mirror of
git://git.kernel.org/pub/scm/linux/kernel/git/xiang/erofs.git
synced 2026-10-28 12:53:14 +01:00
Shashank Mohan Jain
0843b23890
dim_calc_stats() computes the per-millisecond rates as DIV_ROUND_UP(nbytes * USEC_PER_MSEC, delta_us) where nbytes is a u32 and USEC_PER_MSEC is 1000L. On 64-bit the product is done in 64-bit long arithmetic, but on 32-bit architectures long is 32 bits wide and the product wraps as soon as a measurement window carries more than 4294967 bytes (about 4.3 MB). The same applies to the packet and completion counts, although those need more than 4.29 million packets or completions per window. A DIM window spans DIM_NEVENTS (64) events. Drivers count events per interrupt or per NAPI poll, so under sustained load a window can easily carry more than 4.3 MB: 64 full NAPI polls of 64 MTU-sized frames are already 6.2 MB, and drivers such as mtk_eth_soc count one event per interrupt while NAPI keeps polling with the interrupt masked. On 32-bit users of the library (for example mtk_eth_soc on MT7621, bcmgenet and bcmsysport on 32-bit ARM, or virtio_net in a 32-bit guest) bpms then becomes the product modulo 2^32 divided by the window length, and net_dim_stats_compare() makes its BETTER/WORSE decisions on a value that has little to do with the real throughput. For example, a 1 Gbit/s link at line rate that moves 5 MB in a 40 ms window gives bpms = 125000 on 64-bit but 17626 on 32-bit, and 5 million packets in 2 s gives ppms = 353 instead of 2500. Widen the products to 64 bits and divide with DIV_ROUND_UP_ULL(). The results are unchanged on 64-bit. Fixes:cb3c7fd4f8("net/mlx5e: Support adaptive RX coalescing") Fixes:4c4dbb4a73("net/mlx5e: Move dynamic interrupt coalescing code to include/linux") Assisted-by: LLM Signed-off-by: Shashank Mohan Jain <[email protected]> Signed-off-by: David S. Miller <[email protected]>
93 lines
2.3 KiB
C
93 lines
2.3 KiB
C
// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
|
|
/*
|
|
* Copyright (c) 2019, Mellanox Technologies inc. All rights reserved.
|
|
*/
|
|
|
|
#include <linux/dim.h>
|
|
|
|
bool dim_on_top(struct dim *dim)
|
|
{
|
|
switch (dim->tune_state) {
|
|
case DIM_PARKING_ON_TOP:
|
|
case DIM_PARKING_TIRED:
|
|
return true;
|
|
case DIM_GOING_RIGHT:
|
|
return (dim->steps_left > 1) && (dim->steps_right == 1);
|
|
default: /* DIM_GOING_LEFT */
|
|
return (dim->steps_right > 1) && (dim->steps_left == 1);
|
|
}
|
|
}
|
|
EXPORT_SYMBOL(dim_on_top);
|
|
|
|
void dim_turn(struct dim *dim)
|
|
{
|
|
switch (dim->tune_state) {
|
|
case DIM_PARKING_ON_TOP:
|
|
case DIM_PARKING_TIRED:
|
|
break;
|
|
case DIM_GOING_RIGHT:
|
|
dim->tune_state = DIM_GOING_LEFT;
|
|
dim->steps_left = 0;
|
|
break;
|
|
case DIM_GOING_LEFT:
|
|
dim->tune_state = DIM_GOING_RIGHT;
|
|
dim->steps_right = 0;
|
|
break;
|
|
}
|
|
}
|
|
EXPORT_SYMBOL(dim_turn);
|
|
|
|
void dim_park_on_top(struct dim *dim)
|
|
{
|
|
dim->steps_right = 0;
|
|
dim->steps_left = 0;
|
|
dim->tired = 0;
|
|
dim->tune_state = DIM_PARKING_ON_TOP;
|
|
}
|
|
EXPORT_SYMBOL(dim_park_on_top);
|
|
|
|
void dim_park_tired(struct dim *dim)
|
|
{
|
|
dim->steps_right = 0;
|
|
dim->steps_left = 0;
|
|
dim->tune_state = DIM_PARKING_TIRED;
|
|
}
|
|
EXPORT_SYMBOL(dim_park_tired);
|
|
|
|
bool dim_calc_stats(const struct dim_sample *start,
|
|
const struct dim_sample *end,
|
|
struct dim_stats *curr_stats)
|
|
{
|
|
/* u32 holds up to 71 minutes, should be enough */
|
|
u32 delta_us = ktime_us_delta(end->time, start->time);
|
|
u32 npkts = BIT_GAP(BITS_PER_TYPE(u32), end->pkt_ctr, start->pkt_ctr);
|
|
u32 nbytes = BIT_GAP(BITS_PER_TYPE(u32), end->byte_ctr,
|
|
start->byte_ctr);
|
|
u32 ncomps = BIT_GAP(BITS_PER_TYPE(u32), end->comp_ctr,
|
|
start->comp_ctr);
|
|
|
|
if (!delta_us)
|
|
return false;
|
|
|
|
/* u32 * USEC_PER_MSEC overflows a 32-bit long */
|
|
curr_stats->ppms = DIV_ROUND_UP_ULL((u64)npkts * USEC_PER_MSEC,
|
|
delta_us);
|
|
curr_stats->bpms = DIV_ROUND_UP_ULL((u64)nbytes * USEC_PER_MSEC,
|
|
delta_us);
|
|
curr_stats->epms = DIV_ROUND_UP(DIM_NEVENTS * USEC_PER_MSEC,
|
|
delta_us);
|
|
curr_stats->cpms = DIV_ROUND_UP_ULL((u64)ncomps * USEC_PER_MSEC,
|
|
delta_us);
|
|
if (curr_stats->epms != 0)
|
|
curr_stats->cpe_ratio = DIV_ROUND_DOWN_ULL(
|
|
curr_stats->cpms * 100, curr_stats->epms);
|
|
else
|
|
curr_stats->cpe_ratio = 0;
|
|
|
|
return true;
|
|
}
|
|
EXPORT_SYMBOL(dim_calc_stats);
|
|
|
|
MODULE_DESCRIPTION("Dynamic Interrupt Moderation (DIM) library");
|
|
MODULE_LICENSE("Dual BSD/GPL");
|