git: cc604213b597 - stable/14 - sched_4bsd: ESTCPULIM(): Allow any value in the timeshare range
- Go to: [ bottom of page ] [ top of archives ] [ this month ]
Date: Mon, 28 Jul 2025 13:31:39 UTC
The branch stable/14 has been updated by olce:
URL: https://cgit.FreeBSD.org/src/commit/?id=cc604213b59777b33c413e2d2c70f63d4c3665bf
commit cc604213b59777b33c413e2d2c70f63d4c3665bf
Author: Olivier Certner <olce@FreeBSD.org>
AuthorDate: 2024-05-21 12:55:43 +0000
Commit: Olivier Certner <olce@FreeBSD.org>
CommitDate: 2025-07-28 13:28:42 +0000
sched_4bsd: ESTCPULIM(): Allow any value in the timeshare range
The current formula wastes queues and degrades usage estimation
precision, since any increase of ticks that goes over 40 priorities (so,
8 * 40) is clamped to the last of these 40 levels (the nice value is
subsequently added to that number to get the final priority level).
Allow 'ts_estcpu' to grow up to a value corresponding to the greatest
(i.e., lowest) priority of the timeshare range.
MFC after: 1 month
Event: Kitchener-Waterloo Hackathon 202506
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D45392
(cherry picked from commit eebc148f25c3012b943083b48fbfc13494e9c77f)
---
sys/kern/sched_4bsd.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/sys/kern/sched_4bsd.c b/sys/kern/sched_4bsd.c
index e9d180fde303..0e7ac9feb686 100644
--- a/sys/kern/sched_4bsd.c
+++ b/sys/kern/sched_4bsd.c
@@ -80,7 +80,9 @@ dtrace_vtime_switch_func_t dtrace_vtime_switch_func;
#endif
#define NICE_WEIGHT 1 /* Priorities per nice level. */
#define ESTCPULIM(e) \
- min((e), INVERSE_ESTCPU_WEIGHT * (NICE_WEIGHT * (PRIO_MAX - PRIO_MIN)) \
+ min((e), INVERSE_ESTCPU_WEIGHT * \
+ (NICE_WEIGHT * (PRIO_MAX - PRIO_MIN) + \
+ PRI_MAX_TIMESHARE - PRI_MIN_TIMESHARE) \
+ INVERSE_ESTCPU_WEIGHT - 1)
#define TS_NAME_LEN (MAXCOMLEN + sizeof(" td ") + sizeof(__XSTRING(UINT_MAX)))