Resolve "loopback on client - need a Gekko ENV variable or option as the server"

Ramon Nourequested to merge
391-loopback-on-client-need-a-gekko-env-variable-or-option-as-the-server into master

Closes #391 (closed)

Merge request reports

include/client/env.hpp

+5 −0
Changes for include/client/env.hpp: 5 added lines, 0 removed lines.
Original line number Diff line number Diff line
@@ -100,6 +100,11 @@ static constexpr auto METADATA_BATCH_THRESHOLD = 
        ADD_PREFIX("METADATA_BATCH_THRESHOLD");

static constexpr auto ASYNC_WRITE = ADD_PREFIX("ASYNC_WRITE");



// Libfabric interface pinning (consumed by libfabric at HG_init() time)

// OFI_INTERFACE is used with the GKFS_ prefix (e.g., LIBGKFS_OFI_INTERFACE)

// LIBGKFS_OFI_INTERFACE is the literal env var name for client-side pinning

static constexpr auto OFI_INTERFACE = ADD_PREFIX("OFI_INTERFACE");



} // namespace gkfs::env



#undef ADD_PREFIX

include/client/preload_context.hpp

+8 −0
Changes for include/client/preload_context.hpp: 8 added lines, 0 removed lines.
Original line number Diff line number Diff line
@@ -186,6 +186,8 @@ private: 
    std::thread async_write_thread_;

    bool async_write_stop_{false};



    std::string ofi_interface_;





public:

    static PreloadContext*
@@ -434,6 +436,12 @@ public: 
    void

    use_async_write(bool use_async_write);



    std::string

    ofi_interface() const;



    void

    ofi_interface(const std::string& ofi_interface);



    void

    start_async_write_thread();

include/common/rpc/handler_util.hpp

0 → 100644
+38 −0
Changes for include/common/rpc/handler_util.hpp: 38 added lines, 0 removed lines.
Original line number Diff line number Diff line 
#pragma once

#include <thallium.hpp>

#include <spdlog/spdlog.h>



namespace gkfs::utils {



/**

 * @internal

 * Safe wrapper around thallium::request::respond() that contains

 * any margo_exception throws and logs them instead of aborting.

 * This is needed because respond() can throw when the client has

 * vanished mid-RPC (common in malleable workloads).

 * @endinternal

 */

template <typename RequestType, typename ResponseType>

void

safe_respond(RequestType& req, const ResponseType& resp) {

    try {

        req.respond(resp);

    } catch(const thallium::margo_exception& e) {

        // Client vanished — log and silently discard.

        // This is a normal part of malleable workloads, not an error.

        auto logger = spdlog::get("daemon");

        if(logger) {

            logger->debug(

                    "handler: client vanished mid-RPC, respond failed: {}",

                    e.what());

        }

    } catch(const std::exception& e) {

        // Unknown error — log but do not abort

        auto logger = spdlog::get("daemon");

        if(logger) {

            logger->error("handler: unexpected respond error: {}", e.what());

        }

    }

}



} // namespace gkfs::utils
 
 No newline at end of file

include/daemon/classes/fs_data.hpp

+11 −0
Changes for include/daemon/classes/fs_data.hpp: 11 added lines, 0 removed lines.
Original line number Diff line number Diff line
@@ -117,6 +117,11 @@ private: 
    bool enable_forwarding_ = false;

    std::string stats_file_;



    // Environment variables read at startup

    // Default: destroy hosts file on shutdown. Set keep_hosts_file to preserve

    // it.

    bool keep_hosts_file_ = false;



    // Prometheus

    std::string prometheus_gateway_ = gkfs::config::stats::prometheus_gateway;
@@ -328,6 +333,12 @@ public: 
    void

    malleable_manager(const std::shared_ptr<gkfs::malleable::MalleableManager>&

                              malleable_manager);



    bool

    keep_hosts_file() const;



    void

    keep_hosts_file(bool keep);

};

include/daemon/handler/rpc_util.hpp

+3 −2
Changes for include/daemon/handler/rpc_util.hpp: 3 added lines, 2 removed lines.
Original line number Diff line number Diff line
@@ -43,6 +43,7 @@ 
#include <daemon/backend/metadata/db.hpp>

#include <daemon/backend/data/chunk_storage.hpp>

#include <common/rpc/rpc_types_thallium.hpp>

#include <common/rpc/handler_util.hpp>

#include <thallium.hpp>



namespace gkfs::rpc {
@@ -108,7 +109,7 @@ run_rpc_handler(const tl::request& req, const InputType& in, Func func) { 


    GKFS_DATA->spdlogger()->debug("{}() Sending output err '{}'", __func__,

                                  out.err);

    req.respond(out);

    gkfs::utils::safe_respond(req, out);

}



/**
@@ -147,7 +148,7 @@ run_rpc_handler(const tl::request& req, Func func) { 


    GKFS_DATA->spdlogger()->debug("{}() Sending output err '{}'", __func__,

                                  out.err);

    req.respond(out);

    gkfs::utils::safe_respond(req, out);

}



} // namespace gkfs::rpc