In commit f26b3fa04611 ("mm/page_alloc: limit number of high-order
pages on PCP during bulk free"), the PCP (Per-CPU Pageset) will be
drained when PCP is mostly used for high-order pages freeing to
improve the cache-hot pages reusing between page allocating and
freeing CPUs.
On system with small per-CPU data cache slice, pages shouldn't be
cached before draining to guarantee cache-hot. But on a system with
large per-CPU data cache slice, some pages can be cached before
draining to reduce zone lock contention.
So, in this patch, instead of draining without any caching,
"pcp->batch" pages will be cached in PCP before draining if the
size of the per-CPU data cache slice is more than "3 * batch".
In theory, if the size of per-CPU data cache slice is more than "2 *
batch", we can reuse cache-hot pages between CPUs. But considering
the other usage of cache (code, other data accessing, etc.), "3 *
batch" is used.
Note: "3 * batch" is chosen to make sure the optimization works on
recent x86_64 server CPUs. If you want to increase it, please check
whether it breaks the optimization.
On a 2-socket Intel server with 128 logical CPU, with the patch, the
network bandwidth of the UNIX (AF_UNIX) test case of lmbench test
suite with 16-pair processes increase 70.5%. The cycles% of the
spinlock contention (mostly for zone lock) decreases from 46.1% to
21.3%. The number of PCP draining for high order pages
freeing (free_high) decreases 89.9%. The cache miss rate keeps 0.2%.
Signed-off-by: "Huang, Ying" <ying.huang@intel.com>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Sudeep Holla <sudeep.holla@arm.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: David Hildenbrand <david@redhat.com>
Cc: Johannes Weiner <jweiner@redhat.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Christoph Lameter <cl@linux.com>
---
drivers/base/cacheinfo.c | 2 ++
include/linux/gfp.h | 1 +
include/linux/mmzone.h | 6 ++++++
mm/page_alloc.c | 38 +++++++++++++++++++++++++++++++++++++-
4 files changed, 46 insertions(+), 1 deletion(-)
diff --git a/drivers/base/cacheinfo.c b/drivers/base/cacheinfo.c
index 585c66fce9d9..f1e79263fe61 100644
--- a/drivers/base/cacheinfo.c
+++ b/drivers/base/cacheinfo.c
@@ -950,6 +950,7 @@ static int cacheinfo_cpu_online(unsigned int cpu)
if (rc)
goto err;
update_per_cpu_data_slice_size(true, cpu);
+ setup_pcp_cacheinfo();
return 0;
err:
free_cache_attributes(cpu);
@@ -963,6 +964,7 @@ static int cacheinfo_cpu_pre_down(unsigned int cpu)
free_cache_attributes(cpu);
update_per_cpu_data_slice_size(false, cpu);
+ setup_pcp_cacheinfo();
return 0;
}
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 665f06675c83..665edc11fb9f 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -325,6 +325,7 @@ void drain_all_pages(struct zone *zone);
void drain_local_pages(struct zone *zone);
void page_alloc_init_late(void);
+void setup_pcp_cacheinfo(void);
/*
* gfp_allowed_mask is set to GFP_BOOT_MASK during early boot to restrict what
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 19c40a6f7e45..cdff247e8c6f 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -682,8 +682,14 @@ enum zone_watermarks {
* PCPF_PREV_FREE_HIGH_ORDER: a high-order page is freed in the
* previous page freeing. To avoid to drain PCP for an accident
* high-order page freeing.
+ *
+ * PCPF_FREE_HIGH_BATCH: preserve "pcp->batch" pages in PCP before
+ * draining PCP for consecutive high-order pages freeing without
+ * allocation if data cache slice of CPU is large enough. To reduce
+ * zone lock contention and keep cache-hot pages reusing.
*/
#define PCPF_PREV_FREE_HIGH_ORDER BIT(0)
+#define PCPF_FREE_HIGH_BATCH BIT(1)
struct per_cpu_pages {
spinlock_t lock; /* Protects lists field */
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 295e61f0c49d..ba2d8f06523e 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -52,6 +52,7 @@
#include <linux/psi.h>
#include <linux/khugepaged.h>
#include <linux/delayacct.h>
+#include <linux/cacheinfo.h>
#include <asm/div64.h>
#include "internal.h"
#include "shuffle.h"
@@ -2385,7 +2386,9 @@ static void free_unref_page_commit(struct zone *zone, struct per_cpu_pages *pcp,
*/
if (order && order <= PAGE_ALLOC_COSTLY_ORDER) {
free_high = (pcp->free_factor &&
- (pcp->flags & PCPF_PREV_FREE_HIGH_ORDER));
+ (pcp->flags & PCPF_PREV_FREE_HIGH_ORDER) &&
+ (!(pcp->flags & PCPF_FREE_HIGH_BATCH) ||
+ pcp->count >= READ_ONCE(pcp->batch)));
pcp->flags |= PCPF_PREV_FREE_HIGH_ORDER;
} else if (pcp->flags & PCPF_PREV_FREE_HIGH_ORDER) {
pcp->flags &= ~PCPF_PREV_FREE_HIGH_ORDER;
@@ -5418,6 +5421,39 @@ static void zone_pcp_update(struct zone *zone, int cpu_online)
mutex_unlock(&pcp_batch_high_lock);
}
+static void zone_pcp_update_cacheinfo(struct zone *zone)
+{
+ int cpu;
+ struct per_cpu_pages *pcp;
+ struct cpu_cacheinfo *cci;
+
+ for_each_online_cpu(cpu) {
+ pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu);
+ cci = get_cpu_cacheinfo(cpu);
+ /*
+ * If data cache slice of CPU is large enough, "pcp->batch"
+ * pages can be preserved in PCP before draining PCP for
+ * consecutive high-order pages freeing without allocation.
+ * This can reduce zone lock contention without hurting
+ * cache-hot pages sharing.
+ */
+ spin_lock(&pcp->lock);
+ if ((cci->per_cpu_data_slice_size >> PAGE_SHIFT) > 3 * pcp->batch)
+ pcp->flags |= PCPF_FREE_HIGH_BATCH;
+ else
+ pcp->flags &= ~PCPF_FREE_HIGH_BATCH;
+ spin_unlock(&pcp->lock);
+ }
+}
+
+void setup_pcp_cacheinfo(void)
+{
+ struct zone *zone;
+
+ for_each_populated_zone(zone)
+ zone_pcp_update_cacheinfo(zone);
+}
+
/*
* Allocate per cpu pagesets and initialize them.
* Before this call only boot pagesets were available.
--
2.39.2
hi, Huang Ying,
sorry for late of this report.
we reported
"a 14.6% improvement of netperf.Throughput_Mbps"
in
https://lore.kernel.org/all/202310271441.71ce0a9-oliver.sang@intel.com/
later, our auto-bisect tool captured a regression on a netperf test with
different configurations, however, unfortunately, regarded it as 'reported'
so we missed this report at the first time.
now send again FYI.
Hello,
kernel test robot noticed a -60.4% regression of netperf.Throughput_Mbps on:
commit: f5ddc662f07d7d99e9cfc5e07778e26c7394caf8 ("[PATCH -V3 3/9] mm, pcp: reduce lock contention for draining high-order pages")
url: https://github.com/intel-lab-lkp/linux/commits/Huang-Ying/mm-pcp-avoid-to-drain-PCP-when-process-exit/20231017-143633
base: https://git.kernel.org/cgit/linux/kernel/git/gregkh/driver-core.git 36b2d7dd5a8ac95c8c1e69bdc93c4a6e2dc28a23
patch link: https://lore.kernel.org/all/20231016053002.756205-4-ying.huang@intel.com/
patch subject: [PATCH -V3 3/9] mm, pcp: reduce lock contention for draining high-order pages
testcase: netperf
test machine: 128 threads 2 sockets Intel(R) Xeon(R) Gold 6338 CPU @ 2.00GHz (Ice Lake) with 256G memory
parameters:
ip: ipv4
runtime: 300s
nr_threads: 50%
cluster: cs-localhost
test: UDP_STREAM
cpufreq_governor: performance
If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <oliver.sang@intel.com>
| Closes: https://lore.kernel.org/oe-lkp/202311061311.8d63998-oliver.sang@intel.com
Details are as below:
-------------------------------------------------------------------------------------------------->
The kernel config and materials to reproduce are available at:
https://download.01.org/0day-ci/archive/20231106/202311061311.8d63998-oliver.sang@intel.com
=========================================================================================
cluster/compiler/cpufreq_governor/ip/kconfig/nr_threads/rootfs/runtime/tbox_group/test/testcase:
cs-localhost/gcc-12/performance/ipv4/x86_64-rhel-8.3/50%/debian-11.1-x86_64-20220510.cgz/300s/lkp-icl-2sp2/UDP_STREAM/netperf
commit:
c828e65251 ("cacheinfo: calculate size of per-CPU data cache slice")
f5ddc662f0 ("mm, pcp: reduce lock contention for draining high-order pages")
c828e65251502516 f5ddc662f07d7d99e9cfc5e0777
---------------- ---------------------------
%stddev %change %stddev
\ | \
7321 ± 4% +28.2% 9382 uptime.idle
50.65 ± 4% -4.0% 48.64 boot-time.boot
6042 ± 4% -4.2% 5785 boot-time.idle
1.089e+09 ± 2% +232.1% 3.618e+09 cpuidle..time
1087075 ± 2% +24095.8% 2.63e+08 cpuidle..usage
3357014 +99.9% 6710312 vmstat.memory.cache
48731 ± 19% +4666.5% 2322787 vmstat.system.cs
144637 +711.2% 1173334 vmstat.system.in
2.59 ± 2% +6.2 8.79 mpstat.cpu.all.idle%
1.01 +0.7 1.66 mpstat.cpu.all.irq%
6.00 -3.2 2.79 mpstat.cpu.all.soft%
1.13 ± 2% -0.1 1.02 mpstat.cpu.all.usr%
1.407e+09 ± 3% -28.2% 1.011e+09 numa-numastat.node0.local_node
1.407e+09 ± 3% -28.2% 1.01e+09 numa-numastat.node0.numa_hit
1.469e+09 ± 8% -32.0% 9.979e+08 numa-numastat.node1.local_node
1.469e+09 ± 8% -32.1% 9.974e+08 numa-numastat.node1.numa_hit
103.00 ± 19% -44.0% 57.67 ± 20% perf-c2c.DRAM.local
8970 ± 12% -89.4% 951.00 ± 4% perf-c2c.DRAM.remote
8192 ± 5% +68.5% 13807 perf-c2c.HITM.local
6675 ± 11% -92.6% 491.00 ± 2% perf-c2c.HITM.remote
1051014 ± 2% +24922.0% 2.63e+08 turbostat.C1
2.75 ± 2% +6.5 9.29 turbostat.C1%
2.72 ± 2% +178.3% 7.57 turbostat.CPU%c1
0.09 -22.2% 0.07 turbostat.IPC
44589125 +701.5% 3.574e+08 turbostat.IRQ
313.00 ± 57% +1967.0% 6469 ± 8% turbostat.POLL
70.33 +3.3% 72.67 turbostat.PkgTmp
44.23 ± 4% -31.8% 30.15 ± 2% turbostat.RAMWatt
536096 +583.7% 3665194 meminfo.Active
535414 +584.4% 3664543 meminfo.Active(anon)
3238301 +103.2% 6579677 meminfo.Cached
1204424 +278.9% 4563575 meminfo.Committed_AS
469093 +47.9% 693889 ± 3% meminfo.Inactive
467250 +48.4% 693496 ± 3% meminfo.Inactive(anon)
53615 +562.5% 355225 ± 4% meminfo.Mapped
5223078 +64.1% 8571212 meminfo.Memused
557305 +599.6% 3899111 meminfo.Shmem
5660207 +58.9% 8993642 meminfo.max_used_kB
78504 ± 3% -30.1% 54869 netperf.ThroughputBoth_Mbps
5024292 ± 3% -30.1% 3511666 netperf.ThroughputBoth_total_Mbps
7673 ± 5% +249.7% 26832 netperf.ThroughputRecv_Mbps
491074 ± 5% +249.7% 1717287 netperf.ThroughputRecv_total_Mbps
70831 ± 2% -60.4% 28037 netperf.Throughput_Mbps
4533217 ± 2% -60.4% 1794379 netperf.Throughput_total_Mbps
5439 +9.4% 5949 netperf.time.percent_of_cpu_this_job_got
16206 +9.4% 17728 netperf.time.system_time
388.14 -51.9% 186.53 netperf.time.user_time
2.876e+09 ± 3% -30.1% 2.01e+09 netperf.workload
177360 ± 30% -36.0% 113450 ± 20% numa-meminfo.node0.AnonPages
255926 ± 12% -40.6% 152052 ± 12% numa-meminfo.node0.AnonPages.max
22582 ± 61% +484.2% 131916 ± 90% numa-meminfo.node0.Mapped
138287 ± 17% +22.6% 169534 ± 12% numa-meminfo.node1.AnonHugePages
267468 ± 20% +29.1% 345385 ± 6% numa-meminfo.node1.AnonPages
346204 ± 18% +34.5% 465696 ± 2% numa-meminfo.node1.AnonPages.max
279416 ± 19% +77.0% 494652 ± 18% numa-meminfo.node1.Inactive
278445 ± 19% +77.6% 494393 ± 18% numa-meminfo.node1.Inactive(anon)
31726 ± 45% +607.7% 224533 ± 45% numa-meminfo.node1.Mapped
4802 ± 6% +19.4% 5733 ± 3% numa-meminfo.node1.PageTables
297323 ± 12% +792.6% 2653850 ± 63% numa-meminfo.node1.Shmem
44325 ± 30% -36.0% 28379 ± 20% numa-vmstat.node0.nr_anon_pages
5590 ± 61% +491.0% 33042 ± 90% numa-vmstat.node0.nr_mapped
1.407e+09 ± 3% -28.2% 1.01e+09 numa-vmstat.node0.numa_hit
1.407e+09 ± 3% -28.2% 1.011e+09 numa-vmstat.node0.numa_local
66858 ± 20% +29.2% 86385 ± 6% numa-vmstat.node1.nr_anon_pages
69601 ± 20% +77.8% 123729 ± 18% numa-vmstat.node1.nr_inactive_anon
7953 ± 45% +608.3% 56335 ± 45% numa-vmstat.node1.nr_mapped
1201 ± 6% +19.4% 1434 ± 3% numa-vmstat.node1.nr_page_table_pages
74288 ± 11% +792.6% 663111 ± 63% numa-vmstat.node1.nr_shmem
69601 ± 20% +77.8% 123728 ± 18% numa-vmstat.node1.nr_zone_inactive_anon
1.469e+09 ± 8% -32.1% 9.974e+08 numa-vmstat.node1.numa_hit
1.469e+09 ± 8% -32.0% 9.979e+08 numa-vmstat.node1.numa_local
133919 +584.2% 916254 proc-vmstat.nr_active_anon
111196 +3.3% 114828 proc-vmstat.nr_anon_pages
5602484 -1.5% 5518799 proc-vmstat.nr_dirty_background_threshold
11218668 -1.5% 11051092 proc-vmstat.nr_dirty_threshold
809646 +103.2% 1645012 proc-vmstat.nr_file_pages
56374629 -1.5% 55536913 proc-vmstat.nr_free_pages
116775 +48.4% 173349 ± 3% proc-vmstat.nr_inactive_anon
13386 ± 2% +563.3% 88793 ± 4% proc-vmstat.nr_mapped
2286 +6.5% 2434 proc-vmstat.nr_page_table_pages
139393 +599.4% 974869 proc-vmstat.nr_shmem
29092 +6.6% 31019 proc-vmstat.nr_slab_reclaimable
133919 +584.2% 916254 proc-vmstat.nr_zone_active_anon
116775 +48.4% 173349 ± 3% proc-vmstat.nr_zone_inactive_anon
32135 ± 11% +257.2% 114797 ± 21% proc-vmstat.numa_hint_faults
20858 ± 16% +318.3% 87244 ± 6% proc-vmstat.numa_hint_faults_local
2.876e+09 ± 3% -30.2% 2.008e+09 proc-vmstat.numa_hit
2.876e+09 ± 3% -30.2% 2.008e+09 proc-vmstat.numa_local
25453 ± 7% -75.2% 6324 ± 30% proc-vmstat.numa_pages_migrated
178224 ± 2% +76.6% 314680 ± 7% proc-vmstat.numa_pte_updates
160889 ± 3% +267.6% 591393 ± 6% proc-vmstat.pgactivate
2.295e+10 ± 3% -30.2% 1.601e+10 proc-vmstat.pgalloc_normal
1026605 +21.9% 1251671 proc-vmstat.pgfault
2.295e+10 ± 3% -30.2% 1.601e+10 proc-vmstat.pgfree
25453 ± 7% -75.2% 6324 ± 30% proc-vmstat.pgmigrate_success
39208 ± 2% -6.1% 36815 proc-vmstat.pgreuse
3164416 -20.3% 2521344 ± 2% proc-vmstat.unevictable_pgs_scanned
19248627 -22.1% 14989905 sched_debug.cfs_rq:/.avg_vruntime.avg
20722680 -24.9% 15569530 sched_debug.cfs_rq:/.avg_vruntime.max
17634233 -22.5% 13663168 sched_debug.cfs_rq:/.avg_vruntime.min
949063 ± 2% -70.5% 280388 sched_debug.cfs_rq:/.avg_vruntime.stddev
0.78 ± 10% -100.0% 0.00 sched_debug.cfs_rq:/.h_nr_running.min
0.16 ± 8% +113.3% 0.33 ± 2% sched_debug.cfs_rq:/.h_nr_running.stddev
0.56 ±141% +2.2e+07% 122016 ± 52% sched_debug.cfs_rq:/.left_vruntime.avg
45.01 ±141% +2.2e+07% 10035976 ± 28% sched_debug.cfs_rq:/.left_vruntime.max
4.58 ±141% +2.3e+07% 1072762 ± 36% sched_debug.cfs_rq:/.left_vruntime.stddev
5814 ± 10% -100.0% 0.00 sched_debug.cfs_rq:/.load.min
5.39 ± 9% -73.2% 1.44 ± 10% sched_debug.cfs_rq:/.load_avg.min
19248627 -22.1% 14989905 sched_debug.cfs_rq:/.min_vruntime.avg
20722680 -24.9% 15569530 sched_debug.cfs_rq:/.min_vruntime.max
17634233 -22.5% 13663168 sched_debug.cfs_rq:/.min_vruntime.min
949063 ± 2% -70.5% 280388 sched_debug.cfs_rq:/.min_vruntime.stddev
0.78 ± 10% -100.0% 0.00 sched_debug.cfs_rq:/.nr_running.min
0.06 ± 8% +369.2% 0.30 ± 3% sched_debug.cfs_rq:/.nr_running.stddev
4.84 ± 26% +1611.3% 82.79 ± 67% sched_debug.cfs_rq:/.removed.load_avg.avg
27.92 ± 12% +3040.3% 876.79 ± 68% sched_debug.cfs_rq:/.removed.load_avg.stddev
0.56 ±141% +2.2e+07% 122016 ± 52% sched_debug.cfs_rq:/.right_vruntime.avg
45.06 ±141% +2.2e+07% 10035976 ± 28% sched_debug.cfs_rq:/.right_vruntime.max
4.59 ±141% +2.3e+07% 1072762 ± 36% sched_debug.cfs_rq:/.right_vruntime.stddev
900.25 -10.4% 806.45 sched_debug.cfs_rq:/.runnable_avg.avg
533.28 ± 4% -87.0% 69.56 ± 39% sched_debug.cfs_rq:/.runnable_avg.min
122.77 ± 2% +92.9% 236.86 sched_debug.cfs_rq:/.runnable_avg.stddev
896.13 -10.8% 799.44 sched_debug.cfs_rq:/.util_avg.avg
379.06 ± 4% -83.4% 62.94 ± 37% sched_debug.cfs_rq:/.util_avg.min
116.35 ± 8% +99.4% 232.04 sched_debug.cfs_rq:/.util_avg.stddev
550.87 -14.2% 472.66 ± 2% sched_debug.cfs_rq:/.util_est_enqueued.avg
1124 ± 8% +18.2% 1329 ± 3% sched_debug.cfs_rq:/.util_est_enqueued.max
134.17 ± 30% -100.0% 0.00 sched_debug.cfs_rq:/.util_est_enqueued.min
558243 ± 6% -66.9% 184666 sched_debug.cpu.avg_idle.avg
12860 ± 11% -56.1% 5644 sched_debug.cpu.avg_idle.min
365635 -53.5% 169863 ± 5% sched_debug.cpu.avg_idle.stddev
9.56 ± 3% -28.4% 6.84 ± 8% sched_debug.cpu.clock.stddev
6999 ± 2% -85.6% 1007 ± 3% sched_debug.cpu.clock_task.stddev
3985 ± 10% -100.0% 0.00 sched_debug.cpu.curr->pid.min
491.71 ± 10% +209.3% 1520 ± 4% sched_debug.cpu.curr->pid.stddev
270.19 ±141% +1096.6% 3233 ± 51% sched_debug.cpu.max_idle_balance_cost.stddev
0.78 ± 10% -100.0% 0.00 sched_debug.cpu.nr_running.min
0.15 ± 6% +121.7% 0.34 ± 2% sched_debug.cpu.nr_running.stddev
62041 ± 15% +4280.9% 2717948 sched_debug.cpu.nr_switches.avg
1074922 ± 14% +292.6% 4220307 ± 2% sched_debug.cpu.nr_switches.max
1186 ± 2% +1.2e+05% 1379073 ± 4% sched_debug.cpu.nr_switches.min
132392 ± 21% +294.6% 522476 ± 5% sched_debug.cpu.nr_switches.stddev
6.44 ± 4% +21.4% 7.82 ± 12% sched_debug.cpu.nr_uninterruptible.stddev
6.73 ± 13% -84.8% 1.02 ± 5% perf-stat.i.MPKI
1.652e+10 ± 2% -22.2% 1.285e+10 perf-stat.i.branch-instructions
0.72 +0.0 0.75 perf-stat.i.branch-miss-rate%
1.19e+08 ± 3% -19.8% 95493630 perf-stat.i.branch-misses
27.46 ± 12% -26.2 1.30 ± 4% perf-stat.i.cache-miss-rate%
5.943e+08 ± 10% -88.6% 67756219 ± 5% perf-stat.i.cache-misses
2.201e+09 +143.7% 5.364e+09 perf-stat.i.cache-references
48911 ± 19% +4695.4% 2345525 perf-stat.i.context-switches
3.66 ± 2% +28.5% 4.71 perf-stat.i.cpi
3.228e+11 -4.1% 3.097e+11 perf-stat.i.cpu-cycles
190.51 +1363.7% 2788 ± 10% perf-stat.i.cpu-migrations
803.99 ± 6% +510.2% 4905 ± 5% perf-stat.i.cycles-between-cache-misses
0.00 ± 16% +0.0 0.01 ± 14% perf-stat.i.dTLB-load-miss-rate%
755654 ± 18% +232.4% 2512024 ± 14% perf-stat.i.dTLB-load-misses
2.385e+10 ± 2% -26.9% 1.742e+10 perf-stat.i.dTLB-loads
0.00 ± 31% +0.0 0.01 ± 35% perf-stat.i.dTLB-store-miss-rate%
305657 ± 36% +200.0% 916822 ± 35% perf-stat.i.dTLB-store-misses
1.288e+10 ± 2% -28.8% 9.179e+09 perf-stat.i.dTLB-stores
8.789e+10 ± 2% -25.2% 6.578e+10 perf-stat.i.instructions
0.28 ± 2% -21.6% 0.22 perf-stat.i.ipc
2.52 -4.1% 2.42 perf-stat.i.metric.GHz
873.89 ± 12% -67.0% 288.04 ± 8% perf-stat.i.metric.K/sec
435.61 ± 2% -19.6% 350.06 perf-stat.i.metric.M/sec
2799 +29.9% 3637 ± 2% perf-stat.i.minor-faults
99.74 -2.6 97.11 perf-stat.i.node-load-miss-rate%
1.294e+08 ± 12% -92.4% 9879207 ± 7% perf-stat.i.node-load-misses
76.55 +16.4 92.92 perf-stat.i.node-store-miss-rate%
2.257e+08 ± 10% -90.4% 21721672 ± 8% perf-stat.i.node-store-misses
69217511 ± 13% -97.7% 1625810 ± 7% perf-stat.i.node-stores
2799 +29.9% 3637 ± 2% perf-stat.i.page-faults
6.79 ± 13% -84.9% 1.03 ± 5% perf-stat.overall.MPKI
0.72 +0.0 0.74 perf-stat.overall.branch-miss-rate%
27.06 ± 12% -25.8 1.26 ± 4% perf-stat.overall.cache-miss-rate%
3.68 ± 2% +28.1% 4.71 perf-stat.overall.cpi
549.38 ± 10% +736.0% 4592 ± 5% perf-stat.overall.cycles-between-cache-misses
0.00 ± 18% +0.0 0.01 ± 14% perf-stat.overall.dTLB-load-miss-rate%
0.00 ± 36% +0.0 0.01 ± 35% perf-stat.overall.dTLB-store-miss-rate%
0.27 ± 2% -22.0% 0.21 perf-stat.overall.ipc
99.80 -2.4 97.37 perf-stat.overall.node-load-miss-rate%
76.60 +16.4 93.03 perf-stat.overall.node-store-miss-rate%
9319 +5.8% 9855 perf-stat.overall.path-length
1.646e+10 ± 2% -22.2% 1.281e+10 perf-stat.ps.branch-instructions
1.186e+08 ± 3% -19.8% 95167897 perf-stat.ps.branch-misses
5.924e+08 ± 10% -88.6% 67384354 ± 5% perf-stat.ps.cache-misses
2.193e+09 +143.4% 5.339e+09 perf-stat.ps.cache-references
49100 ± 19% +4668.0% 2341074 perf-stat.ps.context-switches
3.218e+11 -4.1% 3.087e+11 perf-stat.ps.cpu-cycles
189.73 +1368.4% 2786 ± 10% perf-stat.ps.cpu-migrations
753056 ± 18% +229.9% 2484575 ± 14% perf-stat.ps.dTLB-load-misses
2.377e+10 ± 2% -26.9% 1.737e+10 perf-stat.ps.dTLB-loads
304509 ± 36% +199.1% 910856 ± 35% perf-stat.ps.dTLB-store-misses
1.284e+10 ± 2% -28.7% 9.152e+09 perf-stat.ps.dTLB-stores
8.76e+10 ± 2% -25.2% 6.557e+10 perf-stat.ps.instructions
2791 +28.2% 3580 ± 2% perf-stat.ps.minor-faults
1.29e+08 ± 12% -92.4% 9815672 ± 7% perf-stat.ps.node-load-misses
2.25e+08 ± 10% -90.4% 21575943 ± 8% perf-stat.ps.node-store-misses
69002373 ± 13% -97.7% 1615410 ± 7% perf-stat.ps.node-stores
2791 +28.2% 3580 ± 2% perf-stat.ps.page-faults
2.68e+13 ± 2% -26.1% 1.981e+13 perf-stat.total.instructions
0.00 ± 35% +2600.0% 0.04 ± 23% perf-sched.sch_delay.avg.ms.__cond_resched.__skb_datagram_iter.skb_copy_datagram_iter.udp_recvmsg.inet_recvmsg
1.18 ± 9% -98.1% 0.02 ± 32% perf-sched.sch_delay.avg.ms.__cond_resched.stop_one_cpu.sched_exec.bprm_execve.part
0.58 ± 3% -62.1% 0.22 ± 97% perf-sched.sch_delay.avg.ms.__x64_sys_pause.do_syscall_64.entry_SYSCALL_64_after_hwframe.[unknown]
0.51 ± 22% -82.7% 0.09 ± 11% perf-sched.sch_delay.avg.ms.do_task_dead.do_exit.do_group_exit.__x64_sys_exit_group.do_syscall_64
0.25 ± 23% -59.6% 0.10 ± 10% perf-sched.sch_delay.avg.ms.do_wait.kernel_wait4.__do_sys_wait4.do_syscall_64
0.03 ± 42% -64.0% 0.01 ± 15% perf-sched.sch_delay.avg.ms.pipe_read.vfs_read.ksys_read.do_syscall_64
0.04 ± 7% +434.6% 0.23 ± 36% perf-sched.sch_delay.avg.ms.schedule_hrtimeout_range_clock.do_poll.constprop.0.do_sys_poll
1.00 ± 20% -84.1% 0.16 ± 78% perf-sched.sch_delay.avg.ms.schedule_hrtimeout_range_clock.do_select.core_sys_select.kern_select
0.01 ± 7% -70.0% 0.00 perf-sched.sch_delay.avg.ms.schedule_timeout.__skb_wait_for_more_packets.__skb_recv_udp.udp_recvmsg
0.02 ± 2% +533.9% 0.12 ± 43% perf-sched.sch_delay.avg.ms.schedule_timeout.kcompactd.kthread.ret_from_fork
0.03 ± 7% +105.9% 0.06 ± 33% perf-sched.sch_delay.avg.ms.schedule_timeout.rcu_gp_fqs_loop.rcu_gp_kthread.kthread
0.01 ± 15% +67.5% 0.02 ± 8% perf-sched.sch_delay.avg.ms.smpboot_thread_fn.kthread.ret_from_fork.ret_from_fork_asm
0.09 ± 50% -85.7% 0.01 ± 33% perf-sched.sch_delay.avg.ms.wait_for_partner.fifo_open.do_dentry_open.do_open
0.04 ± 7% +343.4% 0.16 ± 6% perf-sched.sch_delay.avg.ms.worker_thread.kthread.ret_from_fork.ret_from_fork_asm
0.06 ± 41% +3260.7% 1.88 ± 30% perf-sched.sch_delay.max.ms.__cond_resched.__skb_datagram_iter.skb_copy_datagram_iter.udp_recvmsg.inet_recvmsg
3.78 -96.2% 0.14 ± 3% perf-sched.sch_delay.max.ms.__cond_resched.stop_one_cpu.sched_exec.bprm_execve.part
2.86 ± 4% -72.6% 0.78 ±113% perf-sched.sch_delay.max.ms.__x64_sys_pause.do_syscall_64.entry_SYSCALL_64_after_hwframe.[unknown]
4.09 ± 7% -34.1% 2.69 ± 7% perf-sched.sch_delay.max.ms.do_task_dead.do_exit.do_group_exit.__x64_sys_exit_group.do_syscall_64
3.09 ± 37% -64.1% 1.11 ± 5% perf-sched.sch_delay.max.ms.do_wait.kernel_wait4.__do_sys_wait4.do_syscall_64
0.00 ±141% +6200.0% 0.13 ± 82% perf-sched.sch_delay.max.ms.exit_to_user_mode_loop.exit_to_user_mode_prepare.irqentry_exit_to_user_mode.asm_sysvec_apic_timer_interrupt
3.94 -40.5% 2.35 ± 48% perf-sched.sch_delay.max.ms.pipe_read.vfs_read.ksys_read.do_syscall_64
1.63 ± 21% -77.0% 0.38 ± 90% perf-sched.sch_delay.max.ms.schedule_hrtimeout_range_clock.do_select.core_sys_select.kern_select
7.29 ± 39% +417.5% 37.72 ± 16% perf-sched.sch_delay.max.ms.schedule_timeout.__skb_wait_for_more_packets.__skb_recv_udp.udp_recvmsg
