Skip to contentSkip to conversation

sched: RT throttling activated, 3.12.3

DISCUSSION Howard Chu 2 participants 5 messages Dec 11, 2013

lore
Share & tools
lore

Howard Chu

author
#0 lore raw

I just upgraded a system from a 3.5 kernel to 3.12.3 and attempted to run some new benchmarks on it. I see my test program ramps up in CPU usage for a few seconds and then it gradually tails off. There's nothing obvious in the user code to trigger this behavior, so I check dmesg, and see this:

[   55.037057] JFS: nTxBlock = 8192, nTxLock = 65536
[163591.807470] perf samples too long (2758 > 2500), lowering kernel.perf_event_max_sample_rate to 50000
[164061.362762] perf samples too long (5204 > 5000), lowering kernel.perf_event_max_sample_rate to 25000
[167969.339513] [sched_delayed] sched: RT throttling activated
[182741.484637] perf samples too long (294588 > 10000), lowering kernel.perf_event_max_sample_rate to 12500
[182741.484726] INFO: NMI handler (perf_event_nmi_handler) took too long to run: 36.665 msecs
[182822.633084] perf samples too long (292359 > 20000), lowering kernel.perf_event_max_sample_rate to 6250
[182905.606119] perf samples too long (290291 > 40000), lowering kernel.perf_event_max_sample_rate to 3250
[199384.293514] perf samples too long (288142 > 76923), lowering kernel.perf_event_max_sample_rate to 1750
[208507.301027] perf samples too long (285964 > 142857), lowering kernel.perf_event_max_sample_rate to 1000
[208528.976208] perf samples too long (283799 > 250000), lowering kernel.perf_event_max_sample_rate to 500

Why is the kernel throttling my server?

Signature · 4 lines
  -- Howard Chu
  CTO, Symas Corp.           http://www.symas.com
  Director, Highland Sun     http://highlandsun.com/hyc/
  Chief Architect, OpenLDAP  http://www.openldap.org/project/
#1 lore raw
Quoted 14 lines · Howard Chu

I just upgraded a system from a 3.5 kernel to 3.12.3 and attempted to run some new benchmarks on it. I see my test program ramps up in CPU usage for a few seconds and then it gradually tails off. There's nothing obvious in the user code to trigger this behavior, so I check dmesg, and see this:

[   55.037057] JFS: nTxBlock = 8192, nTxLock = 65536
[163591.807470] perf samples too long (2758 > 2500), lowering kernel.perf_event_max_sample_rate to 50000
[164061.362762] perf samples too long (5204 > 5000), lowering kernel.perf_event_max_sample_rate to 25000
[167969.339513] [sched_delayed] sched: RT throttling activated
[182741.484637] perf samples too long (294588 > 10000), lowering kernel.perf_event_max_sample_rate to 12500
[182741.484726] INFO: NMI handler (perf_event_nmi_handler) took too long to run: 36.665 msecs
[182822.633084] perf samples too long (292359 > 20000), lowering kernel.perf_event_max_sample_rate to 6250
[182905.606119] perf samples too long (290291 > 40000), lowering kernel.perf_event_max_sample_rate to 3250
[199384.293514] perf samples too long (288142 > 76923), lowering kernel.perf_event_max_sample_rate to 1750
[208507.301027] perf samples too long (285964 > 142857), lowering kernel.perf_event_max_sample_rate to 1000
[208528.976208] perf samples too long (283799 > 250000), lowering kernel.perf_event_max_sample_rate to 500
Quoted 2 lines

Why is the kernel throttling my server?

Because that is the default setting of the kernel.

lxc34:/proc/sys/kernel # cat sched_rt_period_us
1000000
lxc34:/proc/sys/kernel # cat sched_rt_runtime_us
950000

author
#2 lore raw
Quoted 15 lines · Li Zefan
Quoted 14 lines · Howard Chu

I just upgraded a system from a 3.5 kernel to 3.12.3 and attempted to run some new benchmarks on it. I see my test program ramps up in CPU usage for a few seconds and then it gradually tails off. There's nothing obvious in the user code to trigger this behavior, so I check dmesg, and see this:

[   55.037057] JFS: nTxBlock = 8192, nTxLock = 65536
[163591.807470] perf samples too long (2758 > 2500), lowering kernel.perf_event_max_sample_rate to 50000
[164061.362762] perf samples too long (5204 > 5000), lowering kernel.perf_event_max_sample_rate to 25000
[167969.339513] [sched_delayed] sched: RT throttling activated
[182741.484637] perf samples too long (294588 > 10000), lowering kernel.perf_event_max_sample_rate to 12500
[182741.484726] INFO: NMI handler (perf_event_nmi_handler) took too long to run: 36.665 msecs
[182822.633084] perf samples too long (292359 > 20000), lowering kernel.perf_event_max_sample_rate to 6250
[182905.606119] perf samples too long (290291 > 40000), lowering kernel.perf_event_max_sample_rate to 3250
[199384.293514] perf samples too long (288142 > 76923), lowering kernel.perf_event_max_sample_rate to 1750
[208507.301027] perf samples too long (285964 > 142857), lowering kernel.perf_event_max_sample_rate to 1000
[208528.976208] perf samples too long (283799 > 250000), lowering kernel.perf_event_max_sample_rate to 500
Quoted 4 lines
Quoted 2 lines

Why is the kernel throttling my server?

Because that is the default setting of the kernel.

Apparently a "new" default that didn't exist in 3.5? The code in question is not a realtime process. This behavior also wasn't seen in 3.10 or any older kernels.

