From mboxrd@z Thu Jan 1 00:00:00 1970 Message-ID: <47F4D87F.7080204@domain.hid> Date: Thu, 03 Apr 2008 15:15:43 +0200 From: Sebastian Smolorz MIME-Version: 1.0 References: <20080402012645.506e53ef.Cornelius.Koepp@domain.hid> <47F34C0D.6090809@domain.hid> <47F37579.7080601@domain.hid> <47F37BF8.6000401@domain.hid> <47F3AD14.4090306@domain.hid> <2ff1a98a0804020905v7019574ai927f213ab6603e41@domain.hid> <47F3B348.1090102@domain.hid> <47F4CAD1.3090002@domain.hid> In-Reply-To: <47F4CAD1.3090002@domain.hid> Content-Type: multipart/mixed; boundary="------------060305050709020306030502" Subject: Re: [Xenomai-core] latencys drifting into negative (Xenomai 2.4.2/2.4.3) List-Id: "Xenomai life and development \(bug reports, patches, discussions\)" List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Jan Kiszka Cc: xenomai-core , =?ISO-8859-1?Q?Cornelius_K=F6pp?= This is a multi-part message in MIME format. --------------060305050709020306030502 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: quoted-printable X-MIME-Autoconverted: from 8bit to quoted-printable by authsmtp.rrzn.uni-hannover.de id m33DFfIV001596 Jan Kiszka wrote: > Sebastian Smolorz wrote: >> Gilles Chanteperdrix wrote: >>> On Wed, Apr 2, 2008 at 5:58 PM, Sebastian Smolorz >>> wrote: >>>> Jan Kiszka wrote: >>>> > Sebastian Smolorz wrote: >>>> >> Jan Kiszka wrote: >>>> >>> Cornelius K=F6pp wrote: >>>> >>>> I talked with Sebastian Smolorz about this and he builds his o= wn >>>> >>>> independent kernel-config to check. He got the same=20 >>>> drifting-effect >>>> >>>> with Xenomai 2.4.2 and Xenomai 2.4.3 running latency over seve= ral >>>> >>>> hours. His kernel-config ist attached as >>>> >>>> 'config-2.6.24-xenomai-2.4.3__ssm'. >>>> >>>> >>>> >>>> Our kernel-configs are both based on a config used with=20 >>>> Xenomai 2.3.4 >>>> >>>> and Linux 2.6.20.15 without any drifting effects. >>>> >>> 2.3.x did not incorporate the new TSC-to-ns conversion. Maybe=20 >>>> it is >>>> >>> not a PIC vs. APIC thing, but rather a rounding problem of=20 >>>> larger TSC >>>> >>> values (that naturally show up when the system runs for a=20 >>>> longer time). >>>> >> This hint seems to point into the right direction. I tried out a >>>> >> modified pod_32.h (xnarch_tsc_to_ns() commented out) so that the= =20 >>>> old >>>> >> implementation in include/asm-generic/bits/pod.h was used. The=20 >>>> drifting >>>> >> bug disappeared. So there seems so be a buggy x86-specific >>>> >> implementation of this routine. >>>> > >>>> > Hmm, maybe even a conceptional issue: the multiply-shift-based >>>> > xnarch_tsc_to_ns is not as precise as the still=20 >>>> multiply-divide-based >>>> > xnarch_ns_to_tsc. So when converting from tsc over ns back to=20 >>>> tsc, we >>>> > may loose some bits, maybe too many bits... >>>> > >>>> > It looks like this bites us in the kernel latency tests (-t2 shou= ld >>>> > suffer as well). Those recalculate their timeouts each round=20 >>>> based on >>>> > absolute nanoseconds. In contrast, the periodic user mode task of= =20 >>>> -t0 >>>> > uses a periodic timer that is forwarded via a tsc-based interval. >>>> > >>>> > You (or Cornelius) could try to analyse the calculation path of t= he >>>> > involved timeouts, specifically to understand why the scheduled=20 >>>> timeout >>>> > of the underlying task timer (which is tsc-based) tend to diverge= =20 >>>> from >>>> > the calculated one (ns-based). >>>> >>>> So here comes the explanation. The error is inside the function >>>> rthal_llmulshft(). It returns wrong values which are too small - th= e >>>> higher the given TSC value the bigger the error. The function >>>> rtdm_clock_read_monotonic() calls rthal_llmulshft(). As >>>> rtdm_clock_read_monotonic() is called every time the latency kernel >>>> thread runs [1] the values reported by latency become smaller over=20 >>>> time. >>>> >>>> In contrast, the latency task in user space only uses the conversio= n >>>> from TSC to ns only once when calling rt_timer_inquire [2]. >>>> timer_info.date is too small, timer_info.tsc is right. So all=20 >>>> calculated >>>> deltas in [3] are shifted to a smaller