@marvell.com> (raw)
In-Reply-To: <20190316190119.6142-1-pbhagavatula@marvell.com>

From: Pavan Nikhilesh <pbhagavatula@marvell.com>

When estimating tsc frequency using sleep/gettime round it up to the
nearest multiple of 10Mhz for more accuracy.

Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
Reviewed-by: Keith Wiles <keith.wiles@intel.com>
---
 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).

 lib/librte_eal/common/eal_common_timer.c | 4 +++-
 lib/librte_eal/linux/eal/eal_timer.c     | 4 +++-
 2 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/lib/librte_eal/common/eal_common_timer.c b/lib/librte_eal/common/eal_common_timer.c
index dcf26bfea..68d67e684 100644
--- a/lib/librte_eal/common/eal_common_timer.c
+++ b/lib/librte_eal/common/eal_common_timer.c
@@ -64,12 +64,14 @@ rte_get_tsc_hz(void)
 static uint64_t
 estimate_tsc_freq(void)
 {
+#define CYC_PER_10MHZ 1E7
 	RTE_LOG(WARNING, EAL, "WARNING: TSC frequency estimated roughly"
 		" - clock timings may be less accurate.\n");
 	/* assume that the sleep(1) will sleep for 1 second */
 	uint64_t start = rte_rdtsc();
 	sleep(1);
-	return rte_rdtsc() - start;
+	/* Round up to 10Mhz. 1E7 ~ 10Mhz */
+	return RTE_ALIGN_MUL_NEAR(rte_rdtsc() - start, CYC_PER_10MHZ);
 }

 void
diff --git a/lib/librte_eal/linux/eal/eal_timer.c b/lib/librte_eal/linux/eal/eal_timer.c
index bc8f05199..76ec17034 100644
--- a/lib/librte_eal/linux/eal/eal_timer.c
+++ b/lib/librte_eal/linux/eal/eal_timer.c
@@ -232,6 +232,7 @@ get_tsc_freq(void)
 {
 #ifdef CLOCK_MONOTONIC_RAW
 #define NS_PER_SEC 1E9
+#define CYC_PER_10MHZ 1E7

 	struct timespec sleeptime = {.tv_nsec = NS_PER_SEC / 10 }; /* 1/10 second */

@@ -248,7 +249,8 @@ get_tsc_freq(void)

 		double secs = (double)ns/NS_PER_SEC;
 		tsc_hz = (uint64_t)((end - start)/secs);
-		return tsc_hz;
+		/* Round up to 10Mhz. 1E7 ~ 10Mhz */
+		return RTE_ALIGN_MUL_NEAR(tsc_hz, CYC_PER_10MHZ);
 	}
 #endif
 	return 0;
--
2.21.0

  parent reply	other threads:[~2019-03-16 19:02 UTC|newest]

Thread overview: 26+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-11-29  8:32 [dpdk-dev] [PATCH] eal: roundup tsc frequency when estimating it Pavan Nikhilesh
2018-11-29  9:08 ` Jerin Jacob
2018-11-29 21:21 ` Stephen Hemminger
2018-11-30  7:17   ` Pavan Nikhilesh
2019-03-16  7:03 ` [dpdk-dev] [PATCH v2 1/2] eal: add macro to align value to the nearest multiple Pavan Nikhilesh Bhagavatula
2019-03-16  7:03   ` Pavan Nikhilesh Bhagavatula
2019-03-16  7:03   ` [dpdk-dev] [PATCH v2 2/2] eal: roundup tsc frequency when estimating it Pavan Nikhilesh Bhagavatula
2019-03-16  7:03     ` Pavan Nikhilesh Bhagavatula
2019-03-16 14:42     ` Wiles, Keith
2019-03-16 14:42       ` Wiles, Keith
2019-03-16 15:06       ` [dpdk-dev] [EXT] " Pavan Nikhilesh Bhagavatula
2019-03-16 15:06         ` Pavan Nikhilesh Bhagavatula
2019-03-16 17:18         ` Wiles, Keith
2019-03-16 17:18           ` Wiles, Keith
2019-03-16 17:56           ` Pavan Nikhilesh Bhagavatula
2019-03-16 17:56             ` Pavan Nikhilesh Bhagavatula
2019-03-16 18:22             ` Wiles, Keith
2019-03-16 18:22               ` Wiles, Keith
2019-03-16 18:27               ` Pavan Nikhilesh Bhagavatula
2019-03-16 18:27                 ` Pavan Nikhilesh Bhagavatula
2019-03-16 19:01 ` [dpdk-dev] [PATCH v3 1/2] eal: add macro to align value to the nearest multiple Pavan Nikhilesh Bhagavatula
2019-03-16 19:01   ` Pavan Nikhilesh Bhagavatula
2019-03-16 19:01   ` Pavan Nikhilesh Bhagavatula [this message]
2019-03-16 19:01     ` [dpdk-dev] [PATCH v3 2/2] eal: roundup tsc frequency when estimating Pavan Nikhilesh Bhagavatula
2019-03-27 22:43     ` Thomas Monjalon
2019-03-27 22:43       ` Thomas Monjalon

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=20190316190119.6142-2-pbhagavatula@marvell.com \
    --to=pbhagavatula@marvell.com \
    --cc=dev@dpdk.org \
    --cc=jerinj@marvell.com \
    --cc=keith.wiles@intel.com \
    --cc=stephen@networkplumber.org \
    --cc=thomas@monjalon.net \
    /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).