EH retries were delayed by 5 seconds to ensure that resets don't occur
back-to-back. However, this 5 second delay is superflous or excessive
in many cases. For example, after IDENTIFY times out, there's no
reason to wait five more seconds before retrying.
This patch adds ehc->last_reset timestamp and record the timestamp for
the last reset trial or success and uses it to space resets by
ATA_EH_RESET_COOL_DOWN which is 5 secs and removes unconditional 5 sec
sleeps.
As this change makes inter-try waits often shorter and they're
redundant in nature, this patch also removes the "retrying..."
messages.
While at it, convert explicit rounding up division to DIV_ROUND_UP().
This change speeds up EH in many cases w/o sacrificing robustness.
Signed-off-by: Tejun Heo <htejun@gmail.com>
Signed-off-by: Jeff Garzik <jgarzik@redhat.com>
ATA_ECAT_DUBIOUS_UNK_DEV = 7,
ATA_ECAT_NR = 8,
ATA_ECAT_DUBIOUS_UNK_DEV = 7,
ATA_ECAT_NR = 8,
+ /* always put at least this amount of time between resets */
+ ATA_EH_RESET_COOL_DOWN = 5000,
+
/* Waiting in ->prereset can never be reliable. It's
* sometimes nice to wait there but it can't be depended upon;
* otherwise, we wouldn't be resetting. Just give it enough
/* Waiting in ->prereset can never be reliable. It's
* sometimes nice to wait there but it can't be depended upon;
* otherwise, we wouldn't be resetting. Just give it enough
if (ata_ncq_enabled(dev))
ehc->saved_ncq_enabled |= 1 << devno;
}
if (ata_ncq_enabled(dev))
ehc->saved_ncq_enabled |= 1 << devno;
}
+
+ /* set last reset timestamp to some time in the past */
+ ehc->last_reset = jiffies - 60 * HZ;
}
ap->pflags |= ATA_PFLAG_EH_IN_PROGRESS;
}
ap->pflags |= ATA_PFLAG_EH_IN_PROGRESS;
+ now = jiffies;
+ deadline = ata_deadline(ehc->last_reset, ATA_EH_RESET_COOL_DOWN);
+ if (time_before(now, deadline))
+ schedule_timeout_uninterruptible(deadline - now);
+
spin_lock_irqsave(ap->lock, flags);
ap->pflags |= ATA_PFLAG_RESETTING;
spin_unlock_irqrestore(ap->lock, flags);
ata_eh_about_to_do(link, NULL, ATA_EH_RESET);
spin_lock_irqsave(ap->lock, flags);
ap->pflags |= ATA_PFLAG_RESETTING;
spin_unlock_irqrestore(ap->lock, flags);
ata_eh_about_to_do(link, NULL, ATA_EH_RESET);
+ ehc->last_reset = jiffies;
ata_link_for_each_dev(dev, link) {
/* If we issue an SRST then an ATA drive (not ATAPI)
ata_link_for_each_dev(dev, link) {
/* If we issue an SRST then an ATA drive (not ATAPI)
+ ehc->last_reset = jiffies;
if (ata_is_host_link(link))
ata_eh_freeze_port(ap);
if (ata_is_host_link(link))
ata_eh_freeze_port(ap);
/* reset successful, schedule revalidation */
ata_eh_done(link, NULL, ATA_EH_RESET);
/* reset successful, schedule revalidation */
ata_eh_done(link, NULL, ATA_EH_RESET);
+ ehc->last_reset = jiffies;
ehc->i.action |= ATA_EH_REVALIDATE;
rc = 0;
ehc->i.action |= ATA_EH_REVALIDATE;
rc = 0;
if (time_before(now, deadline)) {
unsigned long delta = deadline - now;
if (time_before(now, deadline)) {
unsigned long delta = deadline - now;
- ata_link_printk(link, KERN_WARNING, "reset failed "
- "(errno=%d), retrying in %u secs\n",
- rc, (jiffies_to_msecs(delta) + 999) / 1000);
+ ata_link_printk(link, KERN_WARNING,
+ "reset failed (errno=%d), retrying in %u secs\n",
+ rc, DIV_ROUND_UP(jiffies_to_msecs(delta), 1000));
while (delta)
delta = schedule_timeout_uninterruptible(delta);
while (delta)
delta = schedule_timeout_uninterruptible(delta);
{
struct ata_link *link;
struct ata_device *dev;
{
struct ata_link *link;
struct ata_device *dev;
- int nr_failed_devs, nr_disabled_devs;
int rc;
unsigned long flags;
int rc;
unsigned long flags;
retry:
rc = 0;
nr_failed_devs = 0;
retry:
rc = 0;
nr_failed_devs = 0;
/* if UNLOADING, finish immediately */
if (ap->pflags & ATA_PFLAG_UNLOADING)
/* if UNLOADING, finish immediately */
if (ap->pflags & ATA_PFLAG_UNLOADING)
dev_fail:
nr_failed_devs++;
dev_fail:
nr_failed_devs++;
- if (ata_eh_handle_dev_fail(dev, rc))
- nr_disabled_devs++;
+ ata_eh_handle_dev_fail(dev, rc);
if (ap->pflags & ATA_PFLAG_FROZEN) {
/* PMP reset requires working host port.
if (ap->pflags & ATA_PFLAG_FROZEN) {
/* PMP reset requires working host port.
- if (nr_failed_devs) {
- if (nr_failed_devs != nr_disabled_devs) {
- ata_port_printk(ap, KERN_WARNING, "failed to recover "
- "some devices, retrying in 5 secs\n");
- ssleep(5);
- } else {
- /* no device left to recover, repeat fast */
- msleep(500);
- }
-
out:
if (rc && r_failed_link)
out:
if (rc && r_failed_link)
- int sleep = ehc->i.flags & ATA_EHI_DID_RESET;
-
/* consecutive revalidation failures? speed down */
if (reval_failed)
sata_down_spd_limit(link);
else
reval_failed = 1;
/* consecutive revalidation failures? speed down */
if (reval_failed)
sata_down_spd_limit(link);
else
reval_failed = 1;
- ata_dev_printk(dev, KERN_WARNING,
- "retrying reset%s\n",
- sleep ? " in 5 secs" : "");
- if (sleep)
- ssleep(5);
ehc->i.action |= ATA_EH_RESET;
goto retry;
} else {
ehc->i.action |= ATA_EH_RESET;
goto retry;
} else {
goto retry;
if (--pmp_tries) {
goto retry;
if (--pmp_tries) {
- ata_port_printk(ap, KERN_WARNING,
- "failed to recover PMP, retrying in 5 secs\n");
pmp_ehc->i.action |= ATA_EH_RESET;
pmp_ehc->i.action |= ATA_EH_RESET;
unsigned int did_probe_mask;
unsigned int saved_ncq_enabled;
u8 saved_xfer_mode[ATA_MAX_DEVICES];
unsigned int did_probe_mask;
unsigned int saved_ncq_enabled;
u8 saved_xfer_mode[ATA_MAX_DEVICES];
+ /* timestamp for the last reset attempt or success */
+ unsigned long last_reset;