diff options
| author | dzwdz | 2024-07-12 00:12:06 +0200 |
|---|---|---|
| committer | dzwdz | 2024-07-12 00:12:06 +0200 |
| commit | ded843efbdad1ed048fe42c50c8fb68d50bafa51 (patch) | |
| tree | de6b59e3a8e62af367d91f35d2e70d9d54d51975 /src/kernel/proc.c | |
| parent | ed8ff1ff9c4c0f847ffc2ab4624bd999539a0890 (diff) | |
kernel: don't reuse VfsReq allocations for a single process
To use the same testing methodology as when I've introduced request slots:
before:
/ $ iostress 1 1000000 0 > /dev/vtty
run 0: 2585203
1000000 calls, 0 bytes. avg 2585203
after:
/ $ iostress 1 1000000 0 > /dev/vtty
run 0: 2783171
1000000 calls, 0 bytes. avg 2783171
This is around a 7.7% slowdown - that I hope to fix with a better malloc.
While this doesn't really make the code that much simpler, it doesn't feel
like the right approach in the first place
Diffstat (limited to 'src/kernel/proc.c')
| -rw-r--r-- | src/kernel/proc.c | 4 |
1 files changed, 1 insertions, 3 deletions
diff --git a/src/kernel/proc.c b/src/kernel/proc.c index fcb51c6..9a9a84f 100644 --- a/src/kernel/proc.c +++ b/src/kernel/proc.c @@ -223,10 +223,8 @@ void proc_kill(Proc *p, int ret) { if (p->state == PS_WAITS4FS) { assert(p->reqslot); - p->reqslot->caller = NULL; /* transfer ownership */ + p->reqslot->caller = NULL; p->reqslot = NULL; - } else if (p->reqslot) { - kfree(p->reqslot); } if (p->state == PS_WAITS4PIPE) { |