3.35 ± 14% -51.7% 1.62 ± 3% perf-sched.sch_delay.max.ms.schedule_timeout.__wait_for_common.wait_for_completion_state.kernel_clone
0.05 ± 13% +2245.1% 1.13 ± 40% perf-sched.sch_delay.max.ms.schedule_timeout.kcompactd.kthread.ret_from_fork
3.01 ± 26% +729.6% 25.01 ± 91% perf-sched.sch_delay.max.ms.schedule_timeout.rcu_gp_fqs_loop.rcu_gp_kthread.kthread
1.93 ± 59% -85.5% 0.28 ± 62% perf-sched.sch_delay.max.ms.wait_for_partner.fifo_open.do_dentry_open.do_open
0.01 -50.0% 0.00 perf-sched.total_sch_delay.average.ms
7.29 ± 39% +468.8% 41.46 ± 26% perf-sched.total_sch_delay.max.ms
6.04 ± 4% -94.1% 0.35 perf-sched.total_wait_and_delay.average.ms
205790 ± 3% +1811.0% 3932742 perf-sched.total_wait_and_delay.count.ms
6.03 ± 4% -94.2% 0.35 perf-sched.total_wait_time.average.ms
75.51 ± 41% -100.0% 0.00 perf-sched.wait_and_delay.avg.ms.__cond_resched.generic_perform_write.shmem_file_write_iter.vfs_write.ksys_write
23.01 ± 17% -100.0% 0.00 perf-sched.wait_and_delay.avg.ms.__cond_resched.mutex_lock.perf_poll.do_poll.constprop
23.82 ± 7% -100.0% 0.00 perf-sched.wait_and_delay.avg.ms.__cond_resched.shmem_get_folio_gfp.shmem_write_begin.generic_perform_write.shmem_file_write_iter
95.27 ± 41% -100.0% 0.00 perf-sched.wait_and_delay.avg.ms.__cond_resched.shmem_inode_acct_block.shmem_alloc_and_acct_folio.shmem_get_folio_gfp.shmem_write_begin
55.86 ±141% +1014.6% 622.64 ± 5% perf-sched.wait_and_delay.avg.ms.do_nanosleep.hrtimer_nanosleep.common_nsleep.__x64_sys_clock_nanosleep
0.07 ± 23% -82.5% 0.01 perf-sched.wait_and_delay.avg.ms.exit_to_user_mode_loop.exit_to_user_mode_prepare.syscall_exit_to_user_mode.do_syscall_64
137.41 ± 3% +345.1% 611.63 ± 2% perf-sched.wait_and_delay.avg.ms.schedule_hrtimeout_range_clock.do_poll.constprop.0.do_sys_poll
0.04 ± 5% -49.6% 0.02 perf-sched.wait_and_delay.avg.ms.schedule_timeout.__skb_wait_for_more_packets.__skb_recv_udp.udp_recvmsg
536.33 ± 5% -46.5% 287.00 perf-sched.wait_and_delay.avg.ms.smpboot_thread_fn.kthread.ret_from_fork.ret_from_fork_asm
21.67 ± 32% -100.0% 0.00 perf-sched.wait_and_delay.count.__cond_resched.generic_perform_write.shmem_file_write_iter.vfs_write.ksys_write
5.67 ± 8% -100.0% 0.00 perf-sched.wait_and_delay.count.__cond_resched.mutex_lock.perf_poll.do_poll.constprop
1.67 ± 56% -100.0% 0.00 perf-sched.wait_and_delay.count.__cond_resched.shmem_get_folio_gfp.shmem_write_begin.generic_perform_write.shmem_file_write_iter
5.67 ± 29% -100.0% 0.00 perf-sched.wait_and_delay.count.__cond_resched.shmem_inode_acct_block.shmem_alloc_and_acct_folio.shmem_get_folio_gfp.shmem_write_begin
5.33 ± 23% +93.8% 10.33 ± 25% perf-sched.wait_and_delay.count.__cond_resched.smpboot_thread_fn.kthread.ret_from_fork.ret_from_fork_asm
101725 ± 3% +15.3% 117243 ± 10% perf-sched.wait_and_delay.count.exit_to_user_mode_loop.exit_to_user_mode_prepare.syscall_exit_to_user_mode.do_syscall_64
100.00 ± 7% -80.3% 19.67 ± 2% perf-sched.wait_and_delay.count.schedule_hrtimeout_range_clock.do_poll.constprop.0.do_sys_poll
97762 ± 4% +3794.8% 3807606 perf-sched.wait_and_delay.count.schedule_timeout.__skb_wait_for_more_packets.__skb_recv_udp.udp_recvmsg
1091 ± 9% +111.9% 2311 ± 3% perf-sched.wait_and_delay.count.smpboot_thread_fn.kthread.ret_from_fork.ret_from_fork_asm
604.50 ± 43% -100.0% 0.00 perf-sched.wait_and_delay.max.ms.__cond_resched.generic_perform_write.shmem_file_write_iter.vfs_write.ksys_write
37.41 ± 9% -100.0% 0.00 perf-sched.wait_and_delay.max.ms.__cond_resched.mutex_lock.perf_poll.do_poll.constprop
27.08 ± 13% -100.0% 0.00 perf-sched.wait_and_delay.max.ms.__cond_resched.shmem_get_folio_gfp.shmem_write_begin.generic_perform_write.shmem_file_write_iter
275.41 ± 32% -100.0% 0.00 perf-sched.wait_and_delay.max.ms.__cond_resched.shmem_inode_acct_block.shmem_alloc_and_acct_folio.shmem_get_folio_gfp.shmem_write_begin
1313 ± 69% +112.1% 2786 ± 15% perf-sched.wait_and_delay.max.ms.__cond_resched.smpboot_thread_fn.kthread.ret_from_fork.ret_from_fork_asm
333.38 ±141% +200.4% 1001 perf-sched.wait_and_delay.max.ms.do_nanosleep.hrtimer_nanosleep.common_nsleep.__x64_sys_clock_nanosleep
1000 -96.8% 31.85 ± 48% perf-sched.wait_and_delay.max.ms.exit_to_user_mode_loop.exit_to_user_mode_prepare.syscall_exit_to_user_mode.do_syscall_64
17.99 ± 33% +387.5% 87.71 ± 8% perf-sched.wait_and_delay.max.ms.schedule_timeout.__skb_wait_for_more_packets.__skb_recv_udp.udp_recvmsg
0.33 ± 19% -74.1% 0.09 ± 10% perf-sched.wait_time.avg.ms.__cond_resched.__skb_datagram_iter.skb_copy_datagram_iter.udp_recvmsg.inet_recvmsg
0.02 ± 53% +331.4% 0.10 ± 50% perf-sched.wait_time.avg.ms.__cond_resched.aa_sk_perm.security_socket_recvmsg.sock_recvmsg.__sys_recvfrom
0.09 ± 65% -75.9% 0.02 ± 9% perf-sched.wait_time.avg.ms.__cond_resched.aa_sk_perm.security_socket_sendmsg.sock_sendmsg.__sys_sendto
0.02 ± 22% -70.2% 0.01 ±141% perf-sched.wait_time.avg.ms.__cond_resched.dput.__fput.__x64_sys_close.do_syscall_64
75.51 ± 41% -100.0% 0.04 ± 42% perf-sched.wait_time.avg.ms.__cond_resched.generic_perform_write.shmem_file_write_iter.vfs_write.ksys_write
0.10 ± 36% -80.3% 0.02 ± 9% perf-sched.wait_time.avg.ms.__cond_resched.kmem_cache_alloc_node.__alloc_skb.alloc_skb_with_frags.sock_alloc_send_pskb
0.55 ± 61% -94.9% 0.03 ± 45% perf-sched.wait_time.avg.ms.__cond_resched.kmem_cache_alloc_node.kmalloc_reserve.__alloc_skb.alloc_skb_with_frags
23.01 ± 17% -100.0% 0.00 ±141% perf-sched.wait_time.avg.ms.__cond_resched.mutex_lock.perf_poll.do_poll.constprop
23.82 ± 7% -99.7% 0.07 ± 57% perf-sched.wait_time.avg.ms.__cond_resched.shmem_get_folio_gfp.shmem_write_begin.generic_perform_write.shmem_file_write_iter
95.27 ± 41% -100.0% 0.03 ± 89% perf-sched.wait_time.avg.ms.__cond_resched.shmem_inode_acct_block.shmem_alloc_and_acct_folio.shmem_get_folio_gfp.shmem_write_begin
56.30 ±139% +1005.5% 622.44 ± 5% perf-sched.wait_time.avg.ms.do_nanosleep.hrtimer_nanosleep.common_nsleep.__x64_sys_clock_nanosleep
2.78 ± 66% -98.2% 0.05 ± 52% perf-sched.wait_time.avg.ms.exit_to_user_mode_loop.exit_to_user_mode_prepare.irqentry_exit_to_user_mode.asm_sysvec_apic_timer_interrupt
0.07 ± 23% -82.5% 0.01 perf-sched.wait_time.avg.ms.exit_to_user_mode_loop.exit_to_user_mode_prepare.syscall_exit_to_user_mode.do_syscall_64
137.37 ± 3% +345.1% 611.40 ± 2% perf-sched.wait_time.avg.ms.schedule_hrtimeout_range_clock.do_poll.constprop.0.do_sys_poll
0.02 ± 5% -41.9% 0.01 ± 3% perf-sched.wait_time.avg.ms.schedule_timeout.__skb_wait_for_more_packets.__skb_recv_udp.udp_recvmsg
536.32 ± 5% -46.5% 286.98 perf-sched.wait_time.avg.ms.smpboot_thread_fn.kthread.ret_from_fork.ret_from_fork_asm
4.66 ± 20% -56.7% 2.02 ± 26% perf-sched.wait_time.max.ms.__cond_resched.__skb_datagram_iter.skb_copy_datagram_iter.udp_recvmsg.inet_recvmsg
0.03 ± 63% +995.0% 0.37 ± 26% perf-sched.wait_time.max.ms.__cond_resched.aa_sk_perm.security_socket_recvmsg.sock_recvmsg.__sys_recvfrom
1.67 ± 87% -92.6% 0.12 ± 57% perf-sched.wait_time.max.ms.__cond_resched.aa_sk_perm.security_socket_sendmsg.sock_sendmsg.__sys_sendto
0.54 ±117% -95.1% 0.03 ±105% perf-sched.wait_time.max.ms.__cond_resched.down_write_killable.exec_mmap.begin_new_exec.load_elf_binary
0.06 ± 49% -89.1% 0.01 ±141% perf-sched.wait_time.max.ms.__cond_resched.dput.__fput.__x64_sys_close.do_syscall_64
604.50 ± 43% -100.0% 0.16 ± 83% perf-sched.wait_time.max.ms.__cond_resched.generic_perform_write.shmem_file_write_iter.vfs_write.ksys_write
2.77 ± 45% -95.4% 0.13 ± 64% perf-sched.wait_time.max.ms.__cond_resched.kmem_cache_alloc_node.__alloc_skb.alloc_skb_with_frags.sock_alloc_send_pskb
2.86 ± 45% -94.3% 0.16 ± 91% perf-sched.wait_time.max.ms.__cond_resched.kmem_cache_alloc_node.kmalloc_reserve.__alloc_skb.alloc_skb_with_frags
37.41 ± 9% -100.0% 0.01 ±141% perf-sched.wait_time.max.ms.__cond_resched.mutex_lock.perf_poll.do_poll.constprop
27.08 ± 13% -99.7% 0.08 ± 61% perf-sched.wait_time.max.ms.__cond_resched.shmem_get_folio_gfp.shmem_write_begin.generic_perform_write.shmem_file_write_iter
275.41 ± 32% -100.0% 0.03 ± 89% perf-sched.wait_time.max.ms.__cond_resched.shmem_inode_acct_block.shmem_alloc_and_acct_folio.shmem_get_folio_gfp.shmem_write_begin
1313 ± 69% +112.1% 2786 ± 15% perf-sched.wait_time.max.ms.__cond_resched.smpboot_thread_fn.kthread.ret_from_fork.ret_from_fork_asm
334.74 ±140% +198.9% 1000 perf-sched.wait_time.max.ms.do_nanosleep.hrtimer_nanosleep.common_nsleep.__x64_sys_clock_nanosleep
21.74 ± 58% -95.4% 1.00 ±103% perf-sched.wait_time.max.ms.exit_to_user_mode_loop.exit_to_user_mode_prepare.irqentry_exit_to_user_mode.asm_sysvec_apic_timer_interrupt
1000 -97.6% 24.49 ± 50% perf-sched.wait_time.max.ms.exit_to_user_mode_loop.exit_to_user_mode_prepare.syscall_exit_to_user_mode.do_syscall_64
10.90 ± 27% +682.9% 85.36 ± 6% perf-sched.wait_time.max.ms.schedule_timeout.__skb_wait_for_more_packets.__skb_recv_udp.udp_recvmsg
32.91 ± 58% -63.5% 12.01 ±115% perf-sched.wait_time.max.ms.schedule_timeout.__wait_for_common.wait_for_completion_state.kernel_clone
169.97 ± 7% -49.2% 86.29 ± 15% perf-sched.wait_time.max.ms.schedule_timeout.rcu_gp_fqs_loop.rcu_gp_kthread.kthread
44.08 -19.8 24.25 perf-profile.calltrace.cycles-pp._raw_spin_lock_irqsave.free_pcppages_bulk.free_unref_page.skb_release_data.__consume_stateless_skb
44.47 -19.6 24.87 perf-profile.calltrace.cycles-pp.free_pcppages_bulk.free_unref_page.skb_release_data.__consume_stateless_skb.udp_recvmsg
43.63 -19.5 24.15 perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock_irqsave.free_pcppages_bulk.free_unref_page.skb_release_data
45.62 -19.2 26.39 perf-profile.calltrace.cycles-pp.skb_release_data.__consume_stateless_skb.udp_recvmsg.inet_recvmsg.sock_recvmsg
45.62 -19.2 26.40 perf-profile.calltrace.cycles-pp.__consume_stateless_skb.udp_recvmsg.inet_recvmsg.sock_recvmsg.__sys_recvfrom
45.00 -19.1 25.94 perf-profile.calltrace.cycles-pp.free_unref_page.skb_release_data.__consume_stateless_skb.udp_recvmsg.inet_recvmsg
50.41 -16.8 33.64 ± 39% perf-profile.calltrace.cycles-pp.accept_connections.main.__libc_start_main
50.41 -16.8 33.64 ± 39% perf-profile.calltrace.cycles-pp.accept_connection.accept_connections.main.__libc_start_main
50.41 -16.8 33.64 ± 39% perf-profile.calltrace.cycles-pp.spawn_child.accept_connection.accept_connections.main.__libc_start_main
50.41 -16.8 33.64 ± 39% perf-profile.calltrace.cycles-pp.process_requests.spawn_child.accept_connection.accept_connections.main
99.92 -14.2 85.72 ± 15% perf-profile.calltrace.cycles-pp.main.__libc_start_main
99.96 -14.2 85.77 ± 15% perf-profile.calltrace.cycles-pp.__libc_start_main
50.10 -8.6 41.52 perf-profile.calltrace.cycles-pp.udp_recvmsg.inet_recvmsg.sock_recvmsg.__sys_recvfrom.__x64_sys_recvfrom
50.11 -8.6 41.55 perf-profile.calltrace.cycles-pp.inet_recvmsg.sock_recvmsg.__sys_recvfrom.__x64_sys_recvfrom.do_syscall_64
50.13 -8.5 41.64 perf-profile.calltrace.cycles-pp.sock_recvmsg.__sys_recvfrom.__x64_sys_recvfrom.do_syscall_64.entry_SYSCALL_64_after_hwframe
50.28 -8.0 42.27 perf-profile.calltrace.cycles-pp.__sys_recvfrom.__x64_sys_recvfrom.do_syscall_64.entry_SYSCALL_64_after_hwframe.recvfrom
50.29 -8.0 42.29 perf-profile.calltrace.cycles-pp.__x64_sys_recvfrom.do_syscall_64.entry_SYSCALL_64_after_hwframe.recvfrom.recv_omni
50.31 -7.9 42.42 perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.recvfrom.recv_omni.process_requests
50.32 -7.8 42.47 perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.recvfrom.recv_omni.process_requests.spawn_child
50.36 -7.6 42.78 perf-profile.calltrace.cycles-pp.recvfrom.recv_omni.process_requests.spawn_child.accept_connection
50.41 -7.3 43.07 perf-profile.calltrace.cycles-pp.recv_omni.process_requests.spawn_child.accept_connection.accept_connections
19.93 ± 2% -6.6 13.36 perf-profile.calltrace.cycles-pp.ip_generic_getfrag.__ip_append_data.ip_make_skb.udp_sendmsg.sock_sendmsg
19.44 ± 2% -6.3 13.16 perf-profile.calltrace.cycles-pp._copy_from_iter.ip_generic_getfrag.__ip_append_data.ip_make_skb.udp_sendmsg
18.99 ± 2% -6.1 12.90 perf-profile.calltrace.cycles-pp.copyin._copy_from_iter.ip_generic_getfrag.__ip_append_data.ip_make_skb
8.95 -5.1 3.82 perf-profile.calltrace.cycles-pp.udp_send_skb.udp_sendmsg.sock_sendmsg.__sys_sendto.__x64_sys_sendto
8.70 -5.0 3.71 perf-profile.calltrace.cycles-pp.ip_send_skb.udp_send_skb.udp_sendmsg.sock_sendmsg.__sys_sendto
8.10 -4.6 3.45 perf-profile.calltrace.cycles-pp.ip_finish_output2.ip_send_skb.udp_send_skb.udp_sendmsg.sock_sendmsg
7.69 -4.4 3.27 perf-profile.calltrace.cycles-pp.__dev_queue_xmit.ip_finish_output2.ip_send_skb.udp_send_skb.udp_sendmsg
6.51 -3.7 2.78 perf-profile.calltrace.cycles-pp.__local_bh_enable_ip.__dev_queue_xmit.ip_finish_output2.ip_send_skb.udp_send_skb
6.47 -3.7 2.75 perf-profile.calltrace.cycles-pp.do_softirq.__local_bh_enable_ip.__dev_queue_xmit.ip_finish_output2.ip_send_skb
6.41 -3.7 2.71 perf-profile.calltrace.cycles-pp.__do_softirq.do_softirq.__local_bh_enable_ip.__dev_queue_xmit.ip_finish_output2
5.88 -3.5 2.43 perf-profile.calltrace.cycles-pp.net_rx_action.__do_softirq.do_softirq.__local_bh_enable_ip.__dev_queue_xmit
5.73 -3.4 2.35 perf-profile.calltrace.cycles-pp.__napi_poll.net_rx_action.__do_softirq.do_softirq.__local_bh_enable_ip
5.69 -3.4 2.33 perf-profile.calltrace.cycles-pp.process_backlog.__napi_poll.net_rx_action.__do_softirq.do_softirq
5.36 -3.2 2.19 perf-profile.calltrace.cycles-pp.__netif_receive_skb_one_core.process_backlog.__napi_poll.net_rx_action.__do_softirq
4.59 -2.7 1.89 perf-profile.calltrace.cycles-pp.ip_local_deliver_finish.__netif_receive_skb_one_core.process_backlog.__napi_poll.net_rx_action
4.55 ± 2% -2.7 1.88 perf-profile.calltrace.cycles-pp.ip_protocol_deliver_rcu.ip_local_deliver_finish.__netif_receive_skb_one_core.process_backlog.__napi_poll
4.40 ± 2% -2.6 1.81 perf-profile.calltrace.cycles-pp.__udp4_lib_rcv.ip_protocol_deliver_rcu.ip_local_deliver_finish.__netif_receive_skb_one_core.process_backlog
3.81 ± 2% -2.2 1.57 perf-profile.calltrace.cycles-pp.udp_unicast_rcv_skb.__udp4_lib_rcv.ip_protocol_deliver_rcu.ip_local_deliver_finish.__netif_receive_skb_one_core
3.75 ± 2% -2.2 1.55 perf-profile.calltrace.cycles-pp.udp_queue_rcv_one_skb.udp_unicast_rcv_skb.__udp4_lib_rcv.ip_protocol_deliver_rcu.ip_local_deliver_finish
2.21 ± 2% -1.6 0.63 perf-profile.calltrace.cycles-pp.__ip_make_skb.ip_make_skb.udp_sendmsg.sock_sendmsg.__sys_sendto
1.94 ± 2% -1.4 0.51 ± 2% perf-profile.calltrace.cycles-pp.__ip_select_ident.__ip_make_skb.ip_make_skb.udp_sendmsg.sock_sendmsg
1.14 -0.6 0.51 perf-profile.calltrace.cycles-pp.sock_alloc_send_pskb.__ip_append_data.ip_make_skb.udp_sendmsg.sock_sendmsg
0.00 +0.5 0.53 ± 2% perf-profile.calltrace.cycles-pp.schedule_idle.do_idle.cpu_startup_entry.start_secondary.secondary_startup_64_no_verify
0.00 +0.7 0.69 perf-profile.calltrace.cycles-pp.sysvec_call_function_single.asm_sysvec_call_function_single.acpi_safe_halt.acpi_idle_enter.cpuidle_enter_state
0.00 +0.7 0.71 perf-profile.calltrace.cycles-pp.__sk_mem_raise_allocated.__sk_mem_schedule.__udp_enqueue_schedule_skb.udp_queue_rcv_one_skb.udp_unicast_rcv_skb
0.00 +0.7 0.72 perf-profile.calltrace.cycles-pp.__sk_mem_schedule.__udp_enqueue_schedule_skb.udp_queue_rcv_one_skb.udp_unicast_rcv_skb.__udp4_lib_rcv
0.00 +1.0 0.99 ± 20% perf-profile.calltrace.cycles-pp.__schedule.schedule.schedule_timeout.__skb_wait_for_more_packets.__skb_recv_udp
0.00 +1.0 1.01 ± 20% perf-profile.calltrace.cycles-pp.schedule.schedule_timeout.__skb_wait_for_more_packets.__skb_recv_udp.udp_recvmsg
0.00 +1.1 1.05 ± 20% perf-profile.calltrace.cycles-pp.schedule_timeout.__skb_wait_for_more_packets.__skb_recv_udp.udp_recvmsg.inet_recvmsg
0.00 +1.1 1.12 perf-profile.calltrace.cycles-pp.acpi_safe_halt.acpi_idle_enter.cpuidle_enter_state.cpuidle_enter.cpuidle_idle_call
0.00 +1.2 1.18 ± 20% perf-profile.calltrace.cycles-pp.__skb_wait_for_more_packets.__skb_recv_udp.udp_recvmsg.inet_recvmsg.sock_recvmsg
0.00 +1.3 1.32 perf-profile.calltrace.cycles-pp.__udp_enqueue_schedule_skb.udp_queue_rcv_one_skb.udp_unicast_rcv_skb.__udp4_lib_rcv.ip_protocol_deliver_rcu
0.00 +2.2 2.23 perf-profile.calltrace.cycles-pp.__skb_recv_udp.udp_recvmsg.inet_recvmsg.sock_recvmsg.__sys_recvfrom
49.51 +2.6 52.08 perf-profile.calltrace.cycles-pp.send_udp_stream.main.__libc_start_main
49.49 +2.6 52.07 perf-profile.calltrace.cycles-pp.send_omni_inner.send_udp_stream.main.__libc_start_main
0.00 +3.0 2.96 ± 2% perf-profile.calltrace.cycles-pp.acpi_idle_enter.cpuidle_enter_state.cpuidle_enter.cpuidle_idle_call.do_idle
48.71 +3.0 51.73 perf-profile.calltrace.cycles-pp.sendto.send_omni_inner.send_udp_stream.main.__libc_start_main
0.00 +3.1 3.06 ± 2% perf-profile.calltrace.cycles-pp.cpuidle_enter_state.cpuidle_enter.cpuidle_idle_call.do_idle.cpu_startup_entry
0.00 +3.1 3.09 perf-profile.calltrace.cycles-pp.cpuidle_enter.cpuidle_idle_call.do_idle.cpu_startup_entry.start_secondary
48.34 +3.2 51.56 perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.sendto.send_omni_inner.send_udp_stream.main
0.00 +3.3 3.33 ± 2% perf-profile.calltrace.cycles-pp.cpuidle_idle_call.do_idle.cpu_startup_entry.start_secondary.secondary_startup_64_no_verify
48.13 +3.8 51.96 perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.sendto.send_omni_inner.send_udp_stream
47.82 +4.0 51.82 perf-profile.calltrace.cycles-pp.__x64_sys_sendto.do_syscall_64.entry_SYSCALL_64_after_hwframe.sendto.send_omni_inner
47.70 +4.1 51.76 perf-profile.calltrace.cycles-pp.__sys_sendto.__x64_sys_sendto.do_syscall_64.entry_SYSCALL_64_after_hwframe.sendto
0.00 +4.1 4.08 perf-profile.calltrace.cycles-pp.do_idle.cpu_startup_entry.start_secondary.secondary_startup_64_no_verify
0.00 +4.1 4.10 perf-profile.calltrace.cycles-pp.cpu_startup_entry.start_secondary.secondary_startup_64_no_verify
0.00 +4.1 4.10 perf-profile.calltrace.cycles-pp.start_secondary.secondary_startup_64_no_verify
0.00 +4.1 4.14 perf-profile.calltrace.cycles-pp.secondary_startup_64_no_verify
0.00 +4.3 4.35 ± 2% perf-profile.calltrace.cycles-pp.asm_sysvec_call_function_single.acpi_safe_halt.acpi_idle_enter.cpuidle_enter_state.cpuidle_enter
46.52 +4.8 51.27 perf-profile.calltrace.cycles-pp.sock_sendmsg.__sys_sendto.__x64_sys_sendto.do_syscall_64.entry_SYSCALL_64_after_hwframe
46.04 +5.0 51.08 perf-profile.calltrace.cycles-pp.udp_sendmsg.sock_sendmsg.__sys_sendto.__x64_sys_sendto.do_syscall_64
3.67 +8.0 11.63 perf-profile.calltrace.cycles-pp.copyout._copy_to_iter.__skb_datagram_iter.skb_copy_datagram_iter.udp_recvmsg
3.71 +8.1 11.80 perf-profile.calltrace.cycles-pp._copy_to_iter.__skb_datagram_iter.skb_copy_datagram_iter.udp_recvmsg.inet_recvmsg
3.96 +8.5 12.42 perf-profile.calltrace.cycles-pp.__skb_datagram_iter.skb_copy_datagram_iter.udp_recvmsg.inet_recvmsg.sock_recvmsg
3.96 +8.5 12.44 perf-profile.calltrace.cycles-pp.skb_copy_datagram_iter.udp_recvmsg.inet_recvmsg.sock_recvmsg.__sys_recvfrom
35.13 +11.3 46.39 perf-profile.calltrace.cycles-pp.ip_make_skb.udp_sendmsg.sock_sendmsg.__sys_sendto.__x64_sys_sendto
32.68 ± 2% +13.0 45.65 perf-profile.calltrace.cycles-pp.__ip_append_data.ip_make_skb.udp_sendmsg.sock_sendmsg.__sys_sendto
10.27 +20.3 30.59 perf-profile.calltrace.cycles-pp.sk_page_frag_refill.__ip_append_data.ip_make_skb.udp_sendmsg.sock_sendmsg
10.24 +20.3 30.58 perf-profile.calltrace.cycles-pp.skb_page_frag_refill.sk_page_frag_refill.__ip_append_data.ip_make_skb.udp_sendmsg
9.84 +20.5 30.32 perf-profile.calltrace.cycles-pp.__alloc_pages.skb_page_frag_refill.sk_page_frag_refill.__ip_append_data.ip_make_skb
9.59 +20.5 30.11 perf-profile.calltrace.cycles-pp.get_page_from_freelist.__alloc_pages.skb_page_frag_refill.sk_page_frag_refill.__ip_append_data
8.40 +21.0 29.42 perf-profile.calltrace.cycles-pp.rmqueue.get_page_from_freelist.__alloc_pages.skb_page_frag_refill.sk_page_frag_refill
6.13 +21.9 28.05 perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock_irqsave.rmqueue_bulk.rmqueue.get_page_from_freelist
6.20 +22.0 28.15 perf-profile.calltrace.cycles-pp._raw_spin_lock_irqsave.rmqueue_bulk.rmqueue.get_page_from_freelist.__alloc_pages
6.46 +22.5 28.91 perf-profile.calltrace.cycles-pp.rmqueue_bulk.rmqueue.get_page_from_freelist.__alloc_pages.skb_page_frag_refill
48.24 -21.8 26.43 perf-profile.children.cycles-pp.skb_release_data
47.19 -21.2 25.98 perf-profile.children.cycles-pp.free_unref_page
44.48 -19.6 24.88 perf-profile.children.cycles-pp.free_pcppages_bulk
45.62 -19.2 26.40 perf-profile.children.cycles-pp.__consume_stateless_skb
99.95 -14.2 85.76 ± 15% perf-profile.children.cycles-pp.main
99.96 -14.2 85.77 ± 15% perf-profile.children.cycles-pp.__libc_start_main
50.10 -8.6 41.53 perf-profile.children.cycles-pp.udp_recvmsg
50.11 -8.6 41.56 perf-profile.children.cycles-pp.inet_recvmsg
50.13 -8.5 41.65 perf-profile.children.cycles-pp.sock_recvmsg
50.29 -8.0 42.28 perf-profile.children.cycles-pp.__sys_recvfrom
50.29 -8.0 42.30 perf-profile.children.cycles-pp.__x64_sys_recvfrom
50.38 -7.5 42.86 perf-profile.children.cycles-pp.recvfrom
50.41 -7.3 43.07 perf-profile.children.cycles-pp.accept_connections
50.41 -7.3 43.07 perf-profile.children.cycles-pp.accept_connection
50.41 -7.3 43.07 perf-profile.children.cycles-pp.spawn_child
50.41 -7.3 43.07 perf-profile.children.cycles-pp.process_requests
50.41 -7.3 43.07 perf-profile.children.cycles-pp.recv_omni
19.96 ± 2% -6.5 13.50 perf-profile.children.cycles-pp.ip_generic_getfrag
19.46 ± 2% -6.2 13.28 perf-profile.children.cycles-pp._copy_from_iter
19.21 ± 2% -6.1 13.14 perf-profile.children.cycles-pp.copyin
8.96 -5.1 3.86 perf-profile.children.cycles-pp.udp_send_skb
8.72 -5.0 3.75 perf-profile.children.cycles-pp.ip_send_skb
8.11 -4.6 3.49 perf-profile.children.cycles-pp.ip_finish_output2
7.72 -4.4 3.32 perf-profile.children.cycles-pp.__dev_queue_xmit
98.71 -4.1 94.59 perf-profile.children.cycles-pp.entry_SYSCALL_64_after_hwframe
98.51 -4.0 94.46 perf-profile.children.cycles-pp.do_syscall_64
6.49 -3.7 2.78 perf-profile.children.cycles-pp.do_softirq
6.51 -3.7 2.82 perf-profile.children.cycles-pp.__local_bh_enable_ip
6.43 -3.7 2.78 perf-profile.children.cycles-pp.__do_softirq
5.90 -3.4 2.46 perf-profile.children.cycles-pp.net_rx_action
5.74 -3.4 2.38 perf-profile.children.cycles-pp.__napi_poll
5.71 -3.4 2.36 perf-profile.children.cycles-pp.process_backlog
