blkparse: Print PID information for TN_MESSAGE events
PATCH 1/1 blkparse: Print PID information for TN_MESSAGE events
The kernel now provides PID information for TN_MESSAGE events. Print it. Old kernels fill 0 there so the behavior is unaffected for them.
--- blkparse.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
blkparse.c +1 -1
@@ -643,7 +643,7 @@ static void handle_notify(struct blk_io_trace *bit)MAJOR (bit->device),MINOR (bit->device), bit->cpu,"0" , (int )SECONDS (bit->time), (unsigned long )NANO_SECONDS (bit->time), - 0, cgidstr, "m", "N", msg); + bit->pid, cgidstr, "m", "N", msg); }break ;
Signature · 1 line
2.16.4
Jens Axboe
maintainerQuoted 2 lines · Jan Kara
The kernel now provides PID information for
TN_MESSAGEevents. Print it. Old kernels fill 0 there so the behavior is unaffected for them.
Doesn't apply to the current repo, can you resend?
Signature · 1 line
Jens Axboe
Quoted 5 lines · Jens Axboe
Quoted 2 lines · Jan Kara
The kernel now provides PID information for
TN_MESSAGEevents. Print it. Old kernels fill 0 there so the behavior is unaffected for them.Doesn't apply to the current repo, can you resend?
Likely because it is based on top of my blkparse fixes to deal with cgroup information in blktrace events. Did you pick up those? Rebasing this on-liner is simple enough but I'm just wondering...
Honza
Signature · 2 lines
Jan Kara <[email protected]> SUSE Labs, CR
Jens Axboe
maintainerQuoted 10 lines · Jan Kara
Quoted 5 lines · Jens Axboe
Quoted 2 lines · Jan Kara
The kernel now provides PID information for
TN_MESSAGEevents. Print it. Old kernels fill 0 there so the behavior is unaffected for them.Doesn't apply to the current repo, can you resend?
Likely because it is based on top of my blkparse fixes to deal with cgroup information in blktrace events. Did you pick up those? Rebasing this on-liner is simple enough but I'm just wondering...
Indeed, applied this one too. Thanks!
Signature · 1 line
Jens Axboe