From: Mukesh Kumar Chaurasiya <mchauras@linux.ibm.com>
To: grub-devel@gnu.org
Cc: meghanaprakash@in.ibm.com, avnish@linux.vnet.ibm.com,
brking@linux.vnet.ibm.com, mamatha4@linux.vnet.ibm.com,
mchauras@linux.vnet.ibm.com,
Mukesh Kumar Chaurasiya <mchauras@linux.ibm.com>,
Diego Domingos <diegodo@linux.vnet.ibm.com>
Subject: [PATCH v3] ieee1275/ofdisk: retry on open and read failure
Date: Mon, 17 Jul 2023 16:02:34 +0530 [thread overview]
Message-ID: <20230717103233.1292219-1-mchauras@linux.ibm.com> (raw)
Sometimes, when booting from a very busy SAN, the access to the
disk can fail and then grub will eventually drop to grub prompt.
This scenario is more frequent when deploying many machines at
the same time using the same SAN.
This patch aims to force the ofdisk module to retry the open or
read function for network disks excluding after it fails. We use
DEFAULT_RETRY_TIMEOUT, which is 15 seconds to specify the time it'll
retry to access the disk before it definitely fails. The timeout can be
changed by setting the environment variable ofdisk_retry_timeout.
If the environment variable fails to read, grub will consider the
default value of 15 seconds.
Signed-off-by: Diego Domingos <diegodo@linux.vnet.ibm.com>
Signed-off-by: Mukesh Kumar Chaurasiya <mchauras@linux.ibm.com>
---
docs/grub.texi | 8 ++++
grub-core/disk/ieee1275/ofdisk.c | 80 +++++++++++++++++++++++++++++++-
2 files changed, 86 insertions(+), 2 deletions(-)
diff --git a/docs/grub.texi b/docs/grub.texi
index a3e9ce2d1..7a16f8df5 100644
--- a/docs/grub.texi
+++ b/docs/grub.texi
@@ -3336,6 +3336,7 @@ These variables have special meaning to GRUB.
* net_default_ip::
* net_default_mac::
* net_default_server::
+* ofdisk_retry_timeout::
* pager::
* prefix::
* pxe_blksize::
@@ -3758,6 +3759,13 @@ The default is the value of @samp{color_normal} (@pxref{color_normal}).
@xref{Network}.
+@node ofdisk_retry_timeout
+@subsection ofdisk_retry_timeout
+
+The time in seconds till which the grub will retry to open or read a disk in
+case of failure to do so. This value defaults to 15 seconds.
+
+
@node pager
@subsection pager
diff --git a/grub-core/disk/ieee1275/ofdisk.c b/grub-core/disk/ieee1275/ofdisk.c
index c6cba0c8a..c58a1fce8 100644
--- a/grub-core/disk/ieee1275/ofdisk.c
+++ b/grub-core/disk/ieee1275/ofdisk.c
@@ -24,6 +24,9 @@
#include <grub/ieee1275/ofdisk.h>
#include <grub/i18n.h>
#include <grub/time.h>
+#include <grub/env.h>
+
+#define RETRY_DEFAULT_TIMEOUT 15
static char *last_devpath;
static grub_ieee1275_ihandle_t last_ihandle;
@@ -452,7 +455,7 @@ compute_dev_path (const char *name)
}
static grub_err_t
-grub_ofdisk_open (const char *name, grub_disk_t disk)
+grub_ofdisk_open_real (const char *name, grub_disk_t disk)
{
grub_ieee1275_phandle_t dev;
char *devpath;
@@ -525,6 +528,56 @@ grub_ofdisk_open (const char *name, grub_disk_t disk)
return 0;
}
+static grub_uint64_t
+grub_ofdisk_disk_timeout (grub_disk_t disk)
+{
+ grub_uint64_t retry;
