Skip to content

HTTPS clone URL

Subversion checkout URL

You can clone with HTTPS or Subversion.

Download ZIP
Commits on Mar 3, 2015
  1. Merge branch 'requeue-pdu'

    authored
  2. iscsi-util.c: use PRIu64 instead of llu

    authored
    Signed-off-by: Ronnie Sahlberg <ronniesahlberg@gmail.com>
  3. Merge pull request #145 from sitsofe/iscsi-perf-clang

    authored
    Iscsi perf clang
Commits on Mar 1, 2015
  1. Sitsofe Wheeler

    iscsi-perf: Use gettimeofday if clock_gettime is unavailable

    sitsofe authored
    clock_gettime doesn't existing on OS X
    (http://stackoverflow.com/questions/5167269/clock-gettime-alternative-in-mac-os-x
    ) so add an autoconf test to check if the platform has it and fall back
    on gettimeofday if not.
    
    Signed-off-by: Sitsofe Wheeler <sitsofe@yahoo.com>
  2. Sitsofe Wheeler

    test_preventallow_*.c: Silence clang empty body warning

    sitsofe authored
    Clang whinges about an empty loop body when it sees code like
    while (i = 0; i++; i < 2);
    but in test_preventallow_*.c this looks intentional, so move the
    semi-colon to a line of its own to make clang happy.
    
    Signed-off-by: Sitsofe Wheeler <sitsofe@yahoo.com>
  3. Sitsofe Wheeler

    iscsi-perf.c: Use %llu format string.

    sitsofe authored
    Compiling with clang gives a format warning like
    iscsi-perf.c:98:53: error: format specifies type 'unsigned long' but the
    argument has type 'uint64_t' (aka 'unsigned long long')
          [-Werror,-Wformat]
    so replace %lu with %llu where appropriate.
    
    Signed-off-by: Sitsofe Wheeler <sitsofe@yahoo.com>
Commits on Feb 24, 2015
  1. connect.c: improve comment in reconnect code that we ONLY requeue SCS…

    authored
    …I COMMAND
    
    The only PDU type that does not have ISCSI_PDU_DROP_ON_RECONNECT is the
    SCSI COMMAND PDU. Thsi is the only PDU that we re-queue on reconnect.
    All other, including DATA-OUT, NOP, task management, PDUs are simply
    dropped.
    
    Signed-off-by: Ronnie Sahlberg <ronniesahlberg@gmail.com>
  2. reconnect: we need to reset the in/out iovectors on reconnect

    authored
    This is a bug that has been there a long time.
    When we reconnect and requeue a PDU we must reset the iovectors
    for the task. Otherwise, any partially sent/received data when the
    command is reconnected would end up containing garbage.
    
    Signed-off-by: Ronnie Sahlberg <ronniesahlberg@gmail.com>
  3. reconnect logic and pdu handling

    authored
    Rework the reconnect logic so we just call iscsi_scsi_command_async()
    for the scsi commands we are re-quining instead of poking into the
    private fields of the structures themself.
    
    Signed-off-by: Ronnie Sahlberg <ronniesahlberg@gmail.com>
  4. login.c: dont modify pdu->flags directly from iscsi_logout_async_inte…

    authored
    …rnal
    
    We no longer need to modify pdu->flags directly any more from
    iscsi_logout_async_internal. We can just pass these as extra flags to
    iscsi_allocate_pdu().
    
    We also always set ISCSI_PDU_DROP_ON_RECONNECT unconditionally so there is
    no need to pass this flag in from the callers in pdu.c .
    
    Signed-off-by: Ronnie Sahlberg <ronniesahlberg@gmail.com>
  5. task_mgmt.c: drop tmgmt pdus on reconnect

    authored
    Signed-off-by: Ronnie Sahlberg <ronniesahlberg@gmail.com>
  6. login.c: drop login PDUs on reconnect

    authored
    Signed-off-by: Ronnie Sahlberg <ronniesahlberg@gmail.com>
  7. discovery.c: drop discovery requests on reconnect instead or re-queui…

    authored
    …ng them
    
    Signed-off-by: Ronnie Sahlberg <ronniesahlberg@gmail.com>
  8. pdu.c: remove iscsi_allocate_pdu_with_itt_flags()

    authored
    Remove iscsi_allocate_pdu() which is just a wrapper.
    Rename iscsi_allocate_pdu_with_itt_flags() to iscsi_allocate_pdu()
    and update all callers.
    
    This only removes a wrapper function and contains no logic changes.
    
    Signed-off-by: Ronnie Sahlberg <ronniesahlberg@gmail.com>
Commits on Feb 23, 2015
  1. Merge pull request #144 from plieven/fix_unsolicited

    authored
    iscsi-command: fix unsolicited data-out length
  2. plieven

    use MIN and MAX macros at some places

    plieven authored
    Signed-off-by: Peter Lieven <pl@kamp.de>
  3. plieven

    iscsi-command: fix unsolicited data-out length

    plieven authored
    the recent implementation allows to send
    iscsi->first_burst_length + iscsi->target_max_recv_data_segment_length
    bytes if immediate and unsolicited data-out is send and
    iscsi->target_max_recv_data_segment_length < iscsi->first_burst_length.
    