5.37 -3.2 2.21 perf-profile.children.cycles-pp.__netif_receive_skb_one_core
4.60 -2.7 1.91 perf-profile.children.cycles-pp.ip_local_deliver_finish
4.57 ± 2% -2.7 1.90 perf-profile.children.cycles-pp.ip_protocol_deliver_rcu
4.42 ± 2% -2.6 1.83 perf-profile.children.cycles-pp.__udp4_lib_rcv
3.82 ± 2% -2.2 1.58 ± 2% perf-profile.children.cycles-pp.udp_unicast_rcv_skb
3.78 ± 2% -2.2 1.57 ± 2% perf-profile.children.cycles-pp.udp_queue_rcv_one_skb
2.23 ± 2% -1.6 0.65 ± 2% perf-profile.children.cycles-pp.__ip_make_skb
1.95 ± 2% -1.4 0.52 ± 3% perf-profile.children.cycles-pp.__ip_select_ident
1.51 ± 4% -1.2 0.34 perf-profile.children.cycles-pp.free_unref_page_commit
1.17 -0.7 0.51 ± 2% perf-profile.children.cycles-pp.ip_route_output_flow
1.15 -0.6 0.52 perf-profile.children.cycles-pp.sock_alloc_send_pskb
0.91 -0.5 0.39 perf-profile.children.cycles-pp.alloc_skb_with_frags
0.86 -0.5 0.37 perf-profile.children.cycles-pp.__alloc_skb
0.83 -0.5 0.36 ± 2% perf-profile.children.cycles-pp.ip_route_output_key_hash_rcu
0.75 -0.4 0.32 perf-profile.children.cycles-pp.dev_hard_start_xmit
0.72 -0.4 0.31 ± 3% perf-profile.children.cycles-pp.fib_table_lookup
0.67 -0.4 0.28 perf-profile.children.cycles-pp.loopback_xmit
0.70 ± 2% -0.4 0.33 perf-profile.children.cycles-pp.__zone_watermark_ok
0.47 ± 4% -0.3 0.15 perf-profile.children.cycles-pp.kmem_cache_free
0.57 -0.3 0.26 perf-profile.children.cycles-pp.kmem_cache_alloc_node
0.46 -0.3 0.18 ± 2% perf-profile.children.cycles-pp.ip_rcv
0.42 -0.3 0.17 perf-profile.children.cycles-pp.move_addr_to_kernel
0.41 -0.2 0.16 ± 2% perf-profile.children.cycles-pp.__udp4_lib_lookup
0.32 -0.2 0.13 perf-profile.children.cycles-pp.__netif_rx
0.30 -0.2 0.12 perf-profile.children.cycles-pp.netif_rx_internal
0.30 -0.2 0.12 perf-profile.children.cycles-pp._copy_from_user
0.31 -0.2 0.13 perf-profile.children.cycles-pp.kmalloc_reserve
0.63 -0.2 0.46 ± 2% perf-profile.children.cycles-pp.free_unref_page_prepare
0.28 -0.2 0.11 perf-profile.children.cycles-pp.enqueue_to_backlog
0.27 -0.2 0.11 perf-profile.children.cycles-pp.udp4_lib_lookup2
0.29 -0.2 0.13 ± 6% perf-profile.children.cycles-pp.send_data
0.25 -0.2 0.10 perf-profile.children.cycles-pp.__netif_receive_skb_core
0.23 ± 2% -0.1 0.10 ± 4% perf-profile.children.cycles-pp.security_socket_sendmsg
0.19 ± 2% -0.1 0.06 perf-profile.children.cycles-pp.ip_rcv_core
0.37 -0.1 0.24 perf-profile.children.cycles-pp.irqtime_account_irq
0.21 -0.1 0.08 perf-profile.children.cycles-pp.sock_wfree
0.21 ± 3% -0.1 0.08 perf-profile.children.cycles-pp.validate_xmit_skb
0.20 ± 2% -0.1 0.08 perf-profile.children.cycles-pp.ip_output
0.22 ± 2% -0.1 0.10 ± 4% perf-profile.children.cycles-pp.ip_rcv_finish_core
0.20 ± 6% -0.1 0.09 ± 5% perf-profile.children.cycles-pp.__mkroute_output
0.21 ± 2% -0.1 0.09 ± 5% perf-profile.children.cycles-pp._raw_spin_lock_irq
0.28 -0.1 0.18 perf-profile.children.cycles-pp._raw_spin_trylock
0.34 ± 3% -0.1 0.25 perf-profile.children.cycles-pp.__slab_free
0.13 ± 3% -0.1 0.05 perf-profile.children.cycles-pp.siphash_3u32
0.12 ± 4% -0.1 0.03 ± 70% perf-profile.children.cycles-pp.ipv4_pktinfo_prepare
0.14 ± 3% -0.1 0.06 ± 7% perf-profile.children.cycles-pp.__ip_local_out
0.20 ± 2% -0.1 0.12 perf-profile.children.cycles-pp.aa_sk_perm
0.18 ± 2% -0.1 0.10 perf-profile.children.cycles-pp.get_pfnblock_flags_mask
0.12 ± 3% -0.1 0.05 perf-profile.children.cycles-pp.sk_filter_trim_cap
0.13 -0.1 0.06 perf-profile.children.cycles-pp.ip_setup_cork
0.13 ± 7% -0.1 0.06 ± 8% perf-profile.children.cycles-pp.fib_lookup_good_nhc
0.15 ± 3% -0.1 0.08 ± 5% perf-profile.children.cycles-pp.skb_set_owner_w
0.11 ± 4% -0.1 0.05 perf-profile.children.cycles-pp.dst_release
0.23 ± 2% -0.1 0.17 ± 2% perf-profile.children.cycles-pp.__entry_text_start
0.11 -0.1 0.05 perf-profile.children.cycles-pp.ipv4_mtu
0.20 ± 2% -0.1 0.15 ± 3% perf-profile.children.cycles-pp.__list_add_valid_or_report
0.10 -0.1 0.05 perf-profile.children.cycles-pp.ip_send_check
0.31 ± 2% -0.0 0.26 ± 3% perf-profile.children.cycles-pp.sockfd_lookup_light
0.27 -0.0 0.22 ± 2% perf-profile.children.cycles-pp.__fget_light
0.63 -0.0 0.58 perf-profile.children.cycles-pp.__check_object_size
0.15 ± 3% -0.0 0.11 perf-profile.children.cycles-pp.entry_SYSRETQ_unsafe_stack
0.13 -0.0 0.09 ± 5% perf-profile.children.cycles-pp.alloc_pages
0.27 -0.0 0.24 perf-profile.children.cycles-pp.sched_clock_cpu
0.11 ± 4% -0.0 0.08 ± 6% perf-profile.children.cycles-pp.__cond_resched
0.14 ± 3% -0.0 0.11 perf-profile.children.cycles-pp.free_tail_page_prepare
0.11 -0.0 0.08 ± 5% perf-profile.children.cycles-pp.syscall_return_via_sysret
0.09 ± 9% -0.0 0.06 ± 7% perf-profile.children.cycles-pp.__xfrm_policy_check2
0.23 ± 2% -0.0 0.21 ± 2% perf-profile.children.cycles-pp.sched_clock
0.14 ± 3% -0.0 0.11 ± 4% perf-profile.children.cycles-pp.prep_compound_page
0.21 ± 2% -0.0 0.20 ± 2% perf-profile.children.cycles-pp.native_sched_clock
0.06 -0.0 0.05 perf-profile.children.cycles-pp.task_tick_fair
0.06 -0.0 0.05 perf-profile.children.cycles-pp.check_stack_object
0.18 ± 2% +0.0 0.20 ± 2% perf-profile.children.cycles-pp.perf_event_task_tick
0.18 ± 2% +0.0 0.19 ± 2% perf-profile.children.cycles-pp.perf_adjust_freq_unthr_context
0.31 ± 3% +0.0 0.33 perf-profile.children.cycles-pp.tick_sched_handle
0.31 ± 3% +0.0 0.33 perf-profile.children.cycles-pp.update_process_times
0.41 ± 2% +0.0 0.43 perf-profile.children.cycles-pp.__sysvec_apic_timer_interrupt
0.40 ± 2% +0.0 0.42 perf-profile.children.cycles-pp.hrtimer_interrupt
0.32 ± 2% +0.0 0.34 perf-profile.children.cycles-pp.tick_sched_timer
0.36 ± 2% +0.0 0.39 perf-profile.children.cycles-pp.__hrtimer_run_queues
0.06 ± 7% +0.0 0.10 ± 4% perf-profile.children.cycles-pp.exit_to_user_mode_prepare
0.05 ± 8% +0.0 0.10 perf-profile.children.cycles-pp._raw_spin_lock_bh
0.00 +0.1 0.05 perf-profile.children.cycles-pp.update_cfs_group
0.00 +0.1 0.05 perf-profile.children.cycles-pp.cpuidle_governor_latency_req
0.00 +0.1 0.05 perf-profile.children.cycles-pp.flush_smp_call_function_queue
0.00 +0.1 0.05 ± 8% perf-profile.children.cycles-pp.prepare_to_wait_exclusive
0.07 +0.1 0.13 ± 3% perf-profile.children.cycles-pp.__mod_zone_page_state
0.00 +0.1 0.06 ± 13% perf-profile.children.cycles-pp.cgroup_rstat_updated
0.00 +0.1 0.06 perf-profile.children.cycles-pp.__x2apic_send_IPI_dest
0.00 +0.1 0.06 perf-profile.children.cycles-pp.security_socket_recvmsg
0.00 +0.1 0.06 perf-profile.children.cycles-pp.select_task_rq_fair
0.00 +0.1 0.06 perf-profile.children.cycles-pp.tick_irq_enter
0.00 +0.1 0.06 perf-profile.children.cycles-pp.tick_nohz_idle_enter
0.42 ± 2% +0.1 0.49 ± 2% perf-profile.children.cycles-pp.sysvec_apic_timer_interrupt
0.00 +0.1 0.07 ± 7% perf-profile.children.cycles-pp.ktime_get
0.00 +0.1 0.07 perf-profile.children.cycles-pp.__get_user_4
0.00 +0.1 0.07 perf-profile.children.cycles-pp.update_rq_clock
0.00 +0.1 0.07 perf-profile.children.cycles-pp.select_task_rq
0.00 +0.1 0.07 perf-profile.children.cycles-pp.native_apic_msr_eoi
0.49 +0.1 0.57 ± 2% perf-profile.children.cycles-pp.asm_sysvec_apic_timer_interrupt
0.11 ± 11% +0.1 0.19 ± 2% perf-profile.children.cycles-pp._raw_spin_lock
0.00 +0.1 0.08 perf-profile.children.cycles-pp.update_rq_clock_task
0.00 +0.1 0.08 perf-profile.children.cycles-pp.__update_load_avg_se
0.00 +0.1 0.09 ± 5% perf-profile.children.cycles-pp.irq_enter_rcu
0.00 +0.1 0.09 ± 5% perf-profile.children.cycles-pp.__irq_exit_rcu
0.00 +0.1 0.09 perf-profile.children.cycles-pp.__update_load_avg_cfs_rq
0.00 +0.1 0.09 perf-profile.children.cycles-pp.update_blocked_averages
0.00 +0.1 0.09 perf-profile.children.cycles-pp.update_sg_lb_stats
0.00 +0.1 0.09 ± 5% perf-profile.children.cycles-pp.set_next_entity
0.00 +0.1 0.10 perf-profile.children.cycles-pp.__switch_to_asm
0.00 +0.1 0.11 ± 12% perf-profile.children.cycles-pp._copy_to_user
0.00 +0.1 0.12 ± 3% perf-profile.children.cycles-pp.menu_select
0.00 +0.1 0.12 ± 3% perf-profile.children.cycles-pp.recv_data
0.00 +0.1 0.12 ± 3% perf-profile.children.cycles-pp.update_sd_lb_stats
0.00 +0.1 0.13 ± 3% perf-profile.children.cycles-pp.native_irq_return_iret
0.00 +0.1 0.13 ± 3% perf-profile.children.cycles-pp.__switch_to
0.00 +0.1 0.13 ± 3% perf-profile.children.cycles-pp.find_busiest_group
0.00 +0.1 0.14 perf-profile.children.cycles-pp.finish_task_switch
0.00 +0.1 0.15 ± 3% perf-profile.children.cycles-pp.update_curr
0.00 +0.2 0.15 ± 3% perf-profile.children.cycles-pp.mem_cgroup_uncharge_skmem
0.00 +0.2 0.16 perf-profile.children.cycles-pp.ttwu_queue_wakelist
0.05 +0.2 0.22 ± 2% perf-profile.children.cycles-pp.page_counter_try_charge
0.00 +0.2 0.17 ± 2% perf-profile.children.cycles-pp.load_balance
0.00 +0.2 0.17 ± 2% perf-profile.children.cycles-pp.___perf_sw_event
0.02 ±141% +0.2 0.19 ± 2% perf-profile.children.cycles-pp.page_counter_uncharge
0.33 +0.2 0.52 perf-profile.children.cycles-pp.__free_one_page
0.02 ±141% +0.2 0.21 ± 2% perf-profile.children.cycles-pp.drain_stock
0.00 +0.2 0.20 ± 2% perf-profile.children.cycles-pp.prepare_task_switch
0.16 ± 3% +0.2 0.38 ± 2% perf-profile.children.cycles-pp.simple_copy_to_iter
0.07 ± 11% +0.2 0.31 perf-profile.children.cycles-pp.refill_stock
0.07 ± 6% +0.2 0.31 ± 4% perf-profile.children.cycles-pp.move_addr_to_user
0.00 +0.2 0.24 perf-profile.children.cycles-pp.enqueue_entity
0.00 +0.2 0.25 perf-profile.children.cycles-pp.update_load_avg
0.21 ± 2% +0.3 0.48 perf-profile.children.cycles-pp.__list_del_entry_valid_or_report
0.00 +0.3 0.31 ± 4% perf-profile.children.cycles-pp.dequeue_entity
0.08 ± 5% +0.3 0.40 ± 3% perf-profile.children.cycles-pp.try_charge_memcg
0.00 +0.3 0.33 perf-profile.children.cycles-pp.enqueue_task_fair
0.00 +0.4 0.35 ± 2% perf-profile.children.cycles-pp.dequeue_task_fair
0.00 +0.4 0.35 ± 2% perf-profile.children.cycles-pp.activate_task
0.00 +0.4 0.36 ± 2% perf-profile.children.cycles-pp.try_to_wake_up
0.00 +0.4 0.37 ± 2% perf-profile.children.cycles-pp.autoremove_wake_function
0.00 +0.4 0.39 ± 3% perf-profile.children.cycles-pp.newidle_balance
0.12 ± 8% +0.4 0.51 ± 2% perf-profile.children.cycles-pp.mem_cgroup_charge_skmem
0.00 +0.4 0.39 perf-profile.children.cycles-pp.ttwu_do_activate
0.00 +0.4 0.40 ± 2% perf-profile.children.cycles-pp.__wake_up_common
0.18 ± 4% +0.4 0.59 perf-profile.children.cycles-pp.udp_rmem_release
0.11 ± 7% +0.4 0.52 perf-profile.children.cycles-pp.__sk_mem_reduce_allocated
0.00 +0.4 0.43 perf-profile.children.cycles-pp.__wake_up_common_lock
0.00 +0.5 0.46 perf-profile.children.cycles-pp.sched_ttwu_pending
0.00 +0.5 0.49 perf-profile.children.cycles-pp.sock_def_readable
0.00 +0.5 0.53 ± 2% perf-profile.children.cycles-pp.pick_next_task_fair
0.00 +0.5 0.54 ± 2% perf-profile.children.cycles-pp.schedule_idle
0.00 +0.6 0.55 perf-profile.children.cycles-pp.__flush_smp_call_function_queue
0.15 ± 3% +0.6 0.73 ± 2% perf-profile.children.cycles-pp.__sk_mem_raise_allocated
0.00 +0.6 0.57 perf-profile.children.cycles-pp.__sysvec_call_function_single
0.16 ± 5% +0.6 0.74 ± 2% perf-profile.children.cycles-pp.__sk_mem_schedule
0.00 +0.8 0.78 perf-profile.children.cycles-pp.sysvec_call_function_single
0.41 ± 3% +0.9 1.33 ± 2% perf-profile.children.cycles-pp.__udp_enqueue_schedule_skb
0.00 +1.2 1.16 ± 2% perf-profile.children.cycles-pp.schedule
0.00 +1.2 1.21 ± 2% perf-profile.children.cycles-pp.schedule_timeout
0.00 +1.3 1.33 ± 2% perf-profile.children.cycles-pp.__skb_wait_for_more_packets
0.00 +1.7 1.66 ± 2% perf-profile.children.cycles-pp.__schedule
0.27 ± 3% +2.0 2.25 perf-profile.children.cycles-pp.__skb_recv_udp
50.41 +2.4 52.81 perf-profile.children.cycles-pp._raw_spin_lock_irqsave
0.00 +2.7 2.68 perf-profile.children.cycles-pp.asm_sysvec_call_function_single
49.78 +2.7 52.49 perf-profile.children.cycles-pp.native_queued_spin_lock_slowpath
0.00 +3.0 2.98 perf-profile.children.cycles-pp.acpi_safe_halt
0.00 +3.0 3.00 perf-profile.children.cycles-pp.acpi_idle_enter
49.51 +3.1 52.57 perf-profile.children.cycles-pp.send_udp_stream
49.50 +3.1 52.56 perf-profile.children.cycles-pp.send_omni_inner
0.00 +3.1 3.10 perf-profile.children.cycles-pp.cpuidle_enter_state
0.00 +3.1 3.12 perf-profile.children.cycles-pp.cpuidle_enter
0.00 +3.4 3.37 perf-profile.children.cycles-pp.cpuidle_idle_call
48.90 +3.4 52.30 perf-profile.children.cycles-pp.sendto
47.85 +4.0 51.83 perf-profile.children.cycles-pp.__x64_sys_sendto
47.73 +4.0 51.77 perf-profile.children.cycles-pp.__sys_sendto
0.00 +4.1 4.10 perf-profile.children.cycles-pp.start_secondary
0.00 +4.1 4.13 perf-profile.children.cycles-pp.do_idle
0.00 +4.1 4.14 perf-profile.children.cycles-pp.secondary_startup_64_no_verify
0.00 +4.1 4.14 perf-profile.children.cycles-pp.cpu_startup_entry
46.54 +4.7 51.28 perf-profile.children.cycles-pp.sock_sendmsg
46.10 +5.0 51.11 perf-profile.children.cycles-pp.udp_sendmsg
3.70 +8.0 11.71 perf-profile.children.cycles-pp.copyout
3.71 +8.1 11.80 perf-profile.children.cycles-pp._copy_to_iter
3.96 +8.5 12.43 perf-profile.children.cycles-pp.__skb_datagram_iter
3.96 +8.5 12.44 perf-profile.children.cycles-pp.skb_copy_datagram_iter
35.14 +11.3 46.40 perf-profile.children.cycles-pp.ip_make_skb
32.71 ± 2% +13.0 45.66 perf-profile.children.cycles-pp.__ip_append_data
10.28 +20.6 30.89 perf-profile.children.cycles-pp.sk_page_frag_refill
10.25 +20.6 30.88 perf-profile.children.cycles-pp.skb_page_frag_refill
9.86 +20.8 30.63 perf-profile.children.cycles-pp.__alloc_pages
9.62 +20.8 30.42 perf-profile.children.cycles-pp.get_page_from_freelist
8.42 +21.3 29.72 perf-profile.children.cycles-pp.rmqueue
6.47 +22.8 29.22 perf-profile.children.cycles-pp.rmqueue_bulk
19.11 ± 2% -6.0 13.08 perf-profile.self.cycles-pp.copyin
1.81 ± 2% -1.4 0.39 perf-profile.self.cycles-pp.rmqueue
1.81 ± 2% -1.3 0.46 ± 2% perf-profile.self.cycles-pp.__ip_select_ident
1.47 ± 4% -1.2 0.31 perf-profile.self.cycles-pp.free_unref_page_commit
1.29 ± 2% -0.5 0.75 perf-profile.self.cycles-pp.__ip_append_data
0.71 -0.4 0.29 perf-profile.self.cycles-pp.udp_sendmsg
0.68 ± 2% -0.4 0.32 perf-profile.self.cycles-pp.__zone_watermark_ok
0.50 -0.3 0.16 perf-profile.self.cycles-pp.skb_release_data
0.59 ± 3% -0.3 0.26 ± 3% perf-profile.self.cycles-pp.fib_table_lookup
0.46 ± 4% -0.3 0.15 ± 3% perf-profile.self.cycles-pp.kmem_cache_free
0.63 -0.3 0.33 ± 2% perf-profile.self.cycles-pp._raw_spin_lock_irqsave
0.47 -0.3 0.19 perf-profile.self.cycles-pp.__sys_sendto
0.44 -0.2 0.21 ± 2% perf-profile.self.cycles-pp.kmem_cache_alloc_node
0.36 -0.2 0.16 ± 3% perf-profile.self.cycles-pp.send_omni_inner
0.35 ± 2% -0.2 0.15 ± 3% perf-profile.self.cycles-pp.ip_finish_output2
0.29 -0.2 0.12 perf-profile.self.cycles-pp._copy_from_user
0.24 -0.1 0.10 ± 4% perf-profile.self.cycles-pp.__netif_receive_skb_core
0.22 ± 2% -0.1 0.08 ± 5% perf-profile.self.cycles-pp.free_unref_page
0.19 ± 2% -0.1 0.06 perf-profile.self.cycles-pp.ip_rcv_core
0.21 ± 2% -0.1 0.08 perf-profile.self.cycles-pp.__alloc_skb
0.20 ± 2% -0.1 0.08 perf-profile.self.cycles-pp.sock_wfree
0.22 ± 2% -0.1 0.10 ± 4% perf-profile.self.cycles-pp.send_data
0.21 -0.1 0.09 perf-profile.self.cycles-pp.sendto
0.21 ± 2% -0.1 0.10 ± 4% perf-profile.self.cycles-pp.ip_rcv_finish_core
0.21 ± 2% -0.1 0.09 ± 5% perf-profile.self.cycles-pp.__ip_make_skb
0.20 ± 4% -0.1 0.09 ± 5% perf-profile.self.cycles-pp._raw_spin_lock_irq
0.21 ± 2% -0.1 0.10 ± 4% perf-profile.self.cycles-pp.__dev_queue_xmit
0.38 ± 3% -0.1 0.27 perf-profile.self.cycles-pp.get_page_from_freelist
0.20 ± 2% -0.1 0.09 perf-profile.self.cycles-pp.udp_send_skb
0.18 ± 2% -0.1 0.07 perf-profile.self.cycles-pp.__udp_enqueue_schedule_skb
0.18 ± 4% -0.1 0.08 ± 6% perf-profile.self.cycles-pp.__mkroute_output
0.25 -0.1 0.15 ± 3% perf-profile.self.cycles-pp._copy_from_iter
0.27 ± 4% -0.1 0.17 ± 2% perf-profile.self.cycles-pp.skb_page_frag_refill
0.16 -0.1 0.06 ± 7% perf-profile.self.cycles-pp.sock_sendmsg
0.33 ± 2% -0.1 0.24 perf-profile.self.cycles-pp.__slab_free
0.15 ± 3% -0.1 0.06 perf-profile.self.cycles-pp.udp4_lib_lookup2
0.38 ± 2% -0.1 0.29 ± 2% perf-profile.self.cycles-pp.free_unref_page_prepare
0.26 -0.1 0.17 perf-profile.self.cycles-pp._raw_spin_trylock
0.15 -0.1 0.06 perf-profile.self.cycles-pp.ip_output
0.14 -0.1 0.05 ± 8% perf-profile.self.cycles-pp.process_backlog
0.14 -0.1 0.06 perf-profile.self.cycles-pp.ip_route_output_flow
0.14 -0.1 0.06 perf-profile.self.cycles-pp.__udp4_lib_lookup
0.21 ± 2% -0.1 0.13 ± 3% perf-profile.self.cycles-pp.entry_SYSCALL_64_after_hwframe
0.12 ± 3% -0.1 0.05 perf-profile.self.cycles-pp.siphash_3u32
0.13 ± 3% -0.1 0.06 ± 8% perf-profile.self.cycles-pp.ip_send_skb
0.17 -0.1 0.10 perf-profile.self.cycles-pp.__do_softirq
0.15 ± 3% -0.1 0.08 ± 5% perf-profile.self.cycles-pp.skb_set_owner_w
0.17 ± 2% -0.1 0.10 ± 4% perf-profile.self.cycles-pp.aa_sk_perm
0.12 -0.1 0.05 perf-profile.self.cycles-pp.__x64_sys_sendto
0.12 ± 6% -0.1 0.05 perf-profile.self.cycles-pp.fib_lookup_good_nhc
0.19 ± 2% -0.1 0.13 perf-profile.self.cycles-pp.__list_add_valid_or_report
0.14 ± 3% -0.1 0.07 ± 6% perf-profile.self.cycles-pp.net_rx_action
0.16 ± 2% -0.1 0.10 perf-profile.self.cycles-pp.do_syscall_64
0.11 -0.1 0.05 perf-profile.self.cycles-pp.__udp4_lib_rcv
0.16 ± 3% -0.1 0.10 ± 4% perf-profile.self.cycles-pp.get_pfnblock_flags_mask
0.11 ± 4% -0.1 0.05 perf-profile.self.cycles-pp.ip_route_output_key_hash_rcu
0.10 ± 4% -0.1 0.05 perf-profile.self.cycles-pp.ip_generic_getfrag
0.10 -0.1 0.05 perf-profile.self.cycles-pp.ipv4_mtu
0.26 -0.0 0.21 ± 2% perf-profile.self.cycles-pp.__fget_light
0.15 ± 3% -0.0 0.11 ± 4% perf-profile.self.cycles-pp.entry_SYSRETQ_unsafe_stack
0.24 -0.0 0.20 ± 2% perf-profile.self.cycles-pp.__alloc_pages
0.15 ± 3% -0.0 0.12 perf-profile.self.cycles-pp.__check_object_size
0.11 -0.0 0.08 ± 6% perf-profile.self.cycles-pp.syscall_return_via_sysret
0.08 ± 5% -0.0 0.05 perf-profile.self.cycles-pp.loopback_xmit
0.13 -0.0 0.11 ± 4% perf-profile.self.cycles-pp.prep_compound_page
0.11 -0.0 0.09 ± 5% perf-profile.self.cycles-pp.irqtime_account_irq
0.09 ± 10% -0.0 0.06 ± 7% perf-profile.self.cycles-pp.__xfrm_policy_check2
0.07 -0.0 0.05 perf-profile.self.cycles-pp.alloc_pages
0.08 -0.0 0.06 ± 7% perf-profile.self.cycles-pp.__entry_text_start
0.09 ± 5% -0.0 0.07 perf-profile.self.cycles-pp.free_tail_page_prepare
0.10 +0.0 0.11 perf-profile.self.cycles-pp.perf_adjust_freq_unthr_context
0.06 +0.0 0.08 ± 6% perf-profile.self.cycles-pp.free_pcppages_bulk
0.05 ± 8% +0.0 0.10 ± 4% perf-profile.self.cycles-pp._raw_spin_lock_bh
0.07 +0.0 0.12 perf-profile.self.cycles-pp.__mod_zone_page_state
0.00 +0.1 0.05 perf-profile.self.cycles-pp.cpuidle_idle_call
0.00 +0.1 0.05 perf-profile.self.cycles-pp.udp_rmem_release
0.00 +0.1 0.05 perf-profile.self.cycles-pp.__flush_smp_call_function_queue
0.00 +0.1 0.05 perf-profile.self.cycles-pp.sock_def_readable
0.00 +0.1 0.05 perf-profile.self.cycles-pp.update_cfs_group
0.11 ± 11% +0.1 0.17 ± 2% perf-profile.self.cycles-pp._raw_spin_lock
0.00 +0.1 0.05 ± 8% perf-profile.self.cycles-pp.finish_task_switch
0.00 +0.1 0.05 ± 8% perf-profile.self.cycles-pp.cgroup_rstat_updated
0.00 +0.1 0.06 perf-profile.self.cycles-pp.do_idle
0.00 +0.1 0.06 perf-profile.self.cycles-pp.__skb_wait_for_more_packets
0.00 +0.1 0.06 perf-profile.self.cycles-pp.__x2apic_send_IPI_dest
0.00 +0.1 0.06 ± 7% perf-profile.self.cycles-pp.enqueue_entity
0.00 +0.1 0.07 ± 7% perf-profile.self.cycles-pp.schedule_timeout
0.00 +0.1 0.07 ± 7% perf-profile.self.cycles-pp.move_addr_to_user
0.00 +0.1 0.07 ± 7% perf-profile.self.cycles-pp.menu_select
0.00 +0.1 0.07 ± 7% perf-profile.self.cycles-pp.native_apic_msr_eoi
0.00 +0.1 0.07 ± 7% perf-profile.self.cycles-pp.update_sg_lb_stats
0.00 +0.1 0.07 perf-profile.self.cycles-pp.__update_load_avg_se
0.00 +0.1 0.07 perf-profile.self.cycles-pp.__get_user_4
0.00 +0.1 0.08 ± 6% perf-profile.self.cycles-pp.__sk_mem_reduce_allocated
0.00 +0.1 0.08 perf-profile.self.cycles-pp.update_curr
0.00 +0.1 0.08 ± 5% perf-profile.self.cycles-pp.__update_load_avg_cfs_rq
0.00 +0.1 0.09 ± 5% perf-profile.self.cycles-pp.try_to_wake_up
0.00 +0.1 0.09 perf-profile.self.cycles-pp.recvfrom
0.00 +0.1 0.09 perf-profile.self.cycles-pp.mem_cgroup_charge_skmem
0.00 +0.1 0.09 perf-profile.self.cycles-pp.update_load_avg
0.00 +0.1 0.09 ± 5% perf-profile.self.cycles-pp.enqueue_task_fair
0.00 +0.1 0.10 ± 4% perf-profile.self.cycles-pp._copy_to_iter
0.00 +0.1 0.10 ± 4% perf-profile.self.cycles-pp.newidle_balance
0.00 +0.1 0.10 ± 4% perf-profile.self.cycles-pp.recv_data
0.00 +0.1 0.10 perf-profile.self.cycles-pp.refill_stock
0.00 +0.1 0.10 perf-profile.self.cycles-pp.__switch_to_asm
0.00 +0.1 0.11 ± 15% perf-profile.self.cycles-pp._copy_to_user
0.00 +0.1 0.12 perf-profile.self.cycles-pp.recv_omni
0.00 +0.1 0.12 perf-profile.self.cycles-pp.mem_cgroup_uncharge_skmem
0.00 +0.1 0.13 ± 3% perf-profile.self.cycles-pp.native_irq_return_iret
0.00 +0.1 0.13 perf-profile.self.cycles-pp.__switch_to
0.06 +0.1 0.20 ± 2% perf-profile.self.cycles-pp.rmqueue_bulk
0.09 ± 5% +0.1 0.23 ± 4% perf-profile.self.cycles-pp.udp_recvmsg
0.00 +0.1 0.14 ± 3% perf-profile.self.cycles-pp.__skb_recv_udp
0.00 +0.1 0.14 ± 3% perf-profile.self.cycles-pp.___perf_sw_event
0.08 +0.1 0.22 ± 2% perf-profile.self.cycles-pp.__skb_datagram_iter
0.03 ± 70% +0.2 0.20 ± 4% perf-profile.self.cycles-pp.page_counter_try_charge
0.02 ±141% +0.2 0.18 ± 4% perf-profile.self.cycles-pp.__sys_recvfrom
0.00 +0.2 0.17 ± 2% perf-profile.self.cycles-pp.__schedule
0.00 +0.2 0.17 ± 2% perf-profile.self.cycles-pp.try_charge_memcg
0.00 +0.2 0.17 ± 2% perf-profile.self.cycles-pp.page_counter_uncharge
0.00 +0.2 0.21 ± 2% perf-profile.self.cycles-pp.__sk_mem_raise_allocated
0.14 ± 3% +0.2 0.36 perf-profile.self.cycles-pp.__free_one_page
0.20 ± 2% +0.3 0.47 perf-profile.self.cycles-pp.__list_del_entry_valid_or_report
0.00 +2.1 2.07 ± 2% perf-profile.self.cycles-pp.acpi_safe_halt
49.78 +2.7 52.49 perf-profile.self.cycles-pp.native_queued_spin_lock_slowpath
3.68 +8.0 11.64 perf-profile.self.cycles-pp.copyout
Disclaimer:
Results have been estimated based on internal Intel analysis and are provided
for informational purposes only. Any difference in system hardware or software
design or configuration may affect actual performance.
