2ccdbaa6d5
Rollover has to call packet_rcv_has_room on sockets in the fanout
group to find a socket to migrate to. This operation is expensive
especially if the packet sockets use rings, when a lock has to be
acquired.
Avoid pounding on the lock by all sockets by temporarily marking a
socket as "under memory pressure" when such pressure is detected.
While set, only the socket owner may call packet_rcv_has_room on the
socket. Once it detects normal conditions, it clears the flag. The
socket is not used as a victim by any other socket in the meantime.
Under reasonably balanced load, each socket writer frequently calls
packet_rcv_has_room and clears its own pressure field. As a backup
for when the socket is rarely written to, also clear the flag on
reading (packet_recvmsg, packet_poll) if this can be done cheaply
(i.e., without calling packet_rcv_has_room). This is only for
edge cases.
Tested:
Ran bench_rollover: a process with 8 sockets in a single fanout
group, each pinned to a single cpu that receives one nic recv
interrupt. RPS and RFS are disabled. The benchmark uses packet
rx_ring, which has to take a lock when determining whether a
socket has room.
Sent 3.5 Mpps of UDP traffic with sufficient entropy to spread
uniformly across the packet sockets (and inserted an iptables
rule to drop in PREROUTING to avoid protocol stack processing).
Without this patch, all sockets try to migrate traffic to
neighbors, causing lock contention when searching for a non-
empty neighbor. The lock is the top 9 entries.
perf record -a -g sleep 5
- 17.82% bench_rollover [kernel.kallsyms] [k] _raw_spin_lock
- _raw_spin_lock
- 99.00% spin_lock
+ 81.77% packet_rcv_has_room.isra.41
+ 18.23% tpacket_rcv
+ 0.84% packet_rcv_has_room.isra.41
+ 5.20% ksoftirqd/6 [kernel.kallsyms] [k] _raw_spin_lock
+ 5.15% ksoftirqd/1 [kernel.kallsyms] [k] _raw_spin_lock
+ 5.14% ksoftirqd/2 [kernel.kallsyms] [k] _raw_spin_lock
+ 5.12% ksoftirqd/7 [kernel.kallsyms] [k] _raw_spin_lock
+ 5.12% ksoftirqd/5 [kernel.kallsyms] [k] _raw_spin_lock
+ 5.10% ksoftirqd/4 [kernel.kallsyms] [k] _raw_spin_lock
+ 4.66% ksoftirqd/0 [kernel.kallsyms] [k] _raw_spin_lock
+ 4.45% ksoftirqd/3 [kernel.kallsyms] [k] _raw_spin_lock
+ 1.55% bench_rollover [kernel.kallsyms] [k] packet_rcv_has_room.isra.41
On net-next with this patch, this lock contention is no longer a
top entry. Most time is spent in the actual read function. Next up
are other locks:
+ 15.52% bench_rollover bench_rollover [.] reader
+ 4.68% swapper [kernel.kallsyms] [k] memcpy_erms
+ 2.77% swapper [kernel.kallsyms] [k] packet_lookup_frame.isra.51
+ 2.56% ksoftirqd/1 [kernel.kallsyms] [k] memcpy_erms
+ 2.16% swapper [kernel.kallsyms] [k] tpacket_rcv
+ 1.93% swapper [kernel.kallsyms] [k] mlx4_en_process_rx_cq
Looking closer at the remaining _raw_spin_lock, the cost of probing
in rollover is now comparable to the cost of taking the lock later
in tpacket_rcv.
- 1.51% swapper [kernel.kallsyms] [k] _raw_spin_lock
- _raw_spin_lock
+ 33.41% packet_rcv_has_room
+ 28.15% tpacket_rcv
+ 19.54% enqueue_to_backlog
+ 6.45% __free_pages_ok
+ 2.78% packet_rcv_fanout
+ 2.13% fanout_demux_rollover
+ 2.01% netif_receive_skb_internal
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
131 lines
2.9 KiB
C
131 lines
2.9 KiB
C
#ifndef __PACKET_INTERNAL_H__
|
|
#define __PACKET_INTERNAL_H__
|
|
|
|
struct packet_mclist {
|
|
struct packet_mclist *next;
|
|
int ifindex;
|
|
int count;
|
|
unsigned short type;
|
|
unsigned short alen;
|
|
unsigned char addr[MAX_ADDR_LEN];
|
|
};
|
|
|
|
/* kbdq - kernel block descriptor queue */
|
|
struct tpacket_kbdq_core {
|
|
struct pgv *pkbdq;
|
|
unsigned int feature_req_word;
|
|
unsigned int hdrlen;
|
|
unsigned char reset_pending_on_curr_blk;
|
|
unsigned char delete_blk_timer;
|
|
unsigned short kactive_blk_num;
|
|
unsigned short blk_sizeof_priv;
|
|
|
|
/* last_kactive_blk_num:
|
|
* trick to see if user-space has caught up
|
|
* in order to avoid refreshing timer when every single pkt arrives.
