memcg: Keep socket_pressure fresh on 32-bit kernel.
Subsystems (3)
PATCH 1/1 memcg: Keep socket_pressure fresh on 32-bit kernel.
memcg->socket_pressure is initialised with jiffies when the memcg is created.
Once vmpressure detects that the cgroup is under memory pressure, the field is updated with jiffies + HZ to signal the fact to the socket layer and suppress memory allocation for one second.
Otherwise, the field is not updated.
mem_cgroup_under_socket_pressure() uses time_before() to check if jiffies is less than memcg->socket_pressure, and this has a bug on 32-bit kernel.
if (time_before(jiffies, memcg->socket_pressure))
return true;
As time_before() casts the final result to long, the acceptable delta between two timestamps is 2 ^ (BITS_PER_LONG - 1).
On 32-bit kernel with CONFIG_HZ=1000, this is about 24 days.
Quoted 1 line
Quoted 1 line
Quoted 1 line
(2 ** 31) / 1000 / 60 / 60 / 24
24.855134814814818
Once 24 days have passed since the last update of socket_pressure, mem_cgroup_under_socket_pressure() starts to lie until the next 24 days pass.
Thus, we need to update socket_pressure to a recent timestamp periodically on 32-bit kernel.
Let's do that every 24 hours, with a variation of about 0 to 4 hours.
The variation is to avoid bursting by cgroups created within a small timeframe, like boot-up.
The work could be racy but does not take vmpr->sr_lock nor re-evaluate vmpressure_calc_level() under the assumption that socket_pressure will get updated soon if under memory pressure, because it persists only for one second.
Note that we don't need to worry about 64-bit machines unless they serve for 300 million years.
Quoted 1 line
Quoted 1 line
Quoted 1 line
(2 ** 63) / 1000 / 60 / 60 / 24 / 365
292471208.6775361
--- include/linux/vmpressure.h | 3 +++ mm/vmpressure.c | 52 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 55 insertions(+)
include/linux/vmpressure.h +3 -0
@@ -25,6 +25,9 @@ struct vmpressure {struct mutex events_lock;struct work_struct work; +#if BITS_PER_LONG ==32 +struct delayed_work delayed_work; +#endif };struct mem_cgroup ;
mm/vmpressure.c +52 -0
68 lines not on this page · raw message
Signature · 1 line
2.50.0.727.gbf7dc18ff4-goog
Shakeel Butt
maintainerQuoted 44 lines · Kuniyuki Iwashima
memcg->socket_pressureis initialised with jiffies when the memcg is created.Once vmpressure detects that the cgroup is under memory pressure, the field is updated with jiffies + HZ to signal the fact to the socket layer and suppress memory allocation for one second.
Otherwise, the field is not updated.
mem_cgroup_under_socket_pressure()usestime_before()to check if jiffies is less thanmemcg->socket_pressure, and this has a bug on 32-bit kernel.if (
time_before(jiffies, memcg->socket_pressure))return true;As
time_before()casts the final result to long, the acceptable delta between two timestamps is 2 ^ (BITS_PER_LONG- 1).On 32-bit kernel with
CONFIG_HZ=1000, this is about 24 days.Quoted 1 line
Quoted 1 line
Quoted 1 line
(2 ** 31) / 1000 / 60 / 60 / 24
24.855134814814818
Once 24 days have passed since the last update of
socket_pressure,mem_cgroup_under_socket_pressure()starts to lie until the next 24 days pass.Thus, we need to update
socket_pressureto a recent timestamp periodically on 32-bit kernel.Let's do that every 24 hours, with a variation of about 0 to 4 hours.
The variation is to avoid bursting by cgroups created within a small timeframe, like boot-up.
The work could be racy but does not take
vmpr->sr_locknor re-evaluatevmpressure_calc_level()under the assumption thatsocket_pressurewill get updated soon if under memory pressure, because it persists only for one second.Note that we don't need to worry about 64-bit machines unless they serve for 300 million years.
Quoted 6 lines
Quoted 1 line
Quoted 1 line
Quoted 1 line
(2 ** 63) / 1000 / 60 / 60 / 24 / 365
292471208.6775361
Fixes 8e8ae645249b8 ("mm: memcontrol: hook up vmpressure to socket pressure")Reported-by Neal Cardwell <[email protected]>Signed-off-by Kuniyuki Iwashima <[email protected]>
Is this a real issue which you have seen in the production? I wonder if we can just reset memcg->socket_pressure in mem_cgroup_under_socket_pressure() for 32 bit systems if we see overflow?
