net: reduce tcp_memory_allocated inflation
Status from this message: This series was applied to netdev/net-next.git (master)
Get series with b4
b4 am [email protected]Versions newest first
Patches in v1 All 7 applied
| # | Subject and files | Size | Replies | Applied |
|---|---|---|---|---|
| 1/7 | Revert "net: set SK_MEM_QUANTUM to 4096"include/ | +3 | 1 reply | Applied |
| 2/7 | net: remove SK_MEM_QUANTUM and SK_MEM_QUANTUM_SHIFTinclude/ net/ net/ +5 more | +26 | 1 reply | Applied |
| 3/7 | net: add per_cpu_fw_alloc field to struct protoinclude/ include/ include/ +11 more | +43 | 1 reply | Applied |
| 4/7 | net: implement per-cpu reserves for memory_allocatedinclude/ | +29 | 8 replies | Applied |
| 5/7 | net: fix sk_wmem_schedule() and sk_rmem_schedule() errorsinclude/ | +8 | 1 reply | Applied |
| 6/7 | net: keep sk->sk_forward_alloc as small as possibleinclude/ net/ net/ +8 more | +7 | 9 replies | Applied |
| 7/7 | net: unexport __sk_mem_{raise|reduce}_allocatednet/ | +0 | 1 reply | Applied |
Reviews trailers per patch
All 7 patches have a Reviewed-by or Acked-by of their own; the series has one for all of them.
| Patch | Soheil Hassas Yeganeh | Shakeel Butt |
|---|---|---|
| Series | A-b | |
| 1/7 | R-b | |
| 2/7 | R-b | |
| 3/7 | R-b | |
| 4/7 | A-b | R-b |
| 5/7 | R-b | |
| 6/7 | R-b | |
| 7/7 | R-b |
Trailers given in replies are filled; those carried in the patches from earlier versions are outlined with dashes.
Cover letter [PATCH net-next 0/7] net: reduce tcp_memory_allocated inflation
From: Eric Dumazet <[email protected]>
Hosts with a lot of sockets tend to hit so called TCP memory pressure, leading to very bad TCP performance and/or OOM.
The problem is that some TCP sockets can hold up to 2MB of 'forward allocations' in their per-socket cache (sk->sk_forward_alloc), and there is no mechanism to make them relinquish their share under mem pressure.
Only under some potentially rare events their share is reclaimed, one socket at a time.
In this series, I implemented a per-cpu cache instead of a per-socket one.
Each CPU has a +1/-1 MB (256 pages on x86) forward alloc cache, in order to not dirty tcp_memory_allocated shared cache line too often.
We keep sk->sk_forward_alloc values as small as possible, to meet memcg page granularity constraint.
Note that memcg already has a per-cpu cache, although MEMCG_CHARGE_BATCH is defined to 32 pages, which seems a bit small.
Note that while this cover letter mentions TCP, this work is generic and supports TCP, UDP, DECNET, SCTP.
Eric Dumazet (7):
Revert "net: set SK_MEM_QUANTUM to 4096"
net: remove SK_MEM_QUANTUM and SK_MEM_QUANTUM_SHIFT
net: add per_cpu_fw_alloc field to struct proto
net: implement per-cpu reserves for memory_allocated
net: fix sk_wmem_schedule() and sk_rmem_schedule() errors
net: keep sk->sk_forward_alloc as small as possible
net: unexport __sk_mem_{raise|reduce}_allocated
include/net/sock.h | 100 +++++++++++++++-------------------- include/net/tcp.h | 2 + include/net/udp.h | 1 + net/core/datagram.c | 3 -- net/core/sock.c | 22 ++++---- net/decnet/af_decnet.c | 4 ++ net/ipv4/tcp.c | 13 ++--- net/ipv4/tcp_input.c | 6 +-- net/ipv4/tcp_ipv4.c | 3 ++ net/ipv4/tcp_output.c | 2 +- net/ipv4/tcp_timer.c | 19 ++----- net/ipv4/udp.c | 14 +++-- net/ipv4/udplite.c | 3 ++ net/ipv6/tcp_ipv6.c | 3 ++ net/ipv6/udp.c | 3 ++ net/ipv6/udplite.c | 3 ++ net/iucv/af_iucv.c | 2 - net/mptcp/protocol.c | 13 +++-- net/sctp/protocol.c | 4 +- net/sctp/sm_statefuns.c | 2 - net/sctp/socket.c | 12 +++-- net/sctp/stream_interleave.c | 2 - net/sctp/ulpqueue.c | 4 -- 23 files changed, 114 insertions(+), 126 deletions(-)
Signature · 1 line
2.36.1.255.ge46751e96f-goog