On Thu, 2007-04-19 at 19:49 +0200, Miklos Szeredi wrote:
> > +static inline unsigned long bdi_stat_delta(void)
> > +{
> > +#ifdef CONFIG_SMP
> > + return NR_CPUS * FBC_BATCH;
>
> Shouln't this be multiplied by the number of counters to sum? I.e. 3
> if dirty and unstable are separate, and 2 if
> +static inline unsigned long bdi_stat_delta(void)
> +{
> +#ifdef CONFIG_SMP
> + return NR_CPUS * FBC_BATCH;
Shouln't this be multiplied by the number of counters to sum? I.e. 3
if dirty and unstable are separate, and 2 if they are not.
Miklos
-
To unsubscribe from this list: send the line
+static inline unsigned long bdi_stat_delta(void)
+{
+#ifdef CONFIG_SMP
+ return NR_CPUS * FBC_BATCH;
Shouln't this be multiplied by the number of counters to sum? I.e. 3
if dirty and unstable are separate, and 2 if they are not.
Miklos
-
To unsubscribe from this list: send the line
On Thu, 2007-04-19 at 19:49 +0200, Miklos Szeredi wrote:
+static inline unsigned long bdi_stat_delta(void)
+{
+#ifdef CONFIG_SMP
+ return NR_CPUS * FBC_BATCH;
Shouln't this be multiplied by the number of counters to sum? I.e. 3
if dirty and unstable are separate, and 2 if they are
Scale writeback cache per backing device, proportional to its writeout speed.
By decoupling the BDI dirty thresholds a number of problems we currently have
will go away, namely:
- mutual interference starvation (for any number of BDIs);
- deadlocks with stacked BDIs (loop, FUSE and local NFS
Scale writeback cache per backing device, proportional to its writeout speed.
By decoupling the BDI dirty thresholds a number of problems we currently have
will go away, namely:
- mutual interference starvation (for any number of BDIs);
- deadlocks with stacked BDIs (loop, FUSE and local NFS
6 matches
Mail list logo