--
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki
Hi,
kernel test robot <oliver.sang@intel.com> writes:
> hi, Huang Ying,
>
> sorry for late of this report.
> we reported
> "a 14.6% improvement of netperf.Throughput_Mbps"
> in
> https://lore.kernel.org/all/202310271441.71ce0a9-oliver.sang@intel.com/
>
> later, our auto-bisect tool captured a regression on a netperf test with
> different configurations, however, unfortunately, regarded it as 'reported'
> so we missed this report at the first time.
>
> now send again FYI.
>
>
> Hello,
>
> kernel test robot noticed a -60.4% regression of netperf.Throughput_Mbps on:
>
>
> commit: f5ddc662f07d7d99e9cfc5e07778e26c7394caf8 ("[PATCH -V3 3/9] mm, pcp: reduce lock contention for draining high-order pages")
> url: https://github.com/intel-lab-lkp/linux/commits/Huang-Ying/mm-pcp-avoid-to-drain-PCP-when-process-exit/20231017-143633
> base: https://git.kernel.org/cgit/linux/kernel/git/gregkh/driver-core.git 36b2d7dd5a8ac95c8c1e69bdc93c4a6e2dc28a23
> patch link: https://lore.kernel.org/all/20231016053002.756205-4-ying.huang@intel.com/
> patch subject: [PATCH -V3 3/9] mm, pcp: reduce lock contention for draining high-order pages
>
> testcase: netperf
> test machine: 128 threads 2 sockets Intel(R) Xeon(R) Gold 6338 CPU @ 2.00GHz (Ice Lake) with 256G memory
> parameters:
>
> ip: ipv4
> runtime: 300s
> nr_threads: 50%
> cluster: cs-localhost
> test: UDP_STREAM
> cpufreq_governor: performance
>
>
>
> If you fix the issue in a separate patch/commit (i.e. not just a new version of
> the same patch/commit), kindly add following tags
> | Reported-by: kernel test robot <oliver.sang@intel.com>
> | Closes: https://lore.kernel.org/oe-lkp/202311061311.8d63998-oliver.sang@intel.com
>
>
> Details are as below:
> -------------------------------------------------------------------------------------------------->
>
>
> The kernel config and materials to reproduce are available at:
> https://download.01.org/0day-ci/archive/20231106/202311061311.8d63998-oliver.sang@intel.com
>
> =========================================================================================
> cluster/compiler/cpufreq_governor/ip/kconfig/nr_threads/rootfs/runtime/tbox_group/test/testcase:
> cs-localhost/gcc-12/performance/ipv4/x86_64-rhel-8.3/50%/debian-11.1-x86_64-20220510.cgz/300s/lkp-icl-2sp2/UDP_STREAM/netperf
>
> commit:
> c828e65251 ("cacheinfo: calculate size of per-CPU data cache slice")
> f5ddc662f0 ("mm, pcp: reduce lock contention for draining high-order pages")
>
> c828e65251502516 f5ddc662f07d7d99e9cfc5e0777
> ---------------- ---------------------------
> %stddev %change %stddev
> \ | \
> 7321 4% +28.2% 9382 uptime.idle
> 50.65 4% -4.0% 48.64 boot-time.boot
> 6042 4% -4.2% 5785 boot-time.idle
> 1.089e+09 2% +232.1% 3.618e+09 cpuidle..time
> 1087075 2% +24095.8% 2.63e+08 cpuidle..usage
> 3357014 +99.9% 6710312 vmstat.memory.cache
> 48731 19% +4666.5% 2322787 vmstat.system.cs
> 144637 +711.2% 1173334 vmstat.system.in
> 2.59 2% +6.2 8.79 mpstat.cpu.all.idle%
> 1.01 +0.7 1.66 mpstat.cpu.all.irq%
> 6.00 -3.2 2.79 mpstat.cpu.all.soft%
> 1.13 2% -0.1 1.02 mpstat.cpu.all.usr%
> 1.407e+09 3% -28.2% 1.011e+09 numa-numastat.node0.local_node
> 1.407e+09 3% -28.2% 1.01e+09 numa-numastat.node0.numa_hit
> 1.469e+09 8% -32.0% 9.979e+08 numa-numastat.node1.local_node
> 1.469e+09 8% -32.1% 9.974e+08 numa-numastat.node1.numa_hit
> 103.00 19% -44.0% 57.67 20% perf-c2c.DRAM.local
> 8970 12% -89.4% 951.00 4% perf-c2c.DRAM.remote
> 8192 5% +68.5% 13807 perf-c2c.HITM.local
> 6675 11% -92.6% 491.00 2% perf-c2c.HITM.remote
> 1051014 2% +24922.0% 2.63e+08 turbostat.C1
> 2.75 2% +6.5 9.29 turbostat.C1%
> 2.72 2% +178.3% 7.57 turbostat.CPU%c1
> 0.09 -22.2% 0.07 turbostat.IPC
> 44589125 +701.5% 3.574e+08 turbostat.IRQ
> 313.00 57% +1967.0% 6469 8% turbostat.POLL
> 70.33 +3.3% 72.67 turbostat.PkgTmp
> 44.23 4% -31.8% 30.15 2% turbostat.RAMWatt
> 536096 +583.7% 3665194 meminfo.Active
> 535414 +584.4% 3664543 meminfo.Active(anon)
> 3238301 +103.2% 6579677 meminfo.Cached
> 1204424 +278.9% 4563575 meminfo.Committed_AS
> 469093 +47.9% 693889 3% meminfo.Inactive
> 467250 +48.4% 693496 3% meminfo.Inactive(anon)
> 53615 +562.5% 355225 4% meminfo.Mapped
> 5223078 +64.1% 8571212 meminfo.Memused
> 557305 +599.6% 3899111 meminfo.Shmem
> 5660207 +58.9% 8993642 meminfo.max_used_kB
> 78504 3% -30.1% 54869 netperf.ThroughputBoth_Mbps
> 5024292 3% -30.1% 3511666 netperf.ThroughputBoth_total_Mbps
> 7673 5% +249.7% 26832 netperf.ThroughputRecv_Mbps
> 491074 5% +249.7% 1717287 netperf.ThroughputRecv_total_Mbps
> 70831 2% -60.4% 28037 netperf.Throughput_Mbps
> 4533217 2% -60.4% 1794379 netperf.Throughput_total_Mbps
This is a UDP test. So the sender will not wait for receiver. In the
result, you can find that the sender throughput reduces 60.4%, while the
receiver throughput increases 249.7%. And, much less packets are
dropped during the test, and this is good too.
All in all, considering the performance of both the sender and the
receiver, I think the patch helps the performance.
--
Best Regards,
Huang, Ying
> 5439 +9.4% 5949 netperf.time.percent_of_cpu_this_job_got
> 16206 +9.4% 17728 netperf.time.system_time
> 388.14 -51.9% 186.53 netperf.time.user_time
> 2.876e+09 3% -30.1% 2.01e+09 netperf.workload
> 177360 30% -36.0% 113450 20% numa-meminfo.node0.AnonPages
> 255926 12% -40.6% 152052 12% numa-meminfo.node0.AnonPages.max
> 22582 61% +484.2% 131916 90% numa-meminfo.node0.Mapped
> 138287 17% +22.6% 169534 12% numa-meminfo.node1.AnonHugePages
> 267468 20% +29.1% 345385 6% numa-meminfo.node1.AnonPages
> 346204 18% +34.5% 465696 2% numa-meminfo.node1.AnonPages.max
> 279416 19% +77.0% 494652 18% numa-meminfo.node1.Inactive
> 278445 19% +77.6% 494393 18% numa-meminfo.node1.Inactive(anon)
> 31726 45% +607.7% 224533 45% numa-meminfo.node1.Mapped
> 4802 6% +19.4% 5733 3% numa-meminfo.node1.PageTables
> 297323 12% +792.6% 2653850 63% numa-meminfo.node1.Shmem
> 44325 30% -36.0% 28379 20% numa-vmstat.node0.nr_anon_pages
> 5590 61% +491.0% 33042 90% numa-vmstat.node0.nr_mapped
> 1.407e+09 3% -28.2% 1.01e+09 numa-vmstat.node0.numa_hit
> 1.407e+09 3% -28.2% 1.011e+09 numa-vmstat.node0.numa_local
> 66858 20% +29.2% 86385 6% numa-vmstat.node1.nr_anon_pages
> 69601 20% +77.8% 123729 18% numa-vmstat.node1.nr_inactive_anon
> 7953 45% +608.3% 56335 45% numa-vmstat.node1.nr_mapped
> 1201 6% +19.4% 1434 3% numa-vmstat.node1.nr_page_table_pages
> 74288 11% +792.6% 663111 63% numa-vmstat.node1.nr_shmem
> 69601 20% +77.8% 123728 18% numa-vmstat.node1.nr_zone_inactive_anon
> 1.469e+09 8% -32.1% 9.974e+08 numa-vmstat.node1.numa_hit
> 1.469e+09 8% -32.0% 9.979e+08 numa-vmstat.node1.numa_local
> 133919 +584.2% 916254 proc-vmstat.nr_active_anon
> 111196 +3.3% 114828 proc-vmstat.nr_anon_pages
> 5602484 -1.5% 5518799 proc-vmstat.nr_dirty_background_threshold
> 11218668 -1.5% 11051092 proc-vmstat.nr_dirty_threshold
> 809646 +103.2% 1645012 proc-vmstat.nr_file_pages
> 56374629 -1.5% 55536913 proc-vmstat.nr_free_pages
> 116775 +48.4% 173349 3% proc-vmstat.nr_inactive_anon
> 13386 2% +563.3% 88793 4% proc-vmstat.nr_mapped
> 2286 +6.5% 2434 proc-vmstat.nr_page_table_pages
> 139393 +599.4% 974869 proc-vmstat.nr_shmem
> 29092 +6.6% 31019 proc-vmstat.nr_slab_reclaimable
> 133919 +584.2% 916254 proc-vmstat.nr_zone_active_anon
> 116775 +48.4% 173349 3% proc-vmstat.nr_zone_inactive_anon
> 32135 11% +257.2% 114797 21% proc-vmstat.numa_hint_faults
> 20858 16% +318.3% 87244 6% proc-vmstat.numa_hint_faults_local
> 2.876e+09 3% -30.2% 2.008e+09 proc-vmstat.numa_hit
> 2.876e+09 3% -30.2% 2.008e+09 proc-vmstat.numa_local
> 25453 7% -75.2% 6324 30% proc-vmstat.numa_pages_migrated
> 178224 2% +76.6% 314680 7% proc-vmstat.numa_pte_updates
> 160889 3% +267.6% 591393 6% proc-vmstat.pgactivate
> 2.295e+10 3% -30.2% 1.601e+10 proc-vmstat.pgalloc_normal
> 1026605 +21.9% 1251671 proc-vmstat.pgfault
> 2.295e+10 3% -30.2% 1.601e+10 proc-vmstat.pgfree
> 25453 7% -75.2% 6324 30% proc-vmstat.pgmigrate_success
> 39208 2% -6.1% 36815 proc-vmstat.pgreuse
> 3164416 -20.3% 2521344 2% proc-vmstat.unevictable_pgs_scanned
> 19248627 -22.1% 14989905 sched_debug.cfs_rq:/.avg_vruntime.avg
> 20722680 -24.9% 15569530 sched_debug.cfs_rq:/.avg_vruntime.max
> 17634233 -22.5% 13663168 sched_debug.cfs_rq:/.avg_vruntime.min
> 949063 2% -70.5% 280388 sched_debug.cfs_rq:/.avg_vruntime.stddev
> 0.78 10% -100.0% 0.00 sched_debug.cfs_rq:/.h_nr_running.min
> 0.16 8% +113.3% 0.33 2% sched_debug.cfs_rq:/.h_nr_running.stddev
> 0.56 141% +2.2e+07% 122016 52% sched_debug.cfs_rq:/.left_vruntime.avg
> 45.01 141% +2.2e+07% 10035976 28% sched_debug.cfs_rq:/.left_vruntime.max
> 4.58 141% +2.3e+07% 1072762 36% sched_debug.cfs_rq:/.left_vruntime.stddev
> 5814 10% -100.0% 0.00 sched_debug.cfs_rq:/.load.min
> 5.39 9% -73.2% 1.44 10% sched_debug.cfs_rq:/.load_avg.min
> 19248627 -22.1% 14989905 sched_debug.cfs_rq:/.min_vruntime.avg
> 20722680 -24.9% 15569530 sched_debug.cfs_rq:/.min_vruntime.max
> 17634233 -22.5% 13663168 sched_debug.cfs_rq:/.min_vruntime.min
> 949063 2% -70.5% 280388 sched_debug.cfs_rq:/.min_vruntime.stddev
> 0.78 10% -100.0% 0.00 sched_debug.cfs_rq:/.nr_running.min
> 0.06 8% +369.2% 0.30 3% sched_debug.cfs_rq:/.nr_running.stddev
> 4.84 26% +1611.3% 82.79 67% sched_debug.cfs_rq:/.removed.load_avg.avg
> 27.92 12% +3040.3% 876.79 68% sched_debug.cfs_rq:/.removed.load_avg.stddev
> 0.56 141% +2.2e+07% 122016 52% sched_debug.cfs_rq:/.right_vruntime.avg
> 45.06 141% +2.2e+07% 10035976 28% sched_debug.cfs_rq:/.right_vruntime.max
> 4.59 141% +2.3e+07% 1072762 36% sched_debug.cfs_rq:/.right_vruntime.stddev
> 900.25 -10.4% 806.45 sched_debug.cfs_rq:/.runnable_avg.avg
> 533.28 4% -87.0% 69.56 39% sched_debug.cfs_rq:/.runnable_avg.min
> 122.77 2% +92.9% 236.86 sched_debug.cfs_rq:/.runnable_avg.stddev
> 896.13 -10.8% 799.44 sched_debug.cfs_rq:/.util_avg.avg
> 379.06 4% -83.4% 62.94 37% sched_debug.cfs_rq:/.util_avg.min
> 116.35 8% +99.4% 232.04 sched_debug.cfs_rq:/.util_avg.stddev
> 550.87 -14.2% 472.66 2% sched_debug.cfs_rq:/.util_est_enqueued.avg
> 1124 8% +18.2% 1329 3% sched_debug.cfs_rq:/.util_est_enqueued.max
> 134.17 30% -100.0% 0.00 sched_debug.cfs_rq:/.util_est_enqueued.min
> 558243 6% -66.9% 184666 sched_debug.cpu.avg_idle.avg
> 12860 11% -56.1% 5644 sched_debug.cpu.avg_idle.min
> 365635 -53.5% 169863 5% sched_debug.cpu.avg_idle.stddev
> 9.56 3% -28.4% 6.84 8% sched_debug.cpu.clock.stddev
> 6999 2% -85.6% 1007 3% sched_debug.cpu.clock_task.stddev
> 3985 10% -100.0% 0.00 sched_debug.cpu.curr->pid.min
> 491.71 10% +209.3% 1520 4% sched_debug.cpu.curr->pid.stddev
> 270.19 141% +1096.6% 3233 51% sched_debug.cpu.max_idle_balance_cost.stddev
> 0.78 10% -100.0% 0.00 sched_debug.cpu.nr_running.min
> 0.15 6% +121.7% 0.34 2% sched_debug.cpu.nr_running.stddev
> 62041 15% +4280.9% 2717948 sched_debug.cpu.nr_switches.avg
> 1074922 14% +292.6% 4220307 2% sched_debug.cpu.nr_switches.max
> 1186 2% +1.2e+05% 1379073 4% sched_debug.cpu.nr_switches.min
> 132392 21% +294.6% 522476 5% sched_debug.cpu.nr_switches.stddev
> 6.44 4% +21.4% 7.82 12% sched_debug.cpu.nr_uninterruptible.stddev
> 6.73 13% -84.8% 1.02 5% perf-stat.i.MPKI
> 1.652e+10 2% -22.2% 1.285e+10 perf-stat.i.branch-instructions
> 0.72 +0.0 0.75 perf-stat.i.branch-miss-rate%
> 1.19e+08 3% -19.8% 95493630 perf-stat.i.branch-misses
> 27.46 12% -26.2 1.30 4% perf-stat.i.cache-miss-rate%
> 5.943e+08 10% -88.6% 67756219 5% perf-stat.i.cache-misses
> 2.201e+09 +143.7% 5.364e+09 perf-stat.i.cache-references
> 48911 19% +4695.4% 2345525 perf-stat.i.context-switches
> 3.66 2% +28.5% 4.71 perf-stat.i.cpi
> 3.228e+11 -4.1% 3.097e+11 perf-stat.i.cpu-cycles
> 190.51 +1363.7% 2788 10% perf-stat.i.cpu-migrations
> 803.99 6% +510.2% 4905 5% perf-stat.i.cycles-between-cache-misses
> 0.00 16% +0.0 0.01 14% perf-stat.i.dTLB-load-miss-rate%
> 755654 18% +232.4% 2512024 14% perf-stat.i.dTLB-load-misses
> 2.385e+10 2% -26.9% 1.742e+10 perf-stat.i.dTLB-loads
> 0.00 31% +0.0 0.01 35% perf-stat.i.dTLB-store-miss-rate%
> 305657 36% +200.0% 916822 35% perf-stat.i.dTLB-store-misses
> 1.288e+10 2% -28.8% 9.179e+09 perf-stat.i.dTLB-stores
> 8.789e+10 2% -25.2% 6.578e+10 perf-stat.i.instructions
> 0.28 2% -21.6% 0.22 perf-stat.i.ipc
> 2.52 -4.1% 2.42 perf-stat.i.metric.GHz
> 873.89 12% -67.0% 288.04 8% perf-stat.i.metric.K/sec
> 435.61 2% -19.6% 350.06 perf-stat.i.metric.M/sec
> 2799 +29.9% 3637 2% perf-stat.i.minor-faults
> 99.74 -2.6 97.11 perf-stat.i.node-load-miss-rate%
> 1.294e+08 12% -92.4% 9879207 7% perf-stat.i.node-load-misses
> 76.55 +16.4 92.92 perf-stat.i.node-store-miss-rate%
> 2.257e+08 10% -90.4% 21721672 8% perf-stat.i.node-store-misses
> 69217511 13% -97.7% 1625810 7% perf-stat.i.node-stores
> 2799 +29.9% 3637 2% perf-stat.i.page-faults
> 6.79 13% -84.9% 1.03 5% perf-stat.overall.MPKI
> 0.72 +0.0 0.74 perf-stat.overall.branch-miss-rate%
> 27.06 12% -25.8 1.26 4% perf-stat.overall.cache-miss-rate%
> 3.68 2% +28.1% 4.71 perf-stat.overall.cpi
> 549.38 10% +736.0% 4592 5% perf-stat.overall.cycles-between-cache-misses
> 0.00 18% +0.0 0.01 14% perf-stat.overall.dTLB-load-miss-rate%
> 0.00 36% +0.0 0.01 35% perf-stat.overall.dTLB-store-miss-rate%
> 0.27 2% -22.0% 0.21 perf-stat.overall.ipc
> 99.80 -2.4 97.37 perf-stat.overall.node-load-miss-rate%
> 76.60 +16.4 93.03 perf-stat.overall.node-store-miss-rate%
> 9319 +5.8% 9855 perf-stat.overall.path-length
> 1.646e+10 2% -22.2% 1.281e+10 perf-stat.ps.branch-instructions
> 1.186e+08 3% -19.8% 95167897 perf-stat.ps.branch-misses
> 5.924e+08 10% -88.6% 67384354 5% perf-stat.ps.cache-misses
> 2.193e+09 +143.4% 5.339e+09 perf-stat.ps.cache-references
> 49100 19% +4668.0% 2341074 perf-stat.ps.context-switches
> 3.218e+11 -4.1% 3.087e+11 perf-stat.ps.cpu-cycles
> 189.73 +1368.4% 2786 10% perf-stat.ps.cpu-migrations
> 753056 18% +229.9% 2484575 14% perf-stat.ps.dTLB-load-misses
> 2.377e+10 2% -26.9% 1.737e+10 perf-stat.ps.dTLB-loads
> 304509 36% +199.1% 910856 35% perf-stat.ps.dTLB-store-misses
> 1.284e+10 2% -28.7% 9.152e+09 perf-stat.ps.dTLB-stores
> 8.76e+10 2% -25.2% 6.557e+10 perf-stat.ps.instructions
> 2791 +28.2% 3580 2% perf-stat.ps.minor-faults
> 1.29e+08 12% -92.4% 9815672 7% perf-stat.ps.node-load-misses
> 2.25e+08 10% -90.4% 21575943 8% perf-stat.ps.node-store-misses
> 69002373 13% -97.7% 1615410 7% perf-stat.ps.node-stores
> 2791 +28.2% 3580 2% perf-stat.ps.page-faults
> 2.68e+13 2% -26.1% 1.981e+13 perf-stat.total.instructions
> 0.00 35% +2600.0% 0.04 23% perf-sched.sch_delay.avg.ms.__cond_resched.__skb_datagram_iter.skb_copy_datagram_iter.udp_recvmsg.inet_recvmsg
> 1.18 9% -98.1% 0.02 32% perf-sched.sch_delay.avg.ms.__cond_resched.stop_one_cpu.sched_exec.bprm_execve.part
> 0.58 3% -62.1% 0.22 97% perf-sched.sch_delay.avg.ms.__x64_sys_pause.do_syscall_64.entry_SYSCALL_64_after_hwframe.[unknown]
> 0.51 22% -82.7% 0.09 11% perf-sched.sch_delay.avg.ms.do_task_dead.do_exit.do_group_exit.__x64_sys_exit_group.do_syscall_64
> 0.25 23% -59.6% 0.10 10% perf-sched.sch_delay.avg.ms.do_wait.kernel_wait4.__do_sys_wait4.do_syscall_64
> 0.03 42% -64.0% 0.01 15% perf-sched.sch_delay.avg.ms.pipe_read.vfs_read.ksys_read.do_syscall_64
> 0.04 7% +434.6% 0.23 36% perf-sched.sch_delay.avg.ms.schedule_hrtimeout_range_clock.do_poll.constprop.0.do_sys_poll
> 1.00 20% -84.1% 0.16 78% perf-sched.sch_delay.avg.ms.schedule_hrtimeout_range_clock.do_select.core_sys_select.kern_select
> 0.01 7% -70.0% 0.00 perf-sched.sch_delay.avg.ms.schedule_timeout.__skb_wait_for_more_packets.__skb_recv_udp.udp_recvmsg
> 0.02 2% +533.9% 0.12 43% perf-sched.sch_delay.avg.ms.schedule_timeout.kcompactd.kthread.ret_from_fork
> 0.03 7% +105.9% 0.06 33% perf-sched.sch_delay.avg.ms.schedule_timeout.rcu_gp_fqs_loop.rcu_gp_kthread.kthread
> 0.01 15% +67.5% 0.02 8% perf-sched.sch_delay.avg.ms.smpboot_thread_fn.kthread.ret_from_fork.ret_from_fork_asm
> 0.09 50% -85.7% 0.01 33% perf-sched.sch_delay.avg.ms.wait_for_partner.fifo_open.do_dentry_open.do_open
> 0.04 7% +343.4% 0.16 6% perf-sched.sch_delay.avg.ms.worker_thread.kthread.ret_from_fork.ret_from_fork_asm
> 0.06 41% +3260.7% 1.88 30% perf-sched.sch_delay.max.ms.__cond_resched.__skb_datagram_iter.skb_copy_datagram_iter.udp_recvmsg.inet_recvmsg
> 3.78 -96.2% 0.14 3% perf-sched.sch_delay.max.ms.__cond_resched.stop_one_cpu.sched_exec.bprm_execve.part
> 2.86 4% -72.6% 0.78 113% perf-sched.sch_delay.max.ms.__x64_sys_pause.do_syscall_64.entry_SYSCALL_64_after_hwframe.[unknown]
> 4.09 7% -34.1% 2.69 7% perf-sched.sch_delay.max.ms.do_task_dead.do_exit.do_group_exit.__x64_sys_exit_group.do_syscall_64
> 3.09 37% -64.1% 1.11 5% perf-sched.sch_delay.max.ms.do_wait.kernel_wait4.__do_sys_wait4.do_syscall_64
> 0.00 141% +6200.0% 0.13 82% perf-sched.sch_delay.max.ms.exit_to_user_mode_loop.exit_to_user_mode_prepare.irqentry_exit_to_user_mode.asm_sysvec_apic_timer_interrupt
> 3.94 -40.5% 2.35 48% perf-sched.sch_delay.max.ms.pipe_read.vfs_read.ksys_read.do_syscall_64
> 1.63 21% -77.0% 0.38 90% perf-sched.sch_delay.max.ms.schedule_hrtimeout_range_clock.do_select.core_sys_select.kern_select
> 7.29 39% +417.5% 37.72 16% perf-sched.sch_delay.max.ms.schedule_timeout.__skb_wait_for_more_packets.__skb_recv_udp.udp_recvmsg
> 3.35 14% -51.7% 1.62 3% perf-sched.sch_delay.max.ms.schedule_timeout.__wait_for_common.wait_for_completion_state.kernel_clone
> 0.05 13% +2245.1% 1.13 40% perf-sched.sch_delay.max.ms.schedule_timeout.kcompactd.kthread.ret_from_fork
> 3.01 26% +729.6% 25.01 91% perf-sched.sch_delay.max.ms.schedule_timeout.rcu_gp_fqs_loop.rcu_gp_kthread.kthread
> 1.93 59% -85.5% 0.28 62% perf-sched.sch_delay.max.ms.wait_for_partner.fifo_open.do_dentry_open.do_open
> 0.01 -50.0% 0.00 perf-sched.total_sch_delay.average.ms
> 7.29 39% +468.8% 41.46 26% perf-sched.total_sch_delay.max.ms
> 6.04 4% -94.1% 0.35 perf-sched.total_wait_and_delay.average.ms
> 205790 3% +1811.0% 3932742 perf-sched.total_wait_and_delay.count.ms
> 6.03 4% -94.2% 0.35 perf-sched.total_wait_time.average.ms
> 75.51 41% -100.0% 0.00 perf-sched.wait_and_delay.avg.ms.__cond_resched.generic_perform_write.shmem_file_write_iter.vfs_write.ksys_write
> 23.01 17% -100.0% 0.00 perf-sched.wait_and_delay.avg.ms.__cond_resched.mutex_lock.perf_poll.do_poll.constprop
> 23.82 7% -100.0% 0.00 perf-sched.wait_and_delay.avg.ms.__cond_resched.shmem_get_folio_gfp.shmem_write_begin.generic_perform_write.shmem_file_write_iter
> 95.27 41% -100.0% 0.00 perf-sched.wait_and_delay.avg.ms.__cond_resched.shmem_inode_acct_block.shmem_alloc_and_acct_folio.shmem_get_folio_gfp.shmem_write_begin
> 55.86 141% +1014.6% 622.64 5% perf-sched.wait_and_delay.avg.ms.do_nanosleep.hrtimer_nanosleep.common_nsleep.__x64_sys_clock_nanosleep
> 0.07 23% -82.5% 0.01 perf-sched.wait_and_delay.avg.ms.exit_to_user_mode_loop.exit_to_user_mode_prepare.syscall_exit_to_user_mode.do_syscall_64
> 137.41 3% +345.1% 611.63 2% perf-sched.wait_and_delay.avg.ms.schedule_hrtimeout_range_clock.do_poll.constprop.0.do_sys_poll
> 0.04 5% -49.6% 0.02 perf-sched.wait_and_delay.avg.ms.schedule_timeout.__skb_wait_for_more_packets.__skb_recv_udp.udp_recvmsg
> 536.33 5% -46.5% 287.00 perf-sched.wait_and_delay.avg.ms.smpboot_thread_fn.kthread.ret_from_fork.ret_from_fork_asm
> 21.67 32% -100.0% 0.00 perf-sched.wait_and_delay.count.__cond_resched.generic_perform_write.shmem_file_write_iter.vfs_write.ksys_write
> 5.67 8% -100.0% 0.00 perf-sched.wait_and_delay.count.__cond_resched.mutex_lock.perf_poll.do_poll.constprop
> 1.67 56% -100.0% 0.00 perf-sched.wait_and_delay.count.__cond_resched.shmem_get_folio_gfp.shmem_write_begin.generic_perform_write.shmem_file_write_iter
> 5.67 29% -100.0% 0.00 perf-sched.wait_and_delay.count.__cond_resched.shmem_inode_acct_block.shmem_alloc_and_acct_folio.shmem_get_folio_gfp.shmem_write_begin
> 5.33 23% +93.8% 10.33 25% perf-sched.wait_and_delay.count.__cond_resched.smpboot_thread_fn.kthread.ret_from_fork.ret_from_fork_asm
> 101725 3% +15.3% 117243 10% perf-sched.wait_and_delay.count.exit_to_user_mode_loop.exit_to_user_mode_prepare.syscall_exit_to_user_mode.do_syscall_64
> 100.00 7% -80.3% 19.67 2% perf-sched.wait_and_delay.count.schedule_hrtimeout_range_clock.do_poll.constprop.0.do_sys_poll
> 97762 4% +3794.8% 3807606 perf-sched.wait_and_delay.count.schedule_timeout.__skb_wait_for_more_packets.__skb_recv_udp.udp_recvmsg
> 1091 9% +111.9% 2311 3% perf-sched.wait_and_delay.count.smpboot_thread_fn.kthread.ret_from_fork.ret_from_fork_asm
> 604.50 43% -100.0% 0.00 perf-sched.wait_and_delay.max.ms.__cond_resched.generic_perform_write.shmem_file_write_iter.vfs_write.ksys_write