value. This value is consta= nt >>>> during the runtime of lateny in user space because no more conversi= on >>>> from TSC to ns occurs. >>> >>> latency does conversions from tsc to ns, but it converts time >>> differences, so the error is small relative to the results. >> >> Of course. I wasn't precise with my last statement. It should be: No=20 >> more conversions from *absolute* TSC values to ns occur. >> >=20 > This patch may do the trick: it uses the inverted tsc-to-ns function=20 > instead of the frequency-based one. Be warned, it is totally untested=20 > inside Xenomai, I just ran it in a user space test program. But it may=20 > give an idea. Your patch needed two minor corrections (ns instead of ts in functions=20 xnarch_ns_to_tsc()) in order to compile. A short run (30 minutes) of=20 latency -t1 seems to prove your bug-fix: There seems to be no drift. If I got your patch correctly, it doesn't make xnarch_tsc_to_ns more=20 precise but introduces a new function xnarch_ns_to_tsc() which is also=20 less precise than the generic xnarch_ns_to_tsc(), right? So isn't there=20 still the danger of getting wrong values when calling xnarch_tsc_to_ns()=20 not in combination with xnarch_ns_to_tsc()? --=20 Sebastian --------------060305050709020306030502 Content-Type: text/plain; name="fixup-scaled-ns2tsc-conversion.patch" Content-Disposition: inline; filename="fixup-scaled-ns2tsc-conversion.patch" Content-Transfer-Encoding: 7bit --- include/asm-x86/bits/init_32.h | 3 ++- include/asm-x86/bits/init_64.h | 3 ++- include/asm-x86/bits/pod_32.h | 7 +++++++ include/asm-x86/bits/pod_64.h | 7 +++++++ 4 files changed, 18 insertions(+), 2 deletions(-) Index: b/include/asm-x86/bits/init_32.h =================================================================== --- a/include/asm-x86/bits/init_32.h +++ b/include/asm-x86/bits/init_32.h @@ -73,7 +73,7 @@ int xnarch_calibrate_sched(void) static inline int xnarch_init(void) { - extern unsigned xnarch_tsc_scale, xnarch_tsc_shift; + extern unsigned xnarch_tsc_scale, xnarch_tsc_shift, xnarch_tsc_divide; int err; err = rthal_init(); @@ -89,6 +89,7 @@ static inline int xnarch_init(void) xnarch_init_llmulshft(1000000000, RTHAL_CPU_FREQ, &xnarch_tsc_scale, &xnarch_tsc_shift); + xnarch_tsc_divide = 1 << xnarch_tsc_shift; err = xnarch_calibrate_sched(); Index: b/include/asm-x86/bits/init_64.h =================================================================== --- a/include/asm-x86/bits/init_64.h +++ b/include/asm-x86/bits/init_64.h @@ -70,7 +70,7 @@ int xnarch_calibrate_sched(void) static inline int xnarch_init(void) { - extern unsigned xnarch_tsc_scale, xnarch_tsc_shift; + extern unsigned xnarch_tsc_scale, xnarch_tsc_shift, xnarch_tsc_divide; int err; err = rthal_init(); @@ -86,6 +86,7 @@ static inline int xnarch_init(void) xnarch_init_llmulshft(1000000000, RTHAL_CPU_FREQ, &xnarch_tsc_scale, &xnarch_tsc_shift); + xnarch_tsc_divide = 1 << xnarch_tsc_shift; err = xnarch_calibrate_sched(); Index: b/include/asm-x86/bits/pod_32.h =================================================================== --- a/include/asm-x86/bits/pod_32.h +++ b/include/asm-x86/bits/pod_32.h @@ -25,6 +25,7 @@ unsigned xnarch_tsc_scale; unsigned xnarch_tsc_shift; +unsigned xnarch_tsc_divide; long long xnarch_tsc_to_ns(long long ts) { @@ -32,6 +33,12 @@ long long xnarch_tsc_to_ns(long long ts) } #define XNARCH_TSC_TO_NS +long long xnarch_ns_to_tsc(long long ns) +{ + return xnarch_llimd(ns, xnarch_tsc_divide, xnarch_tsc_scale); +} +#define XNARCH_NS_TO_TSC + #include #include Index: b/include/asm-x86/bits/pod_64.h =================================================================== --- a/include/asm-x86/bits/pod_64.h +++ b/include/asm-x86/bits/pod_64.h @@ -24,6 +24,7 @@ unsigned xnarch_tsc_scale; unsigned xnarch_tsc_shift; +unsigned xnarch_tsc_divide; long long xnarch_tsc_to_ns(long long ts) { @@ -31,6 +32,12 @@ long long xnarch_tsc_to_ns(long long ts) } #define XNARCH_TSC_TO_NS +long long xnarch_ns_to_tsc(long long ns) +{ + return xnarch_llimd(ns, xnarch_tsc_divide, xnarch_tsc_scale); +} +#define XNARCH_NS_TO_TSC + #include #include --------------060305050709020306030502--