Message ID | 20200727184605.2945095-2-cheloha@linux.ibm.com (mailing list archive) |
---|---|
State | Accepted |
Commit | 5d1bc776428f34941a6237afb9454061b5b5e1e1 |
Headers | show |
Series | [v2,1/2] powerpc/perf: consolidate GPCI hcall structs into asm/hvcall.h | expand |
Context | Check | Description |
---|---|---|
snowpatch_ozlabs/apply_patch | success | Successfully applied on branch powerpc/merge (3f68564f1f5aca55654fda237fc01495bf050ce9) |
snowpatch_ozlabs/build-ppc64le | success | Build succeeded |
snowpatch_ozlabs/build-ppc64be | success | Build succeeded |
snowpatch_ozlabs/build-ppc64e | warning | Upstream build failed, couldn't test patch |
snowpatch_ozlabs/build-pmac32 | success | Build succeeded |
snowpatch_ozlabs/checkpatch | warning | total: 0 errors, 0 warnings, 1 checks, 47 lines checked |
snowpatch_ozlabs/needsstable | success | Patch has no Fixes tags |
On 7/27/20 11:46 AM, Scott Cheloha wrote: > The H_GetPerformanceCounterInfo (GPCI) PHYP hypercall has a subcall, > Affinity_Domain_Info_By_Partition, which returns, among other things, > a "partition affinity score" for a given LPAR. This score, a value on > [0-100], represents the processor-memory affinity for the LPAR in > question. A score of 0 indicates the worst possible affinity while a > score of 100 indicates perfect affinity. The score can be used to > reason about performance. > > This patch adds the score for the local LPAR to the lparcfg procfile > under a new 'partition_affinity_score' key. > > Signed-off-by: Scott Cheloha <cheloha@linux.ibm.com> I was hoping Michael would chime in the first time around on this patch series about adding another key/value pair to lparcfg. So, barring a NACK from mpe: Reviewed-by: Tyrel Datwyler <tyreld@linux.ibm.com> > --- > arch/powerpc/platforms/pseries/lparcfg.c | 35 ++++++++++++++++++++++++ > 1 file changed, 35 insertions(+) > > diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c > index b8d28ab88178..e278390ab28d 100644 > --- a/arch/powerpc/platforms/pseries/lparcfg.c > +++ b/arch/powerpc/platforms/pseries/lparcfg.c > @@ -136,6 +136,39 @@ static unsigned int h_get_ppp(struct hvcall_ppp_data *ppp_data) > return rc; > } > > +static void show_gpci_data(struct seq_file *m) > +{ > + struct hv_gpci_request_buffer *buf; > + unsigned int affinity_score; > + long ret; > + > + buf = kmalloc(sizeof(*buf), GFP_KERNEL); > + if (buf == NULL) > + return; > + > + /* > + * Show the local LPAR's affinity score. > + * > + * 0xB1 selects the Affinity_Domain_Info_By_Partition subcall. > + * The score is at byte 0xB in the output buffer. > + */ > + memset(&buf->params, 0, sizeof(buf->params)); > + buf->params.counter_request = cpu_to_be32(0xB1); > + buf->params.starting_index = cpu_to_be32(-1); /* local LPAR */ > + buf->params.counter_info_version_in = 0x5; /* v5+ for score */ > + ret = plpar_hcall_norets(H_GET_PERF_COUNTER_INFO, virt_to_phys(buf), > + sizeof(*buf)); > + if (ret != H_SUCCESS) { > + pr_debug("hcall failed: H_GET_PERF_COUNTER_INFO: %ld, %x\n", > + ret, be32_to_cpu(buf->params.detail_rc)); > + goto out; > + } > + affinity_score = buf->bytes[0xB]; > + seq_printf(m, "partition_affinity_score=%u\n", affinity_score); > +out: > + kfree(buf); > +} > + > static unsigned h_pic(unsigned long *pool_idle_time, > unsigned long *num_procs) > { > @@ -487,6 +520,8 @@ static int pseries_lparcfg_data(struct seq_file *m, void *v) > partition_active_processors * 100); > } > > + show_gpci_data(m); > + > seq_printf(m, "partition_active_processors=%d\n", > partition_active_processors); > >