> 37.41 9% -100.0% 0.00 perf-sched.wait_and_delay.max.ms.__cond_resched.mutex_lock.perf_poll.do_poll.constprop
> 27.08 13% -100.0% 0.00 perf-sched.wait_and_delay.max.ms.__cond_resched.shmem_get_folio_gfp.shmem_write_begin.generic_perform_write.shmem_file_write_iter
> 275.41 32% -100.0% 0.00 perf-sched.wait_and_delay.max.ms.__cond_resched.shmem_inode_acct_block.shmem_alloc_and_acct_folio.shmem_get_folio_gfp.shmem_write_begin
> 1313 69% +112.1% 2786 15% perf-sched.wait_and_delay.max.ms.__cond_resched.smpboot_thread_fn.kthread.ret_from_fork.ret_from_fork_asm
> 333.38 141% +200.4% 1001 perf-sched.wait_and_delay.max.ms.do_nanosleep.hrtimer_nanosleep.common_nsleep.__x64_sys_clock_nanosleep
> 1000 -96.8% 31.85 48% perf-sched.wait_and_delay.max.ms.exit_to_user_mode_loop.exit_to_user_mode_prepare.syscall_exit_to_user_mode.do_syscall_64
> 17.99 33% +387.5% 87.71 8% perf-sched.wait_and_delay.max.ms.schedule_timeout.__skb_wait_for_more_packets.__skb_recv_udp.udp_recvmsg
> 0.33 19% -74.1% 0.09 10% perf-sched.wait_time.avg.ms.__cond_resched.__skb_datagram_iter.skb_copy_datagram_iter.udp_recvmsg.inet_recvmsg
> 0.02 53% +331.4% 0.10 50% perf-sched.wait_time.avg.ms.__cond_resched.aa_sk_perm.security_socket_recvmsg.sock_recvmsg.__sys_recvfrom
> 0.09 65% -75.9% 0.02 9% perf-sched.wait_time.avg.ms.__cond_resched.aa_sk_perm.security_socket_sendmsg.sock_sendmsg.__sys_sendto
> 0.02 22% -70.2% 0.01 141% perf-sched.wait_time.avg.ms.__cond_resched.dput.__fput.__x64_sys_close.do_syscall_64
> 75.51 41% -100.0% 0.04 42% perf-sched.wait_time.avg.ms.__cond_resched.generic_perform_write.shmem_file_write_iter.vfs_write.ksys_write
> 0.10 36% -80.3% 0.02 9% perf-sched.wait_time.avg.ms.__cond_resched.kmem_cache_alloc_node.__alloc_skb.alloc_skb_with_frags.sock_alloc_send_pskb
> 0.55 61% -94.9% 0.03 45% perf-sched.wait_time.avg.ms.__cond_resched.kmem_cache_alloc_node.kmalloc_reserve.__alloc_skb.alloc_skb_with_frags
> 23.01 17% -100.0% 0.00 141% perf-sched.wait_time.avg.ms.__cond_resched.mutex_lock.perf_poll.do_poll.constprop
> 23.82 7% -99.7% 0.07 57% perf-sched.wait_time.avg.ms.__cond_resched.shmem_get_folio_gfp.shmem_write_begin.generic_perform_write.shmem_file_write_iter
> 95.27 41% -100.0% 0.03 89% perf-sched.wait_time.avg.ms.__cond_resched.shmem_inode_acct_block.shmem_alloc_and_acct_folio.shmem_get_folio_gfp.shmem_write_begin
> 56.30 139% +1005.5% 622.44 5% perf-sched.wait_time.avg.ms.do_nanosleep.hrtimer_nanosleep.common_nsleep.__x64_sys_clock_nanosleep
> 2.78 66% -98.2% 0.05 52% perf-sched.wait_time.avg.ms.exit_to_user_mode_loop.exit_to_user_mode_prepare.irqentry_exit_to_user_mode.asm_sysvec_apic_timer_interrupt
> 0.07 23% -82.5% 0.01 perf-sched.wait_time.avg.ms.exit_to_user_mode_loop.exit_to_user_mode_prepare.syscall_exit_to_user_mode.do_syscall_64
> 137.37 3% +345.1% 611.40 2% perf-sched.wait_time.avg.ms.schedule_hrtimeout_range_clock.do_poll.constprop.0.do_sys_poll
> 0.02 5% -41.9% 0.01 3% perf-sched.wait_time.avg.ms.schedule_timeout.__skb_wait_for_more_packets.__skb_recv_udp.udp_recvmsg
> 536.32 5% -46.5% 286.98 perf-sched.wait_time.avg.ms.smpboot_thread_fn.kthread.ret_from_fork.ret_from_fork_asm
> 4.66 20% -56.7% 2.02 26% perf-sched.wait_time.max.ms.__cond_resched.__skb_datagram_iter.skb_copy_datagram_iter.udp_recvmsg.inet_recvmsg
> 0.03 63% +995.0% 0.37 26% perf-sched.wait_time.max.ms.__cond_resched.aa_sk_perm.security_socket_recvmsg.sock_recvmsg.__sys_recvfrom
> 1.67 87% -92.6% 0.12 57% perf-sched.wait_time.max.ms.__cond_resched.aa_sk_perm.security_socket_sendmsg.sock_sendmsg.__sys_sendto
> 0.54 117% -95.1% 0.03 105% perf-sched.wait_time.max.ms.__cond_resched.down_write_killable.exec_mmap.begin_new_exec.load_elf_binary
> 0.06 49% -89.1% 0.01 141% perf-sched.wait_time.max.ms.__cond_resched.dput.__fput.__x64_sys_close.do_syscall_64
> 604.50 43% -100.0% 0.16 83% perf-sched.wait_time.max.ms.__cond_resched.generic_perform_write.shmem_file_write_iter.vfs_write.ksys_write
> 2.77 45% -95.4% 0.13 64% perf-sched.wait_time.max.ms.__cond_resched.kmem_cache_alloc_node.__alloc_skb.alloc_skb_with_frags.sock_alloc_send_pskb
> 2.86 45% -94.3% 0.16 91% perf-sched.wait_time.max.ms.__cond_resched.kmem_cache_alloc_node.kmalloc_reserve.__alloc_skb.alloc_skb_with_frags
> 37.41 9% -100.0% 0.01 141% perf-sched.wait_time.max.ms.__cond_resched.mutex_lock.perf_poll.do_poll.constprop
> 27.08 13% -99.7% 0.08 61% perf-sched.wait_time.max.ms.__cond_resched.shmem_get_folio_gfp.shmem_write_begin.generic_perform_write.shmem_file_write_iter
> 275.41 32% -100.0% 0.03 89% perf-sched.wait_time.max.ms.__cond_resched.shmem_inode_acct_block.shmem_alloc_and_acct_folio.shmem_get_folio_gfp.shmem_write_begin
> 1313 69% +112.1% 2786 15% perf-sched.wait_time.max.ms.__cond_resched.smpboot_thread_fn.kthread.ret_from_fork.ret_from_fork_asm
> 334.74 140% +198.9% 1000 perf-sched.wait_time.max.ms.do_nanosleep.hrtimer_nanosleep.common_nsleep.__x64_sys_clock_nanosleep
> 21.74 58% -95.4% 1.00 103% perf-sched.wait_time.max.ms.exit_to_user_mode_loop.exit_to_user_mode_prepare.irqentry_exit_to_user_mode.asm_sysvec_apic_timer_interrupt
> 1000 -97.6% 24.49 50% perf-sched.wait_time.max.ms.exit_to_user_mode_loop.exit_to_user_mode_prepare.syscall_exit_to_user_mode.do_syscall_64
> 10.90 27% +682.9% 85.36 6% perf-sched.wait_time.max.ms.schedule_timeout.__skb_wait_for_more_packets.__skb_recv_udp.udp_recvmsg
> 32.91 58% -63.5% 12.01 115% perf-sched.wait_time.max.ms.schedule_timeout.__wait_for_common.wait_for_completion_state.kernel_clone
> 169.97 7% -49.2% 86.29 15% perf-sched.wait_time.max.ms.schedule_timeout.rcu_gp_fqs_loop.rcu_gp_kthread.kthread
> 44.08 -19.8 24.25 perf-profile.calltrace.cycles-pp._raw_spin_lock_irqsave.free_pcppages_bulk.free_unref_page.skb_release_data.__consume_stateless_skb
> 44.47 -19.6 24.87 perf-profile.calltrace.cycles-pp.free_pcppages_bulk.free_unref_page.skb_release_data.__consume_stateless_skb.udp_recvmsg
> 43.63 -19.5 24.15 perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock_irqsave.free_pcppages_bulk.free_unref_page.skb_release_data
> 45.62 -19.2 26.39 perf-profile.calltrace.cycles-pp.skb_release_data.__consume_stateless_skb.udp_recvmsg.inet_recvmsg.sock_recvmsg
> 45.62 -19.2 26.40 perf-profile.calltrace.cycles-pp.__consume_stateless_skb.udp_recvmsg.inet_recvmsg.sock_recvmsg.__sys_recvfrom
> 45.00 -19.1 25.94 perf-profile.calltrace.cycles-pp.free_unref_page.skb_release_data.__consume_stateless_skb.udp_recvmsg.inet_recvmsg
> 50.41 -16.8 33.64 39% perf-profile.calltrace.cycles-pp.accept_connections.main.__libc_start_main
> 50.41 -16.8 33.64 39% perf-profile.calltrace.cycles-pp.accept_connection.accept_connections.main.__libc_start_main
> 50.41 -16.8 33.64 39% perf-profile.calltrace.cycles-pp.spawn_child.accept_connection.accept_connections.main.__libc_start_main
> 50.41 -16.8 33.64 39% perf-profile.calltrace.cycles-pp.process_requests.spawn_child.accept_connection.accept_connections.main
> 99.92 -14.2 85.72 15% perf-profile.calltrace.cycles-pp.main.__libc_start_main
> 99.96 -14.2 85.77 15% perf-profile.calltrace.cycles-pp.__libc_start_main
> 50.10 -8.6 41.52 perf-profile.calltrace.cycles-pp.udp_recvmsg.inet_recvmsg.sock_recvmsg.__sys_recvfrom.__x64_sys_recvfrom
> 50.11 -8.6 41.55 perf-profile.calltrace.cycles-pp.inet_recvmsg.sock_recvmsg.__sys_recvfrom.__x64_sys_recvfrom.do_syscall_64
> 50.13 -8.5 41.64 perf-profile.calltrace.cycles-pp.sock_recvmsg.__sys_recvfrom.__x64_sys_recvfrom.do_syscall_64.entry_SYSCALL_64_after_hwframe
> 50.28 -8.0 42.27 perf-profile.calltrace.cycles-pp.__sys_recvfrom.__x64_sys_recvfrom.do_syscall_64.entry_SYSCALL_64_after_hwframe.recvfrom
> 50.29 -8.0 42.29 perf-profile.calltrace.cycles-pp.__x64_sys_recvfrom.do_syscall_64.entry_SYSCALL_64_after_hwframe.recvfrom.recv_omni
> 50.31 -7.9 42.42 perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.recvfrom.recv_omni.process_requests
> 50.32 -7.8 42.47 perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.recvfrom.recv_omni.process_requests.spawn_child
> 50.36 -7.6 42.78 perf-profile.calltrace.cycles-pp.recvfrom.recv_omni.process_requests.spawn_child.accept_connection
> 50.41 -7.3 43.07 perf-profile.calltrace.cycles-pp.recv_omni.process_requests.spawn_child.accept_connection.accept_connections
> 19.93 2% -6.6 13.36 perf-profile.calltrace.cycles-pp.ip_generic_getfrag.__ip_append_data.ip_make_skb.udp_sendmsg.sock_sendmsg
> 19.44 2% -6.3 13.16 perf-profile.calltrace.cycles-pp._copy_from_iter.ip_generic_getfrag.__ip_append_data.ip_make_skb.udp_sendmsg
> 18.99 2% -6.1 12.90 perf-profile.calltrace.cycles-pp.copyin._copy_from_iter.ip_generic_getfrag.__ip_append_data.ip_make_skb
> 8.95 -5.1 3.82 perf-profile.calltrace.cycles-pp.udp_send_skb.udp_sendmsg.sock_sendmsg.__sys_sendto.__x64_sys_sendto
> 8.70 -5.0 3.71 perf-profile.calltrace.cycles-pp.ip_send_skb.udp_send_skb.udp_sendmsg.sock_sendmsg.__sys_sendto
> 8.10 -4.6 3.45 perf-profile.calltrace.cycles-pp.ip_finish_output2.ip_send_skb.udp_send_skb.udp_sendmsg.sock_sendmsg
> 7.69 -4.4 3.27 perf-profile.calltrace.cycles-pp.__dev_queue_xmit.ip_finish_output2.ip_send_skb.udp_send_skb.udp_sendmsg
> 6.51 -3.7 2.78 perf-profile.calltrace.cycles-pp.__local_bh_enable_ip.__dev_queue_xmit.ip_finish_output2.ip_send_skb.udp_send_skb
> 6.47 -3.7 2.75 perf-profile.calltrace.cycles-pp.do_softirq.__local_bh_enable_ip.__dev_queue_xmit.ip_finish_output2.ip_send_skb
> 6.41 -3.7 2.71 perf-profile.calltrace.cycles-pp.__do_softirq.do_softirq.__local_bh_enable_ip.__dev_queue_xmit.ip_finish_output2
> 5.88 -3.5 2.43 perf-profile.calltrace.cycles-pp.net_rx_action.__do_softirq.do_softirq.__local_bh_enable_ip.__dev_queue_xmit
> 5.73 -3.4 2.35 perf-profile.calltrace.cycles-pp.__napi_poll.net_rx_action.__do_softirq.do_softirq.__local_bh_enable_ip
> 5.69 -3.4 2.33 perf-profile.calltrace.cycles-pp.process_backlog.__napi_poll.net_rx_action.__do_softirq.do_softirq
> 5.36 -3.2 2.19 perf-profile.calltrace.cycles-pp.__netif_receive_skb_one_core.process_backlog.__napi_poll.net_rx_action.__do_softirq
> 4.59 -2.7 1.89 perf-profile.calltrace.cycles-pp.ip_local_deliver_finish.__netif_receive_skb_one_core.process_backlog.__napi_poll.net_rx_action
> 4.55 2% -2.7 1.88 perf-profile.calltrace.cycles-pp.ip_protocol_deliver_rcu.ip_local_deliver_finish.__netif_receive_skb_one_core.process_backlog.__napi_poll
> 4.40 2% -2.6 1.81 perf-profile.calltrace.cycles-pp.__udp4_lib_rcv.ip_protocol_deliver_rcu.ip_local_deliver_finish.__netif_receive_skb_one_core.process_backlog
> 3.81 2% -2.2 1.57 perf-profile.calltrace.cycles-pp.udp_unicast_rcv_skb.__udp4_lib_rcv.ip_protocol_deliver_rcu.ip_local_deliver_finish.__netif_receive_skb_one_core
> 3.75 2% -2.2 1.55 perf-profile.calltrace.cycles-pp.udp_queue_rcv_one_skb.udp_unicast_rcv_skb.__udp4_lib_rcv.ip_protocol_deliver_rcu.ip_local_deliver_finish
> 2.21 2% -1.6 0.63 perf-profile.calltrace.cycles-pp.__ip_make_skb.ip_make_skb.udp_sendmsg.sock_sendmsg.__sys_sendto
> 1.94 2% -1.4 0.51 2% perf-profile.calltrace.cycles-pp.__ip_select_ident.__ip_make_skb.ip_make_skb.udp_sendmsg.sock_sendmsg
> 1.14 -0.6 0.51 perf-profile.calltrace.cycles-pp.sock_alloc_send_pskb.__ip_append_data.ip_make_skb.udp_sendmsg.sock_sendmsg
> 0.00 +0.5 0.53 2% perf-profile.calltrace.cycles-pp.schedule_idle.do_idle.cpu_startup_entry.start_secondary.secondary_startup_64_no_verify
> 0.00 +0.7 0.69 perf-profile.calltrace.cycles-pp.sysvec_call_function_single.asm_sysvec_call_function_single.acpi_safe_halt.acpi_idle_enter.cpuidle_enter_state
> 0.00 +0.7 0.71 perf-profile.calltrace.cycles-pp.__sk_mem_raise_allocated.__sk_mem_schedule.__udp_enqueue_schedule_skb.udp_queue_rcv_one_skb.udp_unicast_rcv_skb
> 0.00 +0.7 0.72 perf-profile.calltrace.cycles-pp.__sk_mem_schedule.__udp_enqueue_schedule_skb.udp_queue_rcv_one_skb.udp_unicast_rcv_skb.__udp4_lib_rcv
> 0.00 +1.0 0.99 20% perf-profile.calltrace.cycles-pp.__schedule.schedule.schedule_timeout.__skb_wait_for_more_packets.__skb_recv_udp
> 0.00 +1.0 1.01 20% perf-profile.calltrace.cycles-pp.schedule.schedule_timeout.__skb_wait_for_more_packets.__skb_recv_udp.udp_recvmsg
> 0.00 +1.1 1.05 20% perf-profile.calltrace.cycles-pp.schedule_timeout.__skb_wait_for_more_packets.__skb_recv_udp.udp_recvmsg.inet_recvmsg
> 0.00 +1.1 1.12 perf-profile.calltrace.cycles-pp.acpi_safe_halt.acpi_idle_enter.cpuidle_enter_state.cpuidle_enter.cpuidle_idle_call
> 0.00 +1.2 1.18 20% perf-profile.calltrace.cycles-pp.__skb_wait_for_more_packets.__skb_recv_udp.udp_recvmsg.inet_recvmsg.sock_recvmsg
> 0.00 +1.3 1.32 perf-profile.calltrace.cycles-pp.__udp_enqueue_schedule_skb.udp_queue_rcv_one_skb.udp_unicast_rcv_skb.__udp4_lib_rcv.ip_protocol_deliver_rcu
> 0.00 +2.2 2.23 perf-profile.calltrace.cycles-pp.__skb_recv_udp.udp_recvmsg.inet_recvmsg.sock_recvmsg.__sys_recvfrom
> 49.51 +2.6 52.08 perf-profile.calltrace.cycles-pp.send_udp_stream.main.__libc_start_main
> 49.49 +2.6 52.07 perf-profile.calltrace.cycles-pp.send_omni_inner.send_udp_stream.main.__libc_start_main
> 0.00 +3.0 2.96 2% perf-profile.calltrace.cycles-pp.acpi_idle_enter.cpuidle_enter_state.cpuidle_enter.cpuidle_idle_call.do_idle
> 48.71 +3.0 51.73 perf-profile.calltrace.cycles-pp.sendto.send_omni_inner.send_udp_stream.main.__libc_start_main
> 0.00 +3.1 3.06 2% perf-profile.calltrace.cycles-pp.cpuidle_enter_state.cpuidle_enter.cpuidle_idle_call.do_idle.cpu_startup_entry
> 0.00 +3.1 3.09 perf-profile.calltrace.cycles-pp.cpuidle_enter.cpuidle_idle_call.do_idle.cpu_startup_entry.start_secondary
> 48.34 +3.2 51.56 perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.sendto.send_omni_inner.send_udp_stream.main
> 0.00 +3.3 3.33 2% perf-profile.calltrace.cycles-pp.cpuidle_idle_call.do_idle.cpu_startup_entry.start_secondary.secondary_startup_64_no_verify
> 48.13 +3.8 51.96 perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.sendto.send_omni_inner.send_udp_stream
> 47.82 +4.0 51.82 perf-profile.calltrace.cycles-pp.__x64_sys_sendto.do_syscall_64.entry_SYSCALL_64_after_hwframe.sendto.send_omni_inner
> 47.70 +4.1 51.76 perf-profile.calltrace.cycles-pp.__sys_sendto.__x64_sys_sendto.do_syscall_64.entry_SYSCALL_64_after_hwframe.sendto
> 0.00 +4.1 4.08 perf-profile.calltrace.cycles-pp.do_idle.cpu_startup_entry.start_secondary.secondary_startup_64_no_verify
> 0.00 +4.1 4.10 perf-profile.calltrace.cycles-pp.cpu_startup_entry.start_secondary.secondary_startup_64_no_verify
> 0.00 +4.1 4.10 perf-profile.calltrace.cycles-pp.start_secondary.secondary_startup_64_no_verify
> 0.00 +4.1 4.14 perf-profile.calltrace.cycles-pp.secondary_startup_64_no_verify
> 0.00 +4.3 4.35 2% perf-profile.calltrace.cycles-pp.asm_sysvec_call_function_single.acpi_safe_halt.acpi_idle_enter.cpuidle_enter_state.cpuidle_enter
> 46.52 +4.8 51.27 perf-profile.calltrace.cycles-pp.sock_sendmsg.__sys_sendto.__x64_sys_sendto.do_syscall_64.entry_SYSCALL_64_after_hwframe
> 46.04 +5.0 51.08 perf-profile.calltrace.cycles-pp.udp_sendmsg.sock_sendmsg.__sys_sendto.__x64_sys_sendto.do_syscall_64
> 3.67 +8.0 11.63 perf-profile.calltrace.cycles-pp.copyout._copy_to_iter.__skb_datagram_iter.skb_copy_datagram_iter.udp_recvmsg
> 3.71 +8.1 11.80 perf-profile.calltrace.cycles-pp._copy_to_iter.__skb_datagram_iter.skb_copy_datagram_iter.udp_recvmsg.inet_recvmsg
> 3.96 +8.5 12.42 perf-profile.calltrace.cycles-pp.__skb_datagram_iter.skb_copy_datagram_iter.udp_recvmsg.inet_recvmsg.sock_recvmsg
> 3.96 +8.5 12.44 perf-profile.calltrace.cycles-pp.skb_copy_datagram_iter.udp_recvmsg.inet_recvmsg.sock_recvmsg.__sys_recvfrom
> 35.13 +11.3 46.39 perf-profile.calltrace.cycles-pp.ip_make_skb.udp_sendmsg.sock_sendmsg.__sys_sendto.__x64_sys_sendto
> 32.68 2% +13.0 45.65 perf-profile.calltrace.cycles-pp.__ip_append_data.ip_make_skb.udp_sendmsg.sock_sendmsg.__sys_sendto
> 10.27 +20.3 30.59 perf-profile.calltrace.cycles-pp.sk_page_frag_refill.__ip_append_data.ip_make_skb.udp_sendmsg.sock_sendmsg
> 10.24 +20.3 30.58 perf-profile.calltrace.cycles-pp.skb_page_frag_refill.sk_page_frag_refill.__ip_append_data.ip_make_skb.udp_sendmsg
> 9.84 +20.5 30.32 perf-profile.calltrace.cycles-pp.__alloc_pages.skb_page_frag_refill.sk_page_frag_refill.__ip_append_data.ip_make_skb
> 9.59 +20.5 30.11 perf-profile.calltrace.cycles-pp.get_page_from_freelist.__alloc_pages.skb_page_frag_refill.sk_page_frag_refill.__ip_append_data
> 8.40 +21.0 29.42 perf-profile.calltrace.cycles-pp.rmqueue.get_page_from_freelist.__alloc_pages.skb_page_frag_refill.sk_page_frag_refill
> 6.13 +21.9 28.05 perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock_irqsave.rmqueue_bulk.rmqueue.get_page_from_freelist
> 6.20 +22.0 28.15 perf-profile.calltrace.cycles-pp._raw_spin_lock_irqsave.rmqueue_bulk.rmqueue.get_page_from_freelist.__alloc_pages
> 6.46 +22.5 28.91 perf-profile.calltrace.cycles-pp.rmqueue_bulk.rmqueue.get_page_from_freelist.__alloc_pages.skb_page_frag_refill
> 48.24 -21.8 26.43 perf-profile.children.cycles-pp.skb_release_data
> 47.19 -21.2 25.98 perf-profile.children.cycles-pp.free_unref_page
> 44.48 -19.6 24.88 perf-profile.children.cycles-pp.free_pcppages_bulk
> 45.62 -19.2 26.40 perf-profile.children.cycles-pp.__consume_stateless_skb
> 99.95 -14.2 85.76 15% perf-profile.children.cycles-pp.main
> 99.96 -14.2 85.77 15% perf-profile.children.cycles-pp.__libc_start_main
> 50.10 -8.6 41.53 perf-profile.children.cycles-pp.udp_recvmsg
> 50.11 -8.6 41.56 perf-profile.children.cycles-pp.inet_recvmsg
> 50.13 -8.5 41.65 perf-profile.children.cycles-pp.sock_recvmsg
> 50.29 -8.0 42.28 perf-profile.children.cycles-pp.__sys_recvfrom
> 50.29 -8.0 42.30 perf-profile.children.cycles-pp.__x64_sys_recvfrom
> 50.38 -7.5 42.86 perf-profile.children.cycles-pp.recvfrom
> 50.41 -7.3 43.07 perf-profile.children.cycles-pp.accept_connections
> 50.41 -7.3 43.07 perf-profile.children.cycles-pp.accept_connection
> 50.41 -7.3 43.07 perf-profile.children.cycles-pp.spawn_child
> 50.41 -7.3 43.07 perf-profile.children.cycles-pp.process_requests
> 50.41 -7.3 43.07 perf-profile.children.cycles-pp.recv_omni
> 19.96 2% -6.5 13.50 perf-profile.children.cycles-pp.ip_generic_getfrag
> 19.46 2% -6.2 13.28 perf-profile.children.cycles-pp._copy_from_iter
> 19.21 2% -6.1 13.14 perf-profile.children.cycles-pp.copyin
> 8.96 -5.1 3.86 perf-profile.children.cycles-pp.udp_send_skb
> 8.72 -5.0 3.75 perf-profile.children.cycles-pp.ip_send_skb
> 8.11 -4.6 3.49 perf-profile.children.cycles-pp.ip_finish_output2
> 7.72 -4.4 3.32 perf-profile.children.cycles-pp.__dev_queue_xmit
> 98.71 -4.1 94.59 perf-profile.children.cycles-pp.entry_SYSCALL_64_after_hwframe
> 98.51 -4.0 94.46 perf-profile.children.cycles-pp.do_syscall_64
> 6.49 -3.7 2.78 perf-profile.children.cycles-pp.do_softirq
> 6.51 -3.7 2.82 perf-profile.children.cycles-pp.__local_bh_enable_ip
> 6.43 -3.7 2.78 perf-profile.children.cycles-pp.__do_softirq
> 5.90 -3.4 2.46 perf-profile.children.cycles-pp.net_rx_action
> 5.74 -3.4 2.38 perf-profile.children.cycles-pp.__napi_poll
> 5.71 -3.4 2.36 perf-profile.children.cycles-pp.process_backlog
> 5.37 -3.2 2.21 perf-profile.children.cycles-pp.__netif_receive_skb_one_core
> 4.60 -2.7 1.91 perf-profile.children.cycles-pp.ip_local_deliver_finish
> 4.57 2% -2.7 1.90 perf-profile.children.cycles-pp.ip_protocol_deliver_rcu
> 4.42 2% -2.6 1.83 perf-profile.children.cycles-pp.__udp4_lib_rcv
> 3.82 2% -2.2 1.58 2% perf-profile.children.cycles-pp.udp_unicast_rcv_skb
> 3.78 2% -2.2 1.57 2% perf-profile.children.cycles-pp.udp_queue_rcv_one_skb
> 2.23 2% -1.6 0.65 2% perf-profile.children.cycles-pp.__ip_make_skb
> 1.95 2% -1.4 0.52 3% perf-profile.children.cycles-pp.__ip_select_ident
> 1.51 4% -1.2 0.34 perf-profile.children.cycles-pp.free_unref_page_commit
> 1.17 -0.7 0.51 2% perf-profile.children.cycles-pp.ip_route_output_flow
> 1.15 -0.6 0.52 perf-profile.children.cycles-pp.sock_alloc_send_pskb
> 0.91 -0.5 0.39 perf-profile.children.cycles-pp.alloc_skb_with_frags
> 0.86 -0.5 0.37 perf-profile.children.cycles-pp.__alloc_skb
> 0.83 -0.5 0.36 2% perf-profile.children.cycles-pp.ip_route_output_key_hash_rcu
> 0.75 -0.4 0.32 perf-profile.children.cycles-pp.dev_hard_start_xmit
> 0.72 -0.4 0.31 3% perf-profile.children.cycles-pp.fib_table_lookup
> 0.67 -0.4 0.28 perf-profile.children.cycles-pp.loopback_xmit
> 0.70 2% -0.4 0.33 perf-profile.children.cycles-pp.__zone_watermark_ok
> 0.47 4% -0.3 0.15 perf-profile.children.cycles-pp.kmem_cache_free
> 0.57 -0.3 0.26 perf-profile.children.cycles-pp.kmem_cache_alloc_node
> 0.46 -0.3 0.18 2% perf-profile.children.cycles-pp.ip_rcv
> 0.42 -0.3 0.17 perf-profile.children.cycles-pp.move_addr_to_kernel
> 0.41 -0.2 0.16 2% perf-profile.children.cycles-pp.__udp4_lib_lookup
> 0.32 -0.2 0.13 perf-profile.children.cycles-pp.__netif_rx