From: Shakeel Butt <[email protected]>
Date: Wed, 16 Jul 2025 12:59:13 -0700
Quoted 45 lines · Kuniyuki Iwashima
Quoted 44 lines
memcg->socket_pressureis initialised with jiffies when the memcg is created.Once vmpressure detects that the cgroup is under memory pressure, the field is updated with jiffies + HZ to signal the fact to the socket layer and suppress memory allocation for one second.
Otherwise, the field is not updated.
mem_cgroup_under_socket_pressure()usestime_before()to check if jiffies is less thanmemcg->socket_pressure, and this has a bug on 32-bit kernel.if (
time_before(jiffies, memcg->socket_pressure))return true;As
time_before()casts the final result to long, the acceptable delta between two timestamps is 2 ^ (BITS_PER_LONG- 1).On 32-bit kernel with
CONFIG_HZ=1000, this is about 24 days.Quoted 1 line
Quoted 1 line
Quoted 1 line
(2 ** 31) / 1000 / 60 / 60 / 24
24.855134814814818
Once 24 days have passed since the last update of
socket_pressure,mem_cgroup_under_socket_pressure()starts to lie until the next 24 days pass.Thus, we need to update
socket_pressureto a recent timestamp periodically on 32-bit kernel.Let's do that every 24 hours, with a variation of about 0 to 4 hours.
The variation is to avoid bursting by cgroups created within a small timeframe, like boot-up.
The work could be racy but does not take
vmpr->sr_locknor re-evaluatevmpressure_calc_level()under the assumption thatsocket_pressurewill get updated soon if under memory pressure, because it persists only for one second.Note that we don't need to worry about 64-bit machines unless they serve for 300 million years.
Quoted 8 lines
Quoted 6 lines
Quoted 1 line
Quoted 1 line
Quoted 1 line
(2 ** 63) / 1000 / 60 / 60 / 24 / 365
292471208.6775361
Fixes 8e8ae645249b8 ("mm: memcontrol: hook up vmpressure to socket pressure")Reported-by Neal Cardwell <[email protected]>Signed-off-by Kuniyuki Iwashima <[email protected]>Is this a real issue which you have seen in the production?
No, this is a theoretical issue that Neal found a while ago.
Quoted 4 lines
I wonder if
we can just resetmemcg->socket_pressureinmem_cgroup_under_socket_pressure()for 32 bit systems if we see overflow?
I guess you mean like below ? This doesn't work when jiffies is close to ULONG_MAX and socket_pressure is close to 0 and the 'actual' time delta is within HZ.
include/linux/memcontrol.h +4 -0
@@ -1609,6 +1609,10 @@ static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg)return !!memcg->tcpmem_pressure;#endif /* CONFIG_MEMCG_V1 */ do { +#if BITS_PER_LONG == 32 + if (jiffies - READ_ONCE(memcg->socket_pressure) > LONG_MAX) { + WRITE_ONCE(memcg->socket_pressure, jiffies - HZ); +#endif if (time_before(jiffies, READ_ONCE(memcg->socket_pressure))) return true; } while ((memcg = parent_mem_cgroup(memcg)));
Andrew Morton
maintainerQuoted 24 lines · On Wed, 16 Jul 2025 04:29:12 +0000 Kuniyuki Iwashima <[email protected]> wrote:
memcg->socket_pressureis initialised with jiffies when the memcg is created.Once vmpressure detects that the cgroup is under memory pressure, the field is updated with jiffies + HZ to signal the fact to the socket layer and suppress memory allocation for one second.
Otherwise, the field is not updated.
mem_cgroup_under_socket_pressure()usestime_before()to check if jiffies is less thanmemcg->socket_pressure, and this has a bug on 32-bit kernel.if (
time_before(jiffies, memcg->socket_pressure))return true;As
time_before()casts the final result to long, the acceptable delta between two timestamps is 2 ^ (BITS_PER_LONG- 1).On 32-bit kernel with
CONFIG_HZ=1000, this is about 24 days.Quoted 1 line
Quoted 1 line
Quoted 1 line
(2 ** 31) / 1000 / 60 / 60 / 24
24.855134814814818
Quoted 8 lines
Once 24 days have passed since the last update of
socket_pressure,mem_cgroup_under_socket_pressure()starts to lie until the next 24 days pass.Thus, we need to update
socket_pressureto a recent timestamp periodically on 32-bit kernel.Let's do that every 24 hours, with a variation of about 0 to 4 hours.