Tyrel Datwyler <tyreld@linux.ibm.com> writes: > On 7/27/20 11:46 AM, Scott Cheloha wrote: >> The H_GetPerformanceCounterInfo (GPCI) PHYP hypercall has a subcall, >> Affinity_Domain_Info_By_Partition, which returns, among other things, >> a "partition affinity score" for a given LPAR. This score, a value on >> [0-100], represents the processor-memory affinity for the LPAR in >> question. A score of 0 indicates the worst possible affinity while a >> score of 100 indicates perfect affinity. The score can be used to >> reason about performance. >> >> This patch adds the score for the local LPAR to the lparcfg procfile >> under a new 'partition_affinity_score' key. >> >> Signed-off-by: Scott Cheloha <cheloha@linux.ibm.com> > > I was hoping Michael would chime in the first time around on this patch series > about adding another key/value pair to lparcfg. That guy is so unreliable. I don't love adding new stuff in lparcfg, but given the file already exists and there's no prospect of removing it, it's probably not worth the effort to put the new field anywhere else. My other query with this was how on earth anyone is meant to interpret the metric. ie. if my metric is 50, what does that mean? If it's 90 should I worry? Which makes me realise we have no documentation for lparcfg in the kernel at all. So it would be nice to have it mentioned somewhere in Documentation, even if it just points to the manpage in powerpc-ibm-utils. cheers > So, barring a NACK from mpe: > > Reviewed-by: Tyrel Datwyler <tyreld@linux.ibm.com> > >> --- >> arch/powerpc/platforms/pseries/lparcfg.c | 35 ++++++++++++++++++++++++ >> 1 file changed, 35 insertions(+) >> >> diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c >> index b8d28ab88178..e278390ab28d 100644 >> --- a/arch/powerpc/platforms/pseries/lparcfg.c >> +++ b/arch/powerpc/platforms/pseries/lparcfg.c >> @@ -136,6 +136,39 @@ static unsigned int h_get_ppp(struct hvcall_ppp_data *ppp_data) >> return rc; >> } >> >> +static void show_gpci_data(struct seq_file *m) >> +{ >> + struct hv_gpci_request_buffer *buf; >> + unsigned int affinity_score; >> + long ret; >> + >> + buf = kmalloc(sizeof(*buf), GFP_KERNEL); >> + if (buf == NULL) >> + return; >> + >> + /* >> + * Show the local LPAR's affinity score. >> + * >> + * 0xB1 selects the Affinity_Domain_Info_By_Partition subcall. >> + * The score is at byte 0xB in the output buffer. >> + */ >> + memset(&buf->params, 0, sizeof(buf->params)); >> + buf->params.counter_request = cpu_to_be32(0xB1); >> + buf->params.starting_index = cpu_to_be32(-1); /* local LPAR */ >> + buf->params.counter_info_version_in = 0x5; /* v5+ for score */ >> + ret = plpar_hcall_norets(H_GET_PERF_COUNTER_INFO, virt_to_phys(buf), >> + sizeof(*buf)); >> + if (ret != H_SUCCESS) { >> + pr_debug("hcall failed: H_GET_PERF_COUNTER_INFO: %ld, %x\n", >> + ret, be32_to_cpu(buf->params.detail_rc)); >> + goto out; >> + } >> + affinity_score = buf->bytes[0xB]; >> + seq_printf(m, "partition_affinity_score=%u\n", affinity_score); >> +out: >> + kfree(buf); >> +} >> + >> static unsigned h_pic(unsigned long *pool_idle_time, >> unsigned long *num_procs) >> { >> @@ -487,6 +520,8 @@ static int pseries_lparcfg_data(struct seq_file *m, void *v) >> partition_active_processors * 100); >> } >> >> + show_gpci_data(m); >> + >> seq_printf(m, "partition_active_processors=%d\n", >> partition_active_processors); >> >>