+ const char *timeout = grub_env_get ("ofdisk_retry_timeout");
+
+ if (!(grub_strstr (disk->name, "fibre-channel@") ||
+ grub_strstr (disk->name, "vfc-client")) ||
+ grub_strstr(disk->name, "nvme-of"))
+ {
+ /* Do not retry in case of non network drives */
+ return 0;
+ }
+
+ if (timeout != NULL)
+ {
+ retry = grub_strtoul (timeout, 0, 10);
+ if (grub_errno != GRUB_ERR_NONE)
+ {
+ grub_errno = GRUB_ERR_NONE;
+ return RETRY_DEFAULT_TIMEOUT;
+ }
+ if (retry)
+ return retry;
+ }
+ return RETRY_DEFAULT_TIMEOUT;
+}
+
+static grub_err_t
+grub_ofdisk_open (const char *name, grub_disk_t disk)
+{
+ grub_err_t err;
+ grub_uint64_t timeout = grub_get_time_ms () + (grub_ofdisk_disk_timeout (disk) * 1000);
+ _Bool cont;
+ do
+ {
+ err = grub_ofdisk_open_real (name, disk);
+ cont = grub_get_time_ms () < timeout;
+ if (err == GRUB_ERR_UNKNOWN_DEVICE && cont)
+ {
+ grub_dprintf ("ofdisk","Failed to open disk %s. Retrying...\n", name);
+ grub_errno = GRUB_ERR_NONE;
+ }
+ else
+ break;
+ grub_millisleep (1000);
+ } while (cont);
+ return err;
+}
+
static void
grub_ofdisk_close (grub_disk_t disk)
{
@@ -568,7 +621,7 @@ grub_ofdisk_prepare (grub_disk_t disk, grub_disk_addr_t sector)
}
static grub_err_t
-grub_ofdisk_read (grub_disk_t disk, grub_disk_addr_t sector,
+grub_ofdisk_read_real (grub_disk_t disk, grub_disk_addr_t sector,
grub_size_t size, char *buf)
{
grub_err_t err;
@@ -587,6 +640,29 @@ grub_ofdisk_read (grub_disk_t disk, grub_disk_addr_t sector,
return 0;
}
+static grub_err_t
+grub_ofdisk_read (grub_disk_t disk, grub_disk_addr_t sector,
+ grub_size_t size, char *buf)
+{
+ grub_err_t err;
+ grub_uint64_t timeout = grub_get_time_ms () + (grub_ofdisk_disk_timeout (disk) * 1000);
+ _Bool cont;
+ do
+ {
+ err = grub_ofdisk_read_real (disk, sector, size, buf);
+ cont = grub_get_time_ms () < timeout;
+ if (err == GRUB_ERR_UNKNOWN_DEVICE && cont)
+ {
+ grub_dprintf ("ofdisk","Failed to read disk %s. Retrying...\n", (char*)disk->data);
+ grub_errno = GRUB_ERR_NONE;
+ }
+ else
+ break;
+ grub_millisleep (1000);
+ } while (cont);
+ return err;
+}
+
static grub_err_t
grub_ofdisk_write (grub_disk_t disk, grub_disk_addr_t sector,
grub_size_t size, const char *buf)
--
2.39.3
next reply other threads:[~2023-07-17 13:12 UTC|newest]
Thread overview: 3+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-07-17 10:32 Mukesh Kumar Chaurasiya [this message]
2023-10-31 18:48 ` [PATCH v3] ieee1275/ofdisk: retry on open and read failure Daniel Kiper
2023-10-31 21:11 ` Vladimir 'phcoder' Serbinenko
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20230717103233.1292219-1-mchauras@linux.ibm.com \
--to=mchauras@linux.ibm.com \
--cc=avnish@linux.vnet.ibm.com \
--cc=brking@linux.vnet.ibm.com \
--cc=diegodo@linux.vnet.ibm.com \
--cc=grub-devel@gnu.org \
--cc=mamatha4@linux.vnet.ibm.com \
--cc=mchauras@linux.vnet.ibm.com \
--cc=meghanaprakash@in.ibm.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).