net: xsk: introduce XDP_MAX_TX_BUDGET setsockopt
Subsystems (5)
PATCH v4 1/1 net: xsk: introduce XDP_MAX_TX_BUDGET setsockopt
From: Jason Xing <[email protected]>
This patch provides a setsockopt method to let applications leverage to adjust how many descs to be handled at most in one send syscall. It mitigates the situation where the default value (32) that is too small leads to higher frequency of triggering send syscall.
Considering the prosperity/complexity the applications have, there is no absolutely ideal suggestion fitting all cases. So keep 32 as its default value like before.
The patch does the following things:
- Add XDP_MAX_TX_BUDGET socket option.
- Unify TX_BATCH_SIZE and MAX_PER_SOCKET_BUDGET into single one tx_budget_spent.
- Set tx_budget_spent to 32 by default in the initialization phase as a per-socket granular control.
The idea behind this comes out of real workloads in production. We use a user-level stack with xsk support to accelerate sending packets and minimize triggering syscalls. When the packets are aggregated, it's not hard to hit the upper bound (namely, 32). The moment user-space stack fetches the -EAGAIN error number passed from sendto(), it will loop to try again until all the expected descs from tx ring are sent out to the driver. Enlarging the XDP_MAX_TX_BUDGET value contributes to less frequency of sendto() and higher throughput/PPS.
Here is what I did in production, along with some numbers as follows:
For one application I saw lately, I suggested using 128 as max_tx_budget because I saw two limitations without changing any default configuration:
1) XDP_MAX_TX_BUDGET, 2) socket sndbuf which is 212992 decided by net.core.wmem_default. As to XDP_MAX_TX_BUDGET, the scenario behind this was I counted how many descs are transmitted to the driver at one time of sendto() based on [1] patch and then I calculated the possibility of hitting the upper bound. Finally I chose 128 as a suitable value because 1) it covers most of the cases, 2) a higher number would not bring evident results. After twisting the parameters, a stable improvement of around 4% for both PPS and throughput and less resources consumption were found to be observed by strace -c -p xxx:
1) %time was decreased by 7.8%
2) error counter was decreased from 18367 to 572
[1]: https://lore.kernel.org/all/[email protected]/
In terms of how xsk transmits packets, there are two known modes: one is non-copy mode (that is what I used) and the other is zerocopy mode. Zerocopy modes also has two different versions, one is non-batched version and the other is batched version. Only non-batched version which is normally treated as a fallback solution potentially has the same max_tx_budget limitation issue as non-copy mode. So the patch adjusts MAX_PER_SOCKET_BUDGET as well. It's worth mentioning that for non-batched version may be stopped before hitting the limit of max_tx_budget due to another budget limitation the caller (like ixgbe_xmit_zc()) of xsk_tx_peek_desc() has.
---
v4
1. remove getsockopt as it seems no real use case.
2. adjust the position of max_tx_budget to make sure it stays with other read-most fields in one cacheline.
3. set one as the lower bound of max_tx_budget
4. add more descriptions/performance data in Doucmentation and commit message.
V3
1. use a per-socket control (suggested by Stanislav)
2. unify both definitions into one
3. support setsockopt and getsockopt
4. add more description in commit message
V2
1. use a per-netns sysctl knob
2. use sysctl_xsk_max_tx_budget to unify both definitions.