Quoted 6 lines

lxc34:/proc/sys/kernel # cat sched_rt_period_us
1000000
lxc34:/proc/sys/kernel # cat sched_rt_runtime_us
950000

Signature · 4 lines
  -- Howard Chu
  CTO, Symas Corp.           http://www.symas.com
  Director, Highland Sun     http://highlandsun.com/hyc/
  Chief Architect, OpenLDAP  http://www.openldap.org/project/
author
#3 lore raw
Quoted 16 lines · Howard Chu
Quoted 15 lines · Li Zefan
Quoted 14 lines · Howard Chu

I just upgraded a system from a 3.5 kernel to 3.12.3 and attempted to run some new benchmarks on it. I see my test program ramps up in CPU usage for a few seconds and then it gradually tails off. There's nothing obvious in the user code to trigger this behavior, so I check dmesg, and see this:

[   55.037057] JFS: nTxBlock = 8192, nTxLock = 65536
[163591.807470] perf samples too long (2758 > 2500), lowering kernel.perf_event_max_sample_rate to 50000
[164061.362762] perf samples too long (5204 > 5000), lowering kernel.perf_event_max_sample_rate to 25000
[167969.339513] [sched_delayed] sched: RT throttling activated
[182741.484637] perf samples too long (294588 > 10000), lowering kernel.perf_event_max_sample_rate to 12500
[182741.484726] INFO: NMI handler (perf_event_nmi_handler) took too long to run: 36.665 msecs
[182822.633084] perf samples too long (292359 > 20000), lowering kernel.perf_event_max_sample_rate to 6250
[182905.606119] perf samples too long (290291 > 40000), lowering kernel.perf_event_max_sample_rate to 3250
[199384.293514] perf samples too long (288142 > 76923), lowering kernel.perf_event_max_sample_rate to 1750
[208507.301027] perf samples too long (285964 > 142857), lowering kernel.perf_event_max_sample_rate to 1000
[208528.976208] perf samples too long (283799 > 250000), lowering kernel.perf_event_max_sample_rate to 500
Quoted 8 lines
Quoted 4 lines
Quoted 2 lines

Why is the kernel throttling my server?

Because that is the default setting of the kernel.

Apparently a "new" default that didn't exist in 3.5? The code in question is not a realtime process. This behavior also wasn't seen in 3.10 or any older kernels.

I just downgraded to 3.10.23 to doublecheck - everything is running normally there, although a few percent slower than I expected. (Last time I tried 3.10 it was 3.10.11.)

Signature · 4 lines
  -- Howard Chu
  CTO, Symas Corp.           http://www.symas.com
  Director, Highland Sun     http://highlandsun.com/hyc/
  Chief Architect, OpenLDAP  http://www.openldap.org/project/
author
#4 lore raw
Quoted 22 lines · Howard Chu
Quoted 21 lines · Howard Chu
Quoted 19 lines · Li Zefan
Quoted 14 lines · Howard Chu

I just upgraded a system from a 3.5 kernel to 3.12.3 and attempted to run some new benchmarks on it. I see my test program ramps up in CPU usage for a few seconds and then it gradually tails off. There's nothing obvious in the user code to trigger this behavior, so I check dmesg, and see this:

[   55.037057] JFS: nTxBlock = 8192, nTxLock = 65536
[163591.807470] perf samples too long (2758 > 2500), lowering kernel.perf_event_max_sample_rate to 50000
[164061.362762] perf samples too long (5204 > 5000), lowering kernel.perf_event_max_sample_rate to 25000
[167969.339513] [sched_delayed] sched: RT throttling activated
[182741.484637] perf samples too long (294588 > 10000), lowering kernel.perf_event_max_sample_rate to 12500
[182741.484726] INFO: NMI handler (perf_event_nmi_handler) took too long to run: 36.665 msecs
[182822.633084] perf samples too long (292359 > 20000), lowering kernel.perf_event_max_sample_rate to 6250
[182905.606119] perf samples too long (290291 > 40000), lowering kernel.perf_event_max_sample_rate to 3250
[199384.293514] perf samples too long (288142 > 76923), lowering kernel.perf_event_max_sample_rate to 1750
[208507.301027] perf samples too long (285964 > 142857), lowering kernel.perf_event_max_sample_rate to 1000
[208528.976208] perf samples too long (283799 > 250000), lowering kernel.perf_event_max_sample_rate to 500
Quoted 2 lines

Why is the kernel throttling my server?

Because that is the default setting of the kernel.

Quoted 8 lines
Quoted 3 lines

Apparently a "new" default that didn't exist in 3.5? The code in question is not a realtime process. This behavior also wasn't seen in 3.10 or any older kernels.

I just downgraded to 3.10.23 to doublecheck - everything is running normally there, although a few percent slower than I expected. (Last time I tried 3.10 it was 3.10.11.)

For comparison, here's a "normally" behaving benchmark run:
http://highlandsun.com/hyc/linux3.10/

The result is a fairly steady 15,000 ops/sec and CPU usage is around 190% (this is a quadcore machine).

On the 3.12.3 kernel:
http://highlandsun.com/hyc/linux3.12/

The CPU usage is initially around 180% but quickly plummets to about 7% and stays there. This is a pretty major regression for a "default" kernel setting. And given that the target process isn't running with realtime scheduling priority, this can only be considered a bug. (Btw, setting both sched_rt_period_us and sched_rt_runtime_us to -1 has no effect on this behavior.)

Signature · 4 lines
  -- Howard Chu
  CTO, Symas Corp.           http://www.symas.com
  Director, Highland Sun     http://highlandsun.com/hyc/
  Chief Architect, OpenLDAP  http://www.openldap.org/project/