> 0.30 -0.2 0.12 perf-profile.children.cycles-pp.netif_rx_internal
> 0.30 -0.2 0.12 perf-profile.children.cycles-pp._copy_from_user
> 0.31 -0.2 0.13 perf-profile.children.cycles-pp.kmalloc_reserve
> 0.63 -0.2 0.46 2% perf-profile.children.cycles-pp.free_unref_page_prepare
> 0.28 -0.2 0.11 perf-profile.children.cycles-pp.enqueue_to_backlog
> 0.27 -0.2 0.11 perf-profile.children.cycles-pp.udp4_lib_lookup2
> 0.29 -0.2 0.13 6% perf-profile.children.cycles-pp.send_data
> 0.25 -0.2 0.10 perf-profile.children.cycles-pp.__netif_receive_skb_core
> 0.23 2% -0.1 0.10 4% perf-profile.children.cycles-pp.security_socket_sendmsg
> 0.19 2% -0.1 0.06 perf-profile.children.cycles-pp.ip_rcv_core
> 0.37 -0.1 0.24 perf-profile.children.cycles-pp.irqtime_account_irq
> 0.21 -0.1 0.08 perf-profile.children.cycles-pp.sock_wfree
> 0.21 3% -0.1 0.08 perf-profile.children.cycles-pp.validate_xmit_skb
> 0.20 2% -0.1 0.08 perf-profile.children.cycles-pp.ip_output
> 0.22 2% -0.1 0.10 4% perf-profile.children.cycles-pp.ip_rcv_finish_core
> 0.20 6% -0.1 0.09 5% perf-profile.children.cycles-pp.__mkroute_output
> 0.21 2% -0.1 0.09 5% perf-profile.children.cycles-pp._raw_spin_lock_irq
> 0.28 -0.1 0.18 perf-profile.children.cycles-pp._raw_spin_trylock
> 0.34 3% -0.1 0.25 perf-profile.children.cycles-pp.__slab_free
> 0.13 3% -0.1 0.05 perf-profile.children.cycles-pp.siphash_3u32
> 0.12 4% -0.1 0.03 70% perf-profile.children.cycles-pp.ipv4_pktinfo_prepare
> 0.14 3% -0.1 0.06 7% perf-profile.children.cycles-pp.__ip_local_out
> 0.20 2% -0.1 0.12 perf-profile.children.cycles-pp.aa_sk_perm
> 0.18 2% -0.1 0.10 perf-profile.children.cycles-pp.get_pfnblock_flags_mask
> 0.12 3% -0.1 0.05 perf-profile.children.cycles-pp.sk_filter_trim_cap
> 0.13 -0.1 0.06 perf-profile.children.cycles-pp.ip_setup_cork
> 0.13 7% -0.1 0.06 8% perf-profile.children.cycles-pp.fib_lookup_good_nhc
> 0.15 3% -0.1 0.08 5% perf-profile.children.cycles-pp.skb_set_owner_w
> 0.11 4% -0.1 0.05 perf-profile.children.cycles-pp.dst_release
> 0.23 2% -0.1 0.17 2% perf-profile.children.cycles-pp.__entry_text_start
> 0.11 -0.1 0.05 perf-profile.children.cycles-pp.ipv4_mtu
> 0.20 2% -0.1 0.15 3% perf-profile.children.cycles-pp.__list_add_valid_or_report
> 0.10 -0.1 0.05 perf-profile.children.cycles-pp.ip_send_check
> 0.31 2% -0.0 0.26 3% perf-profile.children.cycles-pp.sockfd_lookup_light
> 0.27 -0.0 0.22 2% perf-profile.children.cycles-pp.__fget_light
> 0.63 -0.0 0.58 perf-profile.children.cycles-pp.__check_object_size
> 0.15 3% -0.0 0.11 perf-profile.children.cycles-pp.entry_SYSRETQ_unsafe_stack
> 0.13 -0.0 0.09 5% perf-profile.children.cycles-pp.alloc_pages
> 0.27 -0.0 0.24 perf-profile.children.cycles-pp.sched_clock_cpu
> 0.11 4% -0.0 0.08 6% perf-profile.children.cycles-pp.__cond_resched
> 0.14 3% -0.0 0.11 perf-profile.children.cycles-pp.free_tail_page_prepare
> 0.11 -0.0 0.08 5% perf-profile.children.cycles-pp.syscall_return_via_sysret
> 0.09 9% -0.0 0.06 7% perf-profile.children.cycles-pp.__xfrm_policy_check2
> 0.23 2% -0.0 0.21 2% perf-profile.children.cycles-pp.sched_clock
> 0.14 3% -0.0 0.11 4% perf-profile.children.cycles-pp.prep_compound_page
> 0.21 2% -0.0 0.20 2% perf-profile.children.cycles-pp.native_sched_clock
> 0.06 -0.0 0.05 perf-profile.children.cycles-pp.task_tick_fair
> 0.06 -0.0 0.05 perf-profile.children.cycles-pp.check_stack_object
> 0.18 2% +0.0 0.20 2% perf-profile.children.cycles-pp.perf_event_task_tick
> 0.18 2% +0.0 0.19 2% perf-profile.children.cycles-pp.perf_adjust_freq_unthr_context
> 0.31 3% +0.0 0.33 perf-profile.children.cycles-pp.tick_sched_handle
> 0.31 3% +0.0 0.33 perf-profile.children.cycles-pp.update_process_times
> 0.41 2% +0.0 0.43 perf-profile.children.cycles-pp.__sysvec_apic_timer_interrupt
> 0.40 2% +0.0 0.42 perf-profile.children.cycles-pp.hrtimer_interrupt
> 0.32 2% +0.0 0.34 perf-profile.children.cycles-pp.tick_sched_timer
> 0.36 2% +0.0 0.39 perf-profile.children.cycles-pp.__hrtimer_run_queues
> 0.06 7% +0.0 0.10 4% perf-profile.children.cycles-pp.exit_to_user_mode_prepare
> 0.05 8% +0.0 0.10 perf-profile.children.cycles-pp._raw_spin_lock_bh
> 0.00 +0.1 0.05 perf-profile.children.cycles-pp.update_cfs_group
> 0.00 +0.1 0.05 perf-profile.children.cycles-pp.cpuidle_governor_latency_req
> 0.00 +0.1 0.05 perf-profile.children.cycles-pp.flush_smp_call_function_queue
> 0.00 +0.1 0.05 8% perf-profile.children.cycles-pp.prepare_to_wait_exclusive
> 0.07 +0.1 0.13 3% perf-profile.children.cycles-pp.__mod_zone_page_state
> 0.00 +0.1 0.06 13% perf-profile.children.cycles-pp.cgroup_rstat_updated
> 0.00 +0.1 0.06 perf-profile.children.cycles-pp.__x2apic_send_IPI_dest
> 0.00 +0.1 0.06 perf-profile.children.cycles-pp.security_socket_recvmsg
> 0.00 +0.1 0.06 perf-profile.children.cycles-pp.select_task_rq_fair
> 0.00 +0.1 0.06 perf-profile.children.cycles-pp.tick_irq_enter
> 0.00 +0.1 0.06 perf-profile.children.cycles-pp.tick_nohz_idle_enter
> 0.42 2% +0.1 0.49 2% perf-profile.children.cycles-pp.sysvec_apic_timer_interrupt
> 0.00 +0.1 0.07 7% perf-profile.children.cycles-pp.ktime_get
> 0.00 +0.1 0.07 perf-profile.children.cycles-pp.__get_user_4
> 0.00 +0.1 0.07 perf-profile.children.cycles-pp.update_rq_clock
> 0.00 +0.1 0.07 perf-profile.children.cycles-pp.select_task_rq
> 0.00 +0.1 0.07 perf-profile.children.cycles-pp.native_apic_msr_eoi
> 0.49 +0.1 0.57 2% perf-profile.children.cycles-pp.asm_sysvec_apic_timer_interrupt
> 0.11 11% +0.1 0.19 2% perf-profile.children.cycles-pp._raw_spin_lock
> 0.00 +0.1 0.08 perf-profile.children.cycles-pp.update_rq_clock_task
> 0.00 +0.1 0.08 perf-profile.children.cycles-pp.__update_load_avg_se
> 0.00 +0.1 0.09 5% perf-profile.children.cycles-pp.irq_enter_rcu
> 0.00 +0.1 0.09 5% perf-profile.children.cycles-pp.__irq_exit_rcu
> 0.00 +0.1 0.09 perf-profile.children.cycles-pp.__update_load_avg_cfs_rq
> 0.00 +0.1 0.09 perf-profile.children.cycles-pp.update_blocked_averages
> 0.00 +0.1 0.09 perf-profile.children.cycles-pp.update_sg_lb_stats
> 0.00 +0.1 0.09 5% perf-profile.children.cycles-pp.set_next_entity
> 0.00 +0.1 0.10 perf-profile.children.cycles-pp.__switch_to_asm
> 0.00 +0.1 0.11 12% perf-profile.children.cycles-pp._copy_to_user
> 0.00 +0.1 0.12 3% perf-profile.children.cycles-pp.menu_select
> 0.00 +0.1 0.12 3% perf-profile.children.cycles-pp.recv_data
> 0.00 +0.1 0.12 3% perf-profile.children.cycles-pp.update_sd_lb_stats
> 0.00 +0.1 0.13 3% perf-profile.children.cycles-pp.native_irq_return_iret
> 0.00 +0.1 0.13 3% perf-profile.children.cycles-pp.__switch_to
> 0.00 +0.1 0.13 3% perf-profile.children.cycles-pp.find_busiest_group
> 0.00 +0.1 0.14 perf-profile.children.cycles-pp.finish_task_switch
> 0.00 +0.1 0.15 3% perf-profile.children.cycles-pp.update_curr
> 0.00 +0.2 0.15 3% perf-profile.children.cycles-pp.mem_cgroup_uncharge_skmem
> 0.00 +0.2 0.16 perf-profile.children.cycles-pp.ttwu_queue_wakelist
> 0.05 +0.2 0.22 2% perf-profile.children.cycles-pp.page_counter_try_charge
> 0.00 +0.2 0.17 2% perf-profile.children.cycles-pp.load_balance
> 0.00 +0.2 0.17 2% perf-profile.children.cycles-pp.___perf_sw_event
> 0.02 141% +0.2 0.19 2% perf-profile.children.cycles-pp.page_counter_uncharge
> 0.33 +0.2 0.52 perf-profile.children.cycles-pp.__free_one_page
> 0.02 141% +0.2 0.21 2% perf-profile.children.cycles-pp.drain_stock
> 0.00 +0.2 0.20 2% perf-profile.children.cycles-pp.prepare_task_switch
> 0.16 3% +0.2 0.38 2% perf-profile.children.cycles-pp.simple_copy_to_iter
> 0.07 11% +0.2 0.31 perf-profile.children.cycles-pp.refill_stock
> 0.07 6% +0.2 0.31 4% perf-profile.children.cycles-pp.move_addr_to_user
> 0.00 +0.2 0.24 perf-profile.children.cycles-pp.enqueue_entity
> 0.00 +0.2 0.25 perf-profile.children.cycles-pp.update_load_avg
> 0.21 2% +0.3 0.48 perf-profile.children.cycles-pp.__list_del_entry_valid_or_report
> 0.00 +0.3 0.31 4% perf-profile.children.cycles-pp.dequeue_entity
> 0.08 5% +0.3 0.40 3% perf-profile.children.cycles-pp.try_charge_memcg
> 0.00 +0.3 0.33 perf-profile.children.cycles-pp.enqueue_task_fair
> 0.00 +0.4 0.35 2% perf-profile.children.cycles-pp.dequeue_task_fair
> 0.00 +0.4 0.35 2% perf-profile.children.cycles-pp.activate_task
> 0.00 +0.4 0.36 2% perf-profile.children.cycles-pp.try_to_wake_up
> 0.00 +0.4 0.37 2% perf-profile.children.cycles-pp.autoremove_wake_function
> 0.00 +0.4 0.39 3% perf-profile.children.cycles-pp.newidle_balance
> 0.12 8% +0.4 0.51 2% perf-profile.children.cycles-pp.mem_cgroup_charge_skmem
> 0.00 +0.4 0.39 perf-profile.children.cycles-pp.ttwu_do_activate
> 0.00 +0.4 0.40 2% perf-profile.children.cycles-pp.__wake_up_common
> 0.18 4% +0.4 0.59 perf-profile.children.cycles-pp.udp_rmem_release
> 0.11 7% +0.4 0.52 perf-profile.children.cycles-pp.__sk_mem_reduce_allocated
> 0.00 +0.4 0.43 perf-profile.children.cycles-pp.__wake_up_common_lock
> 0.00 +0.5 0.46 perf-profile.children.cycles-pp.sched_ttwu_pending
> 0.00 +0.5 0.49 perf-profile.children.cycles-pp.sock_def_readable
> 0.00 +0.5 0.53 2% perf-profile.children.cycles-pp.pick_next_task_fair
> 0.00 +0.5 0.54 2% perf-profile.children.cycles-pp.schedule_idle
> 0.00 +0.6 0.55 perf-profile.children.cycles-pp.__flush_smp_call_function_queue
> 0.15 3% +0.6 0.73 2% perf-profile.children.cycles-pp.__sk_mem_raise_allocated
> 0.00 +0.6 0.57 perf-profile.children.cycles-pp.__sysvec_call_function_single
> 0.16 5% +0.6 0.74 2% perf-profile.children.cycles-pp.__sk_mem_schedule
> 0.00 +0.8 0.78 perf-profile.children.cycles-pp.sysvec_call_function_single
> 0.41 3% +0.9 1.33 2% perf-profile.children.cycles-pp.__udp_enqueue_schedule_skb
> 0.00 +1.2 1.16 2% perf-profile.children.cycles-pp.schedule
> 0.00 +1.2 1.21 2% perf-profile.children.cycles-pp.schedule_timeout
> 0.00 +1.3 1.33 2% perf-profile.children.cycles-pp.__skb_wait_for_more_packets
> 0.00 +1.7 1.66 2% perf-profile.children.cycles-pp.__schedule
> 0.27 3% +2.0 2.25 perf-profile.children.cycles-pp.__skb_recv_udp
> 50.41 +2.4 52.81 perf-profile.children.cycles-pp._raw_spin_lock_irqsave
> 0.00 +2.7 2.68 perf-profile.children.cycles-pp.asm_sysvec_call_function_single
> 49.78 +2.7 52.49 perf-profile.children.cycles-pp.native_queued_spin_lock_slowpath
> 0.00 +3.0 2.98 perf-profile.children.cycles-pp.acpi_safe_halt
> 0.00 +3.0 3.00 perf-profile.children.cycles-pp.acpi_idle_enter
> 49.51 +3.1 52.57 perf-profile.children.cycles-pp.send_udp_stream
> 49.50 +3.1 52.56 perf-profile.children.cycles-pp.send_omni_inner
> 0.00 +3.1 3.10 perf-profile.children.cycles-pp.cpuidle_enter_state
> 0.00 +3.1 3.12 perf-profile.children.cycles-pp.cpuidle_enter
> 0.00 +3.4 3.37 perf-profile.children.cycles-pp.cpuidle_idle_call
> 48.90 +3.4 52.30 perf-profile.children.cycles-pp.sendto
> 47.85 +4.0 51.83 perf-profile.children.cycles-pp.__x64_sys_sendto
> 47.73 +4.0 51.77 perf-profile.children.cycles-pp.__sys_sendto
> 0.00 +4.1 4.10 perf-profile.children.cycles-pp.start_secondary
> 0.00 +4.1 4.13 perf-profile.children.cycles-pp.do_idle
> 0.00 +4.1 4.14 perf-profile.children.cycles-pp.secondary_startup_64_no_verify
> 0.00 +4.1 4.14 perf-profile.children.cycles-pp.cpu_startup_entry
> 46.54 +4.7 51.28 perf-profile.children.cycles-pp.sock_sendmsg
> 46.10 +5.0 51.11 perf-profile.children.cycles-pp.udp_sendmsg
> 3.70 +8.0 11.71 perf-profile.children.cycles-pp.copyout
> 3.71 +8.1 11.80 perf-profile.children.cycles-pp._copy_to_iter
> 3.96 +8.5 12.43 perf-profile.children.cycles-pp.__skb_datagram_iter
> 3.96 +8.5 12.44 perf-profile.children.cycles-pp.skb_copy_datagram_iter
> 35.14 +11.3 46.40 perf-profile.children.cycles-pp.ip_make_skb
> 32.71 2% +13.0 45.66 perf-profile.children.cycles-pp.__ip_append_data
> 10.28 +20.6 30.89 perf-profile.children.cycles-pp.sk_page_frag_refill
> 10.25 +20.6 30.88 perf-profile.children.cycles-pp.skb_page_frag_refill
> 9.86 +20.8 30.63 perf-profile.children.cycles-pp.__alloc_pages
> 9.62 +20.8 30.42 perf-profile.children.cycles-pp.get_page_from_freelist
> 8.42 +21.3 29.72 perf-profile.children.cycles-pp.rmqueue
> 6.47 +22.8 29.22 perf-profile.children.cycles-pp.rmqueue_bulk
> 19.11 2% -6.0 13.08 perf-profile.self.cycles-pp.copyin
> 1.81 2% -1.4 0.39 perf-profile.self.cycles-pp.rmqueue
> 1.81 2% -1.3 0.46 2% perf-profile.self.cycles-pp.__ip_select_ident
> 1.47 4% -1.2 0.31 perf-profile.self.cycles-pp.free_unref_page_commit
> 1.29 2% -0.5 0.75 perf-profile.self.cycles-pp.__ip_append_data
> 0.71 -0.4 0.29 perf-profile.self.cycles-pp.udp_sendmsg
> 0.68 2% -0.4 0.32 perf-profile.self.cycles-pp.__zone_watermark_ok
> 0.50 -0.3 0.16 perf-profile.self.cycles-pp.skb_release_data
> 0.59 3% -0.3 0.26 3% perf-profile.self.cycles-pp.fib_table_lookup
> 0.46 4% -0.3 0.15 3% perf-profile.self.cycles-pp.kmem_cache_free
> 0.63 -0.3 0.33 2% perf-profile.self.cycles-pp._raw_spin_lock_irqsave
> 0.47 -0.3 0.19 perf-profile.self.cycles-pp.__sys_sendto
> 0.44 -0.2 0.21 2% perf-profile.self.cycles-pp.kmem_cache_alloc_node
> 0.36 -0.2 0.16 3% perf-profile.self.cycles-pp.send_omni_inner
> 0.35 2% -0.2 0.15 3% perf-profile.self.cycles-pp.ip_finish_output2
> 0.29 -0.2 0.12 perf-profile.self.cycles-pp._copy_from_user
> 0.24 -0.1 0.10 4% perf-profile.self.cycles-pp.__netif_receive_skb_core
> 0.22 2% -0.1 0.08 5% perf-profile.self.cycles-pp.free_unref_page
> 0.19 2% -0.1 0.06 perf-profile.self.cycles-pp.ip_rcv_core
> 0.21 2% -0.1 0.08 perf-profile.self.cycles-pp.__alloc_skb
> 0.20 2% -0.1 0.08 perf-profile.self.cycles-pp.sock_wfree
> 0.22 2% -0.1 0.10 4% perf-profile.self.cycles-pp.send_data
> 0.21 -0.1 0.09 perf-profile.self.cycles-pp.sendto
> 0.21 2% -0.1 0.10 4% perf-profile.self.cycles-pp.ip_rcv_finish_core
> 0.21 2% -0.1 0.09 5% perf-profile.self.cycles-pp.__ip_make_skb
> 0.20 4% -0.1 0.09 5% perf-profile.self.cycles-pp._raw_spin_lock_irq
> 0.21 2% -0.1 0.10 4% perf-profile.self.cycles-pp.__dev_queue_xmit
> 0.38 3% -0.1 0.27 perf-profile.self.cycles-pp.get_page_from_freelist
> 0.20 2% -0.1 0.09 perf-profile.self.cycles-pp.udp_send_skb
> 0.18 2% -0.1 0.07 perf-profile.self.cycles-pp.__udp_enqueue_schedule_skb
> 0.18 4% -0.1 0.08 6% perf-profile.self.cycles-pp.__mkroute_output
> 0.25 -0.1 0.15 3% perf-profile.self.cycles-pp._copy_from_iter
> 0.27 4% -0.1 0.17 2% perf-profile.self.cycles-pp.skb_page_frag_refill
> 0.16 -0.1 0.06 7% perf-profile.self.cycles-pp.sock_sendmsg
> 0.33 2% -0.1 0.24 perf-profile.self.cycles-pp.__slab_free
> 0.15 3% -0.1 0.06 perf-profile.self.cycles-pp.udp4_lib_lookup2
> 0.38 2% -0.1 0.29 2% perf-profile.self.cycles-pp.free_unref_page_prepare
> 0.26 -0.1 0.17 perf-profile.self.cycles-pp._raw_spin_trylock
> 0.15 -0.1 0.06 perf-profile.self.cycles-pp.ip_output
> 0.14 -0.1 0.05 8% perf-profile.self.cycles-pp.process_backlog
> 0.14 -0.1 0.06 perf-profile.self.cycles-pp.ip_route_output_flow
> 0.14 -0.1 0.06 perf-profile.self.cycles-pp.__udp4_lib_lookup
> 0.21 2% -0.1 0.13 3% perf-profile.self.cycles-pp.entry_SYSCALL_64_after_hwframe
> 0.12 3% -0.1 0.05 perf-profile.self.cycles-pp.siphash_3u32
> 0.13 3% -0.1 0.06 8% perf-profile.self.cycles-pp.ip_send_skb
> 0.17 -0.1 0.10 perf-profile.self.cycles-pp.__do_softirq
> 0.15 3% -0.1 0.08 5% perf-profile.self.cycles-pp.skb_set_owner_w
> 0.17 2% -0.1 0.10 4% perf-profile.self.cycles-pp.aa_sk_perm
> 0.12 -0.1 0.05 perf-profile.self.cycles-pp.__x64_sys_sendto
> 0.12 6% -0.1 0.05 perf-profile.self.cycles-pp.fib_lookup_good_nhc
> 0.19 2% -0.1 0.13 perf-profile.self.cycles-pp.__list_add_valid_or_report
> 0.14 3% -0.1 0.07 6% perf-profile.self.cycles-pp.net_rx_action
> 0.16 2% -0.1 0.10 perf-profile.self.cycles-pp.do_syscall_64
> 0.11 -0.1 0.05 perf-profile.self.cycles-pp.__udp4_lib_rcv
> 0.16 3% -0.1 0.10 4% perf-profile.self.cycles-pp.get_pfnblock_flags_mask
> 0.11 4% -0.1 0.05 perf-profile.self.cycles-pp.ip_route_output_key_hash_rcu
> 0.10 4% -0.1 0.05 perf-profile.self.cycles-pp.ip_generic_getfrag
> 0.10 -0.1 0.05 perf-profile.self.cycles-pp.ipv4_mtu
> 0.26 -0.0 0.21 2% perf-profile.self.cycles-pp.__fget_light
> 0.15 3% -0.0 0.11 4% perf-profile.self.cycles-pp.entry_SYSRETQ_unsafe_stack
> 0.24 -0.0 0.20 2% perf-profile.self.cycles-pp.__alloc_pages
> 0.15 3% -0.0 0.12 perf-profile.self.cycles-pp.__check_object_size
> 0.11 -0.0 0.08 6% perf-profile.self.cycles-pp.syscall_return_via_sysret
> 0.08 5% -0.0 0.05 perf-profile.self.cycles-pp.loopback_xmit
> 0.13 -0.0 0.11 4% perf-profile.self.cycles-pp.prep_compound_page
> 0.11 -0.0 0.09 5% perf-profile.self.cycles-pp.irqtime_account_irq
> 0.09 10% -0.0 0.06 7% perf-profile.self.cycles-pp.__xfrm_policy_check2
> 0.07 -0.0 0.05 perf-profile.self.cycles-pp.alloc_pages
> 0.08 -0.0 0.06 7% perf-profile.self.cycles-pp.__entry_text_start
> 0.09 5% -0.0 0.07 perf-profile.self.cycles-pp.free_tail_page_prepare
> 0.10 +0.0 0.11 perf-profile.self.cycles-pp.perf_adjust_freq_unthr_context
> 0.06 +0.0 0.08 6% perf-profile.self.cycles-pp.free_pcppages_bulk
> 0.05 8% +0.0 0.10 4% perf-profile.self.cycles-pp._raw_spin_lock_bh
> 0.07 +0.0 0.12 perf-profile.self.cycles-pp.__mod_zone_page_state
> 0.00 +0.1 0.05 perf-profile.self.cycles-pp.cpuidle_idle_call
> 0.00 +0.1 0.05 perf-profile.self.cycles-pp.udp_rmem_release
> 0.00 +0.1 0.05 perf-profile.self.cycles-pp.__flush_smp_call_function_queue
> 0.00 +0.1 0.05 perf-profile.self.cycles-pp.sock_def_readable
> 0.00 +0.1 0.05 perf-profile.self.cycles-pp.update_cfs_group
> 0.11 11% +0.1 0.17 2% perf-profile.self.cycles-pp._raw_spin_lock
> 0.00 +0.1 0.05 8% perf-profile.self.cycles-pp.finish_task_switch
> 0.00 +0.1 0.05 8% perf-profile.self.cycles-pp.cgroup_rstat_updated
> 0.00 +0.1 0.06 perf-profile.self.cycles-pp.do_idle
> 0.00 +0.1 0.06 perf-profile.self.cycles-pp.__skb_wait_for_more_packets
> 0.00 +0.1 0.06 perf-profile.self.cycles-pp.__x2apic_send_IPI_dest
> 0.00 +0.1 0.06 7% perf-profile.self.cycles-pp.enqueue_entity
> 0.00 +0.1 0.07 7% perf-profile.self.cycles-pp.schedule_timeout
> 0.00 +0.1 0.07 7% perf-profile.self.cycles-pp.move_addr_to_user
> 0.00 +0.1 0.07 7% perf-profile.self.cycles-pp.menu_select
> 0.00 +0.1 0.07 7% perf-profile.self.cycles-pp.native_apic_msr_eoi
> 0.00 +0.1 0.07 7% perf-profile.self.cycles-pp.update_sg_lb_stats
> 0.00 +0.1 0.07 perf-profile.self.cycles-pp.__update_load_avg_se
> 0.00 +0.1 0.07 perf-profile.self.cycles-pp.__get_user_4
> 0.00 +0.1 0.08 6% perf-profile.self.cycles-pp.__sk_mem_reduce_allocated
> 0.00 +0.1 0.08 perf-profile.self.cycles-pp.update_curr
> 0.00 +0.1 0.08 5% perf-profile.self.cycles-pp.__update_load_avg_cfs_rq
> 0.00 +0.1 0.09 5% perf-profile.self.cycles-pp.try_to_wake_up
> 0.00 +0.1 0.09 perf-profile.self.cycles-pp.recvfrom
> 0.00 +0.1 0.09 perf-profile.self.cycles-pp.mem_cgroup_charge_skmem
> 0.00 +0.1 0.09 perf-profile.self.cycles-pp.update_load_avg
> 0.00 +0.1 0.09 5% perf-profile.self.cycles-pp.enqueue_task_fair
> 0.00 +0.1 0.10 4% perf-profile.self.cycles-pp._copy_to_iter
> 0.00 +0.1 0.10 4% perf-profile.self.cycles-pp.newidle_balance
> 0.00 +0.1 0.10 4% perf-profile.self.cycles-pp.recv_data
> 0.00 +0.1 0.10 perf-profile.self.cycles-pp.refill_stock
> 0.00 +0.1 0.10 perf-profile.self.cycles-pp.__switch_to_asm
> 0.00 +0.1 0.11 15% perf-profile.self.cycles-pp._copy_to_user
> 0.00 +0.1 0.12 perf-profile.self.cycles-pp.recv_omni
> 0.00 +0.1 0.12 perf-profile.self.cycles-pp.mem_cgroup_uncharge_skmem
> 0.00 +0.1 0.13 3% perf-profile.self.cycles-pp.native_irq_return_iret
> 0.00 +0.1 0.13 perf-profile.self.cycles-pp.__switch_to
> 0.06 +0.1 0.20 2% perf-profile.self.cycles-pp.rmqueue_bulk
> 0.09 5% +0.1 0.23 4% perf-profile.self.cycles-pp.udp_recvmsg
> 0.00 +0.1 0.14 3% perf-profile.self.cycles-pp.__skb_recv_udp
> 0.00 +0.1 0.14 3% perf-profile.self.cycles-pp.___perf_sw_event
> 0.08 +0.1 0.22 2% perf-profile.self.cycles-pp.__skb_datagram_iter
> 0.03 70% +0.2 0.20 4% perf-profile.self.cycles-pp.page_counter_try_charge
> 0.02 141% +0.2 0.18 4% perf-profile.self.cycles-pp.__sys_recvfrom
> 0.00 +0.2 0.17 2% perf-profile.self.cycles-pp.__schedule
> 0.00 +0.2 0.17 2% perf-profile.self.cycles-pp.try_charge_memcg
> 0.00 +0.2 0.17 2% perf-profile.self.cycles-pp.page_counter_uncharge
> 0.00 +0.2 0.21 2% perf-profile.self.cycles-pp.__sk_mem_raise_allocated
> 0.14 3% +0.2 0.36 perf-profile.self.cycles-pp.__free_one_page
> 0.20 2% +0.3 0.47 perf-profile.self.cycles-pp.__list_del_entry_valid_or_report
> 0.00 +2.1 2.07 2% perf-profile.self.cycles-pp.acpi_safe_halt
> 49.78 +2.7 52.49 perf-profile.self.cycles-pp.native_queued_spin_lock_slowpath
> 3.68 +8.0 11.64 perf-profile.self.cycles-pp.copyout
>
>
>
> Disclaimer:
> Results have been estimated based on internal Intel analysis and are provided
> for informational purposes only. Any difference in system hardware or software
> design or configuration may affect actual performance.