--- Documentation/networking/af_xdp.rst | 9 +++++++++ include/net/xdp_sock.h | 3 ++- include/uapi/linux/if_xdp.h | 1 + net/xdp/xsk.c | 24 ++++++++++++++++++------ tools/include/uapi/linux/if_xdp.h | 1 + 5 files changed, 31 insertions(+), 7 deletions(-)
Documentation/networking/af_xdp.rst +9 -0
@@ -442,6 +442,15 @@ is created by a privileged process and passed to a non-privileged one. Once the option is set, kernel will refuse attempts to bind that socket to a different interface. Updating the value requires CAP_NET_RAW. +XDP_MAX_TX_BUDGET setsockopt +---------------------------- + +This setsockopt sets the maximum number of descriptors that can be handled +and passed to the driver at one send syscall. It is applied in two cases: +non-zero copy mode and non-batched version of zero copy mode, to break +the maximum iteration limitation for better throughput and less frequency +of send syscall. + XDP_STATISTICS getsockopt -------------------------
include/net/xdp_sock.h +2 -1
@@ -65,7 +65,7 @@ struct xdp_sock {struct xsk_queue *tx____cacheline_aligned_in_smp ;struct list_head tx_list;/* record the number of tx descriptors sent by this xsk and -* when it exceeds MAX_PER_SOCKET_BUDGET, an opportunity needs +* when it exceeds max_tx_budget, an opportunity needs * to be given to other xsks for sending tx descriptors, thereby * preventing other XSKs from being starved. */
@@ -84,6 +84,7 @@ struct xdp_sock {struct list_head map_list;/* Protects map_list */ spinlock_t map_list_lock; +u32 max_tx_budget;/* Protects multiple processes in the control path */ struct mutex mutex;struct xsk_queue *fq_tmp;/* Only as tmp storage before bind */
include/uapi/linux/if_xdp.h +1 -0
@@ -79,6 +79,7 @@ struct xdp_mmap_offsets {#define XDP_UMEM_COMPLETION_RING 6#define XDP_STATISTICS 7#define XDP_OPTIONS 8 +#define XDP_MAX_TX_BUDGET 9struct xdp_umem_reg {__u64 addr;/* Start of packet data area */
net/xdp/xsk.c +18 -6
@@ -33,9 +33,6 @@#include "xdp_umem.h" #include "xsk.h" -#define TX_BATCH_SIZE 32 -#define MAX_PER_SOCKET_BUDGET (TX_BATCH_SIZE) -void xsk_set_rx_need_wakeup (struct xsk_buff_pool *pool) {if (pool->cached_need_wakeup &XDP_WAKEUP_RX )
@@ -424,7 +421,9 @@ bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc)rcu_read_lock (); again:list_for_each_entry_rcu (xs, &pool->xsk_tx_list, tx_list) { -if (xs->tx_budget_spent >=MAX_PER_SOCKET_BUDGET ) { +int max_budget =READ_ONCE (xs->max_tx_budget); + +if (xs->tx_budget_spent >= max_budget) { budget_exhausted = true;continue ; }
@@ -779,7 +778,7 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,static int __xsk_generic_xmit (struct sock *sk) {struct xdp_sock *xs =xdp_sk (sk); -u32 max_batch =TX_BATCH_SIZE ; +u32 max_budget =READ_ONCE (xs->max_tx_budget);bool sent_frame = false;struct xdp_desc desc;struct sk_buff *skb;
@@ -797,7 +796,7 @@ static int __xsk_generic_xmit(struct sock *sk) goto out;while (xskq_cons_peek_desc (xs->tx, &desc, xs->pool)) { -if (max_batch-- ==0 ) { +if (max_budget-- ==0 ) { err = -EAGAIN ; goto out; }
@@ -1437,6 +1436,18 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname,mutex_unlock (&xs->mutex);return err; } +case XDP_MAX_TX_BUDGET : + { +unsigned int budget; + +if (optlen !=sizeof (budget)) +return -EINVAL ; +if (copy_from_sockptr (&budget, optval,sizeof (budget))) +return -EFAULT ; + +WRITE_ONCE (xs->max_tx_budget,max (budget,1 )); +return 0 ; + }default :break ; }
@@ -1734,6 +1745,7 @@ static int xsk_create(struct net *net, struct socket *sock, int protocol, xs =xdp_sk (sk); xs->state =XSK_READY ; + xs->max_tx_budget =32 ;mutex_init (&xs->mutex);INIT_LIST_HEAD (&xs->map_list);
tools/include/uapi/linux/if_xdp.h +1 -0
@@ -79,6 +79,7 @@ struct xdp_mmap_offsets {#define XDP_UMEM_COMPLETION_RING 6#define XDP_STATISTICS 7#define XDP_OPTIONS 8 +#define XDP_MAX_TX_BUDGET 9struct xdp_umem_reg {__u64 addr;/* Start of packet data area */
Signature · 1 line
2.43.5
Jakub Kicinski
maintainernet/xdp/xsk.c bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc) · line 429
Quoted 11 lines · On Mon, 23 Jun 2025 10:13:45 +0800 Jason Xing wrote:
net/xdp/xsk.c +3
-1@@ -424,7 +421,9 @@ bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc)rcu_read_lock (); again:list_for_each_entry_rcu (xs, &pool->xsk_tx_list, tx_list) { -if (xs->tx_budget_spent >=MAX_PER_SOCKET_BUDGET ) { +int max_budget =READ_ONCE (xs->max_tx_budget); + +if (xs->tx_budget_spent >= max_budget) { budget_exhausted = true;continue ; }
I still think you're mixing two very different things. In the generic xmit path the value you're changing is a budget. But xsk_tx_peek_desc() *does not* exit after the "per socket budget" gets spent. The per socket budget only controls how many frames we pick from a single sock before we move to the next. But if we run out of budget on all sockets we give every socket a full budget again and start from the first one again.
