qio: raise critical queue bloat threshold from 2 to 10 times to queue limit
the limit for overqueueing was too small for stuff like fcp on a fileserver connected with a standard 32K limit pipe like ramfs. fcp usesd 8K*16procs > 32K*2 the biggest queue limit used in the kernel is 256K making the maximum queue bloat 2.5MB or 320K for standard pipes. that should be big enougth to never happen in practice unless there is a bug which we like to catch before we exhaust all kernel memory.
This commit is contained in:
parent
2d09d805f3
commit
a360bddee7
1 changed files with 2 additions and 2 deletions
|
@ -1193,7 +1193,7 @@ qbwrite(Queue *q, Block *b)
|
|||
poperror();
|
||||
return n;
|
||||
}
|
||||
if(q->len >= q->limit*2){
|
||||
if(q->len >= q->limit*10){
|
||||
iunlock(q);
|
||||
error(Egreg);
|
||||
}
|
||||
|
@ -1241,7 +1241,7 @@ qbwrite(Queue *q, Block *b)
|
|||
*
|
||||
* Note - this is moderately dangerous since a process
|
||||
* that keeps getting interrupted and rewriting will
|
||||
* queue infinite crud.
|
||||
* queue up to 10 times the queue limit before failing.
|
||||
*/
|
||||
for(;;){
|
||||
if(q->noblock || qnotfull(q))
|
||||
|
|
Loading…
Reference in a new issue