    RFC3720 defines the length as:
    
    Length=(min(FirstBurstLength, Expected Data
       Transfer Length) - Received Immediate Data Length).
    
    so that immediate data and unsolicited data-out are together
    FirstBurstLength at maximum.
    
    Signed-off-by: Peter Lieven <pl@kamp.de>
  4. plieven

    iscsi-private: add MIN and MAX macros

    plieven authored
    Signed-off-by: Peter Lieven <pl@kamp.de>
Commits on Feb 21, 2015
  1. iscsi-command.c: Use common function to write unsolicited data-out pdus.

    authored
    We write unsolicited data-out PDUs from two places;
    when we originally write the command in iscsi_scsi_command_async()
    but also when we re-queue the PDUs during a session reconnect.
    
    The re-queuing during the session re-connect was recently (almost) fixed
    but was still buggy in that it did not correctly clamp the amount of written
    data as per first burst length restriction.
    This attempts to fix that.
    
    Signed-off-by: Ronnie Sahlberg <ronniesahlberg@gmail.com>
  2. iscsi-command.c: use pdu->expxferlen instead of pdu->expxferlen

    authored
    Both are the same value at this point but it is better to
    do the computation only based on pdy-> fields.
    
    Signed-off-by: Ronnie Sahlberg <ronniesahlberg@gmail.com>
Commits on Feb 18, 2015
  1. test-tool: fix unregister of initiator 2 in test_prout_reserve_access

    Sebastian Herbszt authored committed
    Initiator 2 registered with key2.
    
    Signed-off-by: Sebastian Herbszt <herbszt@gmx.de>
Commits on Feb 17, 2015
  1. reconnect: we must re-queue any missing data-outs during reconnect

    authored
    If we have writes that do not have the Final bit set during reconnect
    we must send out any missing data-out PDU.
    
    Signed-off-by: Ronnie Sahlberg <ronniesahlberg@gmail.com>
  2. iscsi-command.c: Better fix for the length bug for immediatedata

    authored
    Signed-off-by: Ronnie Sahlberg <ronniesahlberg@gmail.com>
  3. iscsi_command: fix length bug when sending unsolicited data.

    authored
    If we have send unsolicited immediate data and are ALSO sending
    unsilocoted data-out, then we have to exclude the length of data we have already sent.
    
    Signed-off-by: Ronnie Sahlberg <ronniesahlberg@gmail.com>
  4. test-tool: remove the --usb argument and use BLCSECTGET to read max xfer

    authored
    Signed-off-by: Ronnie Sahlberg <ronniesahlberg@gmail.com>
Commits on Feb 16, 2015
  1. test-tool: fix SG_IO

    Sebastian Herbszt authored committed
    Handle io_hdr.resid and adjust datain.size.
    
    Signed-off-by: Sebastian Herbszt <herbszt@gmx.de>
  2. update .gitignore

    Sebastian Herbszt authored committed
    Update .gitignore.
    
    Signed-off-by: Sebastian Herbszt <herbszt@gmx.de>
Commits on Feb 11, 2015
  1. RPM: add iscsi-perf to the package

    authored
    Signed-off-by: Ronnie Sahlberg <ronniesahlberg@gmail.com>
  2. README: add links to useful xml stuff

    authored
    Suggested-by: CyberLoiter <yanming.xiao@gmail.com>
    Signed-off-by: Ronnie Sahlberg <ronniesahlberg@gmail.com>
  3. rand_key: fix non-randomness in rand_key()

    authored
    If rand_key() is called twive within the same second it would return the
    same key both times. Not very random.
    Redo how rand_key() works to make it more likely to be random and more likely
    that two consequtive calls do not yield the same result.
    
    Reported-by: CyberLoiter <yanming.xiao@gmail.com>
    Signed-off-by: Ronnie Sahlberg <ronniesahlberg@gmail.com>
Commits on Jan 27, 2015
  1. test-tool: SEGV when dereferencing a NULL pointer ascq array

    authored
    ascq is NULL if there are no ascqs provided for this failure mode.
    Do not try to dereference the 0-th element in this array before checking
    that the array has at least one element.
    
    Signed-off-by: Ronnie Sahlberg <ronniesahlberg@gmail.com>
  2. test-tool: fix segv in reserve6_2initiators

    authored
    Fix a SEGV in one of the reserve6 tests.
    
    Signed-off-by: Vadim Finkelstein <vadim@pi-coral.com>
    Signed-off-by: Ronnie Sahlberg <ronniesahlberg@gmail.com>
Commits on Jan 23, 2015
  1. Merge pull request #141 from plieven/iscsi-io

    authored
    util: introduce iscsi-perf
Commits on Jan 9, 2015
  1. socket.c: allow re-using a context after disconnect

    authored
    From Adam Endrodi <adam.endrodi@nsn.com>
    Fix a bug and clear is_corked during socket disconnect so that we
    can re-use the context for a new connection.
    
    Signed-off-by: Ronnie Sahlberg <ronniesahlberg@gmail.com>
Something went wrong with that request. Please try again.