|
|
*/
|
|
unsigned short last_kactive_blk_num;
|
|
|
|
char *pkblk_start;
|
|
char *pkblk_end;
|
|
int kblk_size;
|
|
unsigned int max_frame_len;
|
|
unsigned int knum_blocks;
|
|
uint64_t knxt_seq_num;
|
|
char *prev;
|
|
char *nxt_offset;
|
|
struct sk_buff *skb;
|
|
|
|
atomic_t blk_fill_in_prog;
|
|
|
|
/* Default is set to 8ms */
|
|
#define DEFAULT_PRB_RETIRE_TOV (8)
|
|
|
|
unsigned short retire_blk_tov;
|
|
unsigned short version;
|
|
unsigned long tov_in_jiffies;
|
|
|
|
/* timer to retire an outstanding block */
|
|
struct timer_list retire_blk_timer;
|
|
};
|
|
|
|
struct pgv {
|
|
char *buffer;
|
|
};
|
|
|
|
struct packet_ring_buffer {
|
|
struct pgv *pg_vec;
|
|
|
|
unsigned int head;
|
|
unsigned int frames_per_block;
|
|
unsigned int frame_size;
|
|
unsigned int frame_max;
|
|
|
|
unsigned int pg_vec_order;
|
|
unsigned int pg_vec_pages;
|
|
unsigned int pg_vec_len;
|
|
|
|
unsigned int __percpu *pending_refcnt;
|
|
|
|
struct tpacket_kbdq_core prb_bdqc;
|
|
};
|
|
|
|
extern struct mutex fanout_mutex;
|
|
#define PACKET_FANOUT_MAX 256
|
|
|
|
struct packet_fanout {
|
|
possible_net_t net;
|
|
unsigned int num_members;
|
|
u16 id;
|
|
u8 type;
|
|
u8 flags;
|
|
atomic_t rr_cur;
|
|
struct list_head list;
|
|
struct sock *arr[PACKET_FANOUT_MAX];
|
|
spinlock_t lock;
|
|
atomic_t sk_ref;
|
|
struct packet_type prot_hook ____cacheline_aligned_in_smp;
|
|
};
|
|
|
|
struct packet_rollover {
|
|
int sock;
|
|
} ____cacheline_aligned_in_smp;
|
|
|
|
struct packet_sock {
|
|
/* struct sock has to be the first member of packet_sock */
|
|
struct sock sk;
|
|
struct packet_fanout *fanout;
|
|
union tpacket_stats_u stats;
|
|
struct packet_ring_buffer rx_ring;
|
|
struct packet_ring_buffer tx_ring;
|
|
int copy_thresh;
|
|
spinlock_t bind_lock;
|
|
struct mutex pg_vec_lock;
|
|
unsigned int running:1, /* prot_hook is attached*/
|
|
auxdata:1,
|
|
origdev:1,
|
|
has_vnet_hdr:1;
|
|
int pressure;
|
|
int ifindex; /* bound device */
|
|
__be16 num;
|
|
struct packet_rollover *rollover;
|
|
struct packet_mclist *mclist;
|
|
atomic_t mapped;
|
|
enum tpacket_versions tp_version;
|
|
unsigned int tp_hdrlen;
|
|
unsigned int tp_reserve;
|
|
unsigned int tp_loss:1;
|
|
unsigned int tp_tx_has_off:1;
|
|
unsigned int tp_tstamp;
|
|
struct net_device __rcu *cached_dev;
|
|
int (*xmit)(struct sk_buff *skb);
|
|
struct packet_type prot_hook ____cacheline_aligned_in_smp;
|
|
};
|
|
|
|
static struct packet_sock *pkt_sk(struct sock *sk)
|
|
{
|
|
return (struct packet_sock *)sk;
|
|
}
|
|
|
|
#endif
|