Hello,
kernel test robot noticed a 14.6% improvement of netperf.Throughput_Mbps on:
commit: f5ddc662f07d7d99e9cfc5e07778e26c7394caf8 ("[PATCH -V3 3/9] mm, pcp: reduce lock contention for draining high-order pages")
url: https://github.com/intel-lab-lkp/linux/commits/Huang-Ying/mm-pcp-avoid-to-drain-PCP-when-process-exit/20231017-143633
base: https://git.kernel.org/cgit/linux/kernel/git/gregkh/driver-core.git 36b2d7dd5a8ac95c8c1e69bdc93c4a6e2dc28a23
patch link: https://lore.kernel.org/all/20231016053002.756205-4-ying.huang@intel.com/
patch subject: [PATCH -V3 3/9] mm, pcp: reduce lock contention for draining high-order pages
testcase: netperf
test machine: 128 threads 2 sockets Intel(R) Xeon(R) Gold 6338 CPU @ 2.00GHz (Ice Lake) with 256G memory
parameters:
ip: ipv4
runtime: 300s
nr_threads: 200%
cluster: cs-localhost
send_size: 10K
test: SCTP_STREAM_MANY
cpufreq_governor: performance
Details are as below:
-------------------------------------------------------------------------------------------------->
The kernel config and materials to reproduce are available at:
https://download.01.org/0day-ci/archive/20231027/202310271441.71ce0a9-oliver.sang@intel.com
=========================================================================================
cluster/compiler/cpufreq_governor/ip/kconfig/nr_threads/rootfs/runtime/send_size/tbox_group/test/testcase:
cs-localhost/gcc-12/performance/ipv4/x86_64-rhel-8.3/200%/debian-11.1-x86_64-20220510.cgz/300s/10K/lkp-icl-2sp2/SCTP_STREAM_MANY/netperf
commit:
c828e65251 ("cacheinfo: calculate size of per-CPU data cache slice")
f5ddc662f0 ("mm, pcp: reduce lock contention for draining high-order pages")
c828e65251502516 f5ddc662f07d7d99e9cfc5e0777
---------------- ---------------------------
%stddev %change %stddev
\ | \
26471 -11.1% 23520 uptime.idle
2.098e+10 -14.1% 1.802e+10 cpuidle..time
5.798e+08 +14.3% 6.628e+08 cpuidle..usage
1.329e+09 +14.7% 1.525e+09 numa-numastat.node0.local_node
1.329e+09 +14.7% 1.525e+09 numa-numastat.node0.numa_hit
1.336e+09 +14.6% 1.531e+09 numa-numastat.node1.local_node
1.336e+09 +14.6% 1.531e+09 numa-numastat.node1.numa_hit
1.329e+09 +14.7% 1.525e+09 numa-vmstat.node0.numa_hit
1.329e+09 +14.7% 1.525e+09 numa-vmstat.node0.numa_local
1.336e+09 +14.6% 1.531e+09 numa-vmstat.node1.numa_hit
1.336e+09 +14.6% 1.531e+09 numa-vmstat.node1.numa_local
26.31 ± 12% +33.0% 35.00 ± 10% perf-sched.wait_and_delay.avg.ms.__cond_resched.__kmem_cache_alloc_node.kmalloc_trace.sctp_datamsg_from_user.sctp_sendmsg_to_asoc
229.00 ± 13% -24.7% 172.33 ± 5% perf-sched.wait_and_delay.count.__cond_resched.__kmem_cache_alloc_node.kmalloc_trace.sctp_datamsg_from_user.sctp_sendmsg_to_asoc
929.50 ± 2% +8.2% 1005 ± 4% perf-sched.wait_and_delay.count.exit_to_user_mode_loop.exit_to_user_mode_prepare.syscall_exit_to_user_mode.do_syscall_64
26.30 ± 12% +33.0% 35.00 ± 10% perf-sched.wait_time.avg.ms.__cond_resched.__kmem_cache_alloc_node.kmalloc_trace.sctp_datamsg_from_user.sctp_sendmsg_to_asoc
53.98 -14.1% 46.36 vmstat.cpu.id
58.15 +17.6% 68.37 vmstat.procs.r
3720385 +15.6% 4301904 vmstat.system.cs
1991764 +14.5% 2281507 vmstat.system.in
53.69 -7.7 46.03 mpstat.cpu.all.idle%
2.10 +0.3 2.44 mpstat.cpu.all.irq%
7.25 +1.3 8.58 mpstat.cpu.all.soft%
35.74 +5.7 41.46 mpstat.cpu.all.sys%
1.23 +0.3 1.49 mpstat.cpu.all.usr%
2047040 +2.9% 2105598 proc-vmstat.nr_file_pages
1377160 +4.2% 1435588 proc-vmstat.nr_shmem
2.665e+09 +14.7% 3.056e+09 proc-vmstat.numa_hit
2.665e+09 +14.7% 3.056e+09 proc-vmstat.numa_local
1.534e+10 +14.6% 1.758e+10 proc-vmstat.pgalloc_normal
1.534e+10 +14.6% 1.758e+10 proc-vmstat.pgfree
1296 +16.3% 1507 turbostat.Avg_MHz
49.98 +8.1 58.12 turbostat.Busy%
5.797e+08 +14.3% 6.628e+08 turbostat.C1
53.88 -7.6 46.34 turbostat.C1%
50.02 -16.3% 41.88 turbostat.CPU%c1
6.081e+08 +14.5% 6.961e+08 turbostat.IRQ
391.82 +3.5% 405.41 turbostat.PkgWatt
2204 +14.6% 2527 netperf.ThroughputBoth_Mbps
564378 +14.6% 647027 netperf.ThroughputBoth_total_Mbps
2204 +14.6% 2527 netperf.Throughput_Mbps
564378 +14.6% 647027 netperf.Throughput_total_Mbps
146051 +5.9% 154705 netperf.time.involuntary_context_switches
3011 +16.8% 3516 netperf.time.percent_of_cpu_this_job_got
8875 +16.6% 10351 netperf.time.system_time
221.39 +18.0% 261.14 netperf.time.user_time
2759631 +8.0% 2981144 netperf.time.voluntary_context_switches
2.067e+09 +14.6% 2.369e+09 netperf.workload
2920531 +34.4% 3925407 sched_debug.cfs_rq:/.avg_vruntime.avg
3172407 ± 2% +36.5% 4331807 ± 3% sched_debug.cfs_rq:/.avg_vruntime.max
2801767 +35.2% 3787891 ± 2% sched_debug.cfs_rq:/.avg_vruntime.min
45404 ± 5% +33.3% 60516 ± 11% sched_debug.cfs_rq:/.avg_vruntime.stddev
2817265 ± 10% +40.6% 3961862 sched_debug.cfs_rq:/.left_vruntime.max
376003 ± 18% +51.2% 568331 ± 13% sched_debug.cfs_rq:/.left_vruntime.stddev
2920531 +34.4% 3925407 sched_debug.cfs_rq:/.min_vruntime.avg
3172407 ± 2% +36.5% 4331807 ± 3% sched_debug.cfs_rq:/.min_vruntime.max
2801767 +35.2% 3787891 ± 2% sched_debug.cfs_rq:/.min_vruntime.min
45404 ± 5% +33.3% 60516 ± 11% sched_debug.cfs_rq:/.min_vruntime.stddev
2817265 ± 10% +40.6% 3961862 sched_debug.cfs_rq:/.right_vruntime.max
376003 ± 18% +51.2% 568331 ± 13% sched_debug.cfs_rq:/.right_vruntime.stddev
157.25 ± 6% +13.3% 178.14 ± 4% sched_debug.cfs_rq:/.util_est_enqueued.avg
4361500 +15.5% 5035528 sched_debug.cpu.nr_switches.avg
4674667 +14.7% 5363125 sched_debug.cpu.nr_switches.max
3947619 +14.1% 4504637 ± 2% sched_debug.cpu.nr_switches.min
0.56 -3.7% 0.54 perf-stat.i.MPKI
2.293e+10 +14.3% 2.622e+10 perf-stat.i.branch-instructions
1.449e+08 +15.6% 1.675e+08 perf-stat.i.branch-misses
2.15 -0.1 2.05 perf-stat.i.cache-miss-rate%
67409238 +10.2% 74274510 perf-stat.i.cache-misses
3.199e+09 +15.7% 3.702e+09 perf-stat.i.cache-references
3765045 +15.6% 4353228 perf-stat.i.context-switches
1.42 +1.7% 1.45 perf-stat.i.cpi
1.717e+11 +16.5% 2e+11 perf-stat.i.cpu-cycles
5094 +51.1% 7695 ± 3% perf-stat.i.cpu-migrations
2554 +5.7% 2699 perf-stat.i.cycles-between-cache-misses
3.28e+10 +14.5% 3.756e+10 perf-stat.i.dTLB-loads
329792 ± 11% +37.3% 452936 ± 15% perf-stat.i.dTLB-store-misses
2.04e+10 +14.7% 2.339e+10 perf-stat.i.dTLB-stores
1.205e+11 +14.4% 1.379e+11 perf-stat.i.instructions
0.71 -1.7% 0.69 perf-stat.i.ipc
1.34 +16.5% 1.56 perf-stat.i.metric.GHz
221.29 +7.4% 237.74 perf-stat.i.metric.K/sec
619.67 +14.5% 709.77 perf-stat.i.metric.M/sec
7031738 +14.3% 8034255 perf-stat.i.node-load-misses
79.94 -1.3 78.62 perf-stat.i.node-store-miss-rate%
3349862 ± 2% +9.2% 3656880 perf-stat.i.node-stores
0.56 -3.7% 0.54 perf-stat.overall.MPKI
2.11 -0.1 2.01 perf-stat.overall.cache-miss-rate%
1.42 +1.8% 1.45 perf-stat.overall.cpi
2546 +5.7% 2692 perf-stat.overall.cycles-between-cache-misses
0.70 -1.8% 0.69 perf-stat.overall.ipc
79.91 -1.4 78.54 perf-stat.overall.node-store-miss-rate%
2.286e+10 +14.3% 2.614e+10 perf-stat.ps.branch-instructions
1.444e+08 +15.6% 1.669e+08 perf-stat.ps.branch-misses
67192773 +10.2% 74037940 perf-stat.ps.cache-misses
3.189e+09 +15.7% 3.69e+09 perf-stat.ps.cache-references
3753095 +15.6% 4339552 perf-stat.ps.context-switches
1.711e+11 +16.5% 1.994e+11 perf-stat.ps.cpu-cycles
5078 +51.1% 7674 ± 3% perf-stat.ps.cpu-migrations
3.269e+10 +14.5% 3.743e+10 perf-stat.ps.dTLB-loads
328489 ± 11% +37.3% 451131 ± 15% perf-stat.ps.dTLB-store-misses
2.033e+10 +14.7% 2.331e+10 perf-stat.ps.dTLB-stores
1.201e+11 +14.4% 1.374e+11 perf-stat.ps.instructions
7009249 +14.3% 8009170 perf-stat.ps.node-load-misses
3339511 ± 2% +9.2% 3645997 perf-stat.ps.node-stores
3.635e+13 +14.3% 4.155e+13 perf-stat.total.instructions
4.40 ± 2% -1.5 2.87 perf-profile.calltrace.cycles-pp.skb_release_data.kfree_skb_reason.sctp_recvmsg.inet_recvmsg.sock_recvmsg
5.83 -1.4 4.41 perf-profile.calltrace.cycles-pp.kfree_skb_reason.sctp_recvmsg.inet_recvmsg.sock_recvmsg.____sys_recvmsg
1.92 ± 3% -1.4 0.55 perf-profile.calltrace.cycles-pp.free_unref_page.skb_release_data.kfree_skb_reason.sctp_recvmsg.inet_recvmsg
22.33 -1.3 21.03 perf-profile.calltrace.cycles-pp.sctp_recvmsg.inet_recvmsg.sock_recvmsg.____sys_recvmsg.___sys_recvmsg
22.42 -1.3 21.12 perf-profile.calltrace.cycles-pp.inet_recvmsg.sock_recvmsg.____sys_recvmsg.___sys_recvmsg.__sys_recvmsg
22.75 -1.3 21.48 perf-profile.calltrace.cycles-pp.sock_recvmsg.____sys_recvmsg.___sys_recvmsg.__sys_recvmsg.do_syscall_64
23.44 -1.2 22.20 perf-profile.calltrace.cycles-pp.____sys_recvmsg.___sys_recvmsg.__sys_recvmsg.do_syscall_64.entry_SYSCALL_64_after_hwframe
24.65 -1.2 23.47 perf-profile.calltrace.cycles-pp.___sys_recvmsg.__sys_recvmsg.do_syscall_64.entry_SYSCALL_64_after_hwframe.recvmsg
25.14 -1.2 23.98 perf-profile.calltrace.cycles-pp.__sys_recvmsg.do_syscall_64.entry_SYSCALL_64_after_hwframe.recvmsg
25.46 -1.1 24.31 perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.recvmsg
25.59 -1.1 24.46 perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.recvmsg
26.47 -1.1 25.36 perf-profile.calltrace.cycles-pp.recvmsg
3.57 ± 6% -0.6 2.93 ± 9% perf-profile.calltrace.cycles-pp.rmqueue.get_page_from_freelist.__alloc_pages.__kmalloc_large_node.__kmalloc_node_track_caller
5.22 ± 2% -0.4 4.79 perf-profile.calltrace.cycles-pp.__alloc_pages.__kmalloc_large_node.__kmalloc_node_track_caller.kmalloc_reserve.__alloc_skb
4.76 ± 2% -0.4 4.33 perf-profile.calltrace.cycles-pp.get_page_from_freelist.__alloc_pages.__kmalloc_large_node.__kmalloc_node_track_caller.kmalloc_reserve
0.96 -0.4 0.59 ± 2% perf-profile.calltrace.cycles-pp.release_sock.sctp_recvmsg.inet_recvmsg.sock_recvmsg.____sys_recvmsg
3.16 ± 2% -0.3 2.84 perf-profile.calltrace.cycles-pp.__kmalloc_node_track_caller.kmalloc_reserve.__alloc_skb.sctp_packet_transmit.sctp_outq_flush
3.14 ± 2% -0.3 2.82 perf-profile.calltrace.cycles-pp.__kmalloc_large_node.__kmalloc_node_track_caller.kmalloc_reserve.__alloc_skb.sctp_packet_transmit
3.18 ± 2% -0.3 2.86 perf-profile.calltrace.cycles-pp.kmalloc_reserve.__alloc_skb.sctp_packet_transmit.sctp_outq_flush.sctp_cmd_interpreter
3.44 ± 2% -0.3 3.13 perf-profile.calltrace.cycles-pp.__alloc_skb.sctp_packet_transmit.sctp_outq_flush.sctp_cmd_interpreter.sctp_do_sm
1.62 ± 3% -0.3 1.34 ± 2% perf-profile.calltrace.cycles-pp._raw_spin_lock_irqsave.rmqueue.get_page_from_freelist.__alloc_pages.__kmalloc_large_node
1.49 ± 3% -0.3 1.22 ± 3% perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock_irqsave.rmqueue.get_page_from_freelist.__alloc_pages
1.46 ± 2% -0.2 1.25 ± 2% perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock_irqsave.__free_pages_ok.skb_release_data.kfree_skb_reason
1.62 ± 2% -0.2 1.43 ± 2% perf-profile.calltrace.cycles-pp._raw_spin_lock_irqsave.__free_pages_ok.skb_release_data.kfree_skb_reason.sctp_recvmsg
1.99 ± 2% -0.2 1.80 perf-profile.calltrace.cycles-pp.__free_pages_ok.skb_release_data.kfree_skb_reason.sctp_recvmsg.inet_recvmsg
0.76 -0.2 0.58 perf-profile.calltrace.cycles-pp.asm_sysvec_apic_timer_interrupt.acpi_safe_halt.acpi_idle_enter.cpuidle_enter_state.cpuidle_enter
0.85 -0.1 0.74 perf-profile.calltrace.cycles-pp.__slab_free.sctp_recvmsg.inet_recvmsg.sock_recvmsg.____sys_recvmsg
0.84 -0.1 0.73 perf-profile.calltrace.cycles-pp.free_unref_page_commit.free_unref_page.skb_release_data.consume_skb.sctp_chunk_put
1.37 -0.1 1.28 perf-profile.calltrace.cycles-pp.free_unref_page.skb_release_data.consume_skb.sctp_chunk_put.sctp_outq_sack
2.65 -0.1 2.57 perf-profile.calltrace.cycles-pp.kmalloc_reserve.__alloc_skb._sctp_make_chunk.sctp_make_datafrag_empty.sctp_datamsg_from_user
2.56 -0.1 2.48 perf-profile.calltrace.cycles-pp.__kmalloc_node_track_caller.kmalloc_reserve.__alloc_skb._sctp_make_chunk.sctp_make_datafrag_empty
2.49 ± 2% -0.1 2.42 perf-profile.calltrace.cycles-pp.__kmalloc_large_node.__kmalloc_node_track_caller.kmalloc_reserve.__alloc_skb._sctp_make_chunk
1.92 -0.1 1.85 perf-profile.calltrace.cycles-pp.skb_release_data.consume_skb.sctp_chunk_put.sctp_outq_sack.sctp_cmd_interpreter
0.62 +0.0 0.64 perf-profile.calltrace.cycles-pp.simple_copy_to_iter.__skb_datagram_iter.skb_copy_datagram_iter.sctp_recvmsg.inet_recvmsg
0.65 +0.0 0.68 perf-profile.calltrace.cycles-pp.sctp_chunk_put.sctp_ulpevent_free.sctp_recvmsg.inet_recvmsg.sock_recvmsg
0.89 +0.0 0.93 perf-profile.calltrace.cycles-pp.copy_msghdr_from_user.___sys_recvmsg.__sys_recvmsg.do_syscall_64.entry_SYSCALL_64_after_hwframe
1.24 +0.0 1.28 perf-profile.calltrace.cycles-pp.try_to_wake_up.autoremove_wake_function.__wake_up_common.__wake_up_common_lock.sctp_data_ready
0.56 ± 2% +0.0 0.60 perf-profile.calltrace.cycles-pp.sctp_packet_config.sctp_outq_select_transport.sctp_outq_flush_data.sctp_outq_flush.sctp_cmd_interpreter
1.32 +0.0 1.36 perf-profile.calltrace.cycles-pp.autoremove_wake_function.__wake_up_common.__wake_up_common_lock.sctp_data_ready.sctp_ulpq_tail_event
1.29 +0.0 1.33 perf-profile.calltrace.cycles-pp.sctp_ulpevent_free.sctp_recvmsg.inet_recvmsg.sock_recvmsg.____sys_recvmsg
0.71 ± 2% +0.0 0.75 perf-profile.calltrace.cycles-pp.sctp_outq_select_transport.sctp_outq_flush_data.sctp_outq_flush.sctp_cmd_interpreter.sctp_do_sm
0.61 +0.0 0.66 perf-profile.calltrace.cycles-pp.dequeue_entity.dequeue_task_fair.__schedule.schedule.schedule_timeout
0.62 +0.1 0.67 perf-profile.calltrace.cycles-pp.enqueue_entity.enqueue_task_fair.activate_task.ttwu_do_activate.sched_ttwu_pending
1.50 +0.1 1.56 perf-profile.calltrace.cycles-pp.__wake_up_common.__wake_up_common_lock.sctp_data_ready.sctp_ulpq_tail_event.sctp_ulpq_tail_data
1.58 +0.1 1.64 perf-profile.calltrace.cycles-pp.__wake_up_common_lock.sctp_data_ready.sctp_ulpq_tail_event.sctp_ulpq_tail_data.sctp_cmd_interpreter
0.70 +0.1 0.76 perf-profile.calltrace.cycles-pp.dequeue_task_fair.__schedule.schedule.schedule_timeout.sctp_skb_recv_datagram
1.02 +0.1 1.08 perf-profile.calltrace.cycles-pp.ttwu_do_activate.sched_ttwu_pending.__flush_smp_call_function_queue.__sysvec_call_function_single.sysvec_call_function_single
2.02 +0.1 2.09 perf-profile.calltrace.cycles-pp.sctp_outq_flush_data.sctp_outq_flush.sctp_cmd_interpreter.sctp_do_sm.sctp_primitive_SEND
1.86 +0.1 1.93 perf-profile.calltrace.cycles-pp.sctp_data_ready.sctp_ulpq_tail_event.sctp_ulpq_tail_data.sctp_cmd_interpreter.sctp_do_sm
0.76 +0.1 0.83 perf-profile.calltrace.cycles-pp.activate_task.ttwu_do_activate.sched_ttwu_pending.__flush_smp_call_function_queue.__sysvec_call_function_single
0.73 +0.1 0.80 perf-profile.calltrace.cycles-pp.enqueue_task_fair.activate_task.ttwu_do_activate.sched_ttwu_pending.__flush_smp_call_function_queue
0.89 +0.1 0.96 perf-profile.calltrace.cycles-pp.__schedule.schedule_idle.do_idle.cpu_startup_entry.start_secondary
0.82 +0.1 0.89 perf-profile.calltrace.cycles-pp.__sk_mem_reduce_allocated.sctp_wfree.skb_release_head_state.consume_skb.sctp_chunk_put
0.95 +0.1 1.03 perf-profile.calltrace.cycles-pp.schedule_idle.do_idle.cpu_startup_entry.start_secondary.secondary_startup_64_no_verify
2.06 +0.1 2.14 perf-profile.calltrace.cycles-pp.sctp_ulpq_tail_event.sctp_ulpq_tail_data.sctp_cmd_interpreter.sctp_do_sm.sctp_assoc_bh_rcv
3.68 +0.1 3.76 perf-profile.calltrace.cycles-pp.copyin._copy_from_iter.sctp_user_addto_chunk.sctp_datamsg_from_user.sctp_sendmsg_to_asoc
0.98 +0.1 1.06 perf-profile.calltrace.cycles-pp.__sk_mem_reduce_allocated.skb_release_head_state.kfree_skb_reason.sctp_recvmsg.inet_recvmsg
1.34 +0.1 1.43 perf-profile.calltrace.cycles-pp.sched_ttwu_pending.__flush_smp_call_function_queue.__sysvec_call_function_single.sysvec_call_function_single.asm_sysvec_call_function_single
1.38 +0.1 1.47 perf-profile.calltrace.cycles-pp.sctp_wfree.skb_release_head_state.consume_skb.sctp_chunk_put.sctp_outq_sack
1.54 +0.1 1.63 perf-profile.calltrace.cycles-pp.skb_release_head_state.consume_skb.sctp_chunk_put.sctp_outq_sack.sctp_cmd_interpreter
1.25 ± 2% +0.1 1.35 perf-profile.calltrace.cycles-pp.__sk_mem_raise_allocated.__sk_mem_schedule.sctp_sendmsg_to_asoc.sctp_sendmsg.sock_sendmsg
1.28 ± 2% +0.1 1.38 perf-profile.calltrace.cycles-pp.__sk_mem_schedule.sctp_sendmsg_to_asoc.sctp_sendmsg.sock_sendmsg.____sys_sendmsg
1.82 +0.1 1.93 perf-profile.calltrace.cycles-pp.__flush_smp_call_function_queue.__sysvec_call_function_single.sysvec_call_function_single.asm_sysvec_call_function_single.acpi_safe_halt
2.00 +0.1 2.11 perf-profile.calltrace.cycles-pp.__sysvec_call_function_single.sysvec_call_function_single.asm_sysvec_call_function_single.acpi_safe_halt.acpi_idle_enter
1.39 +0.1 1.50 perf-profile.calltrace.cycles-pp.skb_release_head_state.kfree_skb_reason.sctp_recvmsg.inet_recvmsg.sock_recvmsg
4.39 +0.1 4.51 perf-profile.calltrace.cycles-pp.acpi_safe_halt.acpi_idle_enter.cpuidle_enter_state.cpuidle_enter.cpuidle_idle_call
2.68 +0.2 2.84 perf-profile.calltrace.cycles-pp.sysvec_call_function_single.asm_sysvec_call_function_single.acpi_safe_halt.acpi_idle_enter.cpuidle_enter_state
2.98 +0.2 3.14 perf-profile.calltrace.cycles-pp.sctp_ulpevent_make_rcvmsg.sctp_ulpq_tail_data.sctp_cmd_interpreter.sctp_do_sm.sctp_assoc_bh_rcv
1.88 +0.2 2.06 perf-profile.calltrace.cycles-pp.__schedule.schedule.schedule_timeout.sctp_skb_recv_datagram.sctp_recvmsg
0.34 ± 70% +0.2 0.54 perf-profile.calltrace.cycles-pp.pick_next_task_fair.__schedule.schedule.schedule_timeout.sctp_skb_recv_datagram
10.32 +0.2 10.53 perf-profile.calltrace.cycles-pp.sctp_do_sm.sctp_primitive_SEND.sctp_sendmsg_to_asoc.sctp_sendmsg.sock_sendmsg
3.60 +0.2 3.81 perf-profile.calltrace.cycles-pp.sctp_skb_recv_datagram.sctp_recvmsg.inet_recvmsg.sock_recvmsg.____sys_recvmsg
1.94 +0.2 2.14 perf-profile.calltrace.cycles-pp.schedule.schedule_timeout.sctp_skb_recv_datagram.sctp_recvmsg.inet_recvmsg
2.20 +0.2 2.41 perf-profile.calltrace.cycles-pp.schedule_timeout.sctp_skb_recv_datagram.sctp_recvmsg.inet_recvmsg.sock_recvmsg
10.93 +0.2 11.16 perf-profile.calltrace.cycles-pp.acpi_idle_enter.cpuidle_enter_state.cpuidle_enter.cpuidle_idle_call.do_idle