Michael Ellerman <mpe@ellerman.id.au> writes: > Tyrel Datwyler <tyreld@linux.ibm.com> writes: >> On 7/27/20 11:46 AM, Scott Cheloha wrote: >>> The H_GetPerformanceCounterInfo (GPCI) PHYP hypercall has a subcall, >>> Affinity_Domain_Info_By_Partition, which returns, among other things, >>> a "partition affinity score" for a given LPAR. This score, a value on >>> [0-100], represents the processor-memory affinity for the LPAR in >>> question. A score of 0 indicates the worst possible affinity while a >>> score of 100 indicates perfect affinity. The score can be used to >>> reason about performance. >>> >>> This patch adds the score for the local LPAR to the lparcfg procfile >>> under a new 'partition_affinity_score' key. >>> >>> Signed-off-by: Scott Cheloha <cheloha@linux.ibm.com> >> >> I was hoping Michael would chime in the first time around on this patch series >> about adding another key/value pair to lparcfg. > > That guy is so unreliable. > > I don't love adding new stuff in lparcfg, but given the file already > exists and there's no prospect of removing it, it's probably not worth > the effort to put the new field anywhere else. > > My other query with this was how on earth anyone is meant to interpret > the metric. ie. if my metric is 50, what does that mean? If it's 90 > should I worry? Here's some more background. This interface is just passing up what the platform provides, and it's identical to the partition affinity score described in the documentation for the management console's lsmemopt command: https://www.ibm.com/support/knowledgecenter/POWER9/p9edm/lsmemopt.html The score is 0-100, higher values are better. To illustrate: I believe a partition's score will be 100 (or very close to it) if all of its CPUs and memory reside within one node. It will be lower than that when a partition has some memory without local CPUs, and lower still when there is no CPU-memory affinity within the partition. Beyond that I don't have more specific information and the algorithm and scale are set by the platform. The intent is for this to be a metric to gather during problem determination e.g. via sosreport or similar, but as far as Linux is concerned this should be treated as an opaque value.
Scott Cheloha <cheloha@linux.ibm.com> writes: > The H_GetPerformanceCounterInfo (GPCI) PHYP hypercall has a subcall, > Affinity_Domain_Info_By_Partition, which returns, among other things, > a "partition affinity score" for a given LPAR. This score, a value on > [0-100], represents the processor-memory affinity for the LPAR in > question. A score of 0 indicates the worst possible affinity while a > score of 100 indicates perfect affinity. The score can be used to > reason about performance. > > This patch adds the score for the local LPAR to the lparcfg procfile > under a new 'partition_affinity_score' key. > > Signed-off-by: Scott Cheloha <cheloha@linux.ibm.com> > --- > arch/powerpc/platforms/pseries/lparcfg.c | 35 ++++++++++++++++++++++++ > 1 file changed, 35 insertions(+) > > diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c > index b8d28ab88178..e278390ab28d 100644 > --- a/arch/powerpc/platforms/pseries/lparcfg.c > +++ b/arch/powerpc/platforms/pseries/lparcfg.c > @@ -136,6 +136,39 @@ static unsigned int h_get_ppp(struct hvcall_ppp_data *ppp_data) > return rc; > } > > +static void show_gpci_data(struct seq_file *m) > +{ > + struct hv_gpci_request_buffer *buf; > + unsigned int affinity_score; > + long ret; > + > + buf = kmalloc(sizeof(*buf), GFP_KERNEL); > + if (buf == NULL) > + return; > + > + /* > + * Show the local LPAR's affinity score. > + * > + * 0xB1 selects the Affinity_Domain_Info_By_Partition subcall. > + * The score is at byte 0xB in the output buffer. > + */ > + memset(&buf->params, 0, sizeof(buf->params)); > + buf->params.counter_request = cpu_to_be32(0xB1); > + buf->params.starting_index = cpu_to_be32(-1); /* local LPAR */ > + buf->params.counter_info_version_in = 0x5; /* v5+ for score */ > + ret = plpar_hcall_norets(H_GET_PERF_COUNTER_INFO, virt_to_phys(buf), > + sizeof(*buf)); > + if (ret != H_SUCCESS) { > + pr_debug("hcall failed: H_GET_PERF_COUNTER_INFO: %ld, %x\n", > + ret, be32_to_cpu(buf->params.detail_rc)); > + goto out; > + } > + affinity_score = buf->bytes[0xB]; > + seq_printf(m, "partition_affinity_score=%u\n", affinity_score); > +out: > + kfree(buf); > +} > + > static unsigned h_pic(unsigned long *pool_idle_time, > unsigned long *num_procs) > { > @@ -487,6 +520,8 @@ static int pseries_lparcfg_data(struct seq_file *m, void *v) > partition_active_processors * 100); > } > > + show_gpci_data(m); > + > seq_printf(m, "partition_active_processors=%d\n", > partition_active_processors); Acked-by: Nathan Lynch <nathanl@linux.ibm.com>
diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c index b8d28ab88178..e278390ab28d 100644 --- a/arch/powerpc/platforms/pseries/lparcfg.c +++ b/arch/powerpc/platforms/pseries/lparcfg.c @@ -136,6 +136,39 @@ static unsigned int h_get_ppp(struct hvcall_ppp_data *ppp_data) return rc; } +static void show_gpci_data(struct seq_file *m) +{ + struct hv_gpci_request_buffer *buf; + unsigned int affinity_score; + long ret; + + buf = kmalloc(sizeof(*buf), GFP_KERNEL); + if (buf == NULL) + return; + + /* + * Show the local LPAR's affinity score. + * + * 0xB1 selects the Affinity_Domain_Info_By_Partition subcall. + * The score is at byte 0xB in the output buffer. + */ + memset(&buf->params, 0, sizeof(buf->params)); + buf->params.counter_request = cpu_to_be32(0xB1); + buf->params.starting_index = cpu_to_be32(-1); /* local LPAR */ + buf->params.counter_info_version_in = 0x5; /* v5+ for score */ + ret = plpar_hcall_norets(H_GET_PERF_COUNTER_INFO, virt_to_phys(buf), + sizeof(*buf)); + if (ret != H_SUCCESS) { + pr_debug("hcall failed: H_GET_PERF_COUNTER_INFO: %ld, %x\n", + ret, be32_to_cpu(buf->params.detail_rc)); + goto out; + } + affinity_score = buf->bytes[0xB]; + seq_printf(m, "partition_affinity_score=%u\n", affinity_score); +out: + kfree(buf); +} + static unsigned h_pic(unsigned long *pool_idle_time, unsigned long *num_procs) { @@ -487,6 +520,8 @@ static int pseries_lparcfg_data(struct seq_file *m, void *v) partition_active_processors * 100); } + show_gpci_data(m); + seq_printf(m, "partition_active_processors=%d\n", partition_active_processors);
The H_GetPerformanceCounterInfo (GPCI) PHYP hypercall has a subcall, Affinity_Domain_Info_By_Partition, which returns, among other things, a "partition affinity score" for a given LPAR. This score, a value on [0-100], represents the processor-memory affinity for the LPAR in question. A score of 0 indicates the worst possible affinity while a score of 100 indicates perfect affinity. The score can be used to reason about performance. This patch adds the score for the local LPAR to the lparcfg procfile under a new 'partition_affinity_score' key. Signed-off-by: Scott Cheloha <cheloha@linux.ibm.com> --- arch/powerpc/platforms/pseries/lparcfg.c | 35 ++++++++++++++++++++++++ 1 file changed, 35 insertions(+)