Can't we simply convert ->socket_preesure to a 64-bit type? timespec64/time64_t/etc?
Quoted 31 lines · Andrew Morton
Quoted 28 lines · On Wed, 16 Jul 2025 04:29:12 +0000 Kuniyuki Iwashima <[email protected]> wrote:
memcg->socket_pressureis initialised with jiffies when the memcg is created.Once vmpressure detects that the cgroup is under memory pressure, the field is updated with jiffies + HZ to signal the fact to the socket layer and suppress memory allocation for one second.
Otherwise, the field is not updated.
mem_cgroup_under_socket_pressure()usestime_before()to check if jiffies is less thanmemcg->socket_pressure, and this has a bug on 32-bit kernel.if (
time_before(jiffies, memcg->socket_pressure))return true;As
time_before()casts the final result to long, the acceptable delta between two timestamps is 2 ^ (BITS_PER_LONG- 1).On 32-bit kernel with
CONFIG_HZ=1000, this is about 24 days.Quoted 1 line
Quoted 1 line
Quoted 1 line
(2 ** 31) / 1000 / 60 / 60 / 24
24.855134814814818
Once 24 days have passed since the last update of
socket_pressure,mem_cgroup_under_socket_pressure()starts to lie until the next 24 days pass.
Quoted 7 lines
Quoted 4 lines
Thus, we need to update
socket_pressureto a recent timestamp periodically on 32-bit kernel.Let's do that every 24 hours, with a variation of about 0 to 4 hours.
Can't we simply convert ->socket_preesure to a 64-bit type? timespec64/time64_t/etc?
I think it's doable with get_jiffies_64() & time_before64().
My thought was a delayed work would be better than adding two seqlock in the networking fast path.
Andrew Morton
maintainerQuoted 5 lines · On Wed, 16 Jul 2025 16:13:54 -0700 Kuniyuki Iwashima <[email protected]> wrote:
Quoted 5 lines
Quoted 4 lines
Thus, we need to update
socket_pressureto a recent timestamp periodically on 32-bit kernel.Let's do that every 24 hours, with a variation of about 0 to 4 hours.
Quoted 7 lines
Quoted 2 lines
Can't we simply convert ->socket_preesure to a 64-bit type? timespec64/time64_t/etc?
I think it's doable with
get_jiffies_64()&time_before64().My thought was a delayed work would be better than adding two seqlock in the networking fast path.
Is it on a very fast path? mem_cgroup_under_socket_pressure() itself doesn't look very fastpath-friendly and seqcounts are fast. Bearing in mind that this affects 32-bit machines only.
If a get_jiffies_64() call is demonstrated to be a performance issue then perhaps there's something sneaky we can do along the lines of reading jiffies_64 directly then falling back to get_jiffies_64() in the rare something-went-wrong path. Haven't thought about it :)
Dunno, the proposed patch just feels like overkill for a silly 32/66-bit issue?
Quoted 20 lines · Andrew Morton
Quoted 5 lines · On Wed, 16 Jul 2025 16:13:54 -0700 Kuniyuki Iwashima <[email protected]> wrote:
Quoted 5 lines
Quoted 4 lines
Thus, we need to update
socket_pressureto a recent timestamp periodically on 32-bit kernel.Let's do that every 24 hours, with a variation of about 0 to 4 hours.
Quoted 7 lines
Quoted 2 lines
Can't we simply convert ->socket_preesure to a 64-bit type? timespec64/time64_t/etc?
I think it's doable with
get_jiffies_64()&time_before64().My thought was a delayed work would be better than adding two seqlock in the networking fast path.
Is it on a very fast path?
mem_cgroup_under_socket_pressure()itself doesn't look very fastpath-friendly and seqcounts are fast. Bearing in mind that this affects 32-bit machines only.
Quoted 7 lines
If a
get_jiffies_64()call is demonstrated to be a performance issue then perhaps there's something sneaky we can do along the lines of readingjiffies_64directly then falling back toget_jiffies_64()in the rare something-went-wrong path. Haven't thought about it :)Dunno, the proposed patch just feels like overkill for a silly 32/66-bit issue?
Fair enough, I'll make it u64 in v2.
Thank you!
Andrew Morton
maintainerQuoted 26 lines · On Wed, 16 Jul 2025 16:58:29 -0700 Kuniyuki Iwashima <[email protected]> wrote:
Quoted 25 lines · Andrew Morton
Quoted 5 lines · On Wed, 16 Jul 2025 16:13:54 -0700 Kuniyuki Iwashima <[email protected]> wrote:
Quoted 5 lines
Quoted 4 lines
Thus, we need to update
socket_pressureto a recent timestamp periodically on 32-bit kernel.Let's do that every 24 hours, with a variation of about 0 to 4 hours.
