| Message ID | 1601268657-940-1-git-send-email-muneendra.kumar@broadcom.com |
|---|---|
| Headers | show |
| Series | scsi: Support to handle Intermittent errors | expand |
On 9/27/20 11:50 PM, Muneendra wrote: > This patch adds a support to prevent retries of all the pending/inflight > io's after an abort succeeds on a particular device when transport > connectivity to the device is encountering intermittent errors. > > Intermittent connectivity is a condition that can be detected by transport > fabric notifications. A service can monitor the ELS notifications and > take action on all the outstanding io's of a scsi device at that instant. > Is the service mentioned above a new daemon or is it integrated into something like multipathd? What does the part about monitoring ELS notifications mean? Is the service just doing something like a ELS ECHO, or is it able to watch the IO on the wire/card (like if you did tcpdump and watched iscsi/tcp traffic) or is it something completely different?
On 10/2/2020 10:01 AM, Mike Christie wrote: > On 9/27/20 11:50 PM, Muneendra wrote: >> This patch adds a support to prevent retries of all the pending/inflight >> io's after an abort succeeds on a particular device when transport >> connectivity to the device is encountering intermittent errors. >> >> Intermittent connectivity is a condition that can be detected by transport >> fabric notifications. A service can monitor the ELS notifications and >> take action on all the outstanding io's of a scsi device at that instant. >> > > Is the service mentioned above a new daemon or is it integrated into > something like multipathd? > > What does the part about monitoring ELS notifications mean? Is the > service just doing something like a ELS ECHO, or is it able to watch > the IO on the wire/card (like if you did tcpdump and watched iscsi/tcp > traffic) or is it something completely different? > For the last part.... the FC drivers, when receiving FC FPIN ELS's are calling a scsi transport routine with the FPIN payload. The transport is pushing this as an "event" via netlink. An app bound to the local address used by the scsi transport can receive the event and parse it. This is a new daemon, specific to FC, which monitors for FPIN events, parses the related topology devices, then interacts with sysfs and possibly multipath based on what it's seeing from the fabric. -- james
This patch adds a support to prevent retries of all the pending/inflight io's after an abort succeeds on a particular device when transport connectivity to the device is encountering intermittent errors. Intermittent connectivity is a condition that can be detected by transport fabric notifications. A service can monitor the ELS notifications and take action on all the outstanding io's of a scsi device at that instant. This feature is intended to be used when the device is part of a multipath environment. When the service detects the poor connectivity, the multipath path can be placed in a marginal path group and ignored further io operations. After placing a path in the marginal path group,the daemon sets the port_state to Marginal which sets bit in scmd->state for all the outstanding io's on that particular device with the new sysfs interface provided in this patch.This prevent retries of all the pending/inflight io's if an io hits a scsi timeout which inturn issues an abort. On Abort succeeds on a marginal path the io will be immediately retried on another active path.On abort fails then the things escalates to existing target reset sg interface recovery process. Below is the interface provided to set the port state to Marginal and Online. echo "Marginal" >> /sys/class/fc_transport/targetX\:Y\:Z/port_state echo "Online" >> /sys/class/fc_transport/targetX\:Y\:Z/port_state The patches were cut against 5.10/scsi-queue tree --- v2: Added new error code DID_TRANSPORT_MARGINAL to handle marginal errors. Added a new rport_state FC_PORTSTATE_MARGINAL and also added a new sysfs interface port_state to set the port_state to marginal. Added the support in lpfc to handle the marginal state. Muneendra (8): scsi: Added a new definition in scsi_cmnd.h scsi: Added a new error code in scsi.h scsi: Clear state bit SCMD_NORETRIES_ABORT of scsi_cmd before start request scsi: No retries on abort success scsi: Added routine to set/clear SCMD_NORETRIES_ABORT bit for outstanding io on scsi_dev scsi_transport_fc: Added a new rport state FC_PORTSTATE_MARGINAL scsi_transport_fc: Added a new sysfs attribute port_state lpfc: Added support to handle marginal state drivers/scsi/lpfc/lpfc_scsi.c | 6 ++ drivers/scsi/scsi_error.c | 86 +++++++++++++++++++ drivers/scsi/scsi_lib.c | 2 + drivers/scsi/scsi_priv.h | 2 + drivers/scsi/scsi_transport_fc.c | 140 +++++++++++++++++++++++++++---- include/scsi/scsi.h | 1 + include/scsi/scsi_cmnd.h | 3 + include/scsi/scsi_transport_fc.h | 24 ++++++ 8 files changed, 246 insertions(+), 18 deletions(-)