10.51 +0.2 10.74 perf-profile.calltrace.cycles-pp.sctp_cmd_interpreter.sctp_do_sm.sctp_primitive_SEND.sctp_sendmsg_to_asoc.sctp_sendmsg
7.26 +0.2 7.50 perf-profile.calltrace.cycles-pp.copyout._copy_to_iter.__skb_datagram_iter.skb_copy_datagram_iter.sctp_recvmsg
11.17 +0.2 11.42 perf-profile.calltrace.cycles-pp.cpuidle_enter_state.cpuidle_enter.cpuidle_idle_call.do_idle.cpu_startup_entry
5.40 +0.2 5.64 perf-profile.calltrace.cycles-pp.sctp_ulpq_tail_data.sctp_cmd_interpreter.sctp_do_sm.sctp_assoc_bh_rcv.sctp_rcv
11.25 +0.2 11.50 perf-profile.calltrace.cycles-pp.cpuidle_enter.cpuidle_idle_call.do_idle.cpu_startup_entry.start_secondary
7.38 +0.3 7.64 perf-profile.calltrace.cycles-pp._copy_to_iter.__skb_datagram_iter.skb_copy_datagram_iter.sctp_recvmsg.inet_recvmsg
20.03 +0.3 20.29 perf-profile.calltrace.cycles-pp.sctp_backlog_rcv.__release_sock.release_sock.sctp_sendmsg.sock_sendmsg
20.09 +0.3 20.36 perf-profile.calltrace.cycles-pp.__release_sock.release_sock.sctp_sendmsg.sock_sendmsg.____sys_sendmsg
20.30 +0.3 20.57 perf-profile.calltrace.cycles-pp.release_sock.sctp_sendmsg.sock_sendmsg.____sys_sendmsg.___sys_sendmsg
8.40 +0.3 8.68 perf-profile.calltrace.cycles-pp.__skb_datagram_iter.skb_copy_datagram_iter.sctp_recvmsg.inet_recvmsg.sock_recvmsg
8.44 +0.3 8.72 perf-profile.calltrace.cycles-pp.skb_copy_datagram_iter.sctp_recvmsg.inet_recvmsg.sock_recvmsg.____sys_recvmsg
11.85 +0.3 12.14 perf-profile.calltrace.cycles-pp.cpuidle_idle_call.do_idle.cpu_startup_entry.start_secondary.secondary_startup_64_no_verify
11.22 +0.3 11.52 perf-profile.calltrace.cycles-pp.sctp_packet_transmit.sctp_outq_flush.sctp_cmd_interpreter.sctp_do_sm.sctp_primitive_SEND
13.26 +0.3 13.61 perf-profile.calltrace.cycles-pp.sctp_outq_flush.sctp_cmd_interpreter.sctp_do_sm.sctp_primitive_SEND.sctp_sendmsg_to_asoc
13.21 +0.4 13.59 perf-profile.calltrace.cycles-pp.do_idle.cpu_startup_entry.start_secondary.secondary_startup_64_no_verify
13.25 +0.4 13.64 perf-profile.calltrace.cycles-pp.start_secondary.secondary_startup_64_no_verify
13.24 +0.4 13.62 perf-profile.calltrace.cycles-pp.cpu_startup_entry.start_secondary.secondary_startup_64_no_verify
13.34 +0.4 13.74 perf-profile.calltrace.cycles-pp.secondary_startup_64_no_verify
15.70 +0.4 16.12 perf-profile.calltrace.cycles-pp.sctp_primitive_SEND.sctp_sendmsg_to_asoc.sctp_sendmsg.sock_sendmsg.____sys_sendmsg
0.55 +0.5 1.02 ± 19% perf-profile.calltrace.cycles-pp.__sk_mem_raise_allocated.__sk_mem_schedule.sctp_ulpevent_make_rcvmsg.sctp_ulpq_tail_data.sctp_cmd_interpreter
0.66 ± 28% +0.5 1.14 perf-profile.calltrace.cycles-pp.__sk_mem_schedule.sctp_ulpevent_make_rcvmsg.sctp_ulpq_tail_data.sctp_cmd_interpreter.sctp_do_sm
0.00 +0.5 0.54 perf-profile.calltrace.cycles-pp.sctp_sf_eat_data_6_2.sctp_do_sm.sctp_assoc_bh_rcv.sctp_rcv.ip_protocol_deliver_rcu
51.26 +0.5 51.80 perf-profile.calltrace.cycles-pp.sctp_sendmsg.sock_sendmsg.____sys_sendmsg.___sys_sendmsg.__sys_sendmsg
15.28 +0.5 15.82 perf-profile.calltrace.cycles-pp.asm_sysvec_call_function_single.acpi_safe_halt.acpi_idle_enter.cpuidle_enter_state.cpuidle_enter
51.76 +0.6 52.32 perf-profile.calltrace.cycles-pp.sock_sendmsg.____sys_sendmsg.___sys_sendmsg.__sys_sendmsg.do_syscall_64
53.77 +0.6 54.34 perf-profile.calltrace.cycles-pp.____sys_sendmsg.___sys_sendmsg.__sys_sendmsg.do_syscall_64.entry_SYSCALL_64_after_hwframe
6.06 ± 2% -2.4 3.68 perf-profile.children.cycles-pp.native_queued_spin_lock_slowpath
5.94 ± 2% -2.2 3.75 perf-profile.children.cycles-pp._raw_spin_lock_irqsave
6.84 -1.9 4.97 perf-profile.children.cycles-pp.skb_release_data
3.64 -1.7 1.92 perf-profile.children.cycles-pp.free_unref_page
2.04 ± 2% -1.7 0.34 ± 2% perf-profile.children.cycles-pp.free_pcppages_bulk
5.84 -1.4 4.42 perf-profile.children.cycles-pp.kfree_skb_reason
22.43 -1.3 21.14 perf-profile.children.cycles-pp.inet_recvmsg
22.67 -1.3 21.39 perf-profile.children.cycles-pp.sctp_recvmsg
22.76 -1.3 21.50 perf-profile.children.cycles-pp.sock_recvmsg
23.46 -1.2 22.22 perf-profile.children.cycles-pp.____sys_recvmsg
24.68 -1.2 23.50 perf-profile.children.cycles-pp.___sys_recvmsg
25.16 -1.2 24.00 perf-profile.children.cycles-pp.__sys_recvmsg
26.69 -1.1 25.59 perf-profile.children.cycles-pp.recvmsg
82.77 -0.5 82.24 perf-profile.children.cycles-pp.do_syscall_64
83.14 -0.5 82.63 perf-profile.children.cycles-pp.entry_SYSCALL_64_after_hwframe
5.02 -0.5 4.53 perf-profile.children.cycles-pp.get_page_from_freelist
5.46 -0.5 4.98 perf-profile.children.cycles-pp.__alloc_pages
5.96 -0.5 5.50 perf-profile.children.cycles-pp.__kmalloc_node_track_caller
6.21 -0.5 5.76 perf-profile.children.cycles-pp.kmalloc_reserve
3.86 -0.5 3.41 perf-profile.children.cycles-pp.rmqueue
5.88 -0.5 5.44 perf-profile.children.cycles-pp.__kmalloc_large_node
7.47 -0.4 7.07 perf-profile.children.cycles-pp.__alloc_skb
0.65 ± 3% -0.3 0.30 ± 5% perf-profile.children.cycles-pp.sctp_wait_for_sndbuf
1.91 -0.3 1.58 perf-profile.children.cycles-pp._raw_spin_lock_bh
1.78 -0.3 1.46 perf-profile.children.cycles-pp.lock_sock_nested
4.43 -0.2 4.22 perf-profile.children.cycles-pp.consume_skb
6.00 -0.2 5.80 perf-profile.children.cycles-pp.sctp_outq_sack
5.82 -0.2 5.62 perf-profile.children.cycles-pp.sctp_chunk_put
2.00 ± 2% -0.2 1.82 ± 2% perf-profile.children.cycles-pp.__free_pages_ok
1.20 -0.2 1.04 perf-profile.children.cycles-pp.asm_sysvec_apic_timer_interrupt
1.27 -0.1 1.16 perf-profile.children.cycles-pp.__slab_free
0.39 -0.1 0.32 ± 2% perf-profile.children.cycles-pp.__free_one_page
0.86 ± 2% -0.1 0.79 perf-profile.children.cycles-pp.sysvec_apic_timer_interrupt
0.42 -0.1 0.36 ± 2% perf-profile.children.cycles-pp.__zone_watermark_ok
0.45 ± 2% -0.1 0.40 ± 2% perf-profile.children.cycles-pp.rmqueue_bulk
0.54 -0.0 0.51 perf-profile.children.cycles-pp.__list_add_valid_or_report
0.65 ± 2% -0.0 0.62 perf-profile.children.cycles-pp.__sysvec_apic_timer_interrupt
0.47 ± 2% -0.0 0.44 ± 2% perf-profile.children.cycles-pp.__kmalloc
0.25 ± 3% -0.0 0.22 ± 2% perf-profile.children.cycles-pp.__irq_exit_rcu
0.24 ± 4% -0.0 0.22 ± 3% perf-profile.children.cycles-pp.perf_event_task_tick
0.24 ± 3% -0.0 0.22 ± 3% perf-profile.children.cycles-pp.perf_adjust_freq_unthr_context
0.15 ± 5% -0.0 0.13 ± 4% perf-profile.children.cycles-pp.__intel_pmu_enable_all
0.11 ± 4% -0.0 0.09 ± 5% perf-profile.children.cycles-pp.sctp_assoc_rwnd_increase
0.06 +0.0 0.07 perf-profile.children.cycles-pp.ct_idle_exit
0.12 ± 3% +0.0 0.13 ± 2% perf-profile.children.cycles-pp.get_pfnblock_flags_mask
0.42 +0.0 0.44 perf-profile.children.cycles-pp.free_unref_page_prepare
0.14 ± 2% +0.0 0.16 ± 3% perf-profile.children.cycles-pp.check_stack_object
0.13 ± 2% +0.0 0.15 ± 3% perf-profile.children.cycles-pp.__mod_lruvec_page_state
0.27 +0.0 0.28 perf-profile.children.cycles-pp.update_curr
0.22 +0.0 0.24 ± 2% perf-profile.children.cycles-pp.__switch_to_asm
0.16 ± 2% +0.0 0.18 ± 3% perf-profile.children.cycles-pp.__update_load_avg_se
0.29 ± 2% +0.0 0.30 perf-profile.children.cycles-pp.sctp_outq_flush_ctrl
0.42 +0.0 0.44 perf-profile.children.cycles-pp.free_large_kmalloc
0.13 ± 2% +0.0 0.15 ± 7% perf-profile.children.cycles-pp.update_cfs_group
0.40 +0.0 0.42 ± 2% perf-profile.children.cycles-pp.loopback_xmit
0.24 ± 3% +0.0 0.26 ± 2% perf-profile.children.cycles-pp.__update_load_avg_cfs_rq
0.45 +0.0 0.47 perf-profile.children.cycles-pp.dev_hard_start_xmit
0.20 +0.0 0.23 ± 3% perf-profile.children.cycles-pp.set_next_entity
0.63 +0.0 0.65 perf-profile.children.cycles-pp.simple_copy_to_iter
0.13 ± 3% +0.0 0.15 ± 3% perf-profile.children.cycles-pp.sk_leave_memory_pressure
0.30 +0.0 0.32 ± 2% perf-profile.children.cycles-pp.sctp_inet_skb_msgname
0.54 ± 2% +0.0 0.57 ± 2% perf-profile.children.cycles-pp.__copy_skb_header
0.31 +0.0 0.34 perf-profile.children.cycles-pp.___perf_sw_event
0.27 ± 3% +0.0 0.30 ± 2% perf-profile.children.cycles-pp.security_socket_recvmsg
0.24 ± 3% +0.0 0.26 perf-profile.children.cycles-pp.ipv4_dst_check
0.42 ± 2% +0.0 0.44 ± 3% perf-profile.children.cycles-pp.page_counter_try_charge
1.30 +0.0 1.33 perf-profile.children.cycles-pp.try_to_wake_up
0.42 +0.0 0.45 perf-profile.children.cycles-pp.__mod_node_page_state
0.79 +0.0 0.82 perf-profile.children.cycles-pp.__skb_clone
0.44 +0.0 0.48 perf-profile.children.cycles-pp.aa_sk_perm
0.30 +0.0 0.33 ± 4% perf-profile.children.cycles-pp.accept_connection
0.30 +0.0 0.33 ± 4% perf-profile.children.cycles-pp.spawn_child
0.30 +0.0 0.33 ± 4% perf-profile.children.cycles-pp.process_requests
0.36 +0.0 0.40 perf-profile.children.cycles-pp.prepare_task_switch
0.28 ± 2% +0.0 0.31 ± 5% perf-profile.children.cycles-pp.recv_sctp_stream_1toMany
0.66 +0.0 0.70 perf-profile.children.cycles-pp.sctp_addrs_lookup_transport
0.69 +0.0 0.72 perf-profile.children.cycles-pp.__sctp_rcv_lookup
0.39 ± 3% +0.0 0.43 perf-profile.children.cycles-pp.dst_release
1.36 +0.0 1.40 perf-profile.children.cycles-pp.autoremove_wake_function
0.77 +0.0 0.81 perf-profile.children.cycles-pp.kmem_cache_alloc_node
1.31 +0.0 1.35 perf-profile.children.cycles-pp.sctp_ulpevent_free
0.92 +0.0 0.96 perf-profile.children.cycles-pp.try_charge_memcg
0.64 +0.0 0.69 perf-profile.children.cycles-pp.dequeue_entity
0.83 +0.0 0.88 perf-profile.children.cycles-pp.sctp_packet_config
2.48 +0.0 2.53 perf-profile.children.cycles-pp.copy_msghdr_from_user
0.61 ± 3% +0.1 0.66 ± 2% perf-profile.children.cycles-pp.mem_cgroup_uncharge_skmem
0.66 +0.1 0.71 perf-profile.children.cycles-pp.enqueue_entity
1.56 +0.1 1.61 perf-profile.children.cycles-pp.__wake_up_common
1.39 +0.1 1.45 perf-profile.children.cycles-pp.kmem_cache_free
1.02 ± 2% +0.1 1.08 perf-profile.children.cycles-pp.sctp_outq_select_transport
0.00 +0.1 0.06 ± 9% perf-profile.children.cycles-pp.pick_next_task_idle
1.64 +0.1 1.70 perf-profile.children.cycles-pp.__wake_up_common_lock
0.86 ± 3% +0.1 0.92 perf-profile.children.cycles-pp.pick_next_task_fair
0.58 +0.1 0.64 perf-profile.children.cycles-pp.update_load_avg
1.56 +0.1 1.62 perf-profile.children.cycles-pp.__check_object_size
0.71 +0.1 0.77 perf-profile.children.cycles-pp.dequeue_task_fair
0.86 +0.1 0.93 perf-profile.children.cycles-pp.sctp_eat_data
1.92 +0.1 1.99 perf-profile.children.cycles-pp.sctp_data_ready
1.05 +0.1 1.12 perf-profile.children.cycles-pp.ttwu_do_activate
0.26 ± 32% +0.1 0.33 ± 4% perf-profile.children.cycles-pp.accept_connections
2.16 +0.1 2.22 perf-profile.children.cycles-pp.sctp_ulpq_tail_event
0.76 +0.1 0.83 perf-profile.children.cycles-pp.enqueue_task_fair
0.78 +0.1 0.86 perf-profile.children.cycles-pp.activate_task
0.98 +0.1 1.05 perf-profile.children.cycles-pp.sctp_sf_eat_data_6_2
0.97 +0.1 1.04 perf-profile.children.cycles-pp.schedule_idle
3.22 +0.1 3.30 perf-profile.children.cycles-pp.sctp_outq_flush_data
1.78 +0.1 1.85 perf-profile.children.cycles-pp.mem_cgroup_charge_skmem
1.48 +0.1 1.56 perf-profile.children.cycles-pp.sctp_wfree
1.38 +0.1 1.46 perf-profile.children.cycles-pp.sched_ttwu_pending
3.80 +0.1 3.89 perf-profile.children.cycles-pp.copyin
3.92 +0.1 4.00 perf-profile.children.cycles-pp._copy_from_iter
10.14 +0.1 10.24 perf-profile.children.cycles-pp.sctp_datamsg_from_user
1.87 +0.1 1.97 perf-profile.children.cycles-pp.__flush_smp_call_function_queue
4.48 +0.1 4.59 perf-profile.children.cycles-pp.sctp_user_addto_chunk
2.04 +0.1 2.15 perf-profile.children.cycles-pp.__sysvec_call_function_single
6.96 +0.1 7.09 perf-profile.children.cycles-pp.__memcpy
7.57 +0.1 7.71 perf-profile.children.cycles-pp.sctp_packet_pack
3.20 +0.1 3.34 perf-profile.children.cycles-pp.sctp_ulpevent_make_rcvmsg
1.85 +0.2 2.00 perf-profile.children.cycles-pp.__sk_mem_reduce_allocated
12.41 +0.2 12.56 perf-profile.children.cycles-pp.sctp_rcv
2.74 +0.2 2.90 perf-profile.children.cycles-pp.sysvec_call_function_single
2.41 +0.2 2.57 perf-profile.children.cycles-pp.__sk_mem_raise_allocated
2.48 +0.2 2.65 perf-profile.children.cycles-pp.__sk_mem_schedule
13.86 +0.2 14.04 perf-profile.children.cycles-pp.__do_softirq
13.28 +0.2 13.45 perf-profile.children.cycles-pp.process_backlog
13.31 +0.2 13.49 perf-profile.children.cycles-pp.__napi_poll
13.45 +0.2 13.63 perf-profile.children.cycles-pp.net_rx_action
2.04 +0.2 2.21 perf-profile.children.cycles-pp.schedule
2.28 +0.2 2.46 perf-profile.children.cycles-pp.schedule_timeout
12.53 +0.2 12.71 perf-profile.children.cycles-pp.ip_local_deliver_finish
13.05 +0.2 13.23 perf-profile.children.cycles-pp.__netif_receive_skb_one_core
12.51 +0.2 12.69 perf-profile.children.cycles-pp.ip_protocol_deliver_rcu
29.73 +0.2 29.92 perf-profile.children.cycles-pp.sctp_outq_flush
3.63 +0.2 3.84 perf-profile.children.cycles-pp.sctp_skb_recv_datagram
13.78 +0.2 13.98 perf-profile.children.cycles-pp.do_softirq
5.68 +0.2 5.89 perf-profile.children.cycles-pp.sctp_ulpq_tail_data
13.98 +0.2 14.20 perf-profile.children.cycles-pp.__local_bh_enable_ip
3.22 +0.2 3.44 perf-profile.children.cycles-pp.skb_release_head_state
2.90 +0.2 3.13 perf-profile.children.cycles-pp.__schedule
36.67 +0.2 36.90 perf-profile.children.cycles-pp.sctp_do_sm
36.13 +0.2 36.36 perf-profile.children.cycles-pp.sctp_cmd_interpreter
10.99 +0.2 11.22 perf-profile.children.cycles-pp.acpi_safe_halt
7.30 +0.2 7.54 perf-profile.children.cycles-pp.copyout
14.37 +0.2 14.61 perf-profile.children.cycles-pp.__dev_queue_xmit
11.01 +0.2 11.26 perf-profile.children.cycles-pp.acpi_idle_enter
14.53 +0.2 14.78 perf-profile.children.cycles-pp.ip_finish_output2
7.40 +0.3 7.65 perf-profile.children.cycles-pp._copy_to_iter
15.04 +0.3 15.29 perf-profile.children.cycles-pp.__ip_queue_xmit
11.26 +0.3 11.52 perf-profile.children.cycles-pp.cpuidle_enter_state
11.33 +0.3 11.59 perf-profile.children.cycles-pp.cpuidle_enter
29.10 +0.3 29.37 perf-profile.children.cycles-pp.sctp_sendmsg_to_asoc
8.41 +0.3 8.69 perf-profile.children.cycles-pp.__skb_datagram_iter
8.45 +0.3 8.73 perf-profile.children.cycles-pp.skb_copy_datagram_iter
11.94 +0.3 12.25 perf-profile.children.cycles-pp.cpuidle_idle_call
9.15 +0.4 9.52 perf-profile.children.cycles-pp.asm_sysvec_call_function_single
13.25 +0.4 13.64 perf-profile.children.cycles-pp.start_secondary
13.32 +0.4 13.71 perf-profile.children.cycles-pp.do_idle
13.34 +0.4 13.74 perf-profile.children.cycles-pp.secondary_startup_64_no_verify
13.34 +0.4 13.74 perf-profile.children.cycles-pp.cpu_startup_entry
16.00 +0.4 16.41 perf-profile.children.cycles-pp.sctp_primitive_SEND
52.23 +0.6 52.80 perf-profile.children.cycles-pp.sock_sendmsg
52.14 +0.6 52.72 perf-profile.children.cycles-pp.sctp_sendmsg
54.28 +0.6 54.87 perf-profile.children.cycles-pp.____sys_sendmsg
56.24 +0.6 56.85 perf-profile.children.cycles-pp.___sys_sendmsg
56.83 +0.6 57.45 perf-profile.children.cycles-pp.__sys_sendmsg
6.05 ± 2% -2.4 3.68 perf-profile.self.cycles-pp.native_queued_spin_lock_slowpath
0.97 -0.2 0.81 perf-profile.self.cycles-pp._raw_spin_lock_irqsave
1.26 -0.1 1.14 perf-profile.self.cycles-pp.__slab_free
1.22 -0.1 1.14 perf-profile.self.cycles-pp.rmqueue
0.40 -0.1 0.35 ± 2% perf-profile.self.cycles-pp.__zone_watermark_ok
0.46 -0.0 0.42 perf-profile.self.cycles-pp.__list_add_valid_or_report
0.18 ± 4% -0.0 0.16 ± 4% perf-profile.self.cycles-pp.__free_one_page
0.15 ± 5% -0.0 0.13 ± 4% perf-profile.self.cycles-pp.__intel_pmu_enable_all
0.10 ± 3% +0.0 0.11 perf-profile.self.cycles-pp._copy_to_iter
0.31 +0.0 0.32 perf-profile.self.cycles-pp.sctp_v4_xmit
0.24 +0.0 0.26 ± 2% perf-profile.self.cycles-pp.__sys_sendmsg
0.06 ± 7% +0.0 0.08 perf-profile.self.cycles-pp.dequeue_task_fair
0.07 ± 5% +0.0 0.09 ± 5% perf-profile.self.cycles-pp.newidle_balance
0.40 +0.0 0.42 perf-profile.self.cycles-pp.sctp_skb_recv_datagram
0.19 ± 3% +0.0 0.20 ± 2% perf-profile.self.cycles-pp.menu_select
0.11 ± 4% +0.0 0.13 ± 4% perf-profile.self.cycles-pp.enqueue_task_fair
0.37 +0.0 0.39 perf-profile.self.cycles-pp.__check_object_size
0.78 +0.0 0.80 perf-profile.self.cycles-pp._raw_spin_lock_bh
0.22 ± 2% +0.0 0.24 ± 2% perf-profile.self.cycles-pp.__update_load_avg_cfs_rq
0.21 +0.0 0.23 perf-profile.self.cycles-pp.__switch_to_asm
0.27 +0.0 0.30 perf-profile.self.cycles-pp.___perf_sw_event
0.38 +0.0 0.40 ± 2% perf-profile.self.cycles-pp.entry_SYSCALL_64_after_hwframe
0.12 ± 3% +0.0 0.15 ± 6% perf-profile.self.cycles-pp.update_cfs_group
0.35 +0.0 0.38 perf-profile.self.cycles-pp.____sys_recvmsg
0.05 +0.0 0.08 ± 6% perf-profile.self.cycles-pp.schedule
0.20 +0.0 0.22 ± 2% perf-profile.self.cycles-pp.update_load_avg
0.28 ± 2% +0.0 0.31 perf-profile.self.cycles-pp.sctp_inet_skb_msgname
0.23 ± 3% +0.0 0.25 perf-profile.self.cycles-pp.ipv4_dst_check
0.12 ± 4% +0.0 0.14 ± 3% perf-profile.self.cycles-pp.sk_leave_memory_pressure
0.58 +0.0 0.61 ± 2% perf-profile.self.cycles-pp.kmem_cache_alloc_node
0.41 +0.0 0.44 ± 2% perf-profile.self.cycles-pp.__mod_node_page_state
0.36 +0.0 0.39 ± 2% perf-profile.self.cycles-pp.aa_sk_perm
0.27 ± 3% +0.0 0.30 ± 5% perf-profile.self.cycles-pp.recv_sctp_stream_1toMany
0.78 +0.0 0.82 perf-profile.self.cycles-pp.sctp_recvmsg
0.71 +0.0 0.74 perf-profile.self.cycles-pp.sctp_sendmsg
0.38 ± 3% +0.0 0.42 ± 2% perf-profile.self.cycles-pp.dst_release
1.36 +0.1 1.42 perf-profile.self.cycles-pp.kmem_cache_free
0.51 ± 2% +0.1 0.58 ± 2% perf-profile.self.cycles-pp.__sk_mem_raise_allocated
0.63 +0.1 0.70 ± 2% perf-profile.self.cycles-pp.sctp_eat_data
0.47 ± 4% +0.1 0.55 ± 3% perf-profile.self.cycles-pp.__sk_mem_reduce_allocated
3.77 +0.1 3.86 perf-profile.self.cycles-pp.copyin
6.90 +0.1 7.03 perf-profile.self.cycles-pp.__memcpy
7.30 +0.2 7.45 perf-profile.self.cycles-pp.acpi_safe_halt
7.26 +0.2 7.49 perf-profile.self.cycles-pp.copyout
Disclaimer:
Results have been estimated based on internal Intel analysis and are provided
for informational purposes only. Any difference in system hardware or software
design or configuration may affect actual performance.
--
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki
© 2016 - 2026 Red Hat, Inc.