Quoted 7 lines
Quoted 2 lines
Can't we simply convert ->socket_preesure to a 64-bit type? timespec64/time64_t/etc?
I think it's doable with
get_jiffies_64()&time_before64().My thought was a delayed work would be better than adding two seqlock in the networking fast path.
Is it on a very fast path?
mem_cgroup_under_socket_pressure()itself doesn't look very fastpath-friendly and seqcounts are fast. Bearing in mind that this affects 32-bit machines only.If a
get_jiffies_64()call is demonstrated to be a performance issue then perhaps there's something sneaky we can do along the lines of readingjiffies_64directly then falling back toget_jiffies_64()in the rare something-went-wrong path. Haven't thought about it :)
Quoted 5 lines
Quoted 2 lines
Dunno, the proposed patch just feels like overkill for a silly 32/66-bit issue?
Fair enough, I'll make it u64 in v2.
Well, please do pay attention to any performance impact. Measurements with some simple microbenchmark if possible?
Quoted 29 lines · Andrew Morton
Quoted 26 lines · On Wed, 16 Jul 2025 16:58:29 -0700 Kuniyuki Iwashima <[email protected]> wrote:
Quoted 25 lines · Andrew Morton
Quoted 5 lines · On Wed, 16 Jul 2025 16:13:54 -0700 Kuniyuki Iwashima <[email protected]> wrote:
Quoted 5 lines
Quoted 4 lines
Thus, we need to update
socket_pressureto a recent timestamp periodically on 32-bit kernel.Let's do that every 24 hours, with a variation of about 0 to 4 hours.
Quoted 7 lines
Quoted 2 lines
Can't we simply convert ->socket_preesure to a 64-bit type? timespec64/time64_t/etc?
I think it's doable with
get_jiffies_64()&time_before64().My thought was a delayed work would be better than adding two seqlock in the networking fast path.
Is it on a very fast path?
mem_cgroup_under_socket_pressure()itself doesn't look very fastpath-friendly and seqcounts are fast. Bearing in mind that this affects 32-bit machines only.If a
get_jiffies_64()call is demonstrated to be a performance issue then perhaps there's something sneaky we can do along the lines of readingjiffies_64directly then falling back toget_jiffies_64()in the rare something-went-wrong path. Haven't thought about it :)
Quoted 8 lines
Quoted 5 lines
Quoted 2 lines
Dunno, the proposed patch just feels like overkill for a silly 32/66-bit issue?
Fair enough, I'll make it u64 in v2.
Well, please do pay attention to any performance impact. Measurements with some simple microbenchmark if possible?
I don't have a real 32-bit machine so this is a result on QEMU, but with/without the u64 jiffie patch, the time spent in mem_cgroup_under_socket_pressure() was 1~5us and I didn't see any measurable delta.
no patch applied:
iperf3 273 [000] 137.296248:
probe:mem_cgroup_under_socket_pressure: (c13660d0)
c13660d1 mem_cgroup_under_socket_pressure+0x1
([kernel.kallsyms])
iperf3 273 [000] 137.296249:
probe:mem_cgroup_under_socket_pressure__return: (c13660d0 <- c1d8fd7f)
iperf3 273 [000] 137.296251:
probe:mem_cgroup_under_socket_pressure: (c13660d0)
c13660d1 mem_cgroup_under_socket_pressure+0x1
([kernel.kallsyms])
iperf3 273 [000] 137.296253:
probe:mem_cgroup_under_socket_pressure__return: (c13660d0 <- c1d8fd7f)
u64 jiffies patch applied:
iperf3 308 [001] 330.669370:
probe:mem_cgroup_under_socket_pressure: (c12ddba0)
c12ddba1 mem_cgroup_under_socket_pressure+0x1
([kernel.kallsyms])
iperf3 308 [001] 330.669371:
probe:mem_cgroup_under_socket_pressure__return: (c12ddba0 <- c1ce98bf)
iperf3 308 [001] 330.669382:
probe:mem_cgroup_under_socket_pressure: (c12ddba0)
c12ddba1 mem_cgroup_under_socket_pressure+0x1
([kernel.kallsyms])
iperf3 308 [001] 330.669384:
probe:mem_cgroup_under_socket_pressure__return: (c12ddba0 <- c1ce98bf)
So, the u64 approach is good enough :)
Thanks!