For the ZC case the true budget is set by the driver's NAPI loop.
Signature · 1 line
pw-bot: cr
Quoted 12 lines · Jakub Kicinski
Quoted 10 lines · On Mon, 23 Jun 2025 10:13:45 +0800 Jason Xing wrote:
net/xdp/xsk.c +3
-1@@ -424,7 +421,9 @@ bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc)rcu_read_lock (); again:list_for_each_entry_rcu (xs, &pool->xsk_tx_list, tx_list) { -if (xs->tx_budget_spent >=MAX_PER_SOCKET_BUDGET ) { +int max_budget =READ_ONCE (xs->max_tx_budget); + +if (xs->tx_budget_spent >= max_budget) { budget_exhausted = true;continue ;
Quoted 8 lines
Review bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc) · line 429
Quoted 1 line
(quoted diff) +0
-0}I still think you're mixing two very different things. In the generic xmit path the value you're changing is a budget. But
xsk_tx_peek_desc()*does not* exit after the "per socket budget" gets spent. The per socket budget only controls how many frames we pick from a single sock before we move to the next. But if we run out of budget on all sockets we give every socket a full budget again and start from the first one
Ah, my fault. Thanks for reminding me. I missed the 'refilling budget' process...
For the record:xsk_tx_peek_desc()
-> xs->tx_budget_spent = 0;
Quoted 3 lines
again.
For the ZC case the true budget is set by the driver's NAPI loop.
True.
I will remove this one.
Thanks,
Jason
Quoted 2 lines
--
pw-bot: cr
Maciej Fijalkowski
maintainerQuoted 13 lines · Jason Xing
Quoted 12 lines · Jakub Kicinski
Quoted 10 lines · On Mon, 23 Jun 2025 10:13:45 +0800 Jason Xing wrote:
net/xdp/xsk.c +3
-1@@ -424,7 +421,9 @@ bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc)rcu_read_lock (); again:list_for_each_entry_rcu (xs, &pool->xsk_tx_list, tx_list) { -if (xs->tx_budget_spent >=MAX_PER_SOCKET_BUDGET ) { +int max_budget =READ_ONCE (xs->max_tx_budget); + +if (xs->tx_budget_spent >= max_budget) { budget_exhausted = true;continue ;
Quoted 8 lines
Quoted 8 lines
Review bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc) · line 429
Quoted 1 line
(quoted diff) +0
-0}I still think you're mixing two very different things. In the generic xmit path the value you're changing is a budget. But
xsk_tx_peek_desc()*does not* exit after the "per socket budget" gets spent. The per socket budget only controls how many frames we pick from a single sock before we move to the next. But if we run out of budget on all sockets we give every socket a full budget again and start from the first one
On point. Thanks Jakub! Let's stick to generic xmit budget.
Quoted 20 lines
Ah, my fault. Thanks for reminding me. I missed the 'refilling budget' process...
For the record:xsk_tx_peek_desc()-> xs->tx_budget_spent = 0;Quoted 3 lines
again.
For the ZC case the true budget is set by the driver's NAPI loop.
True.
I will remove this one.
Thanks,
JasonQuoted 2 lines
--